Process monitoring and fault diagnosis have been studied widely in recent years, and the number of industrial applications with encouraging results has grown rapidly. In the case of complex processes a computer-aided monitoring enhances operators possibilities to run the process economically. In this paper, a fault diagnosis system will be described and some application results from the Outokumpu Harjavalta smelter will be discussed. The system monitors process states using neural networks (Kohonen selforganizing maps, SOMs) in conjunction with heuristic rules, which are also used to detect equipment malfunctions. r

No abstract

Jämsä-Jounela, Sirkka-Liisa; Vapaavuori, E.; Salmi, T.; Grönbärj, M.; Vermasvuori, M. Fault diagnosis system for the Outokumpu flash smelting process 1) Laboratory of Process Control and Automation, Aalto UniversityAbstract: Fault diagnosis systems have attracted growing interest in a number of engineering fields. The number of applications has increased and successful results have been widely reported. This paper presents and outlines a fault diagnosis system for flash smelting. The system monitors the states of the process by means of Kohonen Self-Organising Maps and performs the fault diagnosis of the process equipment by analysing the operation of the process equipment. Finally the results of the off-line testing of the system are reported and discussed.

No abstract