FAULT DIAGNOSIS SYSTEM FOR THE OUTOKUMPU FLASH SMELTING PROCESS

摘要

Process monitoring and fault diagnosis have been studied widely in recent years, and the number of industrial applications with encouraging results has grown rapidly. Early detection and localisation of undesired process states and equipment failures are essential prerequisites for safe and reliable processes. In the paper a fault diagnosis system for the Outokumpu flash smelting process will be described and discussed. The system monitors process states using neural networks (Kohonen Self-Organizing Maps, SOM) in conjunction with heuristic rules, which are also used to detect equipment malfunctions.