DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 05/21/2024 has been considered by the examiner.
Claim Objections
Claims 1, 7, 11 and 13 objected to because of the following informalities:
(i) Claims 1 and 7 use “a first input data” (line 2) and “a second input data”. It is respectfully suggested to amend the limitation to “first input data”/ “second input data” or “a first data set” or “a second data set” because data is plural/mass noun.
(ii) Claim 11 recites “a trend analysis data” (lines 2-3). It is respectfully suggested to amend the limitation to “trend analysis data or “a trend analysis data set” because data is plural/mass noun.
(iii) Claim 13 recites “the control system in communication with a plurality of sensors comprising a processor and a memory” (lines 5-6) could be read as the sensors comprising the processor/memory. It is respectfully suggested to amend the limitation to “the control system, which is in communication with the plurality of sensors, comprising a processor and a memory…”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claim 4 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regard(s) as the invention.
(i) Claim 4 recites “input data” while claim 1 recites previously recites “a first input data” Claim 12 likewise recites “the input data” without clear antecedent basis. It is indefinite since it is unclear the “input data” refers to the input data of claim 1 or some other input data See MPEP 2173 and 608.01 (o).
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 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.
Claims 1-12 are rejected under 35 USC 103 as being unpatented over Na et al., (US 2023/0213898 A1, hereinafter as “Na”) in view of Piironen et al., (US 2020/0223719 A1, hereinafter as “Piironen”).
Regarding claim 1, Na discloses a method of chemical dosing optimization in water treatment (Abstract; ¶¶ [0002-0007], ¶¶ [0050-0060], ¶¶ [0085-0095]), comprising:
obtaining real-time data from a wastewater treatment plant 1, including operating data and state
data of feed water/treated water (Fig. 1, ¶¶ [0052, 0056), which meets the recited limitation, “obtaining a first input data indicative of properties of a first liquid sample,”
the input attribute data including the operating data and the state data related to the feed water flowing into the water treatment plant 1; input attribute data including flow rate of the feed water flowing into the water treatment plant 1, temperature, turbidity (turbidity can serve as proximate indicator of total suspended solids if calibrated to the local water source), the chemical dosage for the feed water, and pH (Fig. 1, ¶¶ [0056), which meets the recited limitation, “the first input data comprising turbidity data and total suspended solids data, wherein the first liquid sample is acquired from a liquid source;”
determining, using a computer processor (Fig. 12; ¶ [0129-0131]), and a machine-learning/model–based water treatment model (¶ [0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the recited limitation, “determining, using a computer processor and a machine learning model”; and the chemical dosage/control values are configurable by a water treatment control device (¶ [0074]), which meets the recited limitation, “a set of dosage parameters configurable by a water quality system”;
determining, by deriving an optimized control value (optimized chemical dosage concentrations)
using a controller(optimizer) based on a prediction value from the water-treatment model using machine learning-based model (¶¶ [00180, 0071]) and providing the control to the water-treatment control device (Fig.1, ¶ [0092, 0096]), which meets the recited limitation, determining, with an optimizer applied to the machine learning model, an optimized set of dosage parameters.”
adjusting and controlling the set chemical dosage by providing the optimized control value to
the water treatment control device (¶¶ [0095 0096]), which meets the recited limitation, “adjusting the set dosage of the water quality system to the optimal set of dosage parameters.”
But Na does not teach: (I) a first predicted parameter of the first liquid sample based on the first input data is “particle-size distribution”; (II) wherein controlled parameter, at least in part, by a set of dosage parameters configurable by a water quality system, is “particle-size distribution”; and (III) an optimal set of dosage parameters based on the first predicted parameter is “particle-size distribution”.
Regarding the limitations of (I), (II), and (III), Piironen teaches monitoring of suspended solids and/or optimization of coagulation and/or flocculation in a water treatment process using particle characteristics, including particle size distribution and floc size/count, and expressly teaches utilization of particle size distribution for adjusting dosing of chemicals (Abstract; ¶¶ [0036-0037). Piironen discloses the “predicted particle-size distribution”/particle size distribution optimization aspect because particle size distribution is used as a process variable for adjusting chemical dosing in coagulation/flocculation (Fig. 1, ¶¶ [0036-0037]).
Na and Piironen are analogous arts because both refences are directed to automated control or optimization of chemical dosing in water treatment processes, including coagulation/flocculation, turbidity mitigation, and suspended particle removal. Na is classified in water treatment chemical dosing/control and teaches model-based chemical dosage optimization and Piironen is directed to coagulation/flocculation using particle size distribution and floc-size characteristics. These references are reasonably pertinent to the same problem faced by the applicant: determining and adjusting chemical dosage parameters to improve water quality and particle aggregation/removal based on measured water quality conditions.
Therefore, before the effective filing date of the claimed invention, it would have been prima facie obvious to one of ordinary skill in the art to modify Na’s machine learning/water treatment model based chemical dosing optimization system with Piironen’s particle size distribution/floc size information as an optimized state variable to provide the feature of “a first predicted parameter is “a first predicted particle-size distribution of the first liquid sample”, “wherein particle-size distribution is controlled, at least in part, by a set of dosage parameters configurable by a water quality system”, and “an optimal set of dosage parameters based on the first predicted particle-size distribution” because the combination would have predictably improve dosing accuracy and suspended-particle removal while reducing chemical overuse as taught by Piironen (¶¶ [0004, 0024-0025]).
In regard to claim 2, Na discloses deriving an optimized control value for chemical dosing and providing the control value to a water-treatment control device for controlling addition of chemical to the water treatment (¶¶ [0095 0096]), which meets the recited limitation, “determining a set dosage, and injecting the chemical into the liquid source at the dosage, wherein in the dosage is comprised by the optimal set of dosage parameters.”
But Na does not disclose that the optimized value is specifically based on dosage rate and the predicted particle size distribution.
Piironen discloses adjusting chemical dosing (using a chemical dosing controller operated by a PLC device) and in coagulation/flocculation based on particle-size distribution and floc characteristics (Abstract; ¶¶ [0016-0023], [0054]). Piironen further discloses the “predicted particle-size distribution”/particle size distribution optimization aspect because particle size distribution is used as a process variable for adjusting chemical dosing in coagulation/flocculation (Fig. 1, ¶¶ [0036-0037]).
It would have been obvious to implement Na’s optimized chemical dosing control with Piironen’s programmable logic controller-based dosing adjustment based on predicted particle size distribution, as a chemical dosage/feed rate because chemical dosing devices in water treatment systems are conventionally controlled by dosage rate to deliver a desired amount of coagulant/flocculant into a liquid stream as evidenced by Narges et al., (Prediction of the optimal dosage of coagulants in water treatment plants through developing models based on artificial neural network fuzzy inference system (ANFIS), 2021, 19, pp. 1543-1553; p. 1549, right column, line 1 thru, p. 1550 left column, second paragraph line 9), to provide the feature “ determining a dosage rate for a chemical based on the first predicted particle-size distribution, and injecting the chemical into the liquid source at the dosage rate, wherein the dosage rate is comprised by the optimal set of dosage parameters.”
In regard to claim 3, Na discloses the water treatment model is an algorithm including the learning model may be a pattern recognition model or a machine learning model that determines whether the water treatment plant is in the optimized state or not (¶ [0071]). A support vector machine would have been obvious known machine learning model choice for predicting water-treatment outputs from measured inputs as evidenced by Han et al., (Flood forecasting using support vector machines, Journal of Hydroinformatics, 2007, 9(4), pp 267-276; p. 273, second column, Model Response to Rainfall heading, lines 1-2).
In regard to claim 4, Na discloses a computer processor (Fig. 12, ¶¶ [0042, 0131]), input data (¶ [0057]) and data preprocessing, including perform signal processing, normal data processing and outlier removal to remove noise, or to remove noise in data (¶ [0057]). Normalization is an obvious preprocessing technique for machine learning as evidenced by Han et al., (Flood forecasting using support vector machines, Journal of Hydroinformatics, 2007, 9(4), pp 267-276; p. 272, first and second column, The application of SVM in flood forecasting heading, first column lines 1-2 thru second column lines 1-3) where Han emphasizes the importance of normalization in prediction efforts using SVM by rescaling features to a common range to that all variables contribute equally to the model (i.e., scaling input data down to -1 and 1).
In regard to claim 5 and 6, Piironen discloses optimization of coagulation/flocculation using particle size distribution and floc size using statistical value characterizing the particle size distribution may be e.g. skewedness, kurtosis, quartiles, median, and mode information (¶ [0092] and using such information for chemical dosing adjustment (claim 5) (¶ [0043, 0094]). Maximizing aggregation and increased median particle size (claim 6) would have been obvious because coagulation/flocculation converts smaller suspended particles into larger flocs for separation (Piironen: ¶ [0094]).
In regard to claim 7, Na, in view of Piironen, discloses the method of claim 1 as set forth above, comprising:
obtaining second input data from the real-time raw data continuous (i.e., plurality of input data;
first, second, …etc.) collection from water treatment plant, or the water control device 2 (Fig. 1, (¶ [0091]). In particular, Na discloses a closed-loop/current state use of water treatment data and output/correction/adjustment of dosage control values of the dosage parameters (¶ [0055-0056]). Attribute data may include input attribute data may include the flow rate of the feed water, temperature, conductivity, acidity (or hydrogen ion concentration), turbidity, the throughput for the feed water (per unit time), the chemical dosage for the feed water, the chemical dosing concentration, etc.; the output attribute data may include the operating data and the state data related to the treated water subjected to water treatment (¶ [0056], which meets the claim limitation, “obtaining a second input data indicative of properties of a second liquid sample, the second input data comprising turbidity data and total suspended solids data for the second liquid sample, wherein the second liquid sample is collected after adjusting the set of dosage parameters”
determining, using a computer processor (Fig. 12; ¶ [0129-0131]), and a machine-
learning/model–based water treatment model (¶ [0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the recited limitation, “determining, using a computer processor and a machine learning model”; and the chemical dosage/control values are configurable by a water treatment control device (¶ [0074]), which meets the recited limitation, “a set of dosage parameters configurable by a water quality system”;
But Na does not teach: (I) a second predicted parameter of the second liquid sample based on the second input data is “particle-size distribution”; (II) validating an optimal set of dosage parameters for validation based on the second predicted parameter is “particle-size distribution”;
Regarding (I) and (II), Piironen discloses monitoring particle size distribution/floc development during coagulation and flocculation (¶¶ [0036-0037]) and the floc growth rate (i.e., increase in particle aggregation). Piironen further discloses dosage adjustments are determined in the control unit1, based on predefined data P1 stored in a memory and which may contain information about target value(s) for particle size distribution, particle concentration, turbidity and / or color of water, and / or reference values of particle size distribution, particle concentration, turbidity, suspended solids and / or color of water in standard samples (Fig. 1, ¶ [0037]). Data P1 is compared in the control unit 11 with measured feedback data P2 from the image analyzing unit 13 (Fig. 1, ¶ [0037]). Thus, post-adjustment sampling/measurement and validation of increased particle aggregation would have been obvious feedback verification using the computer processor and the machine learning prediction model set forth in claim 1l, which meets the limitation “validating the optimal set of dosage parameters”
Therefore, before the effective filing date of the claimed invention, it would have been prima facie obvious to one of ordinary skill in the art to modify Na’s machine learning/water treatment model based chemical dosing optimization and data collection system with Piironen’s particle size distribution/floc size information as an optimized state variable to provide the feature of “a second predicted parameter is “a second predicted particle-size distribution of the second liquid sample based on the second input data”, and “validating the optimal set of dosage parameters with a determination that a particle aggregation of the second liquid sample is increased relative to a particle aggregation of the first liquid sample based on the first and second predicted particle-size distributions” because the combination would have predictably improve dosing accuracy and suspended-particle removal while reducing chemical overuse as taught by Piironen (¶¶ [0004, 0024-0025]).
In regard to claim 8, Piironen discloses method of claim 1, comprising:
measuring the particle distribution before and after the separation unit at sampling points which
allows refinement of the coagulant dosage control (¶ [(0047]) which meets the limitation “measuring the particle-size distribution of a second liquid sample, wherein the second liquid sample is collected after adjusting the set of dosage parameters”
validating the optimal set of parameters by monitoring particle size distribution/floc development
during coagulation and flocculation (¶¶ [0036-0037]) and the floc growth rate (i.e., increase in particle aggregation). Piironen further discloses dosage adjustments are determined in the control unit1, based on predefined data P1 stored in a memory and which may contain information about target value(s) for particle size distribution, particle concentration, turbidity and / or color of water, and / or reference values of particle size distribution, particle concentration, turbidity, suspended solids and / or color of water in standard samples (Fig. 1, ¶ [0037]). Data P1 is compared in the control unit 11 with measured feedback data P2 from the image analyzing unit 13 (Fig. 1, ¶ [0037]). Thus, post-adjustment sampling/measurement and validation of increased particle aggregation would have been obvious feedback verification using the computer processor and the machine learning prediction model set forth in claim 1l, which meets the limitation “validating the optimal set of dosage parameters with a determination that a particle aggregation of the second liquid sample is increased relative to a particle aggregation of the first liquid sample, the particle aggregation of the first liquid sample determined using the first predicted particle-size distribution.”
In regard to claim 9, Na discloses:
determining, using a computer processor (Fig. 12; ¶ [0129-0131]), and a machine-
learning/model–based water treatment model (¶ [0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the recited limitation, “determining, using a computer processor and a machine learning model”, and a treated-water state and determining whether the state is within the normal range (¶ [0059]). Na further discloses that the state recognition-based processing part 120 may analyze the state data of the water treatment plant 1 to detect an abnormal state of the water treatment plant and determining whether the state is within the normal range (¶ [0059]), thereby determining a second condition for determining whether to perform the chemical dosing optimization process (¶ [0072]), which meets the limitation “a quality assessment metric based on a parameter of the first liquid sample;”
generating, one or more alerts regarding liquid quality by determining whether the water-state is
within the normal range (¶ [0059]) and that the state recognition-based processing part 120 may analyze the state data of the water treatment plant 1 to detect an abnormal state of the water treatment plant, thereby determining a second condition for determining whether to perform the chemical dosing optimization process (¶ [0072]).
But Na does not teach: a quality assessment metric based on the first particle-size distribution of the first liquid sample is “particle-size distribution”
However, Piironen discloses monitoring particle size distribution/floc development during coagulation and flocculation and further discloses monitoring particle size distribution/floc development during coagulation and flocculation, and Data P1 is compared in the control unit 11 with measured feedback data P2 from the image analyzing unit 13 (Fig. 1, ¶¶ [0036-0037]).
Therefore, before the effective filing date of the claimed invention, it would have been prima facie obvious to one of ordinary skill in the art to modify Na’s machine learning/water treatment model based with quality assessment metric system and alert system with Piironen’s particle size distribution/floc size information as an optimized state variable to provide the feature of “a quality assessment metric based on the first particle-size distribution of the first liquid sample” and because the combination would have predictably improve dosing accuracy and suspended-particle removal while reducing chemical overuse as taught by Piironen (¶¶ [0004, 0024-0025]) by having system alert monitoring system and a quality assessment metric.
In regard to claim 10, Na discloses predicting (i.e., using the computer processor and machine learning model) a treated-water state and determining whether the state is within the normal range (¶ [0059]). Na further discloses that the state recognition-based processing part 120 may analyze the state data of the water treatment plant 1 to detect an abnormal state of the water treatment plant, thereby determining a second condition for determining whether to perform the chemical dosing optimization process (¶ [0072]). In addition, Piironen also discloses monitoring particle size distribution/floc development during coagulation and flocculation, and Data P1 is compared in the control unit 11 with measured feedback data P2 from the image analyzing unit 13 (Fig. 1, ¶¶ [0036-0037]). Therefore, generating alerts based on a water quality assessment metric on the first-particle distribution of the liquid sample, that is being outside an acceptable level would have been an obvious system alert monitoring response as taught by Piironen (¶¶ [0036-0037]); thus both teachings by Na and Piironen to claim 10, meets the claim limitation “wherein the quality assessment metric comprises a liquid quality level, wherein the one or more alerts are generated based on a determination that the liquid quality level is lower than an acceptable liquid quality level.”
In regard to claim 11, Na discloses use of real-time data, raw data, training data, verification data, model selection, current state comparison, and output/guidance information (¶¶ [0112-0115]) and using a computer processor (Fig 12; ¶ [0129-0131]), and a machine-learning/model–based water treatment model (¶ [0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the limitation “ determining, using the computer processor and the machine learning model, a trend analysis data based, at least in part, on the first predicted parameter; and generating, using the computer processor and the machine learning model, a liquid quality report based, at least in part, on the first predicted parameter.”
But Na does not teach: (I) a first predicted parameter of the first liquid sample based on the first input data is “particle-size distribution and (II) a liquid quality report based, at least in part, on the first predicted parameter is “particle-size distribution”.
Regarding (I) and (II), Piironen discloses a data processing unit for monitoring particle size distribution/floc development during coagulation and flocculation (Fig. 1, ¶¶ [0036-0037]).
Therefore, before the effective filing date of the claimed invention, it would have been prima facie obvious to one of ordinary skill in the art to modify Na’s machine learning/water treatment model based with trend analysis data set with Piironen’s particle size distribution/floc size information as an optimized state variable to provide the feature of “on the first predicted particle-size distribution” and “a liquid quality report based, at least in part, on the first predicted particle-size distribution”. because the combination would have predictably improved dosing accuracy and suspended-particle removal while reducing chemical overuse as taught by Piironen (¶¶ [0004, 0024-0025]) by having trend analysis data set and water quality reporting.
In regard to claim 12, Na discloses input data comprising a temperature and a pH level of the liquid source (¶ [0077]).
Claims 13-18 are rejected under 35 USC 103 as being unpatented over Na in view of Piironen further in view of Mcleod et al., (US 2022/0298034 A1, hereinafter as “McLeod”).
Regarding claim 13, Na discloses a water treatment system including a water treatment plant, a water treatment control device, and a chemical dosing optimization apparatus (Abstract; ¶¶ [0002-0007], ¶¶ [0050-0060], ¶¶ [0085-0095]), comprising:
a control system configured to receiving water treatment plant’s operating/state data from the
water treatment control device using a computer implemented optimization apparatus to determine optimized chemical dosage control values (¶¶ [0125, 0127]), which meets the recited limitation, “a control system configured to adjust a set of dosage parameters of one or more chemicals used by the water quality system”; the memory storing instructions that, when executed by the processor, cause the processor to (¶¶ [0127-0131]):
perform computing to system optimization having a water treatment model and
controller configured to obtain input data, determine a predicted water-treatment state, derive a control value, and provide control value to a water-treatment control device (¶¶ [0055-0056], [0092]) and input attribute data including flow rate of the feed water flowing into the water treatment plant 1, temperature, turbidity (turbidity can serve as proximate indicator of total suspended solids if calibrated to the local water source), the chemical dosage for the feed water, and pH (Fig. 1, ¶¶ [0056), which meets the limitation, “obtain input data for a first liquid sample, the input data comprising turbidity data and total suspended solids data for the first liquid sample, wherein the first liquid sample is acquired from the liquid source”;
determine using a machine-learning/model–based water treatment model (¶
[0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the recited limitation, “determining, using a computer processor and a machine learning model”; and the chemical dosage/control values are configurable by a water treatment control device (¶ [0074]), which meets the recited limitation, “a set of dosage parameters configurable by a water quality system”;
determining, by deriving an optimized control value using a controller(optimizer)
based on a prediction value from the water-treatment model and providing the control to the water-treatment control device (Fig.1, ¶ [0092, 0096]), which meets the recited limitation, “determining, with an optimizer applied to the machine learning model, an optimized set of dosage parameters.”
adjust the set chemical dosage by providing the optimized
control value to the water treatment control device (¶¶ [0095 0096]), which meets the recited limitation, “adjusting the set dosage of the water quality system to the optimal set of dosage parameters.”
But Na does not teach (I) a plurality of sensors configured to measure property data;
(II) obtain input data for a first liquid sample from the plurality of sensors; and (III) a first predicted particle-size distribution of the first liquid sample based on the input data; and
(IV) an optimal set of dosage parameters based on the first predicted particle-size distribution.
Regarding (I) and (II), McLeod discloses a plurality of sensors configured to measure water quality parameters including pH, turbidity, temperature, flow and other water treatment parameters, and a computer/processor configured to control dosing devices based on sensor data (¶ [0086]) and the display / report functionality may be implemented by any suitable control system architecture (¶ [0101]).
Regarding (III) and (IV), Piironen discloses a data processing unit connected to a particle/floc monitoring devices and teaches using particle size distribution and floc size information for coagulation/flocculation optimization and chemical dosing adjustment (¶¶ [0016-0023]), which the claim limitation, predicted/optimized particle size distribution limitation.
Na, Piironen and McLeod are analogous arts because each is in the same field of endeavor: automated control or optimization of chemical dosing in water treatment processes, including coagulation/flocculation, turbidity mitigation, and suspended particle removal. Na is classified in water treatment chemical dosing/control and teaches model-based chemical dosage optimization. McLeod is directed to automated zeta-potential chemical dosing in water treatment and expressly addresses coagulant dosing, turbidity, temperature and floc agglomeration. Piironen is directed to coagulation/flocculation using particle size distribution and floc-size characteristics.
Therefore, before the effective filing date of the claimed invention, it would have been prima facie obvious to one of ordinary skill in the art to modify Na’s machine learning/water treatment model based chemical dosing optimization system with McLeod’s a plurality of sensors configured to measure property data to provide the feature of “a plurality of sensors configured to measure property data” and obtain input data for a first liquid sample from the plurality of sensors” because sensors provide additional input variables in the machine learning algorithm in determining optimal set-point of chemical dosing for an optimal water treatment outcomes (McLeod : ¶ [0066]); it would have been further obvious to modify Na’s ML/model based chemical dosing optimization system with Piironen’s particle size distribution/floc size information as an optimized state variable to provide the feature of “a first predicted particle-size distribution of the first liquid sample based on the input data” and “ an optimal set of dosage parameters based on the first predicted particle-size distribution” because the combination would have predictably improve dosing accuracy and suspended-particle removal while reducing chemical overuse as taught by Piironen (¶¶ [0004, 0024-0025]).
In regard to claim 14, Na discloses deriving an optimized control value for chemical dosing and providing the control value to a water-treatment control device for controlling addition of chemical to the water treatment (¶¶ [0095 0096]), which meets the recited limitation, “determining a set dosage, and injecting the chemical into the liquid source at the dosage, wherein in the dosage is comprised by the optimal set of dosage parameters.” But Na does not disclose that the optimized value is specifically based on dosage rate and the predicted particle size distribution. Piironen discloses adjusting chemical dosing (using a chemical dosing controller operated by a PLC device) and in coagulation/flocculation based on particle-size distribution and floc characteristics (Abstract; ¶¶ [0016-0023], [0054]). Piironen further discloses the “predicted particle-size distribution”/particle size distribution optimization aspect because particle size distribution is used as a process variable for adjusting chemical dosing in coagulation/flocculation (Fig. 1, ¶¶ [0036-0037]). It would have been obvious to implement Na’s optimized chemical dosing control with Piironen’s programmable logic controller-based dosing adjustment based on predicted particle size distribution, as a chemical dosage/feed rate because chemical dosing devices in water treatment systems are conventionally controlled by dosage rate to deliver a desired amount of coagulant/flocculant into a liquid stream as evidenced by Narges et al., (Prediction of the optimal dosage of coagulants in water treatment plants through developing models based on artificial neural network fuzzy inference system (ANFIS), 2021, 19, pp. 1543-1553; p. 1549, right column, line 1 thru, p. 1550 left column, second paragraph line 9), to provide the feature “ determining a dosage rate for a chemical based on the first predicted particle-size distribution, and injecting the chemical into the liquid source at the dosage rate, wherein the dosage rate is comprised by the optimal set of dosage parameters.”
In regard to claims 15 and 16, Piironen discloses optimization of coagulation or flocculation using particle size distribution and floc size using statistical value characterizing the particle size distribution may be e.g. skewedness, kurtosis, quartiles, median, and mode information (¶ [0092] and using such information for chemical dosing adjustment (claim 15) (¶ [0043, 0094]). Maximizing aggregation and increased median particle size (claim 16) would have been obvious because coagulation/flocculation converts smaller suspended particles into larger flocs for separation (Piironen: ¶ [0094]).
In regard to claim 17, Na in view of Piironen, as set forth above in claim 13, Na discloses:
determining, using a computer processor (Fig. 12; ¶ [0129-0131]), and a machine-
learning/model–based water treatment model (¶ [0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the recited limitation, “determining, using a computer processor and a machine learning model”, and a treated-water state and determining whether the state is within the normal range (¶ [0059]). Na further discloses that the state recognition-based processing part 120 may analyze the state data of the water treatment plant 1 to detect an abnormal state of the water treatment plant and determining whether the state is within the normal range (¶ [0059]), thereby determining a second condition for determining whether to perform the chemical dosing optimization process (¶ [0072]), which meets the limitation “a quality assessment metric based on a parameter of the first liquid sample;”
But Na does not teach: a quality assessment metric based on the first particle-size distribution of the first liquid sample is “particle-size distribution”.
Piironen discloses monitoring particle size distribution/floc development during coagulation and flocculation, and Data P1 is compared in the control unit 11 with measured feedback data P2 from the image analyzing unit 13 (Fig. 1, ¶¶ [0036-0037]).
Therefore, before the effective filing date of the claimed invention, it would have been prima facie obvious to one of ordinary skill in the art to modify Na’s machine learning/water treatment model based with quality assessment metric system with Piironen’s particle size distribution/floc size information as an optimized state variable to provide the feature of “a quality assessment metric based on the first particle-size distribution of the first liquid sample because the combination would have predictably improve dosing accuracy and suspended-particle removal while reducing chemical overuse as taught by Piironen (¶¶ [0004, 0024-0025]) by having system alert monitoring system and a quality assessment metric.
In regard to claim 17, Na discloses predicting (i.e., using the computer processor and machine learning model) a treated-water state and determining whether the state is within the normal range (¶ [0059]). Na further discloses that the state recognition-based processing part 120 may analyze the state data of the water treatment plant 1 to detect an abnormal state of the water treatment plant, thereby determining a second condition for determining whether to perform the chemical dosing optimization process (¶ [0072]). McLeod discloses the chemical dosing system or control logic thereof may provide an auditory or visual alert to an operator or technician when the turbidity exceeds (or falls below) a preselected limit (¶ [0065]). Piironen discloses monitoring particle size distribution/floc development during coagulation and flocculation, and Data P1 is compared in the control unit 11 with measured feedback data P2 from the image analyzing unit 13 (Fig. 1, ¶¶ [0036-0037]). Therefore, generating alerts based on a water quality assessment metric on the first-particle distribution of the liquid sample, that is being outside an acceptable level would have been an obvious system-monitoring response.
In regard to claim 18, Na discloses the water treatment model is an algorithm including the learning model may be a pattern recognition model or a machine learning model that determines whether the water treatment plant is in the optimized state or not (¶ [0071]). A support vector machine would have been obvious known machine learning model choice for predicting water-treatment outputs from measured inputs as evidenced by Han et al., (Flood forecasting using support vector machines, Journal of Hydroinformatics, 2007, 9(4), pp 267-276; p. 273, second column, Model Response to Rainfall heading, lines 1-2).
Claims 19-20 are rejected under 35 USC 103 as being unpatented over Na in view of Piironen.
Regarding claim 19, Na discloses a method of chemical dosing optimization in water treatment (Abstract; ¶¶ [0002-0007], ¶¶ [0050-0060], ¶¶ [0085-0095]). Na further discloses each of the memory TN130 and the storage device TN140 may store therein various types of information related to the operation of the processor TNll0 and each of the memory TN130 and the storage device TN140 may be provided as either a volatile storage medium or a non-volatile
storage (volatile memory is a common example of a non-transitory computer-readable medium) medium or both, which may be implemented in the form of programs readable
through various computer means and recorded on a computer- readable recording medium (Fig. 12, ¶¶ [0126-0131]), comprising:
obtaining real-time data (input data) from a wastewater treatment plant 1, including operating
data and state data of feed water/treated water (Fig. 1, ¶¶ [0052, 0056), which meets the recited limitation, “obtaining a first input data indicative of properties of a first liquid sample,”the input attribute data including the operating data and the state data related to the feed water flowing into the water treatment plant 1; input attribute data including flow rate of the feed water flowing into the water treatment plant 1, temperature, turbidity (turbidity can serve as proximate indicator of total suspended solids if calibrated to the local water source), the chemical dosage for the feed water, and pH (Fig. 1, ¶¶ [0056), which meets the recited limitation, “the first input data comprising turbidity data and total suspended solids data, wherein the first liquid sample is acquired from a liquid source;”
determining, using a computer processor (Fig. 12; ¶ [0129-0131]), and a machine-learning/model–based water treatment model (¶ [0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the recited limitation, “determining, using a computer processor and a machine learning model”; and the chemical dosage/control values are configurable by a water treatment control device (¶ [0074]), which meets the recited limitation, “a set of dosage parameters configurable by a water quality system”;
determining, using a computer processor (Fig. 12; ¶ [0129-0131]), and a machine-learning/model–based water treatment model (¶ [0071], a predicted state of treated water based on the input data (¶ [0065]), which meets the recited limitation, “determining, using a computer processor and a machine learning model”; and the chemical dosage/control values are configurable by a water treatment control device (¶ [0074]), which meets the recited limitation, “a set of dosage parameters configurable by a water quality system”;
determining, by deriving an optimized control value (optimized chemical dosage concentrations)
using a controller(optimizer) based on a prediction value from the water-treatment model using machine learning-based model (¶¶ [00180, 0071]) and providing the control to the water-treatment control device (Fig.1, ¶ [0092, 0096]), which meets the recited limitation, determining, with an optimizer applied to the machine learning model, an optimized set of dosage parameters.”
adjusting and controlling the set chemical dosage by providing the optimized control value to
the water treatment control device (¶¶ [0095 0096]), which meets the recited limitation, “adjusting the set dosage of the water quality system to the optimal set of dosage parameters.”
But Na does not teach: (I) a first predicted parameter of the first liquid sample based on the first input data is “particle-size distribution”; (II) wherein controlled parameter, at least in part, by a set of dosage parameters configurable by a water quality system, is “particle-size distribution”; and (III) an optimal set of dosage parameters based on the first predicted parameter is “particle-size distribution”.
Regarding the limitations of (I), (II), and (III), Piironen teaches monitoring of suspended solids and/or optimization of coagulation and/or flocculation in a water treatment process using particle characteristics, including particle size distribution and floc size/count, and expressly teaches utilization of particle size distribution for adjusting dosing of chemicals (Abstract; ¶¶ [0036-0037). Piironen discloses the “predicted particle-size distribution”/particle size distribution optimization aspect because particle size distribution is used as a process variable for adjusting chemical dosing in coagulation/flocculation (Fig. 1, ¶¶ [0036-0037]). Piironen further teaches non - transitory computer readable medium having stored thereon a set of computer executable instructions pertaining to classifying, computing and comparing particle size distribution to adjusting the dosage of coagulation or flocculation agent (¶¶ [0019-0023]).
Na and Piironen are analogous arts because both refences are directed to automated control or optimization of chemical dosing in water treatment processes, including coagulation/flocculation, turbidity mitigation, and suspended particle removal. Na is classified in water treatment chemical dosing/control and teaches model-based chemical dosage optimization and Piironen is directed to coagulation/flocculation using particle size distribution and floc-size characteristics. These references are reasonably pertinent to the same problem faced by the applicant: determining and adjusting chemical dosage parameters to improve water quality and particle aggregation/removal based on measured water quality conditions.
Therefore, before the effective filing date of the claimed invention, it would have been prima facie obvious to one of ordinary skill in the art to modify Na’s machine learning/water treatment model based chemical dosing optimization system, including non-volatile or non-transitory computer-readbale medium storing instructions with Piironen’s particle size distribution/floc size information as an optimized state variable to provide the feature of “a first predicted parameter is “a first predicted particle-size distribution of the first liquid sample”, “wherein particle-size distribution is controlled, at least in part, by a set of dosage parameters configurable by a water quality system”, and “an optimal set of dosage parameters based on the first predicted particle-size distribution” because the combination would have predictably improve dosing accuracy and suspended-particle removal while reducing chemical overuse as taught by Piironen (¶¶ [0004, 0024-0025]).
In regard to claim 20, Piironen discloses a non-transitory computer readable medium comprising a non - transitory computer readable medium having stored thereon a set of computer executable instructions for causing the data processing unit to carry out the steps of optimizing coagulation/flocculation using particle size distribution and floc size/count or median information and using such information for chemical dosing adjustment (¶¶ [0019-0025, 0043, 0094]). Maximizing aggregation and increased median particle size would have been obvious because coagulation/flocculation converts smaller suspended particles into larger flocs for separation as (Piironen: ¶ [0094]).
Conclusion
Any inquiry concerning this communication or earlier communication from the examiner Any inquiry concerning this communication or earlier communication from the examiner should be directed to Wilson Mendoza whose telephone number is (571) 272-8443. The examiner can normally be reached on Monday – Friday from 9:00 AM until 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, an applicant is encouraged to use the USPTO Automated Interview request at http://www.uspto.gov.intwerviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, In Suk Bullock can be reached on 571-272-5954. The fax phone number for the organization where this application or processing is assigned is 571-273-8300.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, In Suk Bullock can be reached on 571-272-5954. The fax phone number for the organization where this application or processing is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through private PAIR only. For more information about PAIR system, see http://pair-direct.uspto.gov. Should you have any questions on access to the private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Serv ice Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/WILSON GALLARDO MENDOZA/Examiner, Art Unit 1772
/YOUNGSUL JEONG/Primary Examiner, Art Unit 1772
Prosecution Insights