DETAILED ACTION
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 (i.e., changing from AIA to pre-AIA ) 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.
Claim Objections
Claim 7 is objected to because of the following informalities: The metes and bounds of ELU are unclear. For examination purposes, ELU is assumed to be exponential linear unit (ELU). Appropriate correction is required.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-2 and 9-11 are rejected under 35 U.S.C. 102(a)(1) as being unpatentable by
U.S. Patent Application Publication No. 2006/0178762 (Wroblewski).
Claim 1:
The cited prior art describes an AI-based optimal air damper control method comprising: (Wroblewski: “The present invention relates generally to the operation of a power generating plant, and more particularly to a method and apparatus for optimizing the operation of a power generating plant using artificial intelligence techniques.” Paragraph 0001; “Distributed Control System (DCS) 46 is a computer system that provides control of the combustion process by operation of system devices, including, but not limited to, valve actuators for controlling water and steam flows, damper actuators for controlling air flows, and belt-speed control for controlling flow of coal to mills.” Paragraph 0053)
a first step of collecting, by a system, industrial boiler operational data; (Wroblewski: see the sensor/measurement system 14 as illustrated in figure 3 and plant parameters as described in paragraph 0073 and obtain data from plant data sources 102 as illustrated in figure 4A; “Sensor/measurement system(s) 14 sense or measure various plant parameters, described below.” Paragraph 0051)
a second step of calculating, by the system, energy efficiency under a given control condition and an environment by extracting energy efficiency-related data from the collected industrial boiler operational data and analyzing a correlation between corresponding data; (Wroblewski: see the performance calculation system 42 as illustrated in figure 3; “Performance calculation system 42 is a computer or manually collected data system that determines full or partial plant heat rate calculations, efficiencies, or controllable loss components for steam generation. These controllable loss components can be summed to produce an "efficiency reference index" (ERI).” Paragraph 0052; see also the SBCalcs parameters used to establish relationships between parameters of the boiler as described in paragraphs 0061, 0062 and as illustrated in neural network training 134 as illustrated in figure 4C)
a third step of training, by the system, an optimal air volume-for-load prediction model which is based on Al, by using the extracted data and the calculated energy efficiency as training data; and (Wroblewski: see the neural network retraining 138 as illustrated in figure 4C; ‘Neural network model 60 is trained using normal power plant operation, parametric testing and/or historical data. . . . Neural network model 60 thus developed is then utilized in conjunction with an optimizer 70 to determine appropriate adjustments to input parameters for achieving the desired goals, within defined constraints, as will be described in detail below.” Paragraph 0081)
a fourth step of
deriving, by the system, an air volume condition that results in peak energy efficiency under a given load, based on the trained optimal air volume-for-load prediction model, and (Wroblewski: see the optimizer 70 solving for the best desired outcome 114 as described in paragraphs 0083, 0100 and as illustrated in figures 2, 4A; see the boiler efficiency output as described in table 2; “Neural network model 60 thus developed is then utilized in conjunction with an optimizer 70 to determine appropriate adjustments to input parameters for achieving the desired goals, within defined constraints, as will be described in detail below.” Paragraph 0081; “COS 34 is a computer system that optimizes the combustion process by optimizing air flows, fuel flows, distributions, pressures, air/fuel temperatures and heat absorption, to achieve optimal combustion conditions.” Paragraph 0075; “As shown in FIG. 2, neural network model 60 receives input parameters and generates output parameters. The input parameters may include, but are not limited to, parameter values associated with SBCalcs parameters and plant parameters.” Paragraph 0076)
automatically controlling an air damper according to the corresponding air volume condition. (Wroblewski: “Distributed Control System (DCS) 46 is a computer system that provides control of the combustion process by operation of system devices, including, but not limited to, valve actuators for controlling water and steam flows, damper actuators for controlling air flows, and belt-speed control for controlling flow of coal to mills.” paragraphs 0053; “Output data of COS 34 (i.e., the control value recommendations) may be received by Distributed Control System (DCS) 46 to provide real-time optimal control of the combustion process.” Paragraph 0075)
Claim 2:
The cited prior art describes the AI-based optimal air damper control method of claim 1 wherein the collected industrial boiler operational data includes
a quantity of feed water, (Wroblewski: see spray flow as described in table 1; “Distributed Control System (DCS) 46 is a computer system that provides control of the combustion process by operation of system devices, including, but not limited to, valve actuators for controlling water and steam flows” paragraph 0053)
a temperature of feed water, (Wroblewski: “temperatures . . . related to pre-combustion, combustion and post-combustion stages in a power plant.” Paragraph 0073)
a quantity of fuel used, (Wroblewski: see coal feed as described in table 1; “Fuel parameters include, but are not limited to, fuel composition parameters, various flue gases derived from the combustion of fuel, fuel processing inputs such as vibrations, fuel handling flow rates, grind, viscosity, particle size variables, and the like.” Paragraph 0073; “By way of example, and not limitation, fuel parameters 40 may include sensors or calculations that provide data indicative of the volume and type of fuel being consumed, or ready to be consumed.” Paragraph 0050)
a boiler pressure, (Wroblewski: see pressures as described in table 1; “pressures . . . related to pre-combustion, combustion and post-combustion stages in a power plant.” Paragraph 0073)
an exhaust gas NOx, (Wroblewski: “levels of nitrous oxides (NOx)” Paragraph 0073)
02, (Wroblewski: see excess oxygen as described in table 1)
an exhaust gas temperature, (Wroblewski: see outlet temperatures as described in table 1; “temperatures . . . related to pre-combustion, combustion and post-combustion stages in a power plant.” Paragraph 0073)
an air damper input value, and (Wroblewski: see air damper position as described in table 1; “Combustion parameters include, but are not limited to, temperatures, pressures, flows, speeds, weights, volumes, voltages, currents, wattages, resistances, positions, velocities, mass, sizes, vibration measurements, flue gas constituents, grind measurement, viscosity, and the like related to pre-combustion, combustion and post-combustion stages in a power plant. . . State indicators include, but are not limited to, 0/1, on/off, open/close, manual/auto, local/remote, in-calibration, out-of-service, in-hold, not-in-hold, power plant device states (e.g., soot cleaning device states), and the like.” Paragraph 0073)
a fuel damper input value. (Wroblewski: see coal feed as described in table 1; “Fuel parameters include, but are not limited to, fuel composition parameters, various flue gases derived from the combustion of fuel, fuel processing inputs such as vibrations, fuel handling flow rates, grind, viscosity, particle size variables, and the like.” Paragraph 0073)
Claim 9:
The cited prior art describes the AI-based optimal air damper control method of claim 1, wherein the system does not perform the first step to the third step on a one-time basis, and, when new industrial boiler operational data is collected, periodically refines the optimal air volume-for-load prediction model by adding the new industrial boiler operational data to the training data. (Wroblewski: see the neural network model retrainer 62 as illustrated in figures 1, 4C and as described in paragraphs 0126, 0142, 0144; “Neural network model retrainer 62 periodically retrains neural network model 60. This on-line retraining capability permits neural network models to adapt to changing power plant operation, equipment and fuel conditions. A retraining process can be initiated on the basis of event/trigger conditions or elapsed time.” Paragraph 0126)
Claim 10:
The cited prior art describes an AI-based optimal air damper control system comprising: (Wroblewski: “The present invention relates generally to the operation of a power generating plant, and more particularly to a method and apparatus for optimizing the operation of a power generating plant using artificial intelligence techniques.” Paragraph 0001; “Distributed Control System (DCS) 46 is a computer system that provides control of the combustion process by operation of system devices, including, but not limited to, valve actuators for controlling water and steam flows, damper actuators for controlling air flows, and belt-speed control for controlling flow of coal to mills.” Paragraph 0053)
a communication unit configured to collect industrial boiler operational data; and (Wroblewski: see the sensor/measurement system 14 as illustrated in figure 3 and plant parameters as described in paragraph 0073 and obtain data from plant data sources 102 as illustrated in figure 4A; “Sensor/measurement system(s) 14 sense or measure various plant parameters, described below.” Paragraph 0051)
a processor configured (Wroblewski: “The computer hardware may take the form of a conventional computer system including a processor, data storage devices” paragraph 0041)
to calculate energy efficiency under a given control condition and an environment by extracting energy efficiency-related data from the collected industrial boiler operational data and analyzing a correlation between corresponding data, (Wroblewski: see the performance calculation system 42 as illustrated in figure 3; “Performance calculation system 42 is a computer or manually collected data system that determines full or partial plant heat rate calculations, efficiencies, or controllable loss components for steam generation. These controllable loss components can be summed to produce an "efficiency reference index" (ERI).” Paragraph 0052; see also the SBCalcs parameters used to establish relationships between parameters of the boiler as described in paragraphs 0061, 0062 and as illustrated in neural network training 134 as illustrated in figure 4C)
to train an optimal air volume-for-load prediction model which is based on AI, by using the extracted data and the calculated energy efficiency as training data, and (Wroblewski: see the neural network retraining 138 as illustrated in figure 4C; ‘Neural network model 60 is trained using normal power plant operation, parametric testing and/or historical data. . . . Neural network model 60 thus developed is then utilized in conjunction with an optimizer 70 to determine appropriate adjustments to input parameters for achieving the desired goals, within defined constraints, as will be described in detail below.” Paragraph 0081)
to derive an air volume condition that results in peak energy efficiency under a given load, based on the trained optimal air volume-for-load prediction model, and (Wroblewski: see the optimizer 70 solving for the best desired outcome 114 as described in paragraphs 0083, 0100 and as illustrated in figures 2, 4A; see the boiler efficiency output as described in table 2; “Neural network model 60 thus developed is then utilized in conjunction with an optimizer 70 to determine appropriate adjustments to input parameters for achieving the desired goals, within defined constraints, as will be described in detail below.” Paragraph 0081; “COS 34 is a computer system that optimizes the combustion process by optimizing air flows, fuel flows, distributions, pressures, air/fuel temperatures and heat absorption, to achieve optimal combustion conditions.” Paragraph 0075; “As shown in FIG. 2, neural network model 60 receives input parameters and generates output parameters. The input parameters may include, but are not limited to, parameter values associated with SBCalcs parameters and plant parameters.” Paragraph 0076)
to automatically control an air damper according to the corresponding air volume condition. (Wroblewski: “Distributed Control System (DCS) 46 is a computer system that provides control of the combustion process by operation of system devices, including, but not limited to, valve actuators for controlling water and steam flows, damper actuators for controlling air flows, and belt-speed control for controlling flow of coal to mills.” paragraphs 0053; “Output data of COS 34 (i.e., the control value recommendations) may be received by Distributed Control System (DCS) 46 to provide real-time optimal control of the combustion process.” Paragraph 0075)
Claim 11:
The cited prior art describes an AI-based optimal air damper control method comprising: (Wroblewski: “The present invention relates generally to the operation of a power generating plant, and more particularly to a method and apparatus for optimizing the operation of a power generating plant using artificial intelligence techniques.” Paragraph 0001; “Distributed Control System (DCS) 46 is a computer system that provides control of the combustion process by operation of system devices, including, but not limited to, valve actuators for controlling water and steam flows, damper actuators for controlling air flows, and belt-speed control for controlling flow of coal to mills.” Paragraph 0053)
a step of training, by a system, an optimal air volume-for-load prediction model which is based on AI, by using energy efficiency-related data and a result of calculating energy efficiency as training data; and (Wroblewski: see the neural network retraining 138 as illustrated in figure 4C; ‘Neural network model 60 is trained using normal power plant operation, parametric testing and/or historical data. . . . Neural network model 60 thus developed is then utilized in conjunction with an optimizer 70 to determine appropriate adjustments to input parameters for achieving the desired goals, within defined constraints, as will be described in detail below.” Paragraph 0081)
a step of deriving, by the system, an air volume condition that results in peak energy efficiency under a given load, based on the trained optimal air volume- for-load prediction model, and (Wroblewski: see the optimizer 70 solving for the best desired outcome 114 as described in paragraphs 0083, 0100 and as illustrated in figures 2, 4A; see the boiler efficiency output as described in table 2; “Neural network model 60 thus developed is then utilized in conjunction with an optimizer 70 to determine appropriate adjustments to input parameters for achieving the desired goals, within defined constraints, as will be described in detail below.” Paragraph 0081; “COS 34 is a computer system that optimizes the combustion process by optimizing air flows, fuel flows, distributions, pressures, air/fuel temperatures and heat absorption, to achieve optimal combustion conditions.” Paragraph 0075; “As shown in FIG. 2, neural network model 60 receives input parameters and generates output parameters. The input parameters may include, but are not limited to, parameter values associated with SBCalcs parameters and plant parameters.” Paragraph 0076)
automatically controlling an air damper according to the corresponding air volume condition. (Wroblewski: “Distributed Control System (DCS) 46 is a computer system that provides control of the combustion process by operation of system devices, including, but not limited to, valve actuators for controlling water and steam flows, damper actuators for controlling air flows, and belt-speed control for controlling flow of coal to mills.” paragraphs 0053; “Output data of COS 34 (i.e., the control value recommendations) may be received by Distributed Control System (DCS) 46 to provide real-time optimal control of the combustion process.” Paragraph 0075)
Claim Rejections - 35 USC § 103
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 factual inquiries 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.
Claims 3-5 are rejected under 35 U.S.C. 103 as being unpatentable over
U.S. Patent Application Publication No. 2006/0178762 (Wroblewski) in view of
Shah, Sunit, and D. M. Adhyaru. "Boiler efficiency analysis using direct method." 2011 Nirma university international conference on engineering. IEEE, 2011 (Shah).
Claim 3:
Wroblewski does not explicitly describe an equation as described below. However, Shah teaches the equation as described below.
The cited prior art describes the AI-based optimal air damper control method of claim 1 wherein the second step comprises calculating the energy efficiency by referring to Equation 2 presented below:
PNG
media_image1.png
116
605
media_image1.png
Greyscale
Equation 2
(Shah: “ This efficiency can be evaluated using the formula: Boiler Efficiency (η=Q×H−h)q×GCV×00(2) where Q is Quantity of steam (dry) generated in T/hr q is Quantity of coal consumed in T/hr H is Enthalpy of steam kJ/kg h is Enthalpy of feed water in kJ/kg GCV is Gross Calorific Value of coal in kJ/kg” section III)
One of ordinary skill in the art would have recognized that applying the known technique of Wroblewski, namely, power generating plant control using artificial intelligence techniques, with the known techniques of Shah, namely, boiler efficiency analysis, would have yielded predictable results and resulted in an improved system. Accordingly, applying the teachings of Wroblewski to control a power generating plant with a boiler based on various techniques including efficiency techniques with the teachings of Shah to perform boiler efficiency analysis would have been recognized by those of ordinary skill in the art as resulting in an improved industrial boiler control system (i.e., the combination of the references provides for a boiler control system that uses various AI and boiler efficiency analysis techniques based on the teachings of boiler control using various AI in Wroblewski and the teachings of boiler efficiency analysis in Shah).
Claim 4:
Wroblewski does not explicitly describe an equation as described below. However, Shah teaches the equation as described below.
The cited prior art describes the AI-based optimal air damper control method of claim 3, wherein the second step comprises, when energy efficiency is calculated by referring to Equation 2 above,
using a heat transfer value for a boiler pressure in a saturated steam table as the enthalpy of steam, and (Shah: see the enthalpy of steam formula as described in section III.A)
using a higher heating value of fuel used by the boiler as the calorific value of fuel. (Shah: see the use of the calorific value for gaseous fuel, liquid fuel, and solid fuel as described in section III)
Wroblewski and Shah are combinable for the same rationale as set forth above with respect to claim 3.
Claim 5:
The cited prior art describes the AI-based optimal air damper control method of claim 3, wherein the third step comprises,
when training the optimal air volume-for-load prediction model, using, as training data, energy efficiency-related data including (Wroblewski: see the neural network retraining 138 as illustrated in figure 4C; ‘Neural network model 60 is trained using normal power plant operation, parametric testing and/or historical data. . . . Neural network model 60 thus developed is then utilized in conjunction with an optimizer 70 to determine appropriate adjustments to input parameters for achieving the desired goals, within defined constraints, as will be described in detail below.” Paragraph 0081)
a boiler pressure, (Wroblewski: see pressures as described in table 1; “pressures . . . related to pre-combustion, combustion and post-combustion stages in a power plant.” Paragraph 0073)
a quantity of fuel used (load), (Wroblewski: see coal feed as described in table 1; “Fuel parameters include, but are not limited to, fuel composition parameters, various flue gases derived from the combustion of fuel, fuel processing inputs such as vibrations, fuel handling flow rates, grind, viscosity, particle size variables, and the like.” Paragraph 0073; “By way of example, and not limitation, fuel parameters 40 may include sensors or calculations that provide data indicative of the volume and type of fuel being consumed, or ready to be consumed.” Paragraph 0050)
a temperature of feed water, (Wroblewski: “temperatures . . . related to pre-combustion, combustion and post-combustion stages in a power plant.” Paragraph 0073)
an air damper input value, and (Wroblewski: see air damper position as described in table 1; “Combustion parameters include, but are not limited to, temperatures, pressures, flows, speeds, weights, volumes, voltages, currents, wattages, resistances, positions, velocities, mass, sizes, vibration measurements, flue gas constituents, grind measurement, viscosity, and the like related to pre-combustion, combustion and post-combustion stages in a power plant. . . State indicators include, but are not limited to, 0/1, on/off, open/close, manual/auto, local/remote, in-calibration, out-of-service, in-hold, not-in-hold, power plant device states (e.g., soot cleaning device states), and the like.” Paragraph 0073)
the calculated energy efficiency (boiler efficiency). (Wroblewski: see the performance calculation system 42 as illustrated in figure 3; “Performance calculation system 42 is a computer or manually collected data system that determines full or partial plant heat rate calculations, efficiencies, or controllable loss components for steam generation. These controllable loss components can be summed to produce an "efficiency reference index" (ERI).” Paragraph 0052; see also the SBCalcs parameters used to establish relationships between parameters of the boiler as described in paragraphs 0061, 0062 and as illustrated in neural network training 134 as illustrated in figure 4C)
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over
U.S. Patent Application Publication No. 2006/0178762 (Wroblewski) in view of
Shah, Sunit, and D. M. Adhyaru. "Boiler efficiency analysis using direct method." 2011 Nirma university international conference on engineering. IEEE, 2011 (Shah) and further in view of
U.S. Patent Application Publication No. 2020/0173649 (Maeng).
Claim 6:
Wroblewski and Shah do not explicitly describe abnormal data processing as described below. However, Maeng teaches the abnormal data processing as described below.
The cited prior art describes the AI-based optimal air damper control method of claim 5, wherein the third step comprises,
when performing pre-processing on the training data,
determining, as an abnormal data value, an efficiency value that is calculated when a boiler is turned off after water is drained off from a boiler water tank and steam is generated, and water supply is late, and (Maeng: “The pre-processor 20 performs signal restoration, filtering, and outlier processing functions. The signal restoration function is configured to restore signals collected from the boiler when there is some loss in the signals, or to restore the corresponding signal when the boiler has an abnormality or failure. The filtering function is configured to filter out, among the restored signals, data outside a normal data range or remove signal noise, and to further extract only data to be used for modeling, optimization operation, and output control, using a known knowledge-based logic. The outlier processing function is configured to process out-of-trend data, using a data-based logic.” Paragraph 0054) (Wroblewski: see the performance calculation system 42 as illustrated in figure 3; “Performance calculation system 42 is a computer or manually collected data system that determines full or partial plant heat rate calculations, efficiencies, or controllable loss components for steam generation. These controllable loss components can be summed to produce an "efficiency reference index" (ERI).” Paragraph 0052; see also the SBCalcs parameters used to establish relationships between parameters of the boiler as described in paragraphs 0061, 0062 and as illustrated in neural network training 134 as illustrated in figure 4C)
excluding the abnormal efficiency value from the training data. (Maeng: “The filtering function is configured to filter out, among the restored signals, data outside a normal data range or remove signal noise, and to further extract only data to be used for modeling, optimization operation, and output control, using a known knowledge-based logic.” Paragraph 0054)
One of ordinary skill in the art would have recognized that applying the known technique of Wroblewski, namely, power generating plant control using artificial intelligence techniques, with the known techniques of Shah, namely, boiler efficiency analysis, and the known techniques of Maeng, namely, boiler combustion optimization, would have yielded predictable results and resulted in an improved system. Accordingly, applying the teachings of Wroblewski to control a power generating plant with a boiler based on various techniques including efficiency techniques with the teachings of Shah to perform boiler efficiency analysis and the teachings of Maeng to perform data pre-processing for boiler control would have been recognized by those of ordinary skill in the art as resulting in an improved industrial boiler control system (i.e., the combination of the references provides for a boiler control system that uses various AI and boiler efficiency analysis techniques and data preprocessing based on the teachings of boiler control using various AI in Wroblewski and the teachings of boiler efficiency analysis in Shah and the teachings of data preprocessing to remove abnormal data in Maeng).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over
U.S. Patent Application Publication No. 2006/0178762 (Wroblewski) in view of
Shah, Sunit, and D. M. Adhyaru. "Boiler efficiency analysis using direct method." 2011 Nirma university international conference on engineering. IEEE, 2011 (Shah) and further in view of
U.S. Patent Application Publication No. 2020/0320237 (Na) and
U.S. Patent Application Publication No. 2021/0142171 (Jung).
Claim 7:
Wroblewski and Shah do not explicitly describe layers or an ELU as described below. However, Na teaches the layers and Jung teaches the ELU as described below.
The cited prior art describes the AI-based optimal air damper control method of claim 5, wherein the optimal air volume-for-load prediction model is configured to construct an artificial neural network that is comprised of three hidden layers and four neurons per hidden layer, and to use an [exponential linear unit] ELU as an activation function. (see the ANN with various layers in Na and the ELU in Jung) (Na: “The hidden layer may include 1 to 30 hidden layers and each of the hidden layers may include 1 to 5000 nodes.” Paragraph 0009; “he boiler combustion model may include a combination of mathematical models including an artificial neural network (ANN). An activation function of the artificial neural network (ANN) may include a linear function, a step function, a sigmoid function, and a rectified linear unit (ReLU) function. The mathematical model may include a transfer function model, a state space model, and an impulse/step response model.” Paragraph 0010) (Jung: “Examples of the activation function may be various such as sigmoid function, hyperbolic tangent function, rectified linear unit (ReLU) function, exponential linear unit (ELU) function, gaussian error linear unit (GELU) function, swish function, or the like. The activation functions according to the disclosure is not limited to a specific kind of activation function.” Paragraph 0043; “The “neural network model” refers to an artificial intelligence model including an artificial neural network, and may be learned by deep learning.” Paragraph 0041; “As described above, the neural network model 310 is an artificial intelligence model including an artificial neural network, and may use an activation function in performing a learning process and an inference process.” Paragraph 0070)
One of ordinary skill in the art would have recognized that applying the known technique of Wroblewski, namely, power generating plant control using artificial intelligence techniques, with the known techniques of Shah, namely, boiler efficiency analysis, and the known techniques of Na, namely, deriving a boiler combustion model, and the known techniques of Jung, namely, controlling an apparatus using various AI techniques, would have yielded predictable results and resulted in an improved system. Accordingly, applying the teachings of Wroblewski to control a power generating plant with a boiler based on various techniques including efficiency techniques with the teachings of Shah to perform boiler efficiency analysis and the teachings of Na to use various AI techniques for boiler control and the teachings of Jung to use various AI techniques for apparatus control would have been recognized by those of ordinary skill in the art as resulting in an improved industrial boiler control system (i.e., the combination of the references provides for a boiler control system that uses various AI and boiler efficiency analysis techniques based on the teachings of boiler control using various AI in Wroblewski and the teachings of boiler efficiency analysis in Shah and the teachings of using various AI techniques in Na and the teachings of using various AI techniques in Jung).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over
U.S. Patent Application Publication No. 2006/0178762 (Wroblewski) in view of
Shah, Sunit, and D. M. Adhyaru. "Boiler efficiency analysis using direct method." 2011 Nirma university international conference on engineering. IEEE, 2011 (Shah) and further in view of
U.S. Patent Application Publication No. 2007/0234781 (Yamada).
Claim 8:
Wroblewski and Shah do not explicitly describe training as described below. However, Yamada teaches the training as described below.
The cited prior art describes the AI-based optimal air damper control method of claim 5, wherein the fourth step comprises,
when using the trained optimal air volume-for- load prediction model, (Yamada: “A second object of the present invention is to provide plant control method and apparatus based on reinforcement learning method in which a model construction period is short and which has excellent performance.” Paragraph 0029)
fixing a quantity of fuel used, a temperature of feed water, a boiler pressure, and (Yamada: “At a step 510, a result value 245 of air flow rates at every position of the burner and the after-air port from a predetermined period (for example, one month) to the present state, fuel flow rate of every burner, outputs of the generator, NOx concentration and CO concentration is read out from the running results database 240.” Paragraph 0085; see the data creation 580 only if other data is within allowable range 570 as illustrated in figure 4; “a fuel data storage unit for storing operation parameters of the combustion apparatus and data sets of components in gas relative to a plurality of fuel compositions supplied to the combustion apparatus” paragraph 0030) (Wroblewski: see pressures as described in table 1; “pressures . . . related to pre-combustion, combustion and post-combustion stages in a power plant.” Paragraph 0073; “temperatures . . . related to pre-combustion, combustion and post-combustion stages in a power plant.” Paragraph 0073)
changing only an air damper input value within an allowable range, and (Yamada: see the air flow rate of the boiler as illustrated in figure 18 and as described in paragraph 0201; “The reinforcement learning unit 290 outputs the simulated operation command signal 265 composed of the air flow rates of every position of the burner and the after-air port and the fuel flow rate of every burner to a model made by the modeling unit 250. The simulated operation command signal 265 corresponds to the plant operation condition and upper and lower limit values, range (unit width) and the maximum range that can be used in one operation are set.” Paragraph 0130)
predicting boiler efficiency according to a change in the air damper input value, and (Yamada: see the rewards as described in paragraphs 0132, 0133, 0134; “The reinforcement learning unit 290 receives the output data 255 from the modeling unit 250 and calculates a reward value.” Paragraph 0132)
using an air damper input value based on which peak boiler efficiency is predicted for automatically controlling the air damper. (Yamada: “Next, an operation amount operating unit 1015 calculates a value of an air flow rate to be operated by using running data outputted from the external input interface 1003 and the learning result database 1014. If the learning result is that shown in FIG. 16, an air flow rate of 0.45 may become an air flow rate of +0.05 under control of a control signal. The calculated control signal is outputted to a subtracter 1016.” Paragraph 0197; “Since the reinforcement learning unit 290 learns a combination of the simulated operation command signals 265, that is, the operation amounts such that the reward calculated by the equation (5) may become maximum, it can therefore learn a combination of operation amounts to decrease NOx and CO in response to the present state.” Paragraph 0136)
One of ordinary skill in the art would have recognized that applying the known technique of Wroblewski, namely, power generating plant control using artificial intelligence techniques, with the known techniques of Shah, namely, boiler efficiency analysis, and the known techniques of Yamada, namely, boiler control, would have yielded predictable results and resulted in an improved system. Accordingly, applying the teachings of Wroblewski to control a power generating plant with a boiler based on various techniques including efficiency techniques with the teachings of Shah to perform boiler efficiency analysis and the teachings of Yamada to perform AI training for a boiler would have been recognized by those of ordinary skill in the art as resulting in an improved industrial boiler control system (i.e., the combination of the references provides for a boiler control system that uses various AI and boiler efficiency analysis techniques and AI training based on the teachings of boiler control using various AI in Wroblewski and the teachings of boiler efficiency analysis in Shah and the teachings of AI training for a boiler in Maeng).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Patent Application Publication No. 2007/0250215 describes optimizing oxygen in a boiler.
U.S. Patent Application Publication No. 2007/0156288 describes model based control of a steam generating plant.
U.S. Patent Application Publication No. 2007/0142975 describes model based optimization for power generating units.
U.S. Patent Application Publication No. 2009/0132095 describes model based control of a boiler.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTOPHER E EVERETT whose telephone number is (571)272-2851. The examiner can normally be reached Monday-Friday 8:00 am to 5:00 pm (Pacific).
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, Robert Fennema can be reached at 571-272-2748. 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.
/Christopher E. Everett/Primary Examiner, Art Unit 2117