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 .
Claims 1-9 are pending in the application.
Claims 4-7 and 9 are Withdrawn.
Examiner’s Note: The examiner has cited particular passages including column and line numbers, paragraphs as designated numerically and/or figures as designated numerically in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claims, other passages, paragraphs and figures of any and all cited prior art references may apply as well. It is respectfully requested from the applicant, in preparing an eventual response, to fully consider the context of the passages, paragraphs and figures as taught by the prior art and/or cited by the examiner while including in such consideration the cited prior art references in their entirety as potentially teaching all or part of the claimed invention. MPEP 2141.02 VI: “PRIOR ART MUST BE CONSIDERED IN ITS ENTIRETY, INCLUDING DISCLOSURES THAT TEACH AWAY FROM THE CLAIMS."
Response to Arguments
Applicant's arguments filed 06/08/2026 have been fully considered but they are not persuasive.
Applicant argues that Aizawa fails to disclose the limitation:
“estimate a combination of set values of the parameters more suitable for the machining based on the updated value function, and output the estimated combination of the set values of the parameters,” because Aizawa allegedly determines only a “speed distribution” (e.g., acceleration or jerk) of each axis rather than a “combination of set values of parameters.”
The examiner respectfully disagrees.
Claim 1 does not define the claimed “parameters” as any particular type of control parameter, nor does it require that the parameters comprise servo gains, filter coefficients, feedforward coefficients, parameter table, or other specific control settings. The claim does not require maintaining multiple parameter sets, storing parameter combinations, or switching among parameter combinations according to different machining purposes. Accordingly, under the broadest reasonable interpretation consistent with the specification, the recited “combination of set values of the parameters” broadly encompasses multiple values used together to control movement of the machine tool.
Aizawa teaches that the learning section learns a speed distribution for each axis of the machine tool, wherein the speed distribution is an N-th order time-derivative component of speed, such as acceleration or Jerk (par. 0041, 0044, 0047). Further, Decision Making Section 52 generates command values for the machine tool based on the learning speed distribution (par. 0065-0067). Since the learning control values are determined for the respective axes of the machine tool and collectively define the movement of the machine tool during machining, Aizawa teaches estimating and outputting a combination of control values suitable for machining based on the learned value function.
Applicant’s argument relies of paragraph 0044 of the present specification, which describes embodiments in which combinations of parameter values may be maintained and switched according to different machining purposes. However, claim 1 does not positively recite maintaining parameter combinations, storing parameter sets, switching among parameter combinations, or selecting parameter combinations according to machining purpose. It is well settled that limitations appearing only in the specification may not imported into the claims during examination. See MPEP 2111.
Furthermore, Applicant’s characterization that Aizawa determines only “one parameter” is not supported by the references. Aizawa expressly teaches determining speed distributions of each axis of the machine tool, where the speed distribution may comprise acceleration, jerk, or another N-order time derivative (par. 0030, 0066). These collectively constitute multiple control values used together during machining and therefore reasonably satisfy the broadly recited “combination of set values of the parameters.”
Accordingly, Aizawa teaches or at least expressly discloses the disputed limitation, and the rejection under 35 U.S.C. 102(a)(1) is maintained.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-3, 8 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Aizawa et al. US Pub. No. 2018/0307211 (“Aizawa”).
Regarding claim 1, Aizawa discloses a machine learning device [Machine learning Apparatus 20 see fig. 5] or estimating parameters related to control of an amount of movement for each control cycle, including an N-order time differential element (N being a natural number) of each shaft included in a machine tool for performing machining of a workpiece, the machine learning device comprising a processor configured to:
[0006] An acceleration and deceleration controller in one embodiment of the present invention is an acceleration and deceleration controller for controlling a machine tool configured to machine a workpiece. The acceleration and deceleration controller includes a machine learning apparatus configured to learn an Nth-order time-derivative component (N is a natural number) of a speed of each axis of the machine tool.
[0030] In the present invention, by performing machine learning concerning the determination of travel distances for the sake of adjustment of the acceleration and deceleration of each axis of a machine tool in the machining of a workpiece based on a machining program, the speed distribution of each axis of the machine tool in the machining of the workpiece is optimally determined. Here, the speed distribution of each axis means an Nth-order time-derivative component of the speed (N is any natural number), for example, the acceleration or jerk of each axis. The speed distribution (Nth-order time-derivative component of the speed) of each axis is determined so that faster tool travel, improved machining accuracy, and improved machined-surface quality may be achieved. Thus, a workpiece can be machined in a shorter period of time without sacrificing machining accuracy and machined-surface quality.
observe information related to at least one of machining accuracy or machined surface quality in the machining and a machining time consumed for the machining, as data indicating an operating state of the machine tool;
[0033] As represented by functional blocks in FIG. 1, the machine learning apparatus 20 of the acceleration and deceleration controller 10 includes a state observation section 22 for observing a state variable S representing a speed distribution (Nth-order time-derivative component of the speed) of each axis, a determination data acquisition section 24 for acquiring determination data D for a given state variable S, the determination data D including determination data D1 representing the surface quality of a machined workpiece and determination data D2 representing machining time, and a learning section 26 for learning an optimal speed distribution (Nth-order time-derivative component of the speed) of each axis using the state variable S and the determination data D.
[0041] In one modified example of the machine learning apparatus 20 of the acceleration and deceleration controller 10, the state observation section 22 may further observe a machining type S2 representing the shape of a machining path and the like as the state variable S. The machining type S2 may include, for example, the shape (identification data for identifying a straight line portion, a corner portion, a portion machined into a rounded shape, a portion machined into a concentric shape, or the like) of the machining path. The machining type S2 may further include data (such as angle and radius) representing the size of a corner or the like, except a straight line portion. With respect to angle and radius, a plurality of grades may be defined in advance, and the machining type S2 may include identification data indicating which grade is assigned to each of angles and radii included in the machining path. Places where the speed distribution (Nth-order time-derivative component of the speed) of each axis needs to be changed are generally corner portions and the like, except straight line portions. The optimal speed distribution (Nth-order time-derivative component of the speed) of each axis may vary in accordance with the shape of a corner portion or the like. If the machining type S2 is observed, the learning section 26 can learn the surface quality and the machining time of a machined workpiece in relation to both the speed distribution (Nth-order time-derivative component of the speed) S1 of each axis and the machining type S2. Specifically, a model representing the correlation between a combination of surface quality and machining time and the speed distribution (Nth-order time-derivative component of the speed) of each axis can be constructed independently for each machining type S2. Accordingly, the optimal speed distribution (Nth-order time-derivative component of the speed) of each axis in accordance with the shape of a corner portion or the like can be learned.
acquire a target value related to the data as determination data;
[0033] As represented by functional blocks in FIG. 1, the machine learning apparatus 20 of the acceleration and deceleration controller 10 includes a state observation section 22 for observing a state variable S representing a speed distribution (Nth-order time-derivative component of the speed) of each axis, a determination data acquisition section 24 for acquiring determination data D for a given state variable S, the determination data D including determination data D1 representing the surface quality of a machined workpiece and determination data D2 representing machining time, and a learning section 26 for learning an optimal speed distribution (Nth-order time-derivative component of the speed) of each axis using the state variable S and the determination data D.
[0035] The determination data acquisition section 24 can be configured as, for example, one function of a CPU of a computer. Alternatively, the determination data acquisition section 24 can be configured as, for example, software that causes a CPU of a computer to work. The determination data D1 acquired by the determination data acquisition section 24 are numerical data representing results of inspection of a machined surface, such as data obtained from an inspection apparatus (not shown) or a sensor installed in an inspection apparatus or data obtained by using or converting that data. Examples of such an inspection apparatus include a machined-surface analysis apparatus (typically, a laser microscope), a machined-surface image capture apparatus, a light reflectance measurement apparatus, and the like. Examples of data that represent surface quality capable of being measured by an inspection apparatus include surface roughness Sa, surface maximum height Sv, surface texture aspect ratio Str, kurtosis Sku, skewness Ssk, developed interfacial area ratio Sdr, the light reflectance of a machined workpiece, a feature of an image of a machined surface, and the like. Alternatively, the determination data D1 may be data obtained by inputting a file that contains results of evaluation of surface quality by a skilled worker or directly inputting results of evaluation of surface quality through an interface such as a keyboard or data obtained by using or converting that data. Examples of the determination data D2 acquired by the determination data acquisition section 24 include data on machining time actually measured by the acceleration and deceleration controller 10 and data obtained by using or converting that data.
calculate, based on the data and the determination data, a reward for machining based on the parameters;
[0044] In the machine learning apparatus 20 of the acceleration and deceleration controller 10 shown in FIG. 2, the learning section 26 includes a reward calculation section 28 for finding a reward R relating to a result (determination data D representing the surface quality and the machining time of a machined workpiece) of machining performed based on a certain state variable S and a value function update section 30 for updating a function Q representing the value of a speed distribution (Nth-order time-derivative component of the speed) of each axis using the reward R. The learning section 26 learns such speed distribution (Nth-order time-derivative component of the speed) of each axis that improves the surface quality of a machined workpiece and that shortens the machining time, by the value function update section 30 repeating the update of the function Q.
[READ further paragraph 0047-0053]
Update, based on the reward, a value function for calculating a value of a machining state based on the parameters; and
[0044] In the machine learning apparatus 20 of the acceleration and deceleration controller 10 shown in FIG. 2, the learning section 26 includes a reward calculation section 28 for finding a reward R relating to a result (determination data D representing the surface quality and the machining time of a machined workpiece) of machining performed based on a certain state variable S and a value function update section 30 for updating a function Q representing the value of a speed distribution (Nth-order time-derivative component of the speed) of each axis using the reward R. The learning section 26 learns such speed distribution (Nth-order time-derivative component of the speed) of each axis that improves the surface quality of a machined workpiece and that shortens the machining time, by the value function update section 30 repeating the update of the function Q.
[READ further paragraph 0045-0046, 0050-0053]
estimate a combination of set values of the parameters more suitable for the machining based on the updated value function, and output the estimated combination of the set values of the parameters.
[0038] By repeating the above-described learning cycle, the learning section 26 can automatically recognize features implying the correlation between a speed distribution (Nth-order time-derivative component of the speed) of each axis and a combination of the surface quality and the machining time of a machined workpiece. The correlation between a speed distribution (Nth-order time-derivative component of the speed) of each axis and a combination of the surface quality and the machining time of a machined workpiece is substantially unknown. The learning section 26 gradually recognizes features and interprets the correlation as learning progresses. When the correlation between a speed distribution (Nth-order time-derivative component of the speed) of each axis and a combination of the surface quality and the machining time of a machined workpiece is interpreted to some reliable level, learning results repeatedly outputted by the learning section 26 can be used for making a selection of an action (that is, decision-making) as to what surface quality of a machined workpiece and what machining time should be derived for the current state (that is, the speed distribution (Nth-order time-derivative component of the speed) of each axis). Specifically, as the learning algorithm progresses, the learning section 26 can make the correlation between the speed distribution (Nth-order time-derivative component of the speed) of each axis and an action derived from the state which includes the surface quality and the machining time of a machined workpiece gradually closer to the optimal solution.
[0065] A decision-making section 52 can be configured as, for example, one function of a CPU of a computer. Alternatively, the decision-making section 52 can be configured as, for example, software that causes a CPU of a computer to work. The decision-making section 52 generates a command value C to a machine tool that performs machining based on the speed distribution (Nth-order time-derivative component of the speed) of each axis learned by the learning section 26, and outputs the generated command value C. In the case where the command value C based on the speed distribution (Nth-order time-derivative component of the speed) of each axis learned by the decision-making section 52 is outputted to the machine tool, the state (speed distribution (Nth-order time-derivative component of the speed) S1 of each axis) of the environment changes in response to the outputted command value C.
[READ further paragraph 0066-0067]
Regarding claim 2, Aizawa discloses the processor is configured to register an evaluation program capable of evaluating at least one of the machining accuracy or the machined surface quality, and calculate a reward related to at least one of the machining accuracy or the machined surface quality using the evaluation program [SEE par. 0032, 0050-0054, 0079].
Regarding claim 3, Aizawa discloses the processor is configured to estimate the combination of set values of the parameters more shortening a machining time in the machining and more suitable for the machining based on the updated value function, and output the estimated combination of the set values of the parameters [SEE par. 0044].
Regarding claim 8, it is directed to the a non-transitory computer-readable storage medium storing a program to implement the system as set forth in claim 1. Therefore, they are rejected on the same basis as set forth hereinabove.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US Pub. No. 2020/0279158 to Tsunoda et al. teaches
[0007] An aspect of the invention is a machining condition adjustment device that adjusts at least either of a machining condition and a machining parameter for a machine tool to machine a workpiece. The machining condition adjustment device includes: a data acquisition unit that acquires at least one piece of data indicating a state of machining including a machining type in the machine tool; a priority condition storage unit that stores priority condition data in which the machining type in the machine tool is associated with a priority condition for the machining type; a preprocessing unit that produces data to be used for machine learning, based on the data acquired by the data acquisition unit and the priority condition corresponding to the machining type included in the data and stored in the priority condition storage unit; and a machine learning device that carries out processing of the machine learning related to at least either of the machining condition and the machining parameter for machining by the machine tool in an environment where the workpiece is machined by the machine tool, based on the data produced by the preprocessing unit. The machine learning device includes: a learning model storage unit that stores a plurality of learning models generated for each machining type in the machine tool; and a learning model selection unit that selects a learning model to be used for the processing of the machine learning from among the plurality of learning models stored in the learning model storage unit, based on the machine type included in the data produced by the preprocessing unit.
[0055] The decision making by the decision making unit 122 is carried out through the execution of the system programs read from the ROM 102 by the processor 101 included by the machining condition adjustment device 1 illustrated in FIG. 1 and the arithmetic processing primarily by the processor 101 with use of the RAM 103 and the nonvolatile memory 104. The decision making unit 122 determines the optimal solution of the adjustment behavior for at least either of the machining conditions and the machining parameters with use of the learning model selected by the learning model selection unit 105 based on the state data S inputted from the preprocessing unit 36 and outputs the determined adjustment behavior for at least either of the machining conditions and the machining parameters. The decision making unit 122 of the embodiment inputs the state data S (the tool data S1, the machining condition data S2, and the machining parameter data S3) inputted from the preprocessing unit 36 and the adjustment behavior for at least either of the machining conditions and the machining parameters (a combination of adjustment for the feed speed, adjustment for the spindle speed, and the like, or change in setting of the parameters) as input data into the learned model updated (having the parameters determined) through the reinforcement learning by the learning unit 110, so that the reward in case where the pertinent behavior is executed in the current state is calculated. The calculation of the reward in the decision making unit 122 is carried out for the adjustment behavior for at least either of the machining conditions and the machining parameters that may be currently adopted. Through a comparison among a plurality of calculated rewards, the adjustment behavior for at least either of the machining conditions and the machining parameters that results in calculation of the largest reward is determined as the optimal solution. The optimal solution of the adjustment behavior for at least either of the machining conditions and the machining parameters determined by decision making unit 122 is inputted into the control unit 32 and is used for determination of at least either of the machining conditions and the machining parameters in actual machining. The optimal solution of the adjustment behavior may be additionally used by being displayed as output on the display/MDI unit 70 or by being transmitted as output through a wired/wireless network (not illustrated) to a fog computer, a cloud computer, or the like, for instance.
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 VINCENT HUY TRAN whose telephone number is (571)272-7210. The examiner can normally be reached M-F 7:00-4:00.
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, Kamini S Shah can be reached at 571-272-2279. 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.
VINCENT H TRAN
Primary Examiner
Art Unit 2115
/VINCENT H TRAN/Primary Examiner, Art Unit 2115
Prosecution Insights