DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This is in response to the above application filed on 08/16/2023. Claims 1 – 20 are examined.
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.
Claims 1 – 20 are rejected under 35 U.S.C. 102(a)(1) as anticipated by Kobayashi et al. (2021/0299788A1) as evidenced by Wittwer (11,467,561).
Regarding Claim 1, Kobayashi discloses, in Figures 1 – 3 and 9 and Paras. [0011], [0021], [0037], [0039], [0041], [0043], and [0045], all the claimed limitations including a method, comprising: determining first data (Para. [0045] “…are given as first input data…”.) indicative of processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]) for processing a material (10 - Para. [0037]) in a laser processing system (20 – Para. [0037]) comprising a digital twin (54 and 56); providing the first data (Para. [0045] “…are given as first input data…”.) as input to a trained machine learning model (50, 54, and 56), wherein the digital twin (54 and 56) comprises the trained machine learning model (54 and 56); obtaining one or more outputs of the trained machine learning model (54 and 56), the one or more outputs indicating predicted performance data (Para. [0045] “…a relationship used for estimating first output data that is three-dimensional shape data of the processed part after irradiation with the laser beam, …a relationship used for estimating second output data that is laser beam parameters of laser beam which the processed part of the processing object 10 is to be irradiated with…”) associated with the processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]) for processing the material (10); and causing (Para. [0058] “After termination of the learning process of FIG. 3, machine learning may be performed by using learning data accumulated by that time, every time laser processing is performed or at a predetermined timing.”), based on the predicted performance data, the material (10) to be processed according to the processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]).
The Claim 1 limitations recited, “the digital twin comprises the trained machine learning model”; therefore, the “digital twin” was just a different name for the “machine learning model” disclosed by Kobayashi, as evidenced by Wittwer. Wittwer teaches, in Figs. 1 – 12, Col. 2, ll. 40 – 50, Col. 12, l. 55 - Col. 13, l. 30, Col. 13, ll. 45 – 65, Col. 14, ll. 10 – 30, Col. 15, ll. 10 – 35, and Col. 18, ll. 10 – 50, a similar laser processing system (L) with a “digital twin”, i.e., machine learning model, with “The data structures, application cases, algorithms, and data flow form the digital twin of the laser material machining (application). The digital twin is modular and uses, among other things, empirical values to keep the algorithms simple and fast and to ensure the comparability between digital twin and real laser material machining (application). The model includes at least three data structures: i. Data structure 1 contains the data of the parameter set P; ii. Data structure 2 contains the process characteristics PKG; iii. Data structure 3 contains the data of the machining result E.”
Regarding Claim 9, Kobayashi discloses, in Figures 1 – 3 and 9 and Paras. [0011], [0021], [0037], [0039], [0041], [0043], and [0045], all the claimed limitations including a system (20 – Fig. 1) comprising: a memory (Paras. [0041] and [0044]); and a processing device (38 and 50) coupled to the memory, the processing device (38 and 50) to: determining first data (Para. [0045] “…are given as first input data…”.) indicative of processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]) for processing a material (10 - Para. [0037]) in a laser processing system (20 – Para. [0037]) comprising a digital twin (54 and 56); providing the first data (Para. [0045] “…are given as first input data…”.) as input to a trained machine learning model (50, 54, and 56), wherein the digital twin (54 and 56) comprises the trained machine learning model (54 and 56); obtaining one or more outputs of the trained machine learning model (54 and 56), the one or more outputs indicating predicted performance data (Para. [0045] “…a relationship used for estimating first output data that is three-dimensional shape data of the processed part after irradiation with the laser beam, …a relationship used for estimating second output data that is laser beam parameters of laser beam which the processed part of the processing object 10 is to be irradiated with…”) associated with the processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]) for processing the material (10); and causing (Para. [0058] “After termination of the learning process of FIG. 3, machine learning may be performed by using learning data accumulated by that time, every time laser processing is performed or at a predetermined timing.”), based on the predicted performance data, the material (10) to be processed according to the processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]).
The Claim 9 limitations recited, “the digital twin comprises the trained machine learning model”; therefore, the “digital twin” was just a different name for the “machine learning model” disclosed by Kobayashi, as evidenced by Wittwer. Wittwer teaches, in Figs. 1 – 12, Col. 2, ll. 40 – 50, Col. 12, l. 55 - Col. 13, l. 30, Col. 13, ll. 45 – 65, Col. 14, ll. 10 – 30, Col. 15, ll. 10 – 35, and Col. 18, ll. 10 – 50, a similar laser processing system (L) with a “digital twin”, i.e., machine learning model, with “The data structures, application cases, algorithms, and data flow form the digital twin of the laser material machining (application). The digital twin is modular and uses, among other things, empirical values to keep the algorithms simple and fast and to ensure the comparability between digital twin and real laser material machining (application). The model includes at least three data structures: i. Data structure 1 contains the data of the parameter set P; ii. Data structure 2 contains the process characteristics PKG; iii. Data structure 3 contains the data of the machining result E.”
Regarding Claim 15, Kobayashi discloses, in Figures 1 – 3 and 9 and Paras. [0011], [0021], [0037], [0039], [0041], [0043], and [0045], all the claimed limitations including a non-transitory machine-readable storage medium (Paras. [0041] and [0044] – “memory”) comprising instructions (Paras. [0008] and [0060] “When the present disclosure is implemented as an aspect of a program that causes a computer to serve as a machine learning apparatus, the program may be performed by the system controller 50…”) that, when executed by a processing device (38 and 50), cause the processing device (38 and 50) to: determining first data (Para. [0045] “…are given as first input data…”.) indicative of processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]) for processing a material (10 - Para. [0037]) in a laser processing system (20 – Para. [0037]) comprising a digital twin (54 and 56); providing the first data (Para. [0045] “…are given as first input data…”.) as input to a trained machine learning model (50, 54, and 56), wherein the digital twin (54 and 56) comprises the trained machine learning model (54 and 56); obtaining one or more outputs of the trained machine learning model (54 and 56), the one or more outputs indicating predicted performance data (Para. [0045] “…a relationship used for estimating first output data that is three-dimensional shape data of the processed part after irradiation with the laser beam, …a relationship used for estimating second output data that is laser beam parameters of laser beam which the processed part of the processing object 10 is to be irradiated with…”) associated with the processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]) for processing the material (10); and causing (Para. [0058] “After termination of the learning process of FIG. 3, machine learning may be performed by using learning data accumulated by that time, every time laser processing is performed or at a predetermined timing.”), based on the predicted performance data, the material (10) to be processed according to the processing parameters (Paras. [0021], [0037], [0039], [0041], [0043], and [0045]).
The Claim 15 limitations recited, “the digital twin comprises the trained machine learning model”; therefore, the “digital twin” was just a different name for the “machine learning model” disclosed by Kobayashi, as evidenced by Wittwer. Wittwer teaches, in Figs. 1 – 12, Col. 2, ll. 40 – 50, Col. 12, l. 55 - Col. 13, l. 30, Col. 13, ll. 45 – 65, Col. 14, ll. 10 – 30, Col. 15, ll. 10 – 35, and Col. 18, ll. 10 – 50, a similar laser processing system (L) with a “digital twin”, i.e., machine learning model, with “The data structures, application cases, algorithms, and data flow form the digital twin of the laser material machining (application). The digital twin is modular and uses, among other things, empirical values to keep the algorithms simple and fast and to ensure the comparability between digital twin and real laser material machining (application). The model includes at least three data structures: i. Data structure 1 contains the data of the parameter set P; ii. Data structure 2 contains the process characteristics PKG; iii. Data structure 3 contains the data of the machining result E.”
Re Claims 2, 10, and 16, Kobayashi, a.e., Wittwer, discloses the invention as claimed and as discussed above, and Kobayashi further discloses wherein the processing parameters comprise at least one of material type (Para. [0045] “material of the processing object”), material strength, material thermal conductivity, material reflectance (Para. [0043] “optical reflectance spectral data”), laser type (Para. [0039] “The processing laser irradiator 32 is configured, for example, as a titanium sapphire laser irradiator that is capable of outputting laser beam (pulsed laser beam) having a wavelength of 800 nm, a variable pulse width of 35 fs to 10 ps, a repetition frequency of 1 kHz, a maximum output of 6 W, a maximum pulse energy of 6 mJ, and a fluence of 0.1 to 100 J/cm2.” ), laser wavelength (Para. [0021] “The “laser beam parameter” may be at least part of a wavelength, a pulse width, a pulse amplitude, a spot diameter, the number of pulses, and a fluence (pulse energy per unit area).”), pulse energy (“fluence (pulse energy per unit area)”), pulse duration, repetition rate (“repetition frequency”), hatch distance, beam diameter (“spot diameter”), beam shape, beam alignment, beam incidence, gas pressure, focal length (Para. [0037] “…has a focal point and an irradiation position adjusted by a focal lens 42 and a mirror 44”), polarization (Para. [0041] “…also controls the half-wave plate 35 and the polarizing beam splitter 36 such as to provide the polarization direction of laser beam based on the control signal from the system controller 50.”), marking speed, milling strategy, scanning speed, scan pattern, beam collimation, or focus position (Para. [0037] “…has a focal point and an irradiation position adjusted by a focal lens 42 and a mirror 44”).
Re Claim 3, Kobayashi, a.e., Wittwer, discloses the invention as claimed and as discussed above, and Kobayashi further discloses, in Para. [0063], wherein the predicted performance data comprises a predicted profile (“…computes three-dimensional shape data of the processed part (a shape in the course of processing) after irradiation with laser beam based on the input data. The optimization simulation process subsequently computes a difference between the computed three-dimensional shape data of the processed part (the shape in the course of processing) and the target shape and determines whether this difference is within an allowable range (step S330).”) of the processed material (10).
Re Claims 4, 11, and 17, Kobayashi, a.e., Wittwer, discloses the invention as claimed and as discussed above, and Kobayashi further discloses, in Fig. 9 and Para. [0063], determining preferred processing parameters (“After setting the initial values of the processing conditions, the optimization simulation process specifies the material of the processing object, the laser beam parameters, and the laser irradiation locations as input data and performs a processing simulation based on the input data (step S320).”), wherein the preferred processing parameters are determined based on the predicted performance data meeting a performance criterion (“…computes a difference between the computed three-dimensional shape data of the processed part (the shape in the course of processing) and the target shape and determines whether this difference is within an allowable range (step S330).”).
Re Claims 5, 12, and 18, Kobayashi, a.e., Wittwer, discloses the invention as claimed and as discussed above, and Kobayashi further discloses, in Fig. 9 and Para. [0063], wherein the performance criterion is a uniformity criterion (“…shape data of the processed part (the shape in the course of processing) and the target shape and determines whether this difference is within an allowable range (step S330).”).
Re Claim 6, Kobayashi, a.e., Wittwer, discloses the invention as claimed and as discussed above, and Kobayashi further discloses, in Fig. 1 and Para. [0044], wherein the processing parameters for processing the material (10) in the laser processing system (20 - Fig. 1) are determined based on user input (52 – keyboard and mouse). Kobayashi further discloses, in Para. [0021], “The “deep learning” uses the pre-processed part data and the post-processed part data and obtains the first relationship having the output data that is the post-processed part data, as the learning result. This “deep learning” is thus basically supervised learning.”
Re Claims 7, 13, and 19, Kobayashi, a.e., Wittwer, discloses the invention as claimed and as discussed above, and Kobayashi further teaches, in Para. [0060], further comprising: training the machine learning model using training input data comprising historical processing parameters data and training target output data comprising historical performance data associated with the historical processing parameters. Kobayashi teaches, in Para. [0060], “In the case where the machine learning apparatus is not provided with the processing laser irradiation device 30, the motor-driven stage 46, the three-dimensional data measuring instrument 48 or the like but is provided with only a microcomputer corresponding to the system controller 50, the processing of steps S100 to S170 in the learning process of FIG. 3 may be performed in advance by another device to obtain the material of the processing object 10, the laser beam parameters showing the properties of the laser beam which the processing object 10 is irradiated with, and the three-dimensional shape data of the processed part before and after irradiation of the processing object 10 with laser beam.” In other words, “another device” generated and collected the historical processing parameters and the historical performance data associated with the historical processing parameters in advance, i.e., before the collected historical data was provided to a microcomputer to train the machine learning model.
Re Claims 8, 14, and 20, Kobayashi, a.e., Wittwer, discloses the invention as claimed and as discussed above, and Kobayashi further discloses, in Figs. 2 and 3, Paras. [0045], [0046], and [0049], further comprising: determining second data (Paras. [0045], [0046], and [0049] “second input data, based on the first learning result”) indicative of updated processing parameters for processing the material (10) in the laser processing system (20), wherein the second data (Paras. [0045], [0046], and [0049] “second input data, based on the first learning result”) is based on performance data of the material (10) processed according to the processing parameters; providing the second data (Paras. [0045], [0046], and [0049] “second input data, based on the first learning result, a relationship used for estimating second output data that is laser beam parameters of laser beam which the processed part of the processing object 10 is to be irradiated with, is obtained as a second learning result and is also stored as the learning results 56.”) as input to the trained machine learning model (54 and 56); obtaining one or more second outputs (Paras. [0045], [0046], and [0049] “second output data”) of the trained machine learning model (54 and 56), the one or more second outputs (Paras. [0045], [0046], and [0049] “second output data”) indicating updated predicted performance data associated with updated processing parameters for processing the material (10); and causing, based on the updated predicted performance data, the material (10) to be processed according to the updated processing parameters (Para. [0058] “After termination of the learning process of FIG. 3, machine learning may be performed by using learning data accumulated by that time, every time laser processing is performed or at a predetermined timing.”).
Correspondence
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LORNE E MEADE whose telephone number is (571)270-7570. The examiner can normally be reached Monday - Friday 8-5 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, Phutthiwat Wongwian can be reached at 571-270-5426. 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.
/LORNE E MEADE/Primary Examiner, Art Unit 3741