IAM: An Intuitive ANFIS-based method for stiction detection

International Conference on Process Engineering and Advanced Materials 2018

Jeremiah, Sean S.^1 ; Zabiri, H.^1 ; Ramasamy, M.^1 ; Kamaruddin, B.^1 ; Teh, W.K.^1 ; Mohd Amiruddin, A.A.A.^1

Department of Chemical Engineering, Universiti Teknologi PETRONAS (UTP), Seri Iskandar, Perak

32610, Malaysia^1

关键词: Adaptive neuro-fuzzy;    Case-studies;    Control loop;    Control performance;    In-control;    Industrial controls;    New approaches;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/458/1/012054/pdf
DOI  :  10.1088/1757-899X/458/1/012054

来源: IOP

【 摘 要 】

Stiction in control valves is an industry-wide problem which results in degradation of control performance. A new approach to detect the presence of stiction by utilising only the PV-OP data from control loops is proposed using an Adaptive Neuro-fuzzy Inferencing System (ANFIS). Intuitively, the error between the output of an FIS model developed with stiction and a process with stiction would be minimal. When benchmarked against seventeen well-known industrial control loop case studies, the Intuitive ANFIS-based Method (IAM) accurately predicts the presence or absence of stiction in 65% of loops tested.