Community Research and Development Information Service - CORDIS

FP5

CHEM Report Summary

Project ID: G1RD-CT-2001-00466
Funded under: FP5-GROWTH
Country: Poland

Process modelling using fuzzy logic and neural networks for fault detection

The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes.

The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes.

"Process modelling using fuzzy logic and neural networks for fault detection" toolbox is the software package intended to identify, verify and simulate models of process variables. This toolbox's primary tasks are real time process variables reconstruction (virtual sensors, software redundancy) and generation of residuals for fault detection purposes in industrial processes.

It provides easy to use and friendly environment for identification of linear, fuzzy and neural models. Identification is carried out by means of historical process data obtained from SCADA and/or DCS systems. The toolbox is divided into on-line and off-line parts. Fuzzy and neural process models are created in the off-line part. In the "Process modelling using fuzzy logic and neural networks for fault detection" on-line part, residuals are yielded based on models provided by the off-line part of the toolbox. Residuals are generated as differences of models’ outputs and process values.

This toolbox is particularly applicable in the continuous processes such as in: chemical, petrochemical, pharmaceutical, food, power, metallurgical, and thermal industries. It works under MS Windows 2000/XP.

"Process modelling using fuzzy logic and neural networks for fault detection" and "Fault diagnosis using information systems and fuzzy reasoning" toolbox cooperate with each other in AMandD – Advance Monitoring and Diagnostic System.
The preliminary tests of the "Process modelling using fuzzy logic and neural networks for fault detection" were conducted on: IDR Urea Synthesis Section of Urea Manufacturing Process in Nitrogen Factory "Pulawy" SA, Steam Generator Laboratory Stand in LAIL Universite Des Sciences et Technologies de Lille, Laboratory Stand for Diagnostic of Industrial Process at Warsaw University of Technology.

Reported by

Institute of Automatic Control and Robotics, Warsaw University of Technology
A. Boboli 8
02 525 Warszawa
Poland
See on map
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top