ZENG Fengrong¹; SUN Huanqi¹; XIONG Weili^1;2;

Abstract：

In order to solve the problem of multi-scale time series feature extraction of industrial process data, a fault detection method based on feature fusion and temporal convolutional autoencoder was proposed. Firstly, the multi-layer temporal convolutional network structure was used to extract features from the input time series at different scales, and a multi-scale temporal convolutional autoencoder was constructed. Secondly, a feature fusion module based on efficient channel attention was designed, which was added to the temporal convolutional autoencoder through jump joining and connected the temporal series features of different scales across channels. It generated corresponding weights to weight and fuse the features, so as to capture richer temporal information and enhance the model’s discrimination between normal sequence and abnormal sequence reconstruction error. Finally, the statistics were established by reconstructing the error, and the kernel density estimation was used to determine the control limit to realize fault detection. The proposed detection method is applied to numerical cases and Tennessee-Eastman process, and the experimental results show that the proposed method has good fault detection performance, which can provide a certain reference for fault detection in complex industrial processes.

Key Words： fault detection;temporal convolutional networks;autoencoder;attention mechanisms;feature fusion

Abstract:

Keywords:

Foundation: 国家自然科学基金(61773182);国家重点研发计划子课题资助项目(2018YFC1603705-03)。

Authors: ZENG Fengrong¹; SUN Huanqi¹; XIONG Weili^1;2;

References：

• [1] 任佳, 孙思宇, 鲍克. 基于最大信息系数和深度残差图卷积的工业过程故障诊断方法[J]. 高校化学工程学报, 2023, 37(1): 111-119. REN J, SUN S Y, BAO K. Fault diagnosis method in industrial processes based on maximal information coefficient and depth residual graph convolution[J].Journal of Chemical Engineering of Chinese Universities, 2023, 37(1): 111-119.
  [2] DAI X W, GAO Z W. From model, signal to knowledge: A data-driven perspective of fault detection and diagnosis[J].IEEE Transactions on Industrial Informatics, 2013, 9(4): 2226-2238.
  [3] WANG Y F, MA X D, QIAN P. Wind turbine fault detection and identification through PCA-based optimal variable selection[J].IEEE Transactions on Sustainable Energy, 2018, 9(4): 1627-1635.
  [4] WANG G, YIN S. Quality-related fault detection approach based on orthogonal signal correction and modified PLS[J].IEEE Transactions on Industrial Informatics, 2015, 11(2): 398-405.
  [5] LI S, ZHOU X F, PAN F C,et al. Correlated and weakly correlated fault detection based on variable division and ICA[J].Computers & Industrial Engineering, 2017, 112: 320-335.
  [6] NGUYEN V H, GOLINVAL J C. Fault detection based on kernel principal component analysis[J].Engineering Structures, 2010, 32(11): 3683-3691.
  [7] 张成, 潘立志, 李元. 基于加权统计特征KICA的故障检测与诊断方法[J]. 化工学报, 2022, 73(2): 827-837. ZHANG C, PAN L Z, LI Y. Fault detection and diagnosis method based on weighted statistical feature KICA[J].CIESCJournal, 2022, 73(2): 827-837.
  [8] 李益兵, 黄定洪, 马建波, 等. 基于深度置信网络与信息融合的齿轮故障诊断方法[J]. 振动与冲击, 2021, 40(8): 62-69. LI Y B, HUANG D B, MA J B, et al. A gear fault diagnosis method based on deep belief network and information fusion[J].Journal of Vibration and Shock, 2021, 40(8): 62-69.
  [9] 高学金, 刘爽爽, 高慧慧. 基于多变量卷积神经网络的发酵过程故障监测[J]. 高校化学工程学报, 2020, 34(6): 1511-1519. GAO X J, LIU S S, GAO H H. Fault monitoring of fermentation processes based on multivariable convolution neural network[J].Journal of Chemical Engineering of Chinese Universities, 2020, 34(6): 1511-1519.
  [10] LIU H, ZHOU J Z, ZHENG Y, et al. Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders[J].ISATransactions, 2018, 77: 167-178.
  [11] REN Z L, ZHANG W S, ZHANG Z Z. A deep nonnegative matrix factorization approach via autoencoder for nonlinear fault detection[J].IEEE Transactions on Industrial Informatics, 2020, 16(8): 5042-5052.
  [12] MASCI J, MEIER U, CIRESAN D, et al. Stacked convolutional auto-encoders for hierarchical feature extraction: Artificial Neural Networks and Machine Learning - ICANN 2011[C]. Berlin: Springer, 2011.
  [13] CHEN K J, HU J, HE J L. Detection and classification of transmission line faults based on unsupervised feature learning and convolutional sparse autoencoder[J].IEEE Transactions on Smart Grid, 2018, 9(3): 1748-1758.
  [14] LIU X, YU J B, YE L. Residual attention convolutional autoencoder for feature learning and fault detection in nonlinear industrial processes[J].Neural Computing and Applications, 2021, 33(19): 12737-12753.
  [15] 高学金, 姚玉卓, 韩华云, 等. 基于注意力动态卷积自编码器的发酵过程故障监测[J]. 化工学报, 2023, 74(6): 2503-2521. GAO X J, YAO Y Z, HAN H Y, et al. Fault monitoring of fermentation process based on attention dynamic convolutional autoencoder[J].CIESCJournal, 2023, 74(6): 2503-2521.
  [16] YU J B, LIU X, YE L. Convolutional long short-term memory autoencoder-based feature learning for fault detection in industrial processes[J].IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-15.
  [17] 刘兴, 余建波. 注意力卷积GRU自编码器及其在工业过程监控的应用[J]. 浙江大学学报(工学版), 2021, 55(9): 1643-1651, 1659. LIU X, YU J B. Attention convolutional GRU-based autoencoder and its application in industrial process monitoring[J].Journal of Zhejiang University (Engineering Science), 2021, 55(9): 1643-1651, 1659.
  [18] CHEN Y T, KANG Y F, CHEN Y X, et al. Probabilistic forecasting with temporal convolutional neural network[J].Neurocomputing, 2020, 399: 491-501.
  [19] LI Z Y, SUN Y, YANG L H, et al. Unsupervised machine anomaly detection using autoencoder and temporal convolutional network[J].IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-13.
  [20] THILL M, KONEN W, WANG H, et al. Temporal convolutional autoencoder for unsupervised anomaly detection in time series[J].Applied Soft Computing, 2021, 112: 107751.
  [21] LI W X, SHANG Z W, ZHANG J, et al. A novel unsupervised anomaly detection method for rotating machinery based on memory augmented temporal convolutional autoencoder[J].Engineering Applications of Artificial Intelligence, 2023, 123: 106312.
  [22] WANG Y W, DENG L, ZHENG L Y, et al. Temporal convolutional network with soft thresholding and attention mechanism for machinery prognostics[J].Journal of Manufacturing Systems, 2021, 60: 512-526.
  [23] HE Y M, SHI H B, TAN S, et al. Multiblock temporal convolution network-based temporal-correlated feature learning for fault diagnosis of multivariate processes[J].Journal of the Taiwan Institute of Chemical Engineers, 2021, 122: 78-84.
  [24] 刘渊博, 陈相, 刘妤. 基于卷积自编码器和时间卷积网络的轴承性能退化趋势预测[J]. 振动与冲击, 2023, 42(13): 214-225. LIU Y B, CHEN X, LIU Y. Prediction of bearing performance degradation trend based on CAE and TCN[J].Journal of Vibration and Shock, 2023, 42(13): 214-225.
  [25] 狄子钧, 袁东风, 李东阳, 等. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90. DI Z J, YUAN D F, LI D Y, et al. Tool fault diagnosis method based on multiscale-efficient channel attention network[J].Journal of Mechanical Engineering, 2024, 60(6): 82-90.
  [26] 高学金, 李学凤, 齐咏生. 基于扩散距离的信息熵FCM多阶段LSTM-AE间歇过程故障监测[J]. 高校化学工程学报, 2023, 37(1): 120-130. GAO X J, LI X F, QI Y S. Multi-phase LSTM-AE fault monitoring of batch processes based on diffusion distance and entropy FCM[J].Journal of Chemical Engineering of Chinese Universities,2023, 37(1): 120-130.
  [27] VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE[J].Journal of Machine Learning Research, 2008, 9(86): 2579-2605.
  [28] ZHAO H, LIU J W, DONG W, et al. An improved case-based reasoning method and its application on fault diagnosis of Tennessee Eastman process[J].Neurocomputing, 2017, 249: 266-276.
  [29] 牟建鹏, 熊伟丽. 基于滑动窗和多块卷积自编码器的故障检测[J]. 系统仿真学报, 2024, 36(2): 423-435. MOU J P, XIONG W L. Fault detection based on sliding window and multiblock convolutional autoencoders[J].Journal ofSystem Simulation, 2024, 36(2): 423-435.
  [30] 张成, 戴絮年, 李元. 基于DPCA残差互异度的故障检测与诊断方法[J]. 自动化学报, 2022, 48(1): 292-301. ZHANG C, DAI X N, LI Y. Fault detection and diagnosis based on residual dissimilarity in dynamic principal component analysis[J].Acta Automatica Sinica, 2022, 48(1): 292-301.
  [31] 郭金玉, 李文涛, 李元. 在线压缩KECA的自适应算法在故障检测中的应用[J]. 化工学报, 2021, 72(8): 4227-4238. GUO J Y, LI W T, LI Y. Application of adaptive algorithm of online reduced KECA in fault detection[J].CIESCJournal, 2021, 72(8): 4227-4238.
  [32] JANG K, HONG S, KIM M, et al. Adversarial autoencoder based feature learning for fault detection in industrial processes[J].IEEE Transactions on Industrial Informatics, 2022, 18(2): 827-834.
  [33] LI S P, LUO J X, HU Y M. Nonlinear process modeling via unidimensional convolutional neural networks with self-attention on global and local inter-variable structures and its application to process monitoring[J].ISATransactions, 2022, 121: 105-118.