A two-step supervisory fault diagnosis framework

Techniques enabling early detection and diagnosis of faults are important in the processing industries. This paper emphasises a technique for early fault detection and diagnosis based on dynamic fault data and a two-step fault detection and diagnosis framework. The approach shows various advantages over alternative methods including prompt fault detection and localisation, applicability to large-scale systems without the need for excessive computing resources, and a modular architecture that allows plant sections to be treated individually. In the proposed method, the large-scale plant is broken up into sections and a Petri net based on real time data is used to locate the particular section of the plant in which the fault originates. This Petri net then activates secondary neural networks, which diagnose the exact location of the fault in that particular plant section. Applicability of the proposed technique is demonstrated through a pilot plant case study.

[1]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[2]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies , 2003, Comput. Chem. Eng..

[3]  Chuei-Tin Chang,et al.  A prototype for integrating automatic fault tree/event tree/HAZOP analysis , 1997 .

[4]  Derek A. Linkens,et al.  Intelligent Supervisory Control - A Qualitative Bond Graph Reasoning Approach , 1996, World Scientific Series in Robotics and Intelligent Systems.

[5]  Johannes Prock.  On-Line Detection and Diagnosis of Sensor and Process Faults in Nuclear Power Plants , 2000 .

[6]  George C. Verghese,et al.  Power system monitoring using Petri net embeddings , 2000 .

[7]  David Mautner Himmelblau,et al.  Fault detection and diagnosis in chemical and petrochemical processes , 1978 .

[8]  Ramaswamy Vaidyanathan,et al.  Process fault detection and diagnosis using neural networks , 1990 .

[9]  J. Trecat,et al.  Extended Petri net models for fault diagnosis for substation automation , 1999 .

[10]  Anthony Zaknich,et al.  Neural Networks for Intelligent Signal Processing , 2003, Series on Innovative Intelligence.

[11]  Venkat Venkatasubramanian,et al.  Challenges in the industrial applications of fault diagnostic systems , 2000 .

[12]  Michael Nikolaou,et al.  An approach to fault diagnosis of chemical processes via neural networks , 1993 .

[13]  Venkat Venkatasubramanian,et al.  Representing and diagnosing dynamic process data using neural networks , 1992 .

[14]  Venkat Venkatasubramanian,et al.  Causality‐based failure‐driven learning in diagnostic expert systems , 1989 .

[15]  Liya Hou,et al.  Diagnosis of multiple simultaneous fault via hierarchical artificial neural networks , 1994 .

[16]  J. Prock.  A new technique for fault detection using Petri nets , 1991, Autom..

[17]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[18]  Tianlong Gu,et al.  A survey of Petri net applications in batch processes , 2002, Comput. Ind..

[19]  Panos J. Antsaklis,et al.  Supervisory Control of Discrete Event Systems Using Petri Nets , 1998, The International Series on Discrete Event Dynamic Systems.