DETAILED ACTION
Claims 1 – 20 have been presented for examination. Claims 1 – 20 are currently amended.
This office action is in response to submission of the application on 10/12/2023.
The instant Office Action relies on Crothers et al. (US 2020/0272129) which is the PGPUB of the US 11256231 which is cited on the IDS.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 – 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without significantly more.
Independent claim 1 recites at Step 1 a statutory category (i.e. a process) method of evaluating a design of an object, the method comprising: analyzing the design using a machine learning model representative of production data; predicting defect probabilities based on the machine learning model; determining a rework cost of the design based on the defect probabilities; performing strength analysis on the design; determining a weight of the design; determining a weight cost of the design based on the weight of the design; and analyzing the design based on the weight cost and the rework cost. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “analyzing” requires no more than judgements and evaluations based on observations from an pre-existing machine learning model. The “predicting” and “determining” and “performing” and “analyzing” require no more than judgements and evaluations which are recited at a high-level of generality which is not reasonably precluded from being performed in the mind. Accordingly, the claim recites an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention does not further any limitations. The claim is directed to an abstract idea.
At Step 2B the claim does not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception since the claimed invention does not further any limitations. For at least these reasons, the claim is not patent eligible.
Dependent claim 2 – 9 recite(s) at Step 1 the same statutory category as the parent claim(s), and further recite(s): Claim 2 performing the analysis on the design and ensuring the design is within a margin of safety; and determining the weight of the design that is within the margin of safety; Claim 3 performing the analysis on the design and determining that the design is not within a margin of safety; in response, adding one or more composite plies of material to the design and increasing the weight of the design; and performing the analysis again and determining that the design is within the margin of safety; Claim 4 performing the analysis and determining that the design exceeds a margin of safety; in response, removing one or more composite plies of material from the design and decreasing the weight of the design; and performing the analysis again and determining that the design is within the margin of safety; Claim 5 determining the defect probabilities based on an expected process configuration for manufacturing of the design; Claim 6 wherein determining the rework cost of the design comprises factoring one or more of a supply chain dispersion and a total cost of manufacturing of the design; Claim 7 wherein analyzing the design based on the weight cost and the rework cost comprises minimizing the weight cost and the rework cost of the design; Claim 8 factoring the defect probabilities of the design when performing the analysis on the design; Claim 9 determining the defect probabilities of the design prior to determining the rework cost of the design. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “ensuring” and “determining” and “factoring” require no more than judgements and evaluations which are recited at a high-level of generality which is not reasonably precluded from being performed in the mind. The “adding” and “removing” cover changing an intangible design which is not reasonably precluded from being performed in the mind. The “minimizing” covers optimizing a design recited at a high-level of generality which is not reasonably precluded from being performed in the mind. Accordingly, the claim(s) recite(s) an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention does not further any limitations. The claim is directed to an abstract idea.
At Step 2B the claim does not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception since the claimed invention does not further any limitations. For at least these reasons, the claim is not patent eligible.
Independent claim 10 recites at Step 1 a statutory category (i.e. a process) method of evaluating a design of an object, the method comprising: predicting defect probabilities of manufacturing the design based on production data; determining a rework cost of reworking the design; conducting a margin analysis and determining a strength of the design; determining a weight cost of the design; and determining a total cost of the design based on the rework cost and the weight cost. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “predicting” and “determining” and “conducting” require no more than judgements and evaluations which are recited at a high-level of generality which is not reasonably precluded from being performed in the mind. Accordingly, the claim recites an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention does not further any limitations. The claim is directed to an abstract idea.
At Step 2B the claim does not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception since the claimed invention does not further any limitations. For at least these reasons, the claim is not patent eligible.
Dependent claim 11 – 17 recite(s) at Step 1 the same statutory category as the parent claim(s), and further recite(s): Claim 11 predicting the defect probabilities based on a process configuration for manufacturing the design; Claim 12 conducting the margin analysis by factoring the defect probabilities from a machine learning model; Claim 13 conducting the margin analysis based on expected loads that are to be placed on the object during use; Claim 14 removing or adding one or more composite plies from the design based on the margin analysis; Claim 15 predicting the defect probabilities prior to conducting the margin analysis; Claim 16 determining the rework cost of the design comprises factoring one or more of a supply chain dispersion and a total cost of manufacturing of the design; Claim 17 minimizing the weight cost and the rework cost of the design prior to determining the total cost of the design. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “predicting” and “conducting” and “factoring” require no more than judgements and evaluations which are recited at a high-level of generality which is not reasonably precluded from being performed in the mind. The “conducting … from a machine learning model” requires no more than judgements and evaluations based on observations from an pre-existing machine learning model. The “removing” cover changing an intangible design which is not reasonably precluded from being performed in the mind. The “minimizing” covers optimizing a design recited at a high-level of generality which is not reasonably precluded from being performed in the mind. Accordingly, the claim(s) recite(s) an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention does not further any limitations. The claim is directed to an abstract idea.
At Step 2B the claim does not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception since the claimed invention does not further any limitations. For at least these reasons, the claim is not patent eligible.
Independent claim 18 recites at Step 1 a statutory category (i.e. a machine) computing device configured to evaluate a design of an object, the computing device to: predict defect probabilities of manufacturing the design based on a machine learning model; determine a rework cost of reworking the design; determine that the design exceeds a margin of safety for strength; determine a weight cost of the design; and determine a total cost of the design based on the rework cost and the weight cost. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “predict” requires no more than judgements and evaluations based on observations from an pre-existing machine learning model. The “determine” require no more than judgements and evaluations which are recited at a high-level of generality which is not reasonably precluded from being performed in the mind. Accordingly, the claim recites an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention further claims: memory circuitry with stored program instructions; and processing circuitry configured to execute the program instructions to cause the computing device to. The “memory circuitry” and “processing circuitry” are recited at a high-level of generality such that they amount to no more than mere application of the judicial exception using generic computer components which does not amount to an improvement in computer functionality (see MPEP 2106.04(a)(I)). The claim is directed to an abstract idea.
At Step 2B the claim does not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the recited “memory circuitry” and “processing circuitry” amount to no more than mere instructions to apply the judicial exception using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. For at least these reasons, the claim is not patent eligible.
Dependent claim 19 – 20 recite(s) at Step 1 the same statutory category as the parent claim(s), and further recite(s): Claim 19 change the design by one of adding one or more plies to the design or removing one or more plies from the design. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “adding” and “removing” cover changing an intangible design which is not reasonably precluded from being performed in the mind. Accordingly, the claim(s) recite(s) an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention further claims: Claim 20 a machine learning model stored in the memory circuitry that is configured to predict the defect probabilities. The “machine learning model stored” amounts to insignificant data gathering since it utilized from storage in a highly-generic manner (see MPEP 2106.04(d) referencing MPEP 2106.05(g)). The claim is directed to an abstract idea.
At Step 2B the claim does not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception. The “machine learning model stored” covers well-understood, routine, and conventional activity since it is generic and covers receiving and outputting data by any electronics means (see MPEP 2106.05(d)(II) “i. Receiving or transmitting data over a network”). For at least these reasons, the claim is not patent eligible.
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:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1 – 2, 5 – 6, 8 – 13, 15 – 16, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Crothers et al. (US 2020/0272129) (henceforth “Crothers (129)”) in view of Behzadpour et al. (US 2021/0064720) (henceforth “Behzadpour (720)”), and further in view of Marcoe et al. Marcoe et al. (EP 3396484) (henceforth “Marcoe (484)”). Crothers (129) and Behzadpour (720) and Marcoe (484) are analogous art because they solve the same problem of evaluating a design, and because they are from the same field of endeavor of design evaluation.
With regard to claim 1, Crothers (129) teaches a method of evaluating a design of an object, the method comprising: analyzing the design using a machine learning model representative of production data; (Crothers (129) Paragraph 34 and Figure 1 design is analyzed using an ML model trained on production data “The machine learning device 108 is configured to on received production data 168. … the quality data 182 can be representative of the defect data 166 that is generated upon inspection of the object 110A ( e.g. , the quality data 182 includes data indicative of observed defects in produced objects ).”)
predicting defect probabilities based on the machine learning model; (Crothers (129) Paragraph 27 ML models predict defect rate “in light of the machine - learning model 126 to determine one or more of a cost associated with production of the design 120A , one or more geometric feature of the design 120A that is determined to be associated with defects , an estimated defect rate for manufacture of the object 110A based on the design 120A , one or more other factors associated with manufacturing the object 110A based on the design 120A , or any combination thereof .”, and Paragraph 44 the defect rate is statistical and indicates a likelihood (defect probabilities) “In some implementations , defects are statistically more likely to occur in regions of higher curvature , and the likelihood of a defect is affected by the ply angle 210.”)
determining a weight of the design; determining a weight cost of the design based on the weight of the design; and analyzing the design based on the weight cost (Crothers (129) Paragraph 15 weight is considered in the performance (analyzing) as a cost (weight cost) “designers are enabled and encouraged to consider cost and manufacturing consequences, in addition to product performance (e.g., weight and function), when designing parts for manufacture.”)
Crothers (129) does not appear to explicitly disclose: that the determined cost is rework cost; performing strength analysis on the design.
However, Behzadpour (720) teaches:
determining a rework of a design based on defects. (Behzadpour (720) Paragraph 162 manufactured system can have rework, where inspected defects can be desirably replaced “These operations can include at least one of disassembling parts, refurbishing parts, inspecting parts, reworking parts, manufacturing replacement parts, or other operations for performing maintenance on aircraft 1400 in FIG. 14”)
performing strength analysis on the design; (Behzadpour (720) Paragraph 42 design strength is analyzed “In this illustrative example, desired strength 124 can be based on design specifications 119. The specifications can specify a margin of safety that is desired for composite part 102.”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) with the analyzing strength of a composite part design using AI models disclosed by Behzadpour (720). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Behzadpour (720) Abstract).
Crothers (129) in view of Behzadpour (720) does not appear to explicitly disclose: that the determined rework is a rework cost; analyzing the design based on the weight cost and the rework cost.
However, Marcoe (484) teaches:
determining a rework cost of a design based on defects (Marcoe (484) Paragraph 17 “For example, the illustrative embodiments recognize and take into account that utilizing process control during composite fabrication may reduce inspection and rework labor costs for each composite component manufactured in the manufacturing environment”, and Paragraph 7 “hit probability that the detected surface profile is based on a defect of the defect type".”)
analyzing the design based on the rework cost. (Marcoe (484) Paragraph 31 design can desirably be modified to reduce rework (analyzing), included defects that are presented downstream when manufactured (rework cost) “Computer system 208 may change configurations based on at least one of type of composite material, a design/configuration of the component, a location on component 224, or any other desirable characteristic.”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720) with the consideration of rework cost in the manufactured composite part disclosed by Marcoe (484). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Marcoe (484) Paragraph 1 “Still more particularly, the present disclosure relates to using inspection data for process control of a composite fabrication process”).
With regard to claim 10, Crothers (129) teaches a method of evaluating a design of an object, the method comprising: predicting defect probabilities of manufacturing the design based on production data (Crothers (129) Paragraph 27 ML models predict defect rate “in light of the machine - learning model 126 to determine one or more of a cost associated with production of the design 120A , one or more geometric feature of the design 120A that is determined to be associated with defects , an estimated defect rate for manufacture of the object 110A based on the design 120A.”, and Paragraph 44 the defect rate is statistical and indicates a likelihood (defect probabilities) “In some implementations , defects are statistically more likely to occur in regions of higher curvature , and the likelihood of a defect is affected by the ply angle 210.”, and Paragraph 34 and Figure 1 design is analyzed using an ML model trained on production data “The machine learning device 108 is configured to on received production data 168. … the quality data 182 can be representative of the defect data 166 that is generated upon inspection of the object 110A ( e.g. , the quality data 182 includes data indicative of observed defects in produced objects ).”)
determining a weight cost of the design; and (Crothers (129) Paragraph 15 weight is considered in the performance (analyzing) as a cost (weight cost) “designers are enabled and encouraged to consider cost and manufacturing consequences, in addition to product performance (e.g., weight and function), when designing parts for manufacture.”)
determining a total cost of the design based on the weight cost (Crothers (129) Paragraph 28 and Figure 1 all associated costs are included “The cost estimate 198 can include an estimate of a total cost of manufacture of the object 110A and can include costs associated with parts, materials, and labor associated with manufacturing the object 110A, as illustrative, non-limiting examples”)
Crothers (128) does not appear to explicitly disclose: conducting a margin analysis and determining a strength of the design.
However, Behzadpour (720) teaches:
conducting a margin analysis and determining a strength of a design; (Behzadpour (720) Paragraph 42 margin of safety can be used “In this illustrative example, desired strength 124 can be based on design specifications 119. The specifications can specify a margin of safety that is desired for composite part 102.”, and Abstract warpage is controlled up to a level, where the safety margin could also apply to warpage having wholly predictable results (margin analysis) “Orientations in a stacking sequence for plies in the composite part are selected that result in the composite part having the acceptable level of the warpage and a desired strength to form selected orientations”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) with the analyzing strength of a composite part design using AI models disclosed by Behzadpour (720). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Behzadpour (720) Abstract).
Crothers (129) in view of Behzadpour (720) does not appear to explicitly disclose: determining a rework cost of reworking the design; that determining the total cost is based on the rework cost.
However, Marcoe (484) teaches:
determining a rework cost of reworking the design; (Marcoe (484) Paragraph 17 “For example, the illustrative embodiments recognize and take into account that utilizing process control during composite fabrication may reduce inspection and rework labor costs for each composite component manufactured in the manufacturing environment”)
determining a total cost of the design based on the rework cost (Crothers (129) Paragraph 28 and Figure 1 all associated costs are included, where the rework costs of Marcoe (484) are associated with labor “The cost estimate 198 can include an estimate of a total cost of manufacture of the object 110A and can include costs associated with parts, materials, and labor associated with manufacturing the object 110A, as illustrative, non-limiting examples”
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720) with the consideration of rework cost in the manufactured composite part disclosed by Marcoe (484). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Marcoe (484) Paragraph 1 “Still more particularly, the present disclosure relates to using inspection data for process control of a composite fabrication process”).
With regard to claim 18, Crothers (129) teaches a computing device configured to evaluate a design of an object, the computing device comprising: memory circuitry with stored program instructions; and processing circuitry configured to execute the program instructions to cause the computing device to: predict defect probabilities of manufacturing the design based on a machine learning model; (Crothers (129) Paragraph 27 ML models predict defect rate “in light of the machine - learning model 126 to determine one or more of a cost associated with production of the design 120A , one or more geometric feature of the design 120A that is determined to be associated with defects , an estimated defect rate for manufacture of the object 110A based on the design 120A.”, and Paragraph 44 the defect rate is statistical and indicates a likelihood (defect probabilities) “In some implementations , defects are statistically more likely to occur in regions of higher curvature , and the likelihood of a defect is affected by the ply angle 210.”, and Paragraph 34 and Figure 1 design is analyzed using an ML model trained on production data in combination with a memory and processor “The machine learning device 108 is configured to on received production data 168. … the quality data 182 can be representative of the defect data 166 that is generated upon inspection of the object 110A ( e.g. , the quality data 182 includes data indicative of observed defects in produced objects ).”)
determine a weight cost of the design; and (Crothers (129) Paragraph 15 weight is considered in the performance (analyzing) as a cost (weight cost) “designers are enabled and encouraged to consider cost and manufacturing consequences, in addition to product performance (e.g., weight and function), when designing parts for manufacture.”)
determine a total cost of the design based on the weight cost. (Crothers (129) Paragraph 28 and Figure 1 all associated costs are included “The cost estimate 198 can include an estimate of a total cost of manufacture of the object 110A and can include costs associated with parts, materials, and labor associated with manufacturing the object 110A, as illustrative, non-limiting examples”)
Crothers (128) does not appear to explicitly disclose: determine that the design exceeds a margin of safety for strength.
However, Behzadpour (720) teaches:
determine that the design exceeds a margin of safety for strength. (Behzadpour (720) Paragraph 42 margin of safety can be used “In this illustrative example, desired strength 124 can be based on design specifications 119. The specifications can specify a margin of safety that is desired for composite part 102.”, and Abstract warpage is controlled up to a level, where the safety margin could also apply to warpage having wholly predictable results (margin of safety) “Orientations in a stacking sequence for plies in the composite part are selected that result in the composite part having the acceptable level of the warpage and a desired strength to form selected orientations”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) with the analyzing strength of a composite part design using AI models disclosed by Behzadpour (720). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Behzadpour (720) Abstract).
Crothers (129) in view of Behzadpour (720) does not appear to explicitly disclose: determine a rework cost of reworking the design; that determining the total cost is based on the rework cost.
However, Marcoe (484) teaches:
determine a rework cost of reworking the design; (Marcoe (484) Paragraph 17 “For example, the illustrative embodiments recognize and take into account that utilizing process control during composite fabrication may reduce inspection and rework labor costs for each composite component manufactured in the manufacturing environment”)
determining a total cost of the design based on the rework cost (Crothers (129) Paragraph 28 and Figure 1 all associated costs are included, where the rework costs of Marcoe (484) are associated with labor “The cost estimate 198 can include an estimate of a total cost of manufacture of the object 110A and can include costs associated with parts, materials, and labor associated with manufacturing the object 110A, as illustrative, non-limiting examples”
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720) with the consideration of rework cost in the manufactured composite part disclosed by Marcoe (484). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Marcoe (484) Paragraph 1 “Still more particularly, the present disclosure relates to using inspection data for process control of a composite fabrication process”).
With regard to claim 2, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1, and further teaches:
performing the analysis on the design and ensuring the design is within a margin of safety; and (Behzadpour (720) Paragraph 42 and Figure 9 the design is iterated until desired strength is met, where the desired strength can include a margin of safety “In this illustrative example, desired strength 124 can be based on design specifications 119. The specifications can specify a margin of safety that is desired for composite part 102.”)
determining the weight of the design that is within the margin of safety. (Crothers (129) Paragraph 15 the weight of the design is explicitly considered, which can similarly be considered with the margin of safety of Behzadpour (720) having wholly predictable results “designers are enabled and encouraged to consider cost and manufacturing consequences, in addition to product performance (e.g., weight and function), when designing parts for manufacture.”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) with the analyzing strength of a composite part design using AI models disclosed by Behzadpour (720). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Behzadpour (720) Abstract).
With regard to claim 5, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1, and further teaches:
determining the defect probabilities based on an expected process configuration for manufacturing of the design. (Crothers (129) Figure 1 the ML model is based on production data and configuration
PNG
media_image1.png
263
322
media_image1.png
Greyscale
)
With regard to claim 6 and 116, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1 and 10, and further teaches:
wherein determining the rework cost of the design comprises factoring one or more of a supply chain dispersion and a total cost of manufacturing of the design. (Crothers (129) Paragraph 28 and Figure 1 the rework cost taught by Marcoe (484) can further include the total cost of manufacturing or a supply chain dispersion since further costs can be desirably included in a wholly predicated manner “The cost estimate 198 can include an estimate of a total cost of manufacture of the object 110A and can include costs associated with parts, materials, and labor associated with manufacturing the object 110A, as illustrative, non-limiting examples”
PNG
media_image2.png
191
363
media_image2.png
Greyscale
)
With regard to claim 8, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1, and further teaches:
factoring the defect probabilities of the design when performing the analysis on the design. (Crothers (129) Paragraph 27 the same ML that predicts the defect rates (factoring defect probabilities) is used to predict costs (when performing the analysis) associated with the part design “in light of the machine - learning model 126 to determine one or more of a cost associated with production of the design 120A , one or more geometric feature of the design 120A that is determined to be associated with defects , an estimated defect rate for manufacture of the object 110A based on the design 120A , one or more other factors associated with manufacturing the object 110A based on the design 120A , or any combination thereof .”)
With regard to claim 9, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1, and further teaches:
determining the defect probabilities of the design (Crothers (129) Paragraph 27 defect probabilities can be determined based on the design after training the ML model “in light of the machine - learning model 126 to determine one or more of a cost associated with production of the design 120A , one or more geometric feature of the design 120A that is determined to be associated with defects , an estimated defect rate for manufacture of the object 110A based on the design 120A”)
prior to determining the rework cost of the design. (Marcoe (484) Paragraph 17 rework costs are for the manufactured part (prior to determining) “For example, the illustrative embodiments recognize and take into account that utilizing process control during composite fabrication may reduce inspection and rework labor costs for each composite component manufactured in the manufacturing environment”
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720) with the consideration of rework cost in the manufactured composite part disclosed by Marcoe (484). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Marcoe (484) Paragraph 1 “Still more particularly, the present disclosure relates to using inspection data for process control of a composite fabrication process”).
With regard to claim 11, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 10, and further teaches:
predicting the defect probabilities based on a process configuration for manufacturing the design. (Crothers (129) Figure 1 design is analyzed using an ML model trained based on process conditions
PNG
media_image3.png
464
893
media_image3.png
Greyscale
)
With regard to claim 12, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 10, and further teaches:
conducting the margin analysis by factoring the defect probabilities from a machine learning model. (Behzadpour (720) Paragraph 31 warpage is a specific defect which could reasonably be included amongst the more generic defect rate of Crothers (129) (factoring the defect probabilities) “The illustrative embodiments recognize and take into account that, currently, warpage is not considered a defect that can be predicted”, and Abstract warpage is predicted and controlled is controlled up to a level (margin analysis) “Orientations in a stacking sequence for plies in the composite part are selected that result in the composite part having the acceptable level of the warpage and a desired strength to form selected orientations”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) with the analyzing strength of a composite part design using AI models disclosed by Behzadpour (720). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Behzadpour (720) Abstract).
With regard to claim 13, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 10, and further teaches:
conducting the margin analysis based on expected loads that are to be placed on the object during use. (Behzadpour (720) Paragraph 76 the analysis is conducted with a specific kind of loading (based on expected loads) “Laminate analysis 131 can receive structural loads 222 for performing analysis on the set of candidate orientations 128 selected by user input 208”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) with the analyzing strength of a composite part design using AI models disclosed by Behzadpour (720). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Behzadpour (720) Abstract).
With regard to claim 15, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 10, and further teaches:
predicting the defect probabilities prior to conducting the margin analysis. (Crothers (129) Paragraph 27 defect probabilities can be determined based on the design after initially training the ML model prior to part design analysis, where it is noted that the margin analysis does not directly depend on the defect probabilities (prior to) “in light of the machine - learning model 126 to determine one or more of a cost associated with production of the design 120A , one or more geometric feature of the design 120A that is determined to be associated with defects , an estimated defect rate for manufacture of the object 110A based on the design 120A”)
With regard to claim 20, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 18, and further teaches:
a machine learning model stored in the memory circuitry that is configured to predict the defect probabilities. (Crothers (129) Figure 1 design is analyzed using an ML model trained on production data in combination with a memory and processor “The machine learning device 108 is configured to on received production data 168. … the quality data 182 can be representative of the defect data 166 that is generated upon inspection of the object 110A ( e.g. , the quality data 182 includes data indicative of observed defects in produced objects ).”)
Claims 3 – 4, 7, 14, 17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484), and further in view of Nakhjavani, O. (US 2019/0005158) (henceforth “Nakhjavani (982)”). Crothers (129) and Behzadpour (720) and Marcoe (484) and Nakhjavani (982) are analogous art because they solve the same problem of evaluating a design, and because they are from the same field of endeavor of design evaluation.
With regard to claim3, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1, and further teaches:
performing the analysis on the design and determining that the design is not within a margin of safety; performing the analysis again and determining that the design is within the margin of safety.(Behzadpour (720) Paragraph 42 and Figure 9 the design is iterated if desired strength is met (is not within), where the desired strength can include a margin of safety “In this illustrative example, desired strength 124 can be based on design specifications 119. The specifications can specify a margin of safety that is desired for composite part 102.”)
Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) does not appear to explicitly disclose: in response, adding one or more composite plies of material to the design and increasing the weight of the design;
However, Nakhjavani (158) teaches:
in response, adding one or more composite plies of material to a design and increasing the weight of the design (Nakhjavani (158) Claim 8 a design is optimized based on number of part weights (increase the weight), where it is obvious for one of ordinary skill in the art to optimize the result effective variables of the number of plies (in response) (see MPEP 2144.05(II)(B)) “until the optimized configuration is identified by the optimization process based on the number for the part weights and the resource use estimated for the number of configurations processed by the computer system for the part”, and Claim 11 the optimization includes a number of the parts (adding one or more), where it is readily apparent that the number of plies contribute to overall weight as a part count “wherein the resource use is selected from at least one of machining, drilling, molding, labor, material type, a number of parts, a time to perform a manufacturing process, manufacturing building, an assembly line, a robotic equipment, tooling, or preparation time”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) with the iterative optimization of a part configuration for a manufacturing process including number of parts and weight disclosed by Nakhjavani (158). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Nakhjavani (158) Abstract).
With regard to claim 4, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1, and further teaches:
performing the analysis and determining that the design exceeds a margin of safety; performing the analysis again and determining that the design is within the margin of safety.(Behzadpour (720) Paragraph 42 and Figure 9 the design is iterated until desired strength is met (is within), where the desired strength can include a margin of safety “In this illustrative example, desired strength 124 can be based on design specifications 119. The specifications can specify a margin of safety that is desired for composite part 102.”)
Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) does not appear to explicitly disclose: in response, removing one or more composite plies of material from the design and decreasing the weight of the design.
However, Nakhjavani (158) teaches:
in response, removing one or more composite plies of material from a design and decreasing the weight of the design; and (Nakhjavani (158) Claim 8 a design is optimized based on number of part weights (decrease the weight), where it is obvious for one of ordinary skill in the art to optimize the result effective variables of the number of plies (in response) (see MPEP 2144.05(II)(B)) “until the optimized configuration is identified by the optimization process based on the number for the part weights and the resource use estimated for the number of configurations processed by the computer system for the part”, and Claim 11 the optimization includes a number of the parts (removing one or more), where it is readily apparent that the number of plies contribute to overall weight as a part count “wherein the resource use is selected from at least one of machining, drilling, molding, labor, material type, a number of parts, a time to perform a manufacturing process, manufacturing building, an assembly line, a robotic equipment, tooling, or preparation time”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) with the iterative optimization of a part configuration for a manufacturing process including number of parts and weight disclosed by Nakhjavani (158). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Nakhjavani (158) Abstract).
With regard to claim 7, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 1, and does not appear to explicitly disclose: wherein analyzing the design based on the weight cost and the rework cost comprises minimizing the weight cost and the rework cost of the design.
However, Nakhjavani (158) teaches:
wherein analyzing the design based on the weight cost and the rework cost comprises minimizing the weight cost and the rework cost of the design. (Nakhjavani (158) Claim 8 and Figure 3 a part design can be optimized for weight and costs, where it is obvious for one of ordinary skill in the art to optimize the result effective variables of the number of plies (in response) (see MPEP 2144.05(II)(B)) “until the optimized configuration is identified by the optimization process based on the number for the part weights and the resource use estimated for the number of configurations processed by the computer system for the part”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) with the iterative optimization of a part configuration for a manufacturing process including number of parts and weight disclosed by Nakhjavani (158). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Nakhjavani (158) Abstract).
With regard to claim 14, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 10, and further teaches:
optimizing the design based on the margin analysis (Behzadpour (720) Paragraph 42 and Figure 9 the design is iterated until desired strength is met, where the desired strength can include a margin of safety “In this illustrative example, desired strength 124 can be based on design specifications 119. The specifications can specify a margin of safety that is desired for composite part 102.”)
Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) does not appear to explicitly disclose: that the optimizing the design comprises removing or adding one or more composite plies from the design.
However, Nakhjavani (158) teaches:
removing or adding one or more composite plies from the design based on the margin analysis. (Nakhjavani (158) Claim 8 a design is optimized based on number of part weights (decrease the weight), where it is obvious for one of ordinary skill in the art to optimize the result effective variables of the number of plies (in response) (see MPEP 2144.05(II)(B)) “until the optimized configuration is identified by the optimization process based on the number for the part weights and the resource use estimated for the number of configurations processed by the computer system for the part”, and Claim 11 the optimization includes a number of the parts (removing one or more), where it is readily apparent that the number of plies contribute to overall weight as a part count “wherein the resource use is selected from at least one of machining, drilling, molding, labor, material type, a number of parts, a time to perform a manufacturing process, manufacturing building, an assembly line, a robotic equipment, tooling, or preparation time”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) with the iterative optimization of a part configuration for a manufacturing process including number of parts and weight disclosed by Nakhjavani (158). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Nakhjavani (158) Abstract).
With regard to claim 17, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 10, and does not appear to explicitly disclose: minimizing the weight cost and the rework cost of the design prior to determining the total cost of the design.
However, Nakhjavani (158) teaches:
minimizing the weight cost and the rework cost of the design prior to determining the total cost of the design. (Nakhjavani (158) Claim 8 and Figure 3 a part design can be optimized for weight and costs, where it is obvious for one of ordinary skill in the art to optimize the result effective variables of the number of plies (in response) (see MPEP 2144.05(II)(B)) “until the optimized configuration is identified by the optimization process based on the number for the part weights and the resource use estimated for the number of configurations processed by the computer system for the part”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) with the iterative optimization of a part configuration for a manufacturing process including number of parts and weight disclosed by Nakhjavani (158). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Nakhjavani (158) Abstract).
With regard to claim 19, Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) teaches all the elements of the parent claim 18, and does not appear to explicitly disclose: wherein the processing circuitry is configured to change the design by one of adding one or more plies to the design or removing one or more plies from the design.
However, Nakhjavani (158) teaches:
change the design by one of adding one or more plies to the design or removing one or more plies from the design. (Nakhjavani (158) Claim 8 a design is optimized based on number of part weights (increase or decrease the weight), where it is obvious for one of ordinary skill in the art to optimize the result effective variables of the number of plies (in response) (see MPEP 2144.05(II)(B)) “until the optimized configuration is identified by the optimization process based on the number for the part weights and the resource use estimated for the number of configurations processed by the computer system for the part”, and Claim 11 the optimization includes a number of the parts (adding or removing one or more), where it is readily apparent that the number of plies contribute to overall weight as a part count “wherein the resource use is selected from at least one of machining, drilling, molding, labor, material type, a number of parts, a time to perform a manufacturing process, manufacturing building, an assembly line, a robotic equipment, tooling, or preparation time”)
It would have been obvious to one of ordinary skill in the art to combine the method of using an ML model to analyze a composite part design to predict at least defect rates disclosed by Crothers (129) in view of Behzadpour (720), and further in view of Marcoe (484) with the iterative optimization of a part configuration for a manufacturing process including number of parts and weight disclosed by Nakhjavani (158). One of ordinary skill in the art would have been motivated to make this modification in order to optimize the manufacture of a composite part (Nakhjavani (158) Abstract).
Examiner General Comments
With regard to the prior art rejection(s), any cited portion of the relied upon reference(s), either by pointing to specific sections or as quotations, is intended to be interpreted in the context of the reference(s) as a whole as would be understood by one of ordinary skill in the art. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in their entirety as potentially teaching all or part of the claimed invention since the entire reference is considered to provide disclosure relating to the cited portions. Further, the claims and only the claims form the metes and bounds of the invention. Office personnel are to give the claims their broadest reasonable interpretation in light of the supporting disclosure. Unclaimed limitations appearing in the specification are not read into the claim. Prior art was referenced using terminology familiar to one of ordinary skill in the art. Such an approach is broad in concept and can be either explicit or implicit in meaning. Examiner’s notes are provided with the cited references to assist the applicant to better understand how the examiner interprets the applied prior art. Such comments are entirely consistent with the intent and spirit of compact prosecution.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALFRED H. WECHSELBERGER whose telephone number is (571)272-8988. The examiner can normally be reached M - F, 10am to 6pm.
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, Emerson Puente can be reached at 571-272-3652. 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.
/ALFRED H. WECHSELBERGER/ExaminerArt Unit 2187
/EMERSON C PUENTE/Supervisory Patent Examiner, Art Unit 2187
Prosecution Insights