[1]吴晓东,熊伟丽.采用编码输入的生成对抗网络故障检测方法及应用[J].智能系统学报,2022,17(3):496-505.[doi:10.11992/tis.202102003]
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]
点击复制
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]
采用编码输入的生成对抗网络故障检测方法及应用
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
17
期数:
2022年第3期
页码:
496-505
栏目:
学术论文—机器学习
出版日期:
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
- 分类号:
- TP277
- 摘要:
- 针对传统基于生成对抗网络的故障检测方法中，生成器输入使用随机噪声，不包含训练集中有效信息造成模型检测效果不够理想的问题，提出一种采用编码输入的生成对抗网络故障检测策略。通过引入自编码器，基于最小化重构误差构建隐变量空间，将降维后的隐变量信息作为生成器输入以提升生成对抗网络的训练效果；进一步考虑故障检测方法中基于生成器的统计量计算成本高和对离群点敏感的问题，计算待测样本经编码后的隐变量到训练集隐变量空间中心点的曼哈顿距离，并作为新统计量进行故障检测。将所提故障检测方法用于田纳西伊斯曼过程及实际的磨煤机过程，本文方法较传统生成对抗网络故障检测在田纳西伊斯曼过程上报警率提升了13%，在磨煤机过程上各统计量报警率均得到了显著提升且本文所提统计量将传统方法中针对生成器的统计量大大降低了检测用时，从而验证了方法的有效性和性能。
- 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.
- 参考文献/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.
- 相似文献/References:
-
[1]杨梦铎,栾咏红,刘文军,等.基于自编码器的特征迁移算法[J].智能系统学报,2017,12(6):894.[doi:10.11992/tis.201706037]
YANG Mengduo,LUAN Yonghong,LIU Wenjun,et al.Feature transfer algorithm based on an auto-encoder[J].CAAI Transactions on Intelligent Systems,2017,12():894.[doi:10.11992/tis.201706037]
[2]莫凌飞,蒋红亮,李煊鹏.基于深度学习的视频预测研究综述[J].智能系统学报,2018,13(1):85.[doi:10.11992/tis.201707032]
MO Lingfei,JIANG Hongliang,LI Xuanpeng.Review of deep learning-based video prediction[J].CAAI Transactions on Intelligent Systems,2018,13():85.[doi:10.11992/tis.201707032]
[3]杨文元.多标记学习自编码网络无监督维数约简[J].智能系统学报,2018,13(5):808.[doi:10.11992/tis.201804051]
YANG Wenyuan.Unsupervised dimensionality reduction of multi-label learning via autoencoder networks[J].CAAI Transactions on Intelligent Systems,2018,13():808.[doi:10.11992/tis.201804051]
[4]张潇鲲,刘琰,陈静.引入外部词向量的文本信息网络表示学习[J].智能系统学报,2019,14(5):1056.[doi:10.11992/tis.201809037]
ZHANG Xiaokun,LIU Yan,CHEN Jing.Representation learning using network embedding based on external word vectors[J].CAAI Transactions on Intelligent Systems,2019,14():1056.[doi:10.11992/tis.201809037]
[5]朱文霖,刘华平,王博文,等.基于视-触跨模态感知的智能导盲系统[J].智能系统学报,2020,15(1):33.[doi:10.11992/tis.201908015]
ZHU Wenlin,LIU Huaping,WANG Bowen,et al.An intelligent blind guidance system based on visual-touch cross-modal perception[J].CAAI Transactions on Intelligent Systems,2020,15():33.[doi:10.11992/tis.201908015]
[6]毕晓君,潘梦迪.基于生成对抗网络的机载遥感图像超分辨率重建[J].智能系统学报,2020,15(1):74.[doi:10.11992/tis.202002002]
BI Xiaojun,PAN Mengdi.Super-resolution reconstruction of airborne remote sensing images based on the generative adversarial networks[J].CAAI Transactions on Intelligent Systems,2020,15():74.[doi:10.11992/tis.202002002]
[7]王昌安,田金文.生成对抗网络辅助学习的舰船目标精细识别[J].智能系统学报,2020,15(2):296.[doi:10.11992/tis.201901004]
WANG Changan,TIAN Jinwen.Fine-grained inshore ship recognition assisted by deep-learning generative adversarial networks[J].CAAI Transactions on Intelligent Systems,2020,15():296.[doi:10.11992/tis.201901004]
[8]张智,毕晓君.基于风格转换的无监督聚类行人重识别[J].智能系统学报,2021,16(1):48.[doi:10.11992/tis.202012014]
ZHANG Zhi,BI Xiaojun.Clustering approach based on style transfer for unsupervised person re-identification[J].CAAI Transactions on Intelligent Systems,2021,16():48.[doi:10.11992/tis.202012014]
[9]王丽娟,丁世飞.一种基于ELM-AE特征表示的谱聚类算法[J].智能系统学报,2021,16(3):560.[doi:10.11992/tis.202005021]
WANG Lijuan,DING Shifei.A spectral clustering algorithm based on ELM-AE feature representation[J].CAAI Transactions on Intelligent Systems,2021,16():560.[doi:10.11992/tis.202005021]
[10]姜义,吕荣镇,刘明珠,等.基于生成对抗网络的人脸口罩图像合成[J].智能系统学报,2021,16(6):1073.[doi:10.11992/tis.202012010]
JIANG Yi,LYU Rongzhen,LIU Mingzhu,et al.Masked face image synthesis based on a generative adversarial network[J].CAAI Transactions on Intelligent Systems,2021,16():1073.[doi:10.11992/tis.202012010]
备注/Memo
收稿日期:2021-02-03。
基金项目:国家自然科学基金项目（61773182）；国家重点研发计划子课题（2018YFC1603705-03）；广东省科技专项资金项目（2020ST010）
作者简介:吴晓东，硕士研究生，主要研究方向为工业过程故障检测与诊断;熊伟丽，教授，博士生导师，主要研究方向为复杂工业过程建模与监控、智能软测量技术。主持国家自然科学基金面上项目、国家自然科学基金青年项目、江苏省产学研等省部级以上纵向项目多项。获得中国商业联合会科技进步一等奖1项。获授权发明专利近20项，发表学术论文100余篇
通讯作者:熊伟丽.E-mail：greenpre@163.com
更新日期/Last Update:
1900-01-01