CTFR 18/003,589 CTFR 94025 DETAILED ACTION This action is responsive to applicant’s communication filed 02/02/2026. Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Status of the Claims Claims 1-9 are rejected under 35 U.S.C. 103. Response to Arguments Applicant’s arguments regarding the prior art have been fully considered but are not persuasive. Applicant argues on Page 5 of the Remarks that Yang does not teach using the shape of the tool as a process variable to infer wear on the tool because Yang merely describes capturing an image of the tool after machining is complete and using the image to train a model to predict wear using other variables. The examiner respectfully disagrees. Yang teaches capturing the image data to measure “the wear of the tool flank or tool corner” (¶ 40) and measure the “wear size” (¶ 49) on the tool. The examiner considers the measurement of the positioning and size of the wear on the tool as reading on the “shape” of the tool. The collection of the other process data (e.g. current data) as well as the images of the tool wear are done during the machining process, as discussed in Paragraphs 47-48 and in more detail in the below 103 rejections. While the images are captured. While historical image and sensor data is used to build the neural network as discussed in Paragraph 40, there is still a capturing of both image data and other sensor data during the machining process, as discussed in ¶ 47-49 and illustrated in the functional block diagram of Fig. 5. In particular, the “data preprocessing” and “feature extraction” circuits are performed on the process data, which includes the tool wear images, as discussed in Paragraph 48. Paragraphs 47-48 discuss these process variables being captured “during machining”. Furthermore, even if image data is only captured “between two tool runs of operation” (¶ 48), this still reads on the claim language of “detecting at least two process variables during performance of a machining process” since multiple other process variables are collected during machining and a machining process typically involves multiple runs, so any data collected between runs would be considered “during” the machining process. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. 07-20-aia AIA 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. 07-23-aia AIA The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. 07-21-aia AIA Claim s 1-9 are rejected under 35 U.S.C. 103 as being unpatentable over YANG (US 2018/0272491 A1) in view of LIAO (US 2018/0005151 A1) . Regarding Claim 1 , YANG teaches a method for subtractive machining of a workpiece using a tool, the method comprising: (¶ 5-6: The method is for monitoring and predicting tool wear during operation of machine, particularly a cutting tool.) detecting at least two process variables during performance of a machining process; using the at least two process variables to infer a wear on the tool; (¶ 47-49. Fig. 5: Multiple process variables are obtained including current data and image data, which determines shape data. The process variables are used to ultimately predict, or infer, a wear on the tool. ¶ 47-49: “The CPA 500 is communicatively connected to a tool machine 502 and a digital microscope 504. The tool machine 502 may be such as a CNC machine tool on which various sensors are installed, such as a current transducer, an accelerometer, a strain gauge, and a thermocouple, for detecting the statuses of axis motors and spindles during machining … The feature extraction circuit 530 not only extracts the tool wear features according to the operation segments and feature domains but also derives the wear size from the tool wear images.” The sensor data and the image data (captured by a digital microscope) are obtained during the machining process. ¶ 48: “The digital microscope 504 is installed in the machine tool to obtain tool wear images between two tool runs of operation, so as to build and refresh the HDNN model.” Images being obtained between runs still reads on “during performance of a machining process” as a machining process may involve multiple runs.) wherein the at least two process variables are passed on to a neural network, which assigns each process variable a respective degree of wear independently of the other; (¶ 41-42, 46, 49, Fig. 5 element 530: A neural network comprising a feature extraction method receives a set of current, temperature, vibration, and strain data from sensors as well as image capture data, i.e. at least two process variables. The neural network independently assigns a degree of wear to each variable by extracting wear features from the sensor data and by calculating the tool wear from the image data. When refreshing the neural network, both independently determined values are provided to a prediction circuit.) wherein the wear is inferred by means of a logic on the basis of the respective degrees of wear; (¶ 49 with context from ¶ 28 and 31, Fig. 5 element 540: The neural network includes logic which infers or predicts a value of the wear of the tool based upon the wear feature extraction values of the sensor data and the tool wear calculation of the image data, i.e. on the basis of the respective degrees of wear.) and wherein the at least two process variables are each selected from the group consisting of: a shape of the tool. .. (¶ 47-49: The two process variables are the operating current of the machine tool and the shape of the tool, as further discussed directly below.) wherein detecting the shape of the tool includes imaging, using a camera and/or a scanner. (¶ 40, 48-49: An imaging sensor, namely a digital microscope that captures tool wear images, which is equivalent to a camera or scanner, captures image data including wear on the corner or flank of the tool and the size of the wear, which is shape data. ¶ 40: “analyzing and measuring a cutting tool image captured by a digital microscope after each historical tool run of operation, for example, measuring the wear of the tool flank or tool corner ”. The neural network that assesses tool wear is trained on historical image data that is analyzed to assess the wear on the tool flank or tool corner. This reads on “a shape of the tool”. ¶ 49: “The feature extraction circuit 530 not only extracts the tool wear features according to the operation segments and feature domains but also derives the wear size from the tool wear images ”. “The “wear size” reads on “a shape of the tool”.) YANG teaches using two process variables, namely current data (or alternatively temperature, vibration, and strain data) and image data (See Fig. 5), and teaches at least one of the process variables from the claimed grouping, namely the shape of the tool, but it does not teach two process variables from the claimed grouping. YANG does not teach an operating voltage, and interruption information of the machining However, LIAO, which is similarly directed to determining the health assessment of a tool or asset (¶ 11-13), teaches at least one from an operating voltage , and interruption information of the machining (¶ 13-15: Input data, including operating voltage, obtained from sensors over a period of time are fed into a Long Short Term Memory model for inferring the health condition of a machining asset. The model is used to determine a failure or survival state of the asset, as further discussed in ¶ 36-39.) Before the effective filing date of the invention, it would have been obvious to one of ordinary skill in the art to modify the detection of two process variables for determining the wear of a subtractive manufacturing tool taught by YANG by using voltage data over a period of time as one of the at least two processing variables as taught by LIAO. Since the references are similarly directed to using multiple variables to estimate a tool state or a wear or a tool, the combination would have yielded predictable results. LIAO (¶ 2) teaches that asset health assessment, including predicting tool wear, is known to involve reliance on historical operating data, such as operating voltage, sensor data, and maintenance action logs. It therefore would have been obvious for a person of ordinary skill in the art viewing the teachings of YANG and LIAO to have considered any two or more commonly known process variables for feeding into a machine learning algorithm for inferring the state of a tool. Regarding Claim 2 , YANG in view of LIAO further teaches wherein at least one of the process variables is detected in a time-resolved manner. (YANG, ¶ 48, 50: Sensor data is time stamped and synchronized and the tool wear value is predicted in real time, so the process variables are detected in a time-resolved manner.) Regarding Claim 3 , YANG in view of LIAO further teaches wherein the neural network comprises a deep neural network, a convolutional neural network, a multilayer perceptron, a long short-term memory, and/or an autoencoder. (LIAO, ¶ 11, 13-14: The neural network comprises a deep neural network, including a LSTM layer.) The same motivation to combine discussed in the rejection of claim 1 applies to claim 3. Furthermore, LIAO teaches using a LSTM layer is advantageous for extracting features from data obtained over a long period of time. Regarding Claim 4 , YANG in view of LIAO further teaches wherein the wear on the tool is inferred using a binary logic. (LIAO, ¶ 29-30, 52: The health assessment, i.e. wear on the tool in view of YANG, is inferred using a binary logic since there are two states: failure and non-failure.) The same motivation to combine discussed in the rejection of claim 1 applies to claim 4. It would have been further obvious for the learning model to determine the dependency between the captured process variable data and a failure state, as taught by LAIO (¶ 34), in order to predict future failure or survival probability of an asset or tool. Regarding Claim 5 , YANG in view of LIAO further teaches wherein the tool comprises a miller, a drill, and/or an indexable insert. (YANG, ¶ 30: The cutting tool includes a mill tool product. The claim only requires one of the options.) Regarding Claim 6 , YANG in view of LIAO further teaches wherein the process variables are detected using one or more sensors and/or a log file. (YANG, ¶ 41, 47: The process variables, such as the current, are detected using one or more sensors. The claim only requires one of the two options; however, LIAO teaches using log files in ¶ 2, 33 and 40.) Regarding Claim 7 , YANG in view of LIAO further teaches further comprising, when a wear on the tool is inferred, swapping the tool and/or interrupting the machining. (YANG, ¶ 7, 46: If it is determined the tool wear is excessive, i.e. wear has been inferred, the tool is replaced.) Regarding Claim 8 , YANG teaches a machining system for subtractive machining of a workpiece the system comprising: a tool for machining the workpiece; (¶ 5-6: The method and system is for monitoring and predicting tool wear during operation of machine, particularly a cutting tool.) assessment facilities for assessing at least two process variables during performance of the machining, (¶ 47-48. Fig. 5: Multiple process variables are obtained including current data and image data. The process variables are used to ultimately predict, or infer, a wear on the tool. See ¶ 13 and 47, regarding the CPA, which is an assessment facility. ¶ 47-49: “The CPA 500 is communicatively connected to a tool machine 502 and a digital microscope 504. The tool machine 502 may be such as a CNC machine tool on which various sensors are installed, such as a current transducer, an accelerometer, a strain gauge, and a thermocouple, for detecting the statuses of axis motors and spindles during machining … The feature extraction circuit 530 not only extracts the tool wear features according to the operation segments and feature domains but also derives the wear size from the tool wear images.” The sensor data and the image data (captured by a digital microscope) are obtained during the machining process. ¶ 48: “The digital microscope 504 is installed in the machine tool to obtain tool wear images between two tool runs of operation, so as to build and refresh the HDNN model.” Images being obtained between runs still reads on “during performance of a machining process” as a machining process may involve multiple runs.) wherein the assessment facilities comprise a neural network for assigning a respective degree of wear to each of the at least two process variables; (¶ 41-42, 46, 49, Fig. 5 element 530: A neural network comprising a feature extraction method receives a set of current, temperature, vibration, and strain data from sensors as well as image capture data, i.e. at least two process variables. The neural network independently assigns a degree of wear to each variable by extracting wear features from the sensor data and by calculating the tool wear from the image data. When refreshing the neural network, both independently determined values are provided to a prediction circuit.) wherein the at least two process variables (¶ 47-49: The two process variables are the operating current of the machine tool and the shape of the tool, as further discussed directly below.) are each selected from the group consisting of: a shape of the tool … (¶ 40, 48-49: An imaging sensor, namely a digital microscope that captures tool wear images, which is equivalent to a camera or scanner, captures image data including wear on the corner or flank of the tool and the size of the wear, which is shape data. ¶ 40: “analyzing and measuring a cutting tool image captured by a digital microscope after each historical tool run of operation, for example, measuring the wear of the tool flank or tool corner ”. The neural network that assesses tool wear is trained on historical image data that is analyzed to assess the wear on the tool flank or tool corner. This reads on “a shape of the tool”. ¶ 49: “The feature extraction circuit 530 not only extracts the tool wear features according to the operation segments and feature domains but also derives the wear size from the tool wear images ”. “The “wear size” reads on “a shape of the tool”.) a processor programmed to determine a wear on the tool on the basis of the assigned degrees of wear. (¶ 49 with context from ¶ 28 and 31, Fig. 5 element 540: The neural network includes logic which infers or predicts the wear of the tool based upon the wear feature extraction values of the sensor data and the tool wear calculation of the image data, i.e. on the basis of the assigned degrees of wear.) YANG teaches using two process variables, namely current data and image data, and teaches at least one of the process variables from the claimed grouping, namely the shape of the tool, but it does not teach two process variables from the claimed grouping. YANG does not teach an operating voltage, and interruption information of the machining; However, LIAO, which is similarly directed to determining the health assessment of a tool or asset (¶ 11-13), teaches at least one from an operating voltage , and interruption information of the machining (¶ 13-15: Input data, including operating voltage, obtained from sensors over a period of time are fed into a Long Short Term Memory model for inferring the health condition of a machining asset. The model is used to determine a failure or survival state of the asset, as further discussed in ¶ 36-39.) Before the effective filing date of the invention, it would have been obvious to one of ordinary skill in the art to modify the detection of two process variables for determining the wear of a subtractive manufacturing tool taught by YANG by using voltage data over a period of time as one of the at least two processing variables as taught by LIAO. Since the references are similarly directed to using multiple variables to estimate a tool state or a wear or a tool, the combination would have yielded predictable results. LIAO (¶ 2) teaches that asset health assessment, including predicting tool wear, is known to involve reliance on historical operating data, such as operating voltage, sensor data, and maintenance action logs. It therefore would have been obvious for a person of ordinary skill in the art viewing the teachings of YANG and LIAO to have considered any two or more commonly known process variables for feeding into a machine learning algorithm for inferring the state of a tool. Regarding Claim 9 , YANG in view of LIAO further teaches further comprising detectors for determining the at least two process variables; wherein the detectors comprise a camera and/or a scanner as well as a current detector (YANG, ¶ 41, 47: The process variables, such as the current, are detected using one or more sensors. ¶ 40, 48-49: An imaging sensor, namely a microscope, which is equivalent to a camera or scanner, captures image data. A current sensor and the microscope are therefore detectors for determining at least two process variables.) and/ or a detection means for entries in a log file. (LIAO, ¶ 2, 33, 40: The sequential data input into the LSTM model are determined either from sensors or log files/ data stores.) Only one of the options is required by the claim; however, all the means of detection included in the claimed grouping are disclosed by YANG and LIAO. The same motivation to combine discussed in the rejection of claim 8 applies to claim 9. Conclusion 07-39 AIA THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to RAMI RAFAT OKASHA whose telephone number is (571)272-0675. The examiner can normally be reached M-F 10-6 EST. 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, SCOTT BADERMAN can be reached at (571) 272-3644. 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. /RAMI R OKASHA/Primary Examiner, Art Unit 2118 Application/Control Number: 18/003,589 Page 2 Art Unit: 2118 Application/Control Number: 18/003,589 Page 3 Art Unit: 2118 Application/Control Number: 18/003,589 Page 4 Art Unit: 2118 Application/Control Number: 18/003,589 Page 5 Art Unit: 2118 Application/Control Number: 18/003,589 Page 6 Art Unit: 2118 Application/Control Number: 18/003,589 Page 7 Art Unit: 2118 Application/Control Number: 18/003,589 Page 8 Art Unit: 2118 Application/Control Number: 18/003,589 Page 9 Art Unit: 2118 Application/Control Number: 18/003,589 Page 10 Art Unit: 2118 Application/Control Number: 18/003,589 Page 11 Art Unit: 2118 Application/Control Number: 18/003,589 Page 12 Art Unit: 2118 Application/Control Number: 18/003,589 Page 13 Art Unit: 2118 Application/Control Number: 18/003,589 Page 14 Art Unit: 2118 Application/Control Number: 18/003,589 Page 15 Art Unit: 2118
Prosecution Insights