DETAILED ACTION
Status of Claims
The following is a Non-Final Office Action in response to Applicant’s response filed on 12/13/026.
Claims 2, 4, 5, 9, 10, and 17 are cancelled. Claims 1, 3, 6-8, 11-16, and 18-21 are considered in this Office Action. Claims 1, 3, 6-8, 11-16, and 18-21 are currently pending.
Response to Argument
Applicant’s amendment necessitated the new ground(s) of rejection set forth in this Office Action.
Applicant’s arguments with respect to the 35 U.S.C. §101 rejection to claims have been considered, and they are found to be persuasive. The 35 U.S.C. §101 rejection is withdrawn.
Applicant's supporting arguments (Remarks at pgs. 10-16) concerning the 101 rejections of claims 1, 3, 6-8, 11-16, and 18-21 have been considered and found sufficient to overcome the $101 rejection. The claims are patent eligible under 35 USC 101 as amended claims recite limitations which are not abstract under Prong 2 of Step 2A of the Alice analysis, as they are directed at a control unit that uses the at least one processor to control the equipment, so as to output a manipulated variable corresponding to a state of the equipment to be provided to the equipment, wherein the manipulated variable is based on the indicator. Any abstractions recited in the claim limitations which may be construed as "mental processes" or "mathematical concept" are integrated into a practical application, as the additional elements reflect applying or using the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. Accordingly, the §101 rejection is withdrawn.
Applicant’s arguments with respect to the 35 U.S.C. §103 rejection to claims have been considered, and they are found to be persuasive. Therefore, an updated 35 U.S.C. §103 rejection will address applicant’s arguments.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3, 6-8, 11-16, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Tomohiro Kuroda (US 2019/0164102 A1, hereinafter “Kuroda”) in view of Tsutomu Kawamura (US 2020/0387847 A1, hereinafter “Kawamura”) in view of Runkana (EP 3644267 A1, hereinafter “Runkana”) in view of Keita Hada (US 2019/0099850 A1, hereinafter “Hada”).
Claim 1/15/16
Kuroda teaches:
An evaluation apparatus ([0002] method, an operational improvement effect calculation program, and a recording medium)comprising: an environmental data acquisition unit that uses the at least one processor to acquire environmental data indicating an operation environment of equipment([0031] The operational improvement effect calculation device 10 is configured to acquire diverse data, which is to be used when calculating the operational improvement effect, from the plant operation database 20 and the weather database 30 through the network 40, wherein [0028] The weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored);
a performance data acquisition unit that uses the at least one processor to acquire performance data indicating an operation performance of the equipment([0031] The operational improvement effect calculation device 10 is configured to acquire diverse data, which is to be used when calculating the operational improvement effect, from the plant operation database 20 and the weather database 30 through the network 40, wherein [0027] The plant operation database 20 is a database in which a variety of data from the past to the present relating to a plant operation is stored. In the plant operation database 20, data of raw materials such as types and used amounts of raw materials to be used when manufacturing a product in a plant, data of operating conditions (for example, flow rate, pressure, temperature and the like) detected by sensors provided to a facility, and data of plant operations (hereinafter, referred to as “plant operation data”) in which a production volume and a quality of a manufactured product are associated with each other are stored);
an estimation unit that uses the at least one processor to estimate an operation performance on an operation basis in a learning target period under an operation environment in an evaluation target period, based on the environmental data and the performance data in the learning target period([0032] The user operates the processing receiving unit 101 to designate diverse conditions such as a time period for which the operational improvement effect calculation device 10 is to calculate the operational improvement effect and parameters that are to be used when calculating the operational improvement effect. For example, the user designates a time period for which the improvement effect obtained as a result of the improvement measures is to be estimated (evaluated), and a time period of target for which the plant operation data and the weather data are to be retrieved when estimating (evaluating) the improvement effect. [0035] The data acquisition unit 102 is configured to acquire the plant operation data and the weather data, which are included within the time period designated by the user, from the plant operation database 20 and the weather database 30, based on information (hereinafter, referred to as “time period information Ip”) of the evaluation time period and retrieval target time period output from the processing receiving unit 101);
wherein the evaluation target period includes a plurality of evaluation target period ([0064] in the processing of step S130, the similar data retrieval unit 104 calculates the post-improvement KPI at the evaluation target time for each of the pre-processed data Dp after performing the improvement measures at each evaluation target time);
an evaluation unit that uses the at least one processor to calculate, for each of the evaluation target periods, an indicator that relatively evaluates an actually measured value of an operation performance in the respective evaluation target period with respect to an estimated value of the estimated operation performance([0006] a plant operation evaluation device configured to estimate a plant operation before performing energy saving measures by using a statistical model and to compare the estimated plant operation and an actual plant operation after performing the energy saving measures, [0064] in the processing of step S130, the similar data retrieval unit 104 calculates the post-improvement KPI at the evaluation target time for each of the pre-processed data Dp after performing the improvement measures at each evaluation target time), while [0118] the operational improvement effect calculation device is configured to evaluate the effect (operational improvement effect) of the improvement measures performed in the plant with the conditions designated by the user by using the diverse plant operation-related data (plant operation data) from the past to the present, which are included in the retrieval target time period and the evaluation time period designated by the user, and the weather-related data (weather data), which can be considered as the external factor influencing the plant operation. The operational improvement effect calculation device is configured to calculate the pre-improvement KPI and the baseline by retrieving more than once the pre-improvement data similar to the post-improvement data. Then the operational improvement effect calculation device is configured to calculate the minimum improvement effect (operational improvement effect) obtained as a result of the improvement measures, from the calculated baseline and post-improvement KPI);
and an output unit that uses the at least one processor to output the indicator (figures 3, 5, and [0110] when the determination result, which indicates that the baseline is to be calculated for the pre-improvement KPI calculated by the similar data retrieval unit 124, is output from the calculation method determination unit 128, the baseline calculation unit 126 calculates a baseline corresponding to the pre-improvement KPI included in the retrieval result Rs2 output from the calculation method determination unit 128, in the processing of step S250. Then, the baseline calculation unit 126 outputs at least the post-improvement KPI and the pre-improvement KPI, which are included in the retrieval result Rs2 output from the calculation method determination unit 128 or the estimation result Re output from the statistical model preparation unit 129, and the calculated baseline data to the operational improvement effect calculation unit 107, in correspondence to the determination result of the baseline calculation method output from the calculation method determination unit 128. While [0111] the display device 50 displays an image of the operational improvement effect data De output from the operational improvement effect calculation unit 107, in the processing of step S170);
wherein the estimation unit uses the at least one processor to estimate the operation performance on the operation basis in the learning target period under the operation environment in the evaluation target period, based on an output of a learning model machine-learned so as to output an operation performance corresponding to an operation environment by using, as learning data, the environmental data and the performance data in the learning target period obtained [] (Figure 5 illustrates s100 which acquires the plant operation data and weather data, which are included in the retrieval target time period and evaluation time period indicated by the time period information Ip output from the processing receiving unit 101, at steps S232-233 describes the statistical model preparation unit 129 prepares a statistical model on the basis of the pre-processed data Dp before performing the improvement measures in the retrieval target time period, which is included in the pre-processed data Dp output from the pre-processing unit 103 (step S232). Here, the statistical model preparation unit 129 prepares the statistical model by using the PLS regression (a machine learning technique), for example, and Then, the statistical model preparation unit 129 outputs the estimation result Re, which includes the calculated post-improvement KPI at each evaluation target time, each pre-improvement KPI corresponding to the post-improvement KPI at each evaluation target time and the pre-processed data Dp before performing the improvement measures in the retrieval target time period, which has been used to prepare the statistical model in the processing of step S232, to the confidence interval calculation unit 125 and the baseline calculation unit 126. Examiner notes PLS regression is a machine learning technique);
the learning model corresponding to the learning target period ([0088]-[0089] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI);
and the indicator comprises a key performance indicator (KPI) related to energy efficiency([0004] as an indicator of measuring the effect of the improvement measures, a key performance indicator (KPI) such as production cost and yield, energy efficiency and the like may be exemplified. [0071]-[0075] FIG. 3 depicts an example in which when the post-improvement KPI of the evaluation target is the energy efficiency, the operational improvement effect calculation device 10 displays, as the result of the operational improvement effect, temporal changes of the post-improvement KPI, the pre-improvement KPI and the baseline on the display device 50. In FIG. 3, the temporal changes of the post-improvement KPI, the pre-improvement KPI and the baseline are indicated by polygonal curves on a graph of which a vertical axis indicates a magnitude of the energy efficiency and a horizontal axis indicates time).
While Kuroda teaches [0088] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI, however, it does not explicitly teach the following, however analogous reference Kawamura discloses:
acquire performance data indicating an operation performance of the equipment ([0070] the operation plan generation unit 204 receives input of the operation constraint conditions such as the minimum load factor of the apparatus, the upper limit value of the number of start and stop times per day of the apparatus/equipment, the continuation time after the start of the apparatus, the stop continuation time of the apparatus. Further, the operation plan generation unit 204 receives input of fuel consumption characteristic data of the apparatus using a weather condition as a parameter in order to consider a fuel consumption (power consumption and gas consumption) of the apparatus/equipment that changes depending on the weather condition);
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda with Kawamura, because the reference are analogous on the field of environmental and operational evaluation system, to include acquiring performance data indicating an operation performance associated with equipment, because it will can reduce a time required for generation of an operation plan can be provided based on the number of apparatuses in the microgrid/plant [0006].
While Kuroda teaches [0088] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI, and Kawamura describes paragraph [0051] the machine learning unit 102 learns system characteristics of the microgrid 1 on the basis of the KPI calculated by the data generation unit 101 as shown in FIG. 6, outputs the system characteristics to the learning result DB 105, and stores the system characteristics in the learning result DB 105. [0056] The learning result DB 105 stores the system characteristics learned by the machine learning unit 102, however, it does not explicitly teach the following, however analogous reference Runkana teaches:
and a control unit that uses the at least one processor to control the equipment, so as to output a manipulated variable corresponding to a state of the equipment to be provided to the equipment, wherein the manipulated variable is based on the indicator(Figs. 2A-2B; [0026] The current running status of each of the units is updated using data received from disparate sources distributed across the plant. The current running status of a unit consists of the present measured value of the sensors employed in the field, soft sensors developed using simulation models developed using sensor data, lab measurements and other such measurements fetched from the updated plant databases. Data fetched from these sources is used to either tune or develop models for section-wise KPIs and overall KPIs as function of the several manipulated / decision variables and important disturbance variables. These models are utilized to find the set points of decision variables that result in the improvement in the KPIs. The estimated decision variables are communicated to the lower-level controllers as set points (in case of automatic control) or to hand-held devices with the operators (in case of manual control) so that these can be implemented in the field. Thus, the system 100 provides end to end solution to improve existing mining and mineral processing operations).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda and Kawamura with Runkana, because the reference are analogous on the field of environmental and operational evaluation system, to include a control unit that uses the at least one processor to control the equipment, so as to output a manipulated variable corresponding to a state of the equipment to be provided to the equipment, wherein the manipulated variable is based on the indicator, because it will can provide end to end solution to improve existing processing operations of a system [0026].
While Kuroda teaches [0088] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI, and Kawamura describes paragraph [0051] the machine learning unit 102 learns system characteristics of the microgrid 1 on the basis of the KPI calculated by the data generation unit 101 as shown in FIG. 6, outputs the system characteristics to the learning result DB 105, and stores the system characteristics in the learning result DB 105. [0056] The learning result DB 105 stores the system characteristics learned by the machine learning unit 102, however, it does not explicitly teach the following, however analogous reference Hada discloses:
Hada teaches
wherein a plurality of learning models are stored in the learning model storage unit in association with corresponding ones of the learning target periods([0044] The learning model storage section 300 stores a plurality of learning models 1, 2, . . . , N associated with a combination of conditions of individual difference of the machine controlled by the numerical control section 100 specified by the condition specifying section 110. A combination of conditions of individual difference of the machine controlled by the numerical control section 100 as described herein means a combination related to values that can be taken by each condition, for example, conditions may be classified according to combinations of a range of a frequency of use, a range of a cumulative operating time);
the evaluation unit uses the at least one processor to determine whether the learning model corresponding to a respective learning target period(condition)is already stored in the learning model storage unit and, if not, the learning model corresponding to the respective target period(condition) is generated and then stored in the learning model storage unit([0051] When a learning model associated with (a combination of) conditions of individual difference of the machine controlled by the numerical control section 100 specified by the condition specifying section 110 is not stored in the learning model storage section 300, the learning model generating section 500 newly generates a learning model associated with (the combination of) conditions, but when a learning model associated with (a combination of) conditions of individual difference of the machine controlled by the numerical control section 100 specified by the condition specifying section 110 is stored in the learning model storage section 300, the learning model generating section 500 updates the learning model by performing machine learning with respect to the learning model. [0044] The learning model storage section 300 stores a plurality of learning models 1, 2, . . . , N associated with a combination of conditions of individual difference of the machine controlled by the numerical control section 100 specified by the condition specifying section 110);
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda, Kawamura, and Runkana with Hada, because the reference are analogous on the field of environmental and operational evaluation system, to include wherein a plurality of learning models are stored in the learning model storage unit in association with corresponding ones of the learning target periods and the evaluation unit uses the at least one processor to determine whether the learning model corresponding to a respective learning target period(condition)is already stored in the learning model storage unit and, if not, the learning model corresponding to the respective target period(condition) is generated and then stored in the learning model storage unit, because it will can provide improvement countermeasures for production loss with priority based on estimation accuracy.
Claim 3
While Kuroda teaches [0088] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI, however, it does not explicitly teach the following, however analogous reference Kawamura discloses:
The evaluation apparatus according to Claim 1, further comprising a learning unit that uses the at least one processor to generate the learning model ([0051] The machine learning unit 102 learns system characteristics of the microgrid 1 on the basis of the KPI calculated by the data generation unit 101 as shown in FIG. 6, outputs the system characteristics to the learning result DB 105, and stores the system characteristics in the learning result DB 105. That is, the machine learning unit 102 considers not only data when the operation constraint conditions are satisfied (result data and analysis data), but also data when the operation constraint conditions are violated (violation data), and learns the system characteristics of the microgrid 1, where [0022] the microgrid 1 includes a consumer 11 and an energy system 12 that supplies a plurality of types of energy to the consumer 11, and implements an energy supply system for a consumer. The consumer 11 is equipment that consumes a heat and a power, such as a factory, an office building, a mansion, a university, or the like.).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda with Kawamura to include a learning unit that uses the at least one processor to generate the learning model using machine learning, because doing so can reduce a time required for generation of an operation plan can be provided based on the number of apparatuses in the microgrid/plant and generates a highly accurate operation plan [0006].
Claim 6
Kuroda further teaches:
the learning model in association with each learning target period ([0088]-[0089] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI).
wherein the learning unit is that uses the at least one processor, in a case where a learning model corresponding to a specified learning target period is not stored, to generate a learning model corresponding to the specified learning target period by using, as learning data, environmental data and performance data in the specified learning target period(Figure 5 illustrates s100 which acquires the plant operation data and weather data, which are included in the retrieval target time period and evaluation time period indicated by the time period information Ip output from the processing receiving unit 101, at steps S232-233 describes the statistical model preparation unit 129 prepares a statistical model on the basis of the pre-processed data Dp before performing the improvement measures in the retrieval target time period, which is included in the pre-processed data Dp output from the pre-processing unit 103 (step S232). Here, the statistical model preparation unit 129 prepares the statistical model by using the PLS regression (a machine learning technique), for example, and Then, the statistical model preparation unit 129 outputs the estimation result Re, which includes the calculated post-improvement KPI at each evaluation target time, each pre-improvement KPI corresponding to the post-improvement KPI at each evaluation target time and the pre-processed data Dp before performing the improvement measures in the retrieval target time period, which has been used to prepare the statistical model in the processing of step S232, to the confidence interval calculation unit 125 and the baseline calculation unit 126. Examiner notes PLS regression is a machine learning technique).
While Kuroda teaches [0088] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI, however, it does not explicitly teach the following, however analogous reference Kawamura discloses:
The evaluation apparatus according to Claim 1, further comprising: a learning unit that uses the at least one processor to generate the learning model ([0051] The machine learning unit 102 learns system characteristics of the microgrid 1 on the basis of the KPI calculated by the data generation unit 101 as shown in FIG. 6, outputs the system characteristics to the learning result DB 105, and stores the system characteristics in the learning result DB 105. That is, the machine learning unit 102 considers not only data when the operation constraint conditions are satisfied (result data and analysis data), but also data when the operation constraint conditions are violated (violation data), and learns the system characteristics of the microgrid 1, where [0022] the microgrid 1 includes a consumer 11 and an energy system 12 that supplies a plurality of types of energy to the consumer 11, and implements an energy supply system for a consumer. The consumer 11 is equipment that consumes a heat and a power, such as a factory, an office building, a mansion, a university, or the like.).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda with Kawamura to include a learning unit configured to generate the learning model using machine learning taught in Kuroda, because doing so can reduce a time required for generation of an operation plan can be provided based on the number of apparatuses in the microgrid/plant and generates a highly accurate operation plan [0006].
Claim 7
Kuroda further teaches:
The evaluation apparatus according to Claim 1, wherein the evaluation target period includes a plurality of evaluation target periods, and the output unit is that uses the at least one processor to output the indicator in each of the plurality of evaluation target periods([0088] The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI. Figure 3 illustrates an example in which when the post-improvement KPI of the evaluation target is the energy efficiency, the operational improvement effect calculation device 10 displays, as the result of the operational improvement effect, temporal changes of the post-improvement KPI, the pre-improvement KPI and the baseline on the display device 50).
Claim 8
Kuroda further teaches:
The evaluation apparatus according to Claim 1, wherein the evaluation target period includes a plurality of evaluation target periods, and the output unit that uses the at least one processor to output the indicator in each of the plurality of evaluation target periods([0088] The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI. Figure 3 illustrates an example in which when the post-improvement KPI of the evaluation target is the energy efficiency, the operational improvement effect calculation device 10 displays, as the result of the operational improvement effect, temporal changes of the post-improvement KPI, the pre-improvement KPI and the baseline on the display device 50).
Claim 11
Kuroda further teaches:
The evaluation apparatus according to Claim 1, wherein the environmental data acquisition unit that uses the at least one processor to acquire data indicating an outside air condition, as the environmental data ([0028] the weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored).
Claim 12
Kuroda further teaches:
The evaluation apparatus according to Claim 1, wherein the environmental data acquisition unit that uses the at least one processor to acquire data indicating an outside air condition, as the environmental data ([0028] the weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored).
Claim 13
While Kuroda teaches [0027] The plant operation database 20 is a database in which a variety of data from the past to the present relating to a plant operation is stored. In the plant operation database 20, data of raw materials such as types and used amounts of raw materials to be used when manufacturing a product in a plant, data of operating conditions (for example, flow rate, pressure, temperature and the like) detected by sensors provided to a facility, and data of plant operations (hereinafter, referred to as “plant operation data”) in which a production volume and a quality of a manufactured product are associated with each other are stored. [0028] The weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored. [0029] The network 40 is a network via which the operational improvement effect calculation device 10 is to acquire the data of plant operations stored in the plant operation database 20 and the weather data stored in the weather database 30, however Kuroda does not explicitly teach the following, however Kawamura teaches:
The evaluation apparatus according to Claim 1, wherein the environmental data acquisition unit that uses the at least one processor to acquire data indicating an operational state in a facility provided with the equipment, as the environmental data (Fig. 2 and [0070] the operation plan generation unit 204 receives input of the operation constraint conditions such as the minimum load factor of the apparatus, the upper limit value of the number of start and stop times per day of the apparatus, the continuation time after the start of the apparatus, the stop continuation time of the apparatus. Further, the operation plan generation unit 204 receives input of fuel consumption characteristic data of the apparatus using a weather condition as a parameter in order to consider a fuel consumption (power consumption and gas consumption) of the apparatus that changes depending on the weather condition).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda with Kawamura to include the environmental data acquisition unit is configured to acquire data indicating an operational state in a facility provided with the equipment, as the environmental data, because doing so can reduce a time required for generation of an operation plan can be provided based on the number of apparatuses in the microgrid/plant and generates a highly accurate operation plan [0006].
Claim 14
While Kuroda teaches [0027] The plant operation database 20 is a database in which a variety of data from the past to the present relating to a plant operation is stored. In the plant operation database 20, data of raw materials such as types and used amounts of raw materials to be used when manufacturing a product in a plant, data of operating conditions (for example, flow rate, pressure, temperature and the like) detected by sensors provided to a facility, and data of plant operations (hereinafter, referred to as “plant operation data”) in which a production volume and a quality of a manufactured product are associated with each other are stored. [0028] The weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored. [0029] The network 40 is a network via which the operational improvement effect calculation device 10 is to acquire the data of plant operations stored in the plant operation database 20 and the weather data stored in the weather database 30, however Kuroda does not explicitly teach the following, however Kawamura teaches:
The evaluation apparatus according to Claim 1, wherein the performance data acquisition unit is that uses the at least one processor to acquire data, which indicates at least any of a used amount of fuel in the equipment and power consumption in the equipment, as the performance data(Fig. 2 and [0070] the operation plan generation unit 204 receives input of the operation constraint conditions such as the minimum load factor of the apparatus, the upper limit value of the number of start and stop times per day of the apparatus, the continuation time after the start of the apparatus, the stop continuation time of the apparatus. Further, the operation plan generation unit 204 receives input of fuel consumption characteristic data of the apparatus using a weather condition as a parameter in order to consider a fuel consumption (power consumption and gas consumption) of the apparatus that changes depending on the weather condition).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda with Kawamura to include the performance data acquisition unit is configured to acquire data, which indicates at least any of a used amount of fuel in the equipment and power consumption in the equipment, as the performance data, because doing so can reduce a time required for generation of an operation plan can be provided based on the number of apparatuses in the microgrid/plant and generates a highly accurate operation plan [0006].
Claim 21
Kuroda further teaches:
[storage]supplies the learning model corresponding to the learning target period to the estimation unit (fig. 1 and [0037] the data acquisition unit 102 is configured to output, to the pre-processing unit 103, the plant operation data and weather data, i.e., raw data of the evaluation time period and the retrieval target time period acquired from the plant operation database 20 and the weather database 30 via the network 40. In the below, when the plant operation data and the weather data are not distinguished, they are referred to as “original data Dr”. While [0088]-[0089] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post improvement KPI).
While Kuroda teaches [0088] The statistical model preparation unit 129 is configured to calculate a post-improvement KPI, based on the pre-processed data Dp after performing the improvement measures (pre-processed data Dp of evaluation target) at the evaluation target time included in the pre-processed data Dp output from the pre-processing unit 103. The post-improvement KPI that is to be calculated by the statistical model preparation unit 129 is a KPI similar to the post-improvement KPI that is to be calculated by the similar data retrieval unit 124. Also, the statistical model preparation unit 129 is configured to calculate (estimate) a pre-improvement KPI corresponding to the pre-processed data Dp after performing the improvement measures at the evaluation target time, i.e., the calculated post-improvement KPI by using the prepared statistical model. The statistical model preparation unit 129 is configured to calculate (estimate) the post-improvement KPI at each evaluation target time included in the evaluation time period and the pre-improvement KPI corresponding to each post-improvement KPI, however, it does not explicitly teach the following, however analogous reference Kawamura discloses:
The evaluation apparatus according to claim 1, wherein the learning model storage unit ([0051] The machine learning unit 102 learns system characteristics of the microgrid 1 on the basis of the KPI calculated by the data generation unit 101 as shown in FIG. 6, outputs the system characteristics to the learning result DB 105, and stores the system characteristics in the learning result DB 105. [0056] The learning result DB 105 stores the system characteristics learned by the machine learning unit 102).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda with Kawamura to include a learning model storage unit configured to store the learning model in association with each learning target period taught in Kuroda, because doing so can reduce a time required for generation of an operation plan can be provided based on the number of apparatuses in the microgrid/plant and generates a highly accurate operation plan [0006].
Claims 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kuroda in view of Kawamura in view of Runkana in view of Hada, as applied in claims 1 and 16, and further in view of Mahesh Kumar Asati (US 2016/0281607 A1, hereinafter “Asati”).
Claim 18
While Kuroda teaches [0027] The plant operation database 20 is a database in which a variety of data from the past to the present relating to a plant operation is stored. In the plant operation database 20, data of raw materials such as types and used amounts of raw materials to be used when manufacturing a product in a plant, data of operating conditions (for example, flow rate, pressure, temperature and the like) detected by sensors provided to a facility, and data of plant operations (hereinafter, referred to as “plant operation data”) in which a production volume and a quality of a manufactured product are associated with each other are stored. [0028] The weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored. [0029] The network 40 is a network via which the operational improvement effect calculation device 10 is to acquire the data of plant operations stored in the plant operation database 20 and the weather data stored in the weather database 30, however Kuroda does not explicitly teach the following, however Asati teaches:
The control apparatus according to Claim 1, wherein the control unit is that uses the at least one processor to control the equipment, based on an output of a control model machine-learned so as to output the manipulated variable to be provided to the equipment by using the indicator( [0231] As illustrated in FIG. 27 and 28, the block controller 855 may communicate with a data and analytics component 865, which may include several modules by which relevant data is collected, normalized, stored, and made available upon query to the block controller 855. A data records module may receive real-time and historical data inputs from a monitoring system associated with generating assets. A module related to performance monitoring may also be included, and related thereto one or more off-line models may be maintained. A learning module may also be included for the collection of operating data from similarly configured assets or power blocks that are not operating within the fleet 861. This data, as will be appreciated, may support a learning function by which a deeper and more thorough operational understanding of the assets is obtained. Such data may also be used to normalize measured data collected from the fleet 861 so that performance degradation of the generating assets may be calculated accurately, which may include accounting for the effects of other variables, such as fuel characteristics, ambient conditions, etc., that also may affect output capacity and efficiency. [0239] The master control system 907 may be communicatively linked to the gas turbines 901 of the power block 902 so to implement control solutions given the output 906).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda, Kawamura, Runkana, and Hada with Asati, because the reference are analogous on the field of environmental and operational evaluation system, to include controlling the equipment, based on an output of a control model machine-learned so as to output a manipulated variable to be provided to the equipment by using the indicator based on the indicator determined by Kuroda’s system, because doing so will ensure efficient operation of the plant based on evaluation model[0002].
Claim 19
While Kuroda teaches [0027] The plant operation database 20 is a database in which a variety of data from the past to the present relating to a plant operation is stored. In the plant operation database 20, data of raw materials such as types and used amounts of raw materials to be used when manufacturing a product in a plant, data of operating conditions (for example, flow rate, pressure, temperature and the like) detected by sensors provided to a facility, and data of plant operations (hereinafter, referred to as “plant operation data”) in which a production volume and a quality of a manufactured product are associated with each other are stored. [0028] The weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored. [0029] The network 40 is a network via which the operational improvement effect calculation device 10 is to acquire the data of plant operations stored in the plant operation database 20 and the weather data stored in the weather database 30, however Kuroda does not explicitly teach the following, however Kawamura teaches:
The control apparatus according to Claim 18, […] and the control unit is that uses the at least one processor to generate the control model by performing reinforcement learning so that a manipulated variable whose reward including the indicator as at least a part is higher is output as a more recommended manipulated variable([0052] Machine learning can be classified into various algorithms according to purposes and conditions, such as reinforcement learning [0053] By an interaction between the machine learning unit 102, which is a learning subject, and the microgrid 1, which is a control target, learning and actions of the reinforcement learning are promoted on the basis of an effect of the action on an environment, so that a reward obtained in the future is maximized. [0054] The operation plan generation unit 103 obtains various operation conditions on an operation day necessary for generating an operation plan from the microgrid 1 and further obtains the system characteristics from the learning result DB 105. Then, the operation plan generation unit 103 generates an optimal operation planon the basis of the various operation conditions and the system characteristics on the operation day, and outputs the generated operation plan to the microgrid 1. [0057] on the basis of a combination of the plurality of operation plans and KPIs, the optimal operation plan is generated by causing the machine learning unit serving as artificial intelligence to learn the characteristics of the microgrid 1. Accordingly, even when the number of apparatuses in the microgrid increases, an operation plan generation device that generates a highly accurate (small energy cost) operation plan in a short time can be implemented).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda with Kawamura to include generating the control model by performing reinforcement learning so that a manipulated variable whose reward including the indicator as at least a part is higher is output as a more recommended manipulated variable, because doing so can reduce a time required for generation of an operation plan can be provided based on the number of apparatuses in the microgrid/plant and generates a highly accurate operation plan [0006].
While Kuroda teaches [0027] The plant operation database 20 is a database in which a variety of data from the past to the present relating to a plant operation is stored. In the plant operation database 20, data of raw materials such as types and used amounts of raw materials to be used when manufacturing a product in a plant, data of operating conditions (for example, flow rate, pressure, temperature and the like) detected by sensors provided to a facility, and data of plant operations (hereinafter, referred to as “plant operation data”) in which a production volume and a quality of a manufactured product are associated with each other are stored. [0028] The weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored. [0029] The network 40 is a network via which the operational improvement effect calculation device 10 is to acquire the data of plant operations stored in the plant operation database 20 and the weather data stored in the weather database 30, however Kuroda does not explicitly teach the following, however Asati teaches:
wherein the evaluation unit is that uses the at least one processor to calculate the indicator by dividing the estimated value of the operation performance by the actually measured value of the operation performance ([0218] and figure 23 a tuning or data reconciliation process may be completed using performance calculations that compare actual or measured values against those predicted by the plant or asset model),
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda, Kawamura, Runkana, and Hada with Asati, because the reference are analogous on the field of environmental and operational evaluation system, to include calculating the indicator by dividing the estimated value of the operation performance by the actually measured value of the operation performance, because doing so will ensure efficient operation control of the plant based on evaluation model[0002].
Claim 20
Kuroda further teaches:
A non-transitory recording medium having recorded thereon a control program that, when executed by a computer, causes the computer to function as:the environmental data acquisition unit, the performance data acquisition unit, the estimation unit, the evaluation unit, and the output unit of the evaluation apparatus according to Claim 1 (figure 1 illustrates the environmental data acquisition unit, the performance data acquisition unit, the estimation unit, the evaluation unit, and the output unit of the evaluation apparatus).
While Kuroda teaches [0027] The plant operation database 20 is a database in which a variety of data from the past to the present relating to a plant operation is stored. In the plant operation database 20, data of raw materials such as types and used amounts of raw materials to be used when manufacturing a product in a plant, data of operating conditions (for example, flow rate, pressure, temperature and the like) detected by sensors provided to a facility, and data of plant operations (hereinafter, referred to as “plant operation data”) in which a production volume and a quality of a manufactured product are associated with each other are stored. [0028] The weather database 30 is a database in which data of weather (hereinafter, referred to as “weather data”), which is considered as external factors influencing the plant operation, is stored. In the weather database 30, the weather data in which data of weather such as “temperature”, “atmospheric pressure”, “humidity”, “atmospheric conditions” and the like and data of time such as “date”, “time” and the like are associated with each other is stored. [0029] The network 40 is a network via which the operational improvement effect calculation device 10 is to acquire the data of plant operations stored in the plant operation database 20 and the weather data stored in the weather database 30, however Kuroda does not explicitly teach the following, however Asati teaches:
and a control unit that uses the at least one processor to control the equipment, based on the indicator ([0125] Offline model 124 may use any suitable information, such as historical, current, and/or forecast information, in determining estimated operating costs and/or conditions of the power plant 12. Tuning may include, for example, periodically adjusting parameters for offline model 124 based on information received and/or provided by other parts of the plant controller 22 to better reflect actual operation of the power plant 12 so as to better simulate operation of the power plant 12 ).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Kuroda, Kawamura, Runkana, and Hada with Asati, because the reference is analogous on the field of environmental and operational evaluation system, to include controlling the equipment based on the indicator determined by Kuroda system, because doing so will ensure efficient operation of the plant based on evaluation model[0002].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Kaneharu Nishino (US 2021/0287154 A1, hereinafter “Nishino”):an information processing device configured to generate a plurality of segments segmented by respective operating states of a target device based on time-series sensor data detected by a sensor that observes the target device; extract target data included in a segment having the same operating state as the operating state at certain first time out of the segments; and generate estimated data estimated to be output from the sensor at specified time different from the first time based on the target data.
Fan Zhang (US 20220128983 A1): methods includes: obtaining parameter data of equipment parameters of target equipment within a preset time period; where the parameter data includes values recorded at a preset interval for each of the equipment parameters when a product passes through the target equipment; obtaining fusion features indicating features of the target equipment based on the parameter data; inputting the fusion features into a preset prediction model; and obtaining a prediction result output by the preset prediction model, where the prediction result indicates whether the product is abnormal.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REHAM K ABOUZAHRA whose telephone number is (571)272-0419. The examiner can normally be reached M-F 7:00 AM to 5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Brian Epstein can be reached at (571)-270-5389. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/REHAM K ABOUZAHRA/ Examiner, Art Unit 3625
Prosecution Insights