Affiliation:
1. ELKH-PE Complex Systems Monitoring Research Group, Department of Process Engineering, University of Pannonia, Egyetem u. 10, H-8200 Veszprém, Hungary
Abstract
This study introduces particle filtering (PF) for the tracking and fault diagnostics of complex process systems. In process systems, model equations are often nonlinear and environmental noise is non-Gaussian. We propose a method for state estimation and fault detection in a wastewater treatment system. The contributions of the paper are the following: (1) A method is suggested for sensor placement based on the state estimation performance; (2) based on the sensitivity analysis of the particle filter parameters, a tuning method is proposed; (3) a case study is presented to compare the performances of the classical PF and intelligent particle filtering (IPF) algorithms; (4) for fault diagnostics purposes, bias and impact sensor faults were examined; moreover, the efficiency of fault detection was evaluated. The results verify that particle filtering is applicable and highly efficient for tracking and fault diagnostics tasks in process systems.
Funder
(Monitoring Complex Systems by goal-oriented clustering algorithms)
Ministry for Innovation and Technology of Hungary from the National Research, Development and Innovation Fund
Foundation of the University of Pannonia
Subject
Process Chemistry and Technology,Chemical Engineering (miscellaneous),Bioengineering
Reference18 articles.
1. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking;Arulampalam;IEEE Trans. Signal Process.,2002
2. Stelzer, I., Kager, J., and Herwig, C. (2017). Computer Aided Chemical Engineering, Elsevier.
3. Particle filtering-based fault detection in non-linear stochastic systems;Kadirkamanathan;Int. J. Syst. Sci.,2002
4. Elfring, J., Torta, E., and van de Molengraft, R. (2021). Particle Filters: A Hands-On Tutorial. Sensors, 21.
5. Fault diagnosis using particle filter for MEA typical components;Hongliang;J. Eng.,2018
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献