A deep learning model for process fault prognosis

Abstract Early fault detection and fault prognosis are crucial functions to ensure safe process operations. Fault prognosis can detect and isolate early developing faults as well as predict fault propagation. To promptly detect potential faults in process systems, it is important to examine the fault symptoms as early as possible. In recent years, fault prognosis approaches have led to the remaining useful life prediction. Therefore, in a process system, advancing prognosis approaches will be beneficial for early fault detection in terms of process safety, and to predict the remaining useful life, targeting the system's reliability. In data-driven models, early fault detection is regarded as a time-dependent sequence learning problem; the future data sequence is predicted using the previous data pattern. Studying recent years' research shows that a recurrent neural network (RNN) can solve the sequence learning problem. This paper proposes an early potential fault detection approach by examining the fault symptoms in multivariate complex process systems. The proposed model has been developed using the Convolutional Neural Network (CNN)- Long Short-Term Memory (LSTM) approach to forecast the system parameters for future sampling windows' recognition and an unsupervised One-class-SVM used for fault symptoms' detection using forecasted data window. The performance of the proposed method is assessed using Tennessee Eastman process time-series data. The results confirm that the proposed method effectively detects potential fault conditions in multivariate dynamic systems by detecting the fault symptoms early as possible.

[1]  Efstratios N. Pistikopoulos,et al.  A Nonlinear Support Vector Machine-Based Feature Selection Approach for Fault Detection and Diagnosis: Application to the Tennessee Eastman Process. , 2019, AIChE journal. American Institute of Chemical Engineers.

[2]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[3]  Syed Imtiaz,et al.  Fault detection and diagnosis in process system using artificial intelligence-based cognitive technique , 2020, Comput. Chem. Eng..

[4]  Josiah C. Hoskins,et al.  Artificial neural network models for knowledge representation in chemical engineering , 1990 .

[5]  Steven X. Ding,et al.  A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches , 2015, IEEE Transactions on Industrial Electronics.

[6]  Hee-Jun Kang,et al.  A survey on Deep Learning based bearing fault diagnosis , 2019, Neurocomputing.

[7]  Ming Chen,et al.  A data-driven model for milling tool remaining useful life prediction with convolutional and stacked LSTM network , 2020 .

[8]  Lirong Cui,et al.  Availability and maintenance modelling for systems subject to multiple failure modes , 2017, Comput. Ind. Eng..

[9]  Gong Ping,et al.  An End-to-End model based on CNN-LSTM for Industrial Fault Diagnosis and Prognosis , 2018, 2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC).

[10]  Zengtao Hou,et al.  An Integrative Framework for Online Prognostic and Health Management Using Internet of Things and Convolutional Neural Network , 2019, Sensors.

[11]  Faisal Khan,et al.  An analysis of process fault diagnosis methods from safety perspectives , 2021, Comput. Chem. Eng..

[12]  Wei Li,et al.  Remaining Useful Life Estimation Based on a New Convolutional and Recurrent Neural Network , 2019, 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE).

[13]  Ling Zheng,et al.  A Fault Prediction Of Equipment Based On CNN-LSTM Network , 2019, 2019 IEEE International Conference on Energy Internet (ICEI).

[14]  Hongfu Zuo,et al.  Fault prediction of bearings based on LSTM and statistical process analysis , 2021, Reliab. Eng. Syst. Saf..

[15]  E. F. Vogel,et al.  A plant-wide industrial process control problem , 1993 .

[16]  Enrico Sciubba,et al.  Automatic diagnostics and prognostics of energy conversion processes via knowledge-based systems , 2004 .

[17]  Yu Zheng,et al.  An ensemble framework based on convolutional bi-directional LSTM with multiple time windows for remaining useful life estimation , 2020, Comput. Ind..

[18]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[19]  Yongming Han,et al.  An optimized long short-term memory network based fault diagnosis model for chemical processes , 2020 .

[20]  Kay Chen Tan,et al.  Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Huanxin Chen,et al.  Ensemble 1-D CNN diagnosis model for VRF system refrigerant charge faults under heating condition , 2020 .

[22]  Bo Jin,et al.  Sequential Fault Diagnosis Based on LSTM Neural Network , 2018, IEEE Access.

[23]  Jianfeng Zhao,et al.  Speech emotion recognition using deep 1D & 2D CNN LSTM networks , 2019, Biomed. Signal Process. Control..

[24]  Sirish L. Shah,et al.  Fault detection and diagnosis in process data using one-class support vector machines , 2009 .

[25]  Chen Meng,et al.  Data-Driven Feature Extraction for Analog Circuit Fault Diagnosis Using 1-D Convolutional Neural Network , 2020, IEEE Access.

[26]  Xiang Li,et al.  Remaining useful life estimation in prognostics using deep convolution neural networks , 2018, Reliab. Eng. Syst. Saf..

[27]  Gerald Penn,et al.  Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[28]  Jizhong Tao,et al.  A Novel Bearing Health Indicator Construction Method Based on Ensemble Stacked Autoencoder , 2019, 2019 IEEE International Conference on Prognostics and Health Management (ICPHM).

[29]  Piergiuseppe Di Marco,et al.  Fault Detection and Diagnosis Using Combined Autoencoder and Long Short-Term Memory Network , 2019, Sensors.

[30]  Weihua Gui,et al.  A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network. , 2019, ISA transactions.

[31]  Fanming Meng,et al.  An Improved Bearing Fault Diagnosis Method using One-Dimensional CNN and LSTM , 2018, Strojniški vestnik - Journal of Mechanical Engineering.

[32]  Jun Wu,et al.  Machine Health Monitoring Using Adaptive Kernel Spectral Clustering and Deep Long Short-Term Memory Recurrent Neural Networks , 2019, IEEE Transactions on Industrial Informatics.

[33]  Taoying Li,et al.  A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5) , 2020, IEEE Access.

[34]  Heikki N. Koivo,et al.  Application of artificial neural networks in process fault diagnosis , 1991, Autom..

[35]  Mohammad Modarres,et al.  A Deep Adversarial Approach Based on Multi-Sensor Fusion for Semi-Supervised Remaining Useful Life Prognostics , 2019, Sensors.

[36]  Faisal Khan,et al.  Process Fault Prognosis Using Hidden Markov Model–Bayesian Networks Hybrid Model , 2019, Industrial & Engineering Chemistry Research.

[37]  M. A. Djeziri,et al.  Data-driven approach augmented in simulation for robust fault prognosis , 2019, Eng. Appl. Artif. Intell..

[38]  Noureddine Zerhouni,et al.  State of the art and taxonomy of prognostics approaches, trends of prognostics applications and open issues towards maturity at different technology readiness levels , 2017 .