A data driven fault isolation method based on reference faulty situations with application to a nonlinear chemical process

Ragot, José ; Mourot, Gilles  ; Kallas, Maya

International Journal of Applied Mathematics and Computer Science, Tome 32 (2022) no. 4, pp. 635-655.

Résumé

The diagnosis of systems is one of the major steps in their control and its purpose is to determine the possible presence of dysfunctions, which affect the sensors and actuators associated with a system but also the internal components of the system itself. On the one hand, the diagnosis must therefore focus on the detection of a dysfunction and, on the other hand, on the physical localization of the dysfunction by specifying the component in a faulty situation, and then on its temporal localization. In this contribution, the emphasis is on the use of software redundancy applied to the detection of anomalies within the measurements collected in the system. The systems considered here are characterized by non-linear behaviours whose model is not known a priori. The proposed strategy therefore focuses on processing the data acquired on the system for which it is assumed that a healthy operating regime is known. Diagnostic procedures usually use this data corresponding to good operating regimes by comparing them with new situations that may contain faults. Our approach is fundamentally different in that the good functioning data allow us, by means of a non-linear prediction technique, to generate a lot of data that reflect all the faults under different excitation situations of the system. The database thus created characterizes the dysfunctions and then serves as a reference to be compared with real situations. This comparison, which then makes it possible to recognize the faulty situation, is based on a technique for evaluating the main angle between subspaces of system dysfunction situations. An important point of the discussion concerns the robustness and sensitivity of fault indicators. In particular, it is shown how, by non-linear combinations, it is possible to increase the size of these indicators in such a way as to facilitate the location of faults.

Détail

Keywords: fault detection, fault isolation, nonlinear system, data modelling, kernel
Mots-clés : wykrywanie uszkodzeń, izolacja uszkodzeń, układ nieliniowy, modelowanie danych

Bibliographie

[1] [1] Alcala, C. and Qin, S. (2010). Reconstruction-based contribution for process monitoring with kernel principal component analysis, Industrial and Engineering Chemistry Research 49(17): 7849–7857.

[2] [2] Bates, D.M. and Watts, D.G. (1988). Nonlinear Regression Analysis and Its Applications, Wiley, New York.

[3] [3] Benaicha, A., Mourot, G., Benothman, K. and Ragot, J. (2013). Determination of principal component analysis models for sensor fault detection and isolation, International Journal of Control, Automation and Systems 11(2): 296–305.

[4] [4] Blanke, M., Kinnaert, M., Lunze, J. and Staroswiecki, M.D. (2006). Diagnosis and Fault-Tolerant Control, Springer, Berlin.

[5] [5] Botre, C., Mansouri, M., Karim, N., Nounou, H. and Nounou, M. (2016). Kernel PLS-based GLRT method for fault detection of chemical processes, Journal of Loss Prevention in the Process Industries 43: 212–223.

[6] [6] Buchberger, B. and Kauers, M. (2010). Bases de Gröbner, Scholarpedia 4249(5): 7763, DOI: 10. 4249/scholarpedia.

[7] [7] Dagnelie, P. (2012). Principes d’Expérimentation: Planification des Expériences et Analyse de leurs Résultats, Presses Agronomiques, Gembloux.

[8] [8] Diop, S. (1989). A state elimination procedure for nonlinear systems, in J. Descusse et al. (Eds), New Trends in Nonlinear Control Theory, Springer, Berlin, pp. 190–198.

[9] [9] Fazai, R., Taouali, O., Harkat, M.F. and Bouguila, N. (2016). A new fault detection method for nonlinear process monitoring, International Journal of Advanced Manufacturing Technology 87: 3425–3436.

[10] [10] Frank, P.M. (1990). Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy—A survey and some new results, Automatica 26(3): 459–474.

[11] [11] Gao, Q., Liu, W., Zhao, X., Li, J. and Yu, X. (2017). Research and application of the distillation column process fault prediction based on the improved KPCA, IEEE International Conference on Mechatronics and Automation, Takamatsu, Japan, pp. 247–251.

[12] [12] Gu, S., Liu, Y., Zhang, N. and Du, D. (2015). Fault detection approach based on weighted principal component analysis applied to continuous stirred tank reactor, Open Mechanical Engineering Journal 9(1): 966–972.

[13] [13] Gunawan, H. (2018). n-Inner products, n-norms and angles between two subspaces, in M. Rozhansky et al. (Eds), Mathematical Analysis and Applications: Selected Topics, Wiley, Hoboken, pp. 493–515.

[14] [14] Huang, D., Zhang, D., Liu, Y., Zhang, S. and Zhu, W. (2014). A KPCA based fault detection approach for feed water treatment process of coal-fired power plant, 11th World Congress on Intelligent Control and Automation, Shenyang, China, pp. 3222–3227.

[15] [15] Jia, Q. and Huang, Y. (2016). Quality-related fault detection approach based on dynamic kernel partial least squares, Chemical Engineering Research and Design 106: 242–252.

[16] [16] Jordan, C. (1875). Essai sur la géométrie n dimensions, Bulletin de la Société Mathématique de France 3: 103–174.

[17] [17] Jun, B.H., Park, J.H., Lee, S.I. and Chun, M.G. (2006). Kernel PCA based faults diagnosis for wastewater treatment system, in Wang J. et al. (Eds), Advances in Neural Networks, Lecture Notes in Computer Science, Vol. 3973, Springer, Berlin, pp. 426–431.

[18] [18] Kallas, M., Mourot, G., Maquin, D. and Ragot, J. (2018). Data driven approach for fault detection and isolation in nonlinear system, International Journal of Adaptive Control and Signal Processing 32(11): 1569–1590.

[19] [19] Kallas, M., Mourot, G., Maquin, D. and Ragot, J. (2014). Diagnosis of nonlinear systems using kernel principal component analysis, 11th European Workshop on Advanced Control and Diagnosis, Berlin, Germany.

[20] [20] Manikandan, P., Geetha, M., Jubi, K. and Jovitha, J. (2013). Fault tolerant fuzzy gain scheduling proportional-integral-derivative controller for continuous stirred tank reactor, Australian Journal of Basic and Applied Sciences 7(13): 84–93.

[21] [21] Navi, M., Meskin, N. and Davoodi, M. (2018). Sensor fault detection and isolation of an industrial gas turbine using partial adaptive KPCA, Journal of Process Control 64: 37–48.

[22] [22] Nithya, N. and Vijayachitra, S. (2018). Fault detection and analysis using statistical data for continuous stirred tank reactor, International Journal of ChemTech Research 11(2): 266–274.

[23] [23] Nur, M., Gunawan, H. and Neswan, O. (2018). A formula for the g-angle between two subspaces of a normed space, Beiträge zur Algebra und Geometrie/Contributions to Algebra and Geometry 59(1): 133–143.

[24] [24] Ren, Z., Hou, J. and Zhou, H. (2016a). Fault detection and process monitoring of industrial process based on spherical kernel T-PLS, 42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy, pp. 7161–7166.

[25] [25] Ren, Z., Liu, J., She, Z., Yang, C. and Han, Y. (2016b). Data-driven approach of FS-SKPLS monitoring with application to wastewater treatment process, IEEE International Conference on Industrial Technology, Taipei, Taiwan, pp. 550–555.

[26] [26] Ritt, J.F. (1950). Differential Algebra, American Mathematical Society, New York.

[27] [27] Simani, S., Farsoni, S. and Castaldi, S. (2018). Data-driven techniques for the fault diagnosis of a wind turbine benchmark, International Journal of Applied Mathematics and Computer Science 28(2): 247–268, DOI: 10.2478/amcs-2018-0018.

[28] [28] Smyth, G. (2006). Nonlinear Regression, Wiley, Hoboken.

[29] [29] Wang, L. (2018). Enhanced fault detection for nonlinear processes using modified kernel partial least squares and the statistical local approach, Canadian Journal Chemical Engineering 96(5): 1116–1126.

[30] [30] Wang, Z.Y. and Wan, G.X. (2017). Temperature fault-tolerant control system of CSTR with coil and jacket heat exchanger based on dual control and fault diagnosis, Journal of Central South University 24(3): 655–664.