[1]WU Xiaodong,XIONG Weili.Fault detection method and its application using GAN with an encoded input[J].CAAI Transactions on Intelligent Systems,2022,17(3):496-505.[doi:10.11992/tis.202102003]
Copy
Fault detection method and its application using GAN with an encoded input
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
17
Number of periods:
2022 3
Page number:
496-505
Column:
学术论文—机器学习
Public date:
2022-05-05
- Title:
- Fault detection method and its application using GAN with an encoded input
- Keywords:
- generative adversarial network; autoencoder; latent variable; kernel density estimation; dimensionality reduction; fault detection; TE process; coal pulverization process
- CLC:
- TP277
- DOI:
- 10.11992/tis.202102003
- Abstract:
- In a traditional fault detection method based on a generative adversarial network, random noise is used as the generator input, which does not contain the effective information of training sets and causes unsatisfactory fault detection by the model. This paper proposes a generative adversarial network fault detection strategy using an encoded input. By introducing an autoencoder based on minimizing the reconstruction error, a latent variable space is constructed. The latent variable information after dimensionality reduction is used as the generator input to improve the training effect of the generated confrontation network. Furthermore, a generator-based statistic has drawbacks such as high computational cost and sensitivity to outliers. The Manhattan distance is calculated beginning from the encoded hidden variable of the sample to be tested to the center of the hidden variable space of the training set. This distance is then used as a new statistic for fault detection. The proposed fault detection method is used in the TE and actual coal pulverization processes. Compared with the traditional GAN fault detection, the alarming rate of the TE process increases by 13%. The alarming rate of all statistics in the coal pulverization process also improves considerably. The proposed statistics greatly reduce the detection time for generators in traditional methods, which validates their effectiveness and performance.
- References:
-
[1] 彭开香, 马亮, 张凯. 复杂工业过程质量相关的故障检测与诊断技术综述[J]. 自动化学报, 2017, 43(3): 349–365
PENG Kaixiang, MA Liang, ZHANG Kai. Review of quality-related fault detection and diagnosis techniques for complex industrial processes[J]. Acta automatica sinica, 2017, 43(3): 349–365
[2] 刘强, 卓洁, 郎自强, 等. 数据驱动的工业过程运行监控与自优化研究展望[J]. 自动化学报, 2018, 44(11): 1944–1956
LIU Qiang, ZHUO Jie, LANG Ziqiang, et al. Perspectives on data-driven operation monitoring and self-optimization of industrial processes[J]. Acta automatica sinica, 2018, 44(11): 1944–1956
[3] 曹跃, 陈志文, 袁小锋, 等. 部分子块通讯的分布式PCA厂级工业过程监测方法[J]. 控制与决策, 2020, 35(6): 1281–1290
CAO Yue, CHEN Zhiwen, YUAN Xiaofeng, et al. Distributed PCA for plant-wide processes monitoring with partial block communication[J]. Control and decision, 2020, 35(6): 1281–1290
[4] 童楚东, 史旭华, 蓝艇. 正交信号校正的自回归模型及其在动态过程监测中的应用[J]. 控制与决策, 2016, 31(8): 1505–1508
TONG Chudong, SHI Xuhua, LAN Ting. Orthogonal signal correction based auto-regression model with application to dynamic process monitoring[J]. Control and decision, 2016, 31(8): 1505–1508
[5] 冯立伟, 张成, 李元, 等. 基于标准距离k近邻的多模态过程故障检测策略[J]. 控制理论与应用, 2019, 36(4): 553–560
FENG Liwei, ZHANG Cheng, LI Yuan, et al. Fault detection strategy of standard-distance-based k nearest neighbor rule in multimode processes[J]. Control theory and applications, 2019, 36(4): 553–560
[6] HUANG Yi, SUN Shiyu, DUAN Xiusheng, et al. A study on deep neural networks framework[C]//2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC). Xi’an: IEEE, 2016: 1519–1522.
[7] CHEN Xuemei, ZHENG Xuelong, WANG Zijia, et al. Multi-frequency data fusion for attitude estimation based on multi-layer perception and Cubature Kalman Filter[J]. IEEE access, 2020, 8: 144373–144381.
[8] LIU Shuo, LIU Yulong, GU Yuhai, et al. Method of extracting gear fault feature based on stacked autoencoder[J]. The journal of engineering, 2019, 2019(23): 8765–8769.
[9] MIAO Jun, SUN Keqiang, LIAO Xuan, et al. Human segmentation based on compressed deep convolutional neural network[J]. IEEE access, 2020, 8: 167585–167595.
[10] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Advances in neural information processing systems, 2014, 3(11): 2672–2680.
[11] LUC P, COUPRIE C, CHINTALA S, et al. Semantic segmentation using adversarial networks[EB/OL].(2016–11-25)[2021-02-03]https://arxiv.org/abs/1611.08408.
[12] LI Jianan, LIANG Xiaodan, WEI Yunchao, et al. Perceptual generative adversarial networks for small object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 1951–1959.
[13] REED S E, AKATA Z, YAN Xinchen, et al. Generative adversarial text to image synthesis[C]//Proceedings of the 33nd International Conference on Machine Learning (ICML). New York: ACM, 2016: 1060–1069.
[14] JIANG Tao, LI Yunsong, XIE Weiying, et al. Discriminative reconstruction constrained generative adversarial network for hyperspectral anomaly detection[J]. IEEE transactions on geoscience and remote sensing, 2020, 58(7): 4666–4679.
[15] LEE Y O, JO J, HWANG J. Application of deep neural network and generative adversarial network to industrial maintenance: a case study of induction motor fault detection[C]//2017 IEEE International Conference on Big Data (Big Data). Boston: IEEE, 2017: 3248–3253.
[16] VIOLA J, CHEN Yangquan, WANG Jing. FaultFace: deep convolutional generative adversarial network (DCGAN) based ball-bearing failure detection method[J]. Information sciences, 2021, 542: 195–211.
[17] 顾炳斌, 熊伟丽, 史旭东. 基于故障敏感主元的多块PCA故障监测方法[J]. 高校化学工程学报, 2019, 33(6): 1499–1508
GU Bingbin, XIONG Weili, SHI Xudong. Multi-block PCA process monitoring based on fault sensitive principal components[J]. Journal of chemical engineering of Chinese universities, 2019, 33(6): 1499–1508
[18] WANG Huangang, LI Xin, ZHANG Tao. Generative adversarial network based novelty detection usingminimized reconstruction error[J]. Frontiers of information technology and electronic engineering, 2018, 19(1): 116–125.
[19] 金晓航, 许壮伟, 孙毅, 等. 基于生成对抗网络的风电机组在线状态监测[J]. 仪器仪表学报, 2020, 41(4): 68–76
JIN Xiaohang, XU Zhuangwei, SUN Yi, et al. Online condition monitoring of wind turbine based on generative adversarial network[J]. Chinese journal of scientific instrument, 2020, 41(4): 68–76
[20] YANG Xin, FENG Dajun. Generative adversarial network based anomaly detection on the benchmark Tennessee Eastman process[C]//2019 5th International Conference on Control, Automation and Robotics (ICCAR). Beijing: IEEE, 2019: 644–648.
[21] SPYRIDON P, BOUTALIS Y S. Generative adversarial networks for unsupervised fault detection[C]//2018 European Control Conference (ECC). Limassol: IEEE, 2018: 691–696.
[22] 陈伟宏, 安吉尧, 李仁发, 等. 深度学习认知计算综述[J]. 自动化学报, 2017, 43(11): 1886–1897
CHEN Weihong, AN Jiyao, LI Renfa, et al. Review on deep-learning-based cognitive computing[J]. Acta automatica sinica, 2017, 43(11): 1886–1897
[23] 袁非牛, 章琳, 史劲亭, 等. 自编码神经网络理论及应用综述[J]. 计算机学报, 2019, 42(1): 203–230
YUAN Feiniu, ZHANG Lin, SHI Jinting, et al. Theories and applications of auto-encoder neural networks: a literature survey[J]. Chinese journal of computers, 2019, 42(1): 203–230
[24] 顾炳斌, 熊伟丽. 基于多块信息提取的PCA故障诊断方法[J]. 化工学报, 2019, 70(2): 736–749
GU Bingbin, XIONG Weili. Fault diagnosis based on PCA method with multi-block information extraction[J]. CIESC journal, 2019, 70(2): 736–749
[25] GE Zhiqiang, SONG Zhihuan. Distributed PCA model for plant-wide process monitoring[J]. Industrial & engineering chemistry research, 2013, 52(5): 1947–1957.
- Similar References:
Memo
-
Last Update:
1900-01-01