Sparse Causal Residual Neural Network for Linear and Nonlinear Concurrent Causal Inference and Root Cause Diagnosis

Reliable and effective fault diagnosis methods are necessary for complex industrial processes that consists of various units. After a process fault is detected, it remains a challenging task to locate the root cause unit and determine the propagation path of the fault. In this paper, a novel method, termed Sparse Causal Residual Neural Network (SCRNN), is proposed and applied for modern industrial root cause diagnosis. The advantage of SCRNN lies in that it can not only recognize linear and nonlinear causal relationships in parallel, but also automatically determine the causality lags and deduce the time delay of causal transmission. Besides, due to the specially designed sparse constraint and optimization algorithm, the SCRNN model can realize the function of key dependent variable selection, avoiding the high computational complexity and complicated procedure brought by pairwise comparison. The feasibility of the proposed method is illustrated through the benchmark TE process.

[1]  Daniele Marinazzo,et al.  Radial basis function approach to nonlinear Granger causality of time series. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  Chunhui Zhao,et al.  Fault Description Based Attribute Transfer for Zero-Sample Industrial Fault Diagnosis , 2021, IEEE Transactions on Industrial Informatics.

[3]  W. Marsden.  I and J , 2012 .

[4]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[5]  H. Akaike.  A new look at the statistical model identification , 1974 .

[6]  Anders L. Madsen,et al.  Applications of object-oriented Bayesian networks for condition monitoring, root cause analysis and decision support on operation of complex continuous processes , 2005, Comput. Chem. Eng..

[7]  Tongwen Chen,et al.  Methods for root cause diagnosis of plant‐wide oscillations , 2014 .

[8]  Stephen P. Boyd,et al.  Proximal Algorithms , 2013, Found. Trends Optim..

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Chunhui Zhao,et al.  Online Fault Diagnosis in Industrial Processes Using Multimodel Exponential Discriminant Analysis Algorithm , 2019, IEEE Transactions on Control Systems Technology.

[11]  Rolf Isermann,et al.  Fault-Diagnosis Applications: Model-Based Condition Monitoring: Actuators, Drives, Machinery, Plants, Sensors, and Fault-tolerant Systems , 2011 .

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

[13]  Fei Liu,et al.  Fault Detection and Diagnosis of Multiple-Model Systems With Mismodeled Transition Probabilities , 2015, IEEE Transactions on Industrial Electronics.

[14]  E. Fox,et al.  Neural Granger Causality for Nonlinear Time Series , 2018, 1802.05842.

[15]  Chunhui Zhao,et al.  A Fine-Grained Adversarial Network Method for Cross-Domain Industrial Fault Diagnosis , 2020, IEEE Transactions on Automation Science and Engineering.

[16]  David J. Spiegelhalter,et al.  Probabilistic Networks and Expert Systems - Exact Computational Methods for Bayesian Networks , 1999, Information Science and Statistics.

[17]  William B. Nicholson,et al.  High Dimensional Forecasting via Interpretable Vector Autoregression , 2014, J. Mach. Learn. Res..

[18]  Naoki Abe,et al.  Grouped graphical Granger modeling methods for temporal causal modeling , 2009, KDD.

[19]  Schreiber,et al.  Measuring information transfer , 2000, Physical review letters.

[20]  Chunhui Zhao,et al.  Online Fault Diagnosis for Industrial Processes With Bayesian Network-Based Probabilistic Ensemble Learning Strategy , 2019, IEEE Transactions on Automation Science and Engineering.

[21]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[22]  Chunhui Zhao,et al.  Critical-to-Fault-Degradation Variable Analysis and Direction Extraction for Online Fault Prognostic , 2017, IEEE Transactions on Control Systems Technology.

[23]  Chunhui Zhao,et al.  Root Cause Diagnosis of Oscillation-Type Plant Faults Using Nonlinear Causality Analysis , 2017 .

[24]  Nina F. Thornhill,et al.  Finding the Direction of Disturbance Propagation in a Chemical Process Using Transfer Entropy , 2007, IEEE Transactions on Control Systems Technology.