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 .
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 10 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 10 recites the limitation “prediction value.” There is insufficient antecedent basis for this limitation in the claim.
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 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 no obviousness.
Claims 1-15 are rejected under 35 U.S.C. 103 as being unpatentable over Xiuquan et al. (CN 111426639A.), relied on machine translation, and in view of Higgins. (US 9239349 B2.), and further in view of Schwarz (DE 102018129441A1, relied on machine translation.).
As per claim 1, Xiuquan et al. teach
A method for analysing a laser machining process (page 1, claim 1, page 3, para 2), comprising:
detecting a plurality of spectra of process emissions at successive points in time (page 6, para 21, spectral detection method, page 4, para 8, acquiring spectral dataset, train a deep learning algorithm and combine this with spectral acquisition to achieve real-time detection, also see page 8, para 41, spectrometer 5 records the spectrum in real time and matches it with the welded workpiece);
wherein the neural network receives the spectral dataset as an input tensor and outputs the physical quantity and/or the classification of the laser machining process as an output tensor (page 9, para 44, S3 uses the labelled spectral dataset for deep learning to train the neural network and obtains a neural network algorithm to implement a welding judgment model. The labelled spectral dataset teaches input tensor, and the welding judgment model teaches the output tensor.).
Xiuquan et al. do not teach
generating at least one spectrogram based on the detected spectra;
However, in the same field of endeavor, Higgins teaches
generating at least one spectrogram based on the detected spectra (Higgins, Fig. 1, System 10, spectrogram generating module 18, Fig. 2, generating spectrogram 38 and storing spectrogram 40, Also see, col. 5, lines 55-64, a sequence array of spectra inserted into a sequencing array as representative of spectrogram,);
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the detecting plurality of spectra process taught by Xiuquan et al. and to include the spectra generation module taught by Higgins. This would have been obvious because both Xiuquan et al. and Higgins utilize the spectra generation process. By adding the FFT output of spectra in a database within the time interval, the spectra of process emissions will be done at successive points in time. This process will make the spectrogram generation more accurate (Higgins, Fig. 1, Fig. 2. col. 5, lines 55-64).
The combination of Xiuquan et al. and Higgins do not teach
determining at least one value of a physical quantity and/or determining at least one classification of the laser machining process by means of a neural network,
In the same field of endeavor Schwarz teaches
determining at least one value of a physical quantity (Schwarz, para 39, a keyhole depth) and/or determining at least one classification of the laser machining process by means of a neural network (Schwarz, page 6, para 27, a type of machining defect on a surface of a machined workpiece could be a gap, page 18, para 93, a transfer function formed by deep neural network that determines a processing error which has occurred at a time of the acquisition sample. The output tensor 640 contains information “error yes/no” with presence of probability error in “hole,’ “spatter” or “gap”, Evaluating machining defect could be one of the classification of machining process. Also see, page 5, para 23, where it describes that the computing unit determines input tensors of the laser machining process and determines an output tensor, which contains information about a current machining result. These are formed by a learned neural network. The machining result may include information about a machining error. Further, see page 10, paras 46-47 where it describes the neural networks classifying the data. Also see para 36, the computing unit can be configured to collect data of machining process corresponding to the same current point in time. By the transfer function, the collected data can be mapped to the input tensor and output tensor. With the simultaneous data collection process, the determination of machining process can be done more quickly and reliably.).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the detecting plurality of spectra process taught by Xiuquan et al. and to include the gap error analysis taught by Schwarz. This would have been obvious because both Xiuquan et al. and Schwarz teach a process for evaluating laser welding. By adding the process analysis error during samples acquisition by a deep neural network, the data acquisition would be more refined. By applying the transfer function mapped to both input and output tensor simultaneously, the machining process will be determined more reliably and accurately (Schwarz, para 36, page 18, para 93).
As per claim 2, the combination of Xiuquan et al. and Higgins and Schwarz teach
The method according to claim 1,
wherein detecting each of the spectra comprises detecting intensities of the process emissions as a function of the wavelength at the respective point in time (Xiuquan et al., page 1, claim 1, S2 collects the spectral data and marks the continuous spectrum in the wavelength range 550nm to 750 nm as successful welding and obtain the marked spectral data. S3 trains the neural network using the labelled data and generate real time evaluation of welding quality, also see page 8, para 41. Higgins, Fig. 2, #32 capturing and/or receiving waveform, Fig. 4, #82, locate time domain capture on scatter plot and determine repetition rate).
As per claim 3, the combination of Xiuquan et al., Higgins, and Schwarz teach
The method according to claim 2, wherein the detected intensities are raw data (Schwarz, para 35, “The input tensors can comprise or consist of current data of the laser machining process as raw data.”, Xiuquan et al., page 1, claim 1, S1 performs welding and simultaneously collects data for spectral data set. S2 collects both data such as data that that shows continuous spectrum, and the data do not show continuous spectrum. S2 marked them. S3 collects the labelled data to train the neural network to obtain welding quality judgment model. The data containing continuous and non-continuous spectra teaches raw data.).
As per claim 4, the combination of Xiuquan et al., Higgins, and Schwarz teach
The method according to claim 2, wherein the detected intensities of a spectrum are detected simultaneously and/or wherein the detection of each spectrum comprises a local spectral splitting at a detector (Xiuquan et al., page 8, para 42, spectrometer 5 is used to collect spectral images and at the same time, the spectrometer 5 records the spectrum in the real time and matches it with the welded workpiece to obtain the spectral dataset).
As per claim 5, Xiuquan et al. teach
The method according to claim 1 (page 1, claim 1, page 3, para 2),
The combination of Xiuquan et al. and Higgins do not teach,
wherein the process emissions comprise a temperature radiation, a plasma radiation and/or a laser radiation reflected from a surface of a workpiece.
However, in the same field of endeavor, Schwarz teaches
wherein the process emissions comprise a temperature radiation, a plasma radiation and/or a laser radiation reflected from a surface of a workpiece (Schwarz, page 9, para 39, current sensor data may include one or more temperatures, plasma radiation).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the detecting plurality of spectra process taught by Xiuquan et al. and to include the emissions comprising temperature radiation or plasma /laser radiation. This would have been obvious because both Xiuquan et al. and Schwarz teach a process for evaluating laser welding. By adding the plasma radiation or temperature radiation to this process, both Xiuquan et al. and Schwarz can upgrade the welding process with proper radiation evaluation (Schwarz, page 9, para 39).
As per claim 6, Xiuquan et al. teach
The method according to claim 1 (page 1, claim 1, page 3, para 2), wherein generating the at least one spectrogram comprises:
Xiuquan et al. do not teach
generating of a first spectrogram for a first-time interval and generating of a second spectrogram for a second time interval, wherein the second time interval overlaps with and/or immediately follows the first time interval; and/or chronological assembling of the plurality of spectra.
However, in the same field of endeavor, Higgins teaches
generating of a first spectrogram for a first time interval and generating of a second spectrogram for a second time interval, wherein the second time interval overlaps with and/or immediately follows the first time interval (Higgins, col. 6, lines 35-58, describes a scatter plot generation module 8 where first order infinite impulse response (IIR) filter 26 is arranged based on the time interval between each of the FFT in the spectrogram.); and/or
chronological assembling of the plurality of spectra (Higgins, Col. 5, lines 58-60, database 16 is arranged to store the set of frequency domain spectra, sequence of spectra inserted into a sequencing array as representative of spectrogram).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the detecting plurality of spectra process taught by Xiuquan et al. and to include the spectra generation module by time interval taught by Higgins. This would have been obvious because both Xiuquan et al. and Higgins utilize the spectra generation process. By adding the FFT output of spectra in a database within the time interval, the spectra of process emissions will be done at successive point in time. This process will make data more refined (Higgins, col. 6, lines 35-58, Col. 5, lines 58-60).
As per claim 7, Xiuquan et al. teach
The method according to claim 1 (Xiuquan et al., page 1, claim 1, page 3, para 2) ,
The combination of Xiuquan et al. and Higgins do not teach
wherein the physical quantity comprises at least one of the following:
a tensile, a compressive strength, an electrical conductivity, a keyhole depth , a weld-in depth ,a gap size of a gap between two workpieces joined by the laser machining process, a roughness of a cut edge of a workpiece cut by the laser machining process, a burr of a cut edge of a workpiece cut by the laser machining process, a burr height of a cut edge of a workpiece cut by the laser machining process, a steepness of the cutting front and a perpendicularity of a cut edge of a workpiece cut by the laser machining process; and/or
wherein the classification of the workpiece corresponds to a classification into a error class and comprises at least one of the following: gap, offset, missing weld penetration and/or weld-in, defective removal, cut quality and alloy quality.
In the same field of endeavor Schwarz teaches
wherein the physical quantity comprises at least one of the following:
a tensile strength , a compressive strength, an electrical conductivity, a keyhole depth (Schwarz, para 24, a keyhole has been formed, para 26, a depth of the keyhole) , a weld-in depth ,a gap size of a gap between two workpieces joined by the laser machining process (Schwarz, para 27, a gap in the workpiece) , a roughness of a cut edge of a workpiece cut by the laser machining process (Schwarz, para 27, para 112, machining process defect such as a pore, hole, eject, spatter, adhesion, or a lack of weld through) a burr of a cut edge of a workpiece cut by the laser machining process, a burr height of a cut edge of a workpiece cut by the laser machining process, a steepness of the cutting front and a perpendicularity of a cut edge of a workpiece cut by the laser machining process; and/or
wherein the classification of the workpiece corresponds to a classification into a error class and comprises at least one of the following: gap, offset, missing weld penetration and/or weld-in, defective removal, cut quality and alloy quality (Schwarz, page 6, para 27 , a type of machining defect on a surface of a machined workpiece could be a lack of weld-through and a gap, page 18, para 93, a transfer function formed by deep neural network that determines a processing error which has occurred at a time of the acquisition sample, the output tensor 640 contains information “error yes/no” presence of probability error “hole’ presence of probability of error “spatter” Presence of probability of error “gap” , also presence of probability of error “false Freund/lack of weld-through”.).
As per claim 8, the combination of Xiuquan et al., Higgins, and Schwarz teach
The method according to claim 1, wherein the spectra are detected at a sampling rate between about 100 Hz and 100 kHz or between about 800 Hz and 10 kHz or between about 900 Hz and 2 kHz (Xiuquan et al., page 8, para 39, “the repetition frequency is 0.1kHz to 10kHz, and the center wavelength is 750nm to 850nm.”).
As per claim 9, the combination of Xiuquan et al., Higgins, and Schwarz teach
The method according to claim 1, wherein the spectra are detected in a wavelength range between about 100 nm to about 1500 nm or between about 130 nm to 1300 nm or between about 150 nm and 1050 nm or between about 340 nm and 850 nm; and/or wherein the spectra are detected with a spectral resolution of between about 0.1 nm and 1 nm or between about 0.2 nm to 0.8 nm or between about 0.4 nm to 0.6 nm (Xiuquan et al., page 8, para 39, “the repetition frequency is 0.1kHz to 10kHz, and the center wavelength is 750nm to 850nm.”).
As per claim 10, Xiuquan et al. teach
The method according to claim 1,
Xiuquan et al. do not teach
wherein the value of the physical quantity and/or the classification is determined in real time and, based thereon, control data is output to a laser machining system performing the laser machining process.
In the same field of endeavor Schwarz teaches
wherein the value of the physical quantity and/or the classification is determined in real time and, based thereon, control data is output to a laser machining system performing the laser machining process (Schwarz, paras 23- 24, a computing unit is configured to determine input tensors and a neural network forms a transfer function that maps between the input tensor and output tensor. The output tensor contains the machining results that may include machining errors. The system can also determine processing results. The machining process can be compared with a predefined result or predefined geometry. The error can be adjusted based on that. Para 28 states that the configuration of the computing unit can be done while it is still being executed. Therefore, the evaluation of the machining process can be done in real time by directly determining the processing result.)
As per claim 11, the combination of Xiuquan et al., Higgins, and Schwarz teach
The method according to claim 1, wherein the neural network is a trained neural network which can be adapted by means of training data by transfer learning (Xiuquan et al., page 1, claim 1, page 4, para 7, S3 acquires spectra datasets and trains a deep learning network to obtain a suitable neural network algorithm).
As per claim 12, Xiuquan et al. teach
A system for analysing a laser machining process (page 2, claim 5), comprising:
at least one sensor unit which is arranged to detect a plurality of spectra of process emissions at successive points in time (Please refer to the analysis of claim 1 above);
at least one computing unit which is arranged to generate at least one spectrogram based on the detected spectra as an input tensor (Please refer to the analysis of claim 1 above); and
a neural network which is arranged to output at least one value of a physical quantity and/or a classification of the laser machining process as an output tensor based on the input tensor (Please refer to the analysis of claim 1 above).
As per claim 13, the combination of Xiuquan et al. and Schwarz teach
The system according to claim 12, wherein the sensor unit has at least one spectrometer or a MEMS spectrometer (Xiuquan et al., page 5, para 14, spectrometer to acquire spectrum, Schwarz, page 10, para 45, the sensor data from the sensor unit and the image data from the image acquisition unit are used to train the deep learning).
As per claim 14, the combination of Xiuquan et al. and Schwarz teach
The system according to claim 12, wherein the at least one computing unit is designed to control the laser machining process on the basis of control data (Xiuquan et al., page 4, para 11, “S3 trains the neural network using a labeled spectral dataset to obtain a welding quality judgment model. Based on this welding quality judgment model and the spectral map of the laser welding dissimilar materials, it realizes automatic real-time evaluation of welding quality”. The labeled spectral dataset teaches control data. Also see page 2, claim 5, a computer is used to store, display and identify the spectral images and to judge the welding quality of the dissimilar material workpieces 4. Schwarz, page 8, para 37, the sensor data are considered as control data and the data comprises 512 samples, each sample is assigned to a point in time. Also see, Schwarz, page 5, para 23, the computing unit is configured to determine input tensor based on the current data of the machining process and to determine the output tensor. A deep learning model uses the transfer function between the input and output tensor and generates the information contains machining error and the machining area of the workpiece).
As per claim 15, the combination of Xiuquan et al. and Schwarz teach
A laser machining system for machining a workpiece by means of a machining laser beam, comprising:
a laser machining head for irradiating the machining laser beam onto the workpiece (Xiuquan et al., page 2, claim 5, page 5, para 15, a laser welding unit, Schwarz, page 9, para 41, a laser machining head of the laser machining system); and a system according to claim 12 (Xiuquan et al., page 2, claim 5, Schwarz, page 1, para 1).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Please refer to the form 892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Rokeya Alam whose telephone number is (571)272-0083. The examiner can normally be reached on 7:30am - 4:30pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mr. Scott Baderman can be reached at telephone number (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 an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/ROKEYA SHAWALI ALAM/Examiner, Art Unit 2118
/SCOTT T BADERMAN/Supervisory Patent Examiner, Art Unit 2118
