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 .
Comments
The Amendment – After Non-Final Rejection filed on June 11, 2026 has been entered and made of record.
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.
Claims 1, 7, 13, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Peng et al. (“Automatic Internal Wrinkles Detection of Lithium-ion Batteries using Convolutional Neural Network”, 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), 23-27 August 2021, pp. 1422-1427) in view of Bufi et al. (U.S. Pub. No. 2022/0366558) and Witt (U.S. Pub. No. 2022/0301282).
As to claims 1 and 7, Peng et al. teaches an electrode plate wrinkling detection method/system (i.e., “detection method based on X-ray technology and convolutional neural network(CNN) is proposed for internal wrinkles detection in LIBs”, Abstract, page 1422), comprising:
acquiring/electrode plate wrinkling detection apparatus configured to acquire (i.e., Fig. 2, “X-ray device”, page 1423) images of cells with wrinkled electrode plates and images of cells with non-wrinkled electrode plates (i.e., “X-ray device is employed to acquire LIBs four corners inner images with contrasts between light and dark for different thickness, which is the foundation of automatic internal wrinkles detection of LIBs using CNN”, A. Data Capture, page 1423; “The image dataset which are used in this study contains 2602 original X-ray images in total. All the images are obtained from X-ray device and grouped based on expert experience into two categories: unqualified-1098 images with serious internal wrinkles flaw, qualified-1504 images without any internal wrinkles flaw”, B. Classify images based on CNN, page 1423);
performing/processing module configured to: (i.e., “a computer with 80G RAM, Intel(R) Core(TM) i9-10980XE CPU, and NVIDIA GeForce RTX 2080Ti GPU”, C. Real-Time, page 1427) perform type labeling processing on the images of the cells with wrinkled electrode plates and the images of the cells with non-wrinkled electrode plates (i.e., “The image dataset which are used in this study contains 2602 original X-ray images in total. All the images are obtained from X-ray device and grouped based on expert experience into two categories: unqualified-1098 images with serious internal wrinkles flaw, qualified-1504 images without any internal wrinkles flaw”, B. Classify images based on CNN, page 1423), and constructing/construct a database by using the labeled images (i.e., “The image dataset which are used in this study contains 2602 original X-ray images in total”, B. Classify images based on CNN, page 1423; and “Shuffling samples sequence and randomly selecting 80 percent qualified images and 80 percent unqualified images to compose training set”, B. Classification performance comparison, page 1426);
a training module configured to: (i.e., “a computer with 80G RAM, Intel(R) Core(TM) i9-10980XE CPU, and NVIDIA GeForce RTX 2080Ti GPU”, C. Real-Time, page 1427) based on the database, training via a convolutional neural network to generate an electrode plate wrinkling detection model (i.e., 2. Training with three CNN architectures, page 1424);
testing and calibrating/testing module configured to (i.e., “a computer with 80G RAM, Intel(R) Core(TM) i9-10980XE CPU, and NVIDIA GeForce RTX 2080Ti GPU”, C. Real-Time, page 1427) test and calibrate the electrode plate wrinkling detection model (i.e., 3. Modify loss function to reduce false positive rate, pages 1424-1425); and
performing/detection module configured to perform (i.e., “a computer with 80G RAM, Intel(R) Core(TM) i9-10980XE CPU, and NVIDIA GeForce RTX 2080Ti GPU”, C. Real-Time, page 1427) electrode plate wrinkling detection on cell images obtained in a real-time manner by using the tested and calibrated electrode plate wrinkling detection model (See for example, C. Real-Time, page 1427).
However, Peng et al. does not explicitly disclose the testing and calibrating the model by using images outside the database, and the cell images obtained in a real-time manner are obtained during a battery winding process.
Bufi et al. teaches training and testing a model by using images outside a database (See for example, “the neural network 156 is generated using model training and conversion for inference which may include taking a pretrained model, training the pretrained model with new data”, Paragraph [0216]; and “Training of the defect detection model 154 may include image augmentation. Data augmentation may be performed to increase the variability of the input images, so that the designed object detection model has higher robustness to the images obtained from different environments”, Paragraph [0231]).
The combination of Peng et al. and Bufi et al. do not explicitly disclose the cell images obtained in a real-time manner are obtained during a battery winding process.
Witt teaches cell images (i.e., “the capture 138 of an image 134 of the front side of the wound battery cell 132. In this case, this image 134 is recorded such that the wound layer structure can be seen”, Paragraph [0164]) that are obtained in a during a battery winding process (See for example, “FIG. 1 shows three process phases of a process for winding film layers 112, 114, 116 for producing a wound battery cell 132 that constitutes an intermediate product in the context of corresponding battery production”, Paragraph [0157]).
Peng et al., Bufi et al. and Witt are analogous art because they are from the field of digital image processing for image analysis.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify Peng et al. by incorporating the testing and calibrating the model by using images outside the database, as taught by Bufi et al., and the cell images obtained in a real-time manner are obtained during a battery winding process, as taught by Witt.
The suggestion/motivation for doing so would have been to obtain a tested and calibrated model that has higher robustness to images obtained from different environments, and to output a warning message or a corresponding control command to the production installation to trigger a check of different or all machine parameters corresponding to an error criterion.
Therefore, it would have been obvious to combine Bufi et al. and Witt with Peng et al. to obtain the invention as specified in claims 1 and 7.
As to claims 13 and 14, Peng et al. teaches a terminal (i.e., “a computer with 80G RAM, Intel(R) Core(TM) i9-10980XE CPU, and NVIDIA GeForce RTX 2080Ti GPU”, C. Real-Time, page 1427), comprising:
at least one processor (i.e., “a computer with 80G RAM, Intel(R) Core(TM) i9-10980XE CPU, and NVIDIA GeForce RTX 2080Ti GPU”, C. Real-Time, page 1427);
and the at least one processor to implement an electrode plate wrinkling detection method, comprising:
acquiring images of cells with wrinkled electrode plates and images of cells with non-wrinkled electrode plates (i.e., “X-ray device is employed to acquire LIBs four corners inner images with contrasts between light and dark for different thickness, which is the foundation of automatic internal wrinkles detection of LIBs using CNN”, A. Data Capture, page 1423; “The image dataset which are used in this study contains 2602 original X-ray images in total. All the images are obtained from X-ray device and grouped based on expert experience into two categories: unqualified-1098 images with serious internal wrinkles flaw, qualified-1504 images without any internal wrinkles flaw”, B. Classify images based on CNN, page 1423); performing type labeling processing on the images of the cells with wrinkled electrode plates and the images of the cells with non-wrinkled electrode plates (i.e., “The image dataset which are used in this study contains 2602 original X-ray images in total. All the images are obtained from X-ray device and grouped based on expert experience into two categories: unqualified-1098 images with serious internal wrinkles flaw, qualified-1504 images without any internal wrinkles flaw”, B. Classify images based on CNN, page 1423), and constructing a database by using the labeled images (i.e., “The image dataset which are used in this study contains 2602 original X-ray images in total”, B. Classify images based on CNN, page 1423; and “Shuffling samples sequence and randomly selecting 80 percent qualified images and 80 percent unqualified images to compose training set”, B. Classification performance comparison, page 1426); based on the database, training via a convolutional neural network to generate an electrode plate wrinkling detection model (i.e., 2. Training with three CNN architectures, page 1424); testing and calibrating the electrode plate wrinkling detection model (i.e., 3. Modify loss function to reduce false positive rate, pages 1424-1425); and performing electrode plate wrinkling detection on cell images obtained in a real-time manner by using the tested and calibrated electrode plate wrinkling detection model (See for example, C. Real-Time, page 1427).
However, Peng et al. does not explicitly disclose a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to implement the electrode plate wrinkling detection method/a non-transitory storage medium storing a computer program, wherein the computer program is executed by a processor to implement the electrode plate wrinkling detection method, the testing and calibrating the model by using images outside the database, and the cell images obtained in a real-time manner are obtained during a battery winding process.
Bufi et al. teaches a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to implement a defect detection method/non-transitory storage medium storing a computer program, wherein the computer program is executed by a processor to implement a defect detection method (See for example, Paragraphs [0071]-[0072]), training and testing a model by using images outside a database (See for example, “the neural network 156 is generated using model training and conversion for inference which may include taking a pretrained model, training the pretrained model with new data”, Paragraph [0216]; and “Training of the defect detection model 154 may include image augmentation. Data augmentation may be performed to increase the variability of the input images, so that the designed object detection model has higher robustness to the images obtained from different environments”, Paragraph [0231]).
The combination of Peng et al. and Bufi et al. do not explicitly disclose the cell images obtained in a real-time manner are obtained during a battery winding process.
Witt teaches cell images (i.e., “the capture 138 of an image 134 of the front side of the wound battery cell 132. In this case, this image 134 is recorded such that the wound layer structure can be seen”, Paragraph [0164]) that are obtained in a during a battery winding process (See for example, “FIG. 1 shows three process phases of a process for winding film layers 112, 114, 116 for producing a wound battery cell 132 that constitutes an intermediate product in the context of corresponding battery production”, Paragraph [0157]).
Therefore, in view of Bufi et al. and Witt, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Peng et al. by incorporating the memory communicatively connected to the at least one processor to store instructions executable by the at least one processor/non-transitory storage medium storing a computer program, wherein the computer program is executed by a processor to implement the wrinkling detection model and the testing and calibrating the model by using images outside the database, as taught by Bufi et al., and the cell images obtained in a real-time manner are obtained during a battery winding process, as taught by Witt, in order to incorporate the method in a conventional manner to be executed in a computer, to obtain a tested and calibrated model that has higher robustness to images obtained from different environments, and to output a warning message or a corresponding control command to the production installation to trigger a check of different or all machine parameters corresponding to an error criterion.
Allowable Subject Matter
Claims 2-6 and 8-12 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter: the closest prior art made of record fails to disclose, teach, and/or suggest, inter alia, the electrode plate wrinkling detection of claims 1 and 7, and further comprising after the acquiring images of cells with wrinkled electrode plates and images of cells with non-wrinkled electrode plates, the electrode plate wrinkling detection method further comprises: pre-processing the acquired images of the cells with wrinkled electrode plates and images of the cells with non-wrinkled electrode plates, wherein the pre-processing comprises: performing cleansing on the images of the cells with wrinkled electrode plates and the images of the cells with non-wrinkled electrode plates, removing interference parts, and broadening, enhancing, and brightening the images of the cells with wrinkled electrode plates and the images of the cells with non-wrinkled electrode plates; or the performing type labeling processing on the images of the cells with wrinkled electrode plates and the images of the cells with non-wrinkled electrode plates, and constructing a database by using the labeled images comprises: labeling the images of the cells with wrinkled electrode plates and the images of the cells with non-wrinkled electrode plates with types comprising wrinkling of electrode plate, wrinkling of separator, stripe pattern on separator, stain on separator, and full qualification, and constructing a database by using the images labeled with the types comprising wrinkling of electrode plate, wrinkling of separator, stripe pattern on separator, stain on separator, and full qualification; or the testing and calibrating the electrode plate wrinkling detection model by using images outside the database comprises: testing the electrode plate wrinkling detection model by using the images outside the database, under a condition that a test result meets a target requirement, performing electrode plate wrinkling detection on cell images obtained in a real-time manner during a battery winding process by using the tested and calibrated electrode plate wrinkling detection model, or under a condition that the test result does not meet the target requirement, retraining the electrode plate wrinkling detection model by modifying parameters of the convolutional neural network until the test result meets the target requirement; or the performing electrode plate wrinkling detection on cell images obtained in a real-time manner during a battery winding process by using the tested and calibrated electrode plate wrinkling detection model comprises: shooting to-be-inspected cells during a winding process to obtain images of the cells, inputting the images of the cells into the electrode plate wrinkling detection model for detection, when determining that defective cells with wrinkled electrode plates exist, discharging the defective cells into a defective product tank, or when determining that no defective cell with wrinkled electrode plates exists, discharging normal cells into a next production procedure, as claimed.
Response to Arguments
Claim Rejections - 35 USC § 101
With respect to claim 14, Applicant has amended the claim in order to recite statutory subject matter. Therefore, the rejection has been withdrawn.
Claim Rejections - 35 USC § 103
With respect to claims 1, 7, 13, and 14, Applicant’s arguments (Remarks dated June 11, 2026, page 8) have been fully considered and they are persuasive. Therefore, the previous ground(s) of rejection have been withdrawn. However, upon further consideration and search, a new ground(s) of rejection is made in view of Peng et al., Bufi et al. and Witt (Refer to Claim Rejections - 35 USC § 103 Section above).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSE M TORRES whose telephone number is (571)270-1356. The examiner can normally be reached Monday thru Friday; 10:00 AM to 6:00 PM 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, Jennifer Mehmood can be reached at 571-272-2976. 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.
/JOSE M TORRES/Examiner, Art Unit 2664 09/10/2026
Prosecution Insights