Department of Electrical Engineering, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran.
Abstract: (154 Views)
1, *2, 3 1-Ph.D. student, *2-Assistant Professor, Department of Electrical Engineering, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran, m.forouzanfar@iauahvaz.ac.ir 3- Assistant Professor, . In chemical closed-loop processes, interconnected industrial tanks are described by nonlinear dynamic models, sometimes under simultaneous Gaussian and non-Gaussian perturbations. Timely detection of simultaneous pipe jamming and tank leakage incipient faults is a concern of this art. In this work, a new incipient fault detection approach is proposed for application in such a system. First, the state vector is estimated using an accurate mathematical model and controller model. Then, the primary residual signal is generated using the measurements and the estimated states. Next, the generated residual signal is processed using statistical features, such as the autocorrelation test. After that, by an adaptive either fixed threshold applied in the online monitoring devised with the introduced evaluation technique, while the fault detectability is improved, the false detection problem is restricted to the system permitted number. Finally, in order to evaluate the proposed approach, the simultaneous fouling incipient fault diagnosis over the heat transfer unit built-in nonlinear closed-loop three-vessel tank system DTS200 is considered. For quantitative evaluation of the simulation results, the confusion matrix, related evaluation indices, and F1-score have been calculated.
Safaeipour H, Forouzanfar M, Ramezani A. Simultaneous Pipe Jamming and Tank Leakage Incipient Fault Detection in Interconnected Industrial Tank Systems. تحقیقات نوین در سیستمهای قدرت هوشمند 2022; 11 (1) :9-18 URL: http://jeps.dezful.iau.ir/article-1-391-en.html