Patents by Inventor Xingxing JIANG

Xingxing JIANG has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20240353829
    Abstract: The present invention provides an unsupervised fault diagnosis method for mechanical equipment based on an adversarial flow model, main steps including: data preprocessing, converting a mechanical vibration signal into a frequency domain signal, and normalizing the amplitude value of the signal into a range of [0, 1]; prior distribution designing: designing a mixture of Gaussian distribution with K subdistributions, wherein K is determined by the number of mechanical equipment status; model construction: constructing an unsupervised fault diagnosis model by combining an autoencoder, a flow model, and a classifier; model training: training the unsupervised fault diagnosis model by using various classes of status data, along with the designed prior distribution, preset training steps, loss functions, and an optimization algorithm; and fault diagnosis: inputting status data of mechanical equipment into the trained unsupervised fault diagnosis model to obtain a data clustering result and a fault diagnosis result.
    Type: Application
    Filed: October 12, 2021
    Publication date: October 24, 2024
    Inventors: Jun WANG, Jun DAI, Xingxing JIANG, Weiguo HUANG, Zhongkui ZHU
  • Patent number: 12044595
    Abstract: The present invention provides a dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions, including acquiring bearing vibration data under different working conditions to obtain a source domain sample and a target domain sample; establishing a deep convolutional neural network model with dynamic joint distribution alignment; feeding both the source domain sample and the target domain sample into the deep convolutional neural network model with initialized parameters, and extracting, by a feature extractor, high-level features of the source domain sample and the target domain sample; calculating a marginal distribution distance and a conditional distribution distance; obtaining a joint distribution distance according to the marginal distribution distance and the conditional distribution distance, and combining the joint distribution distance and a label loss to obtain a target function; and optimizing the target function by using SGD, and training the
    Type: Grant
    Filed: January 13, 2021
    Date of Patent: July 23, 2024
    Assignee: SOOCHOW UNIVERSITY
    Inventors: Changqing Shen, Shuangjie Liu, Xu Wang, Dong Wang, Yongjun Shen, Zaigang Chen, Aiwen Zhang, Xingxing Jiang, Juanjuan Shi, Weiguo Huang, Jun Wang, Guifu Du, Zhongkui Zhu
  • Publication number: 20240210242
    Abstract: The disclosure provides a photoelectric sensor capable of resisting high-frequency light interference. It comprises a transmitting tube, double receiving tubes, a filter arranged at the front ends of the double receiving tubes for filtering optical signals, a band-pass filter circuit coupled to the double receiving tubes, a differential amplifier coupled to the band-pass filter circuit, a control module for controlling the synchronous receiving of optical signals, and a sensor hysteresis error setting system for improving the anti-interference performance of sensors; the control module further collects and obtains ambient light interference signals and sets an interference signal threshold value, and when it is detected that the amplitude of the collected ambient light interference signals is larger than the set interference signal threshold value, the control module discards the light signals lower than the interference signal threshold value after the interference signals are overlaid.
    Type: Application
    Filed: August 31, 2022
    Publication date: June 27, 2024
    Applicant: SHANGHAI LANBAO SENSING TECHNOLOGY CO., LTD.
    Inventors: Yongtong XU, Yong XIE, Dugui ZHAO, Hongguang WEI, Xingxing JIANG, Chengsong ZHOU
  • Patent number: 11886311
    Abstract: The invention relates to a fault diagnosis method for a rolling bearing under variable working conditions. Based on a convolutional neural network, a transfer learning algorithm is combined to handle the problem of the reduced universality of deep learning models. Data acquired under different working conditions is segmented to obtain samples. The samples are preprocessed by using FFT. Low-level features of the samples are extracted by using improved ResNet-50, and a multi-scale feature extractor analyzes the low-level features to obtain high-level features as inputs of a classifier. In a training process, high-level features of training samples and test samples are extracted, and a conditional distribution distance between them is calculated as a part of a target function for backpropagation to implement intra-class adaptation, thereby reducing the impact of domain shift, to enable a deep learning model to better carry out fault diagnosis tasks.
    Type: Grant
    Filed: August 4, 2020
    Date of Patent: January 30, 2024
    Assignee: SOOCHOW UNIVERSITY
    Inventors: Changqing Shen, Xu Wang, Jing Xie, Aiwen Zhang, Dong Wang, Xiaofeng Shang, Dongmiao Song, Xingxing Jiang, Jun Wang, Juanjuan Shi, Weiguo Huang, Zhongkui Zhu
  • Publication number: 20230168150
    Abstract: The present invention provides a dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions, including acquiring bearing vibration data under different working conditions to obtain a source domain sample and a target domain sample; establishing a deep convolutional neural network model with dynamic joint distribution alignment; feeding both the source domain sample and the target domain sample into the deep convolutional neural network model with initialized parameters, and extracting, by a feature extractor, high-level features of the source domain sample and the target domain sample; calculating a marginal distribution distance and a conditional distribution distance; obtaining a joint distribution distance according to the marginal distribution distance and the conditional distribution distance, and combining the joint distribution distance and a label loss to obtain a target function; and optimizing the target function by using SGD, and training the
    Type: Application
    Filed: January 13, 2021
    Publication date: June 1, 2023
    Inventors: Changqing SHEN, Shuangjie LIU, Xu WANG, Dong WANG, Yongjun SHEN, Zaigang CHEN, Aiwen ZHANG, Xingxing JIANG, Juanjuan SHI, Weiguo HUANG, Jun WANG, Guifu DU, Zhongkui ZHU
  • Patent number: 11644383
    Abstract: The invention provides an adaptive manifold probability distribution-based bearing fault diagnosis method, including constructing transferable domains and transfer tasks; converting a data sample in each transfer task into frequency domain data via Fourier transform, inputting the frequency domain data into a GFK algorithm model, and calculating a manifold feature representation matrix related to a bearing fault in each transfer task by using the GFK algorithm model; calculating a cosine distance between centers of a target domain and a source domain in each transfer task according to a manifold feature representation, and defining a target function of in-domain classifier learning; then solving the target function, to obtain a probability distribution matrix of the target domain; and selecting a label corresponding to the largest probability value corresponding to each data sample in the target domain from the probability distribution matrix as a predicted label of the data sample in the target domain.
    Type: Grant
    Filed: November 26, 2020
    Date of Patent: May 9, 2023
    Assignee: SOOCHOW UNIVERSITY
    Inventors: Changqing Shen, Yu Xia, Lin Kong, Liang Chen, Piao Lei, Yongjun Shen, Dong Wang, Hongbo Que, Aiwen Zhang, Minjie Chen, Chuancang Ding, Xingxing Jiang, Jun Wang, Juanjuan Shi, Weiguo Huang, Zhongkui Zhu
  • Patent number: 11644391
    Abstract: The present invention discloses a fault diagnosis method under a convergence trend of a center frequency, including: (1) acquiring a dynamic signal x(t) of a rotary machine equipment; (2) setting initial decomposition parameters of a variational model; (3) decomposing the dynamic signal x(t) by using the variational model with the set initial decomposition parameters, and traversing a signal analysis band and performing iterative decomposition on the dynamic signal x(t) under the guidance of a convergence trend of a center frequency, to obtain optimized modals {m1 . . . mn . . . mN} and corresponding center frequencies {?1 . . . ?n . . . ?N}; (4) searching a fault related modal mI, guiding parameter optimization by using a center frequency ?I of the fault related modal mI, and retrieving an optimal target component mI including fault information; and (5) performing envelopment analysis on the optimal target component mI, and diagnosing the rotary machine equipment according to an envelope spectrum.
    Type: Grant
    Filed: July 30, 2020
    Date of Patent: May 9, 2023
    Assignee: SOOCHOW UNIVERSITY
    Inventors: Xingxing Jiang, Changqing Shen, Jianqin Zhou, Dongmiao Song, Wenjun Guo, Guifu Du, Jun Wang, Juanjuan Shi, Weiguo Huang, Zhongkui Zhu
  • Publication number: 20220373430
    Abstract: The invention provides an adaptive manifold probability distribution-based bearing fault diagnosis method, including constructing transferable domains and transfer tasks; converting a data sample in each transfer task into frequency domain data via Fourier transform, inputting the frequency domain data into a GFK algorithm model, and calculating a manifold feature representation matrix related to a bearing fault in each transfer task by using the GFK algorithm model; calculating a cosine distance between centers of a target domain and a source domain in each transfer task according to a manifold feature representation, and defining a target function of in-domain classifier learning; then solving the target function, to obtain a probability distribution matrix of the target domain; and selecting a label corresponding to the largest probability value corresponding to each data sample in the target domain from the probability distribution matrix as a predicted label of the data sample in the target domain.
    Type: Application
    Filed: November 26, 2020
    Publication date: November 24, 2022
    Inventors: Changqing SHEN, Yu XIA, Lin KONG, Liang CHEN, Piao LEI, Yongjun SHEN, Dong WANG, Hongbo QUE, Aiwen ZHANG, Minjie CHEN, Chuancang DING, Xingxing JIANG, Jun WANG, Juanjuan SHI, Weiguo HUANG, Zhongkui ZHU
  • Publication number: 20220327035
    Abstract: The invention relates to a fault diagnosis method for a rolling bearing under variable working conditions. Based on a convolutional neural network, a transfer learning algorithm is combined to handle the problem of the reduced universality of deep learning models. Data acquired under different working conditions is segmented to obtain samples. The samples are preprocessed by using FFT. Low-level features of the samples are extracted by using improved ResNet-50, and a multi-scale feature extractor analyzes the low-level features to obtain high-level features as inputs of a classifier. In a training process, high-level features of training samples and test samples are extracted, and a conditional distribution distance between them is calculated as a part of a target function for backpropagation to implement intra-class adaptation, thereby reducing the impact of domain shift, to enable a deep learning model to better carry out fault diagnosis tasks.
    Type: Application
    Filed: August 4, 2020
    Publication date: October 13, 2022
    Inventors: Changqing SHEN, Xu WANG, Jing XIE, Aiwen ZHANG, Dong WANG, Xiaofeng SHANG, Dongmiao SONG, Xingxing JIANG, Jun WANG, Juanjuan SHI, Weiguo HUANG, Zhongkui ZHU
  • Publication number: 20220050024
    Abstract: The present invention discloses a fault diagnosis method under a convergence trend of a center frequency, including: (1) acquiring a dynamic signal x(t) of a rotary machine equipment; (2) setting initial decomposition parameters of a variational model; (3) decomposing the dynamic signal x(t) by using the variational model with the set initial decomposition parameters, and traversing a signal analysis band and performing iterative decomposition on the dynamic signal x(t) under the guidance of a convergence trend of a center frequency, to obtain optimized modals {m1 . . . mn . . . mN} and corresponding center frequencies {?1 . . . ?n . . . ?N}; (4) searching a fault related modal mI, guiding parameter optimization by using a center frequency ?I of the fault related modal mI, and retrieving an optimal target component mI including fault information; and (5) performing envelopment analysis on the optimal target component mI, and diagnosing the rotary machine equipment according to an envelope spectrum.
    Type: Application
    Filed: July 30, 2020
    Publication date: February 17, 2022
    Inventors: Xingxing JIANG, Changqing SHEN, Jianqin ZHOU, Dongmiao SONG, Wenjun GUO, Guifu DU, Jun WANG, Juanjuan SHI, Weiguo HUANG, Zhongkui ZHU