Reduced Gaussian process regression for fault detection of chemical processes

In this paper, a reduced Gaussian process regression (RGPR)-based generalized likelihood ratio test (GLRT) is proposed for fault detection in industrial systems. In contrast to the classical GPR technique, the RGPR model can handle domains with a large number of activities that require very large training sets. The developed RGPR-based GLRT method aims first to build a RGPR model, then, it consists to apply GLRT to the monitored residuals obtained from PGPR for fault detection purposes. The fault detection performance of the developed RGPR-based GLRT method is illustrated through the Tennessee Eastman process. The simulation results show that the RGPR-based GLRT method outperforms the conventional GPR-based GLRT technique in terms of miss detection rate and CPU-time.

[1]  Juraj Kabzan,et al.  Cautious Model Predictive Control Using Gaussian Process Regression , 2017, IEEE Transactions on Control Systems Technology.

[2]  Majdi Mansouri,et al.  Multiscale Kernel PLS-Based Exponentially Weighted-GLRT and Its Application to Fault Detection , 2019, IEEE Transactions on Emerging Topics in Computational Intelligence.

[3]  V. Ebrahimipour,et al.  A flexible algorithm for fault diagnosis in a centrifugal pump with corrupted data and noise based on ANN and support vector machine with hyper-parameters optimization , 2013, Appl. Soft Comput..

[4]  Hazem Nounou,et al.  Fault detection of uncertain nonlinear process using interval-valued data-driven approach , 2019, Chemical Engineering Science.

[5]  Rahat Iqbal,et al.  Fault Detection and Isolation in Industrial Processes Using Deep Learning Approaches , 2019, IEEE Transactions on Industrial Informatics.

[6]  Mazin Abed Mohammed,et al.  K-Means clustering and neural network for object detecting and identifying abnormality of brain tumor , 2018, Soft Computing.

[7]  D. Devaraj,et al.  Artificial neural network approach for fault detection in rotary system , 2008, Appl. Soft Comput..

[8]  Hazem Nounou,et al.  Online reduced gaussian process regression based generalized likelihood ratio test for fault detection , 2020 .

[9]  Shan Chen,et al.  Model Calibration Method for Soft Sensors Using Adaptive Gaussian Process Regression , 2019, IEEE Access.

[10]  Bengt Carlsson,et al.  Gaussian process regression for monitoring and fault detection of wastewater treatment processes. , 2017, Water science and technology : a journal of the International Association on Water Pollution Research.

[11]  Reza Eslamloueyan,et al.  Designing a hierarchical neural network based on fuzzy clustering for fault diagnosis of the Tennessee-Eastman process , 2011, Appl. Soft Comput..

[12]  Chun-Chin Hsu,et al.  Integrate Independent Component Analysis and Support Vector Machine for Monitoring Non-Gaussian Multivariate Process , 2008, 2008 4th International Conference on Wireless Communications, Networking and Mobile Computing.

[13]  Anyi Li,et al.  Fault diagnosis in industrial chemical processes using optimal probabilistic neural network , 2019, The Canadian Journal of Chemical Engineering.

[14]  Carl E. Rasmussen,et al.  Gaussian Processes for Machine Learning (GPML) Toolbox , 2010, J. Mach. Learn. Res..

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

[16]  Wei-Ping Xiao,et al.  A Probabilistic Machine Learning Approach to Detect Industrial Plant Faults , 2016, International Journal of Prognostics and Health Management.

[17]  Hazem Nounou,et al.  Multiscale Gaussian process regression-based generalized likelihood ratio test for fault detection in water distribution networks , 2019, Eng. Appl. Artif. Intell..

[18]  Hazem Nounou,et al.  Kernel Generalized Likelihood Ratio Test for Fault Detection of Biological Systems , 2018, IEEE Transactions on NanoBioscience.

[19]  Ilias K. Savvas,et al.  A novel near-parallel version of k-means algorithm for n-dimensional data objects using MPI , 2016, Int. J. Grid Util. Comput..

[20]  Dražen Slišković,et al.  Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models , 2013, Comput. Chem. Eng..

[21]  Philip N. Klein,et al.  Local Search Yields Approximation Schemes for k-Means and k-Median in Euclidean and Minor-Free Metrics , 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

[22]  Peng Jiang,et al.  Fault Diagnosis Based on Chemical Sensor Data with an Active Deep Neural Network , 2016, Sensors.

[23]  Richard D. Braatz,et al.  Data-driven Methods for Fault Detection and Diagnosis in Chemical Processes , 2000 .