Intelligent control system for process monitoring

Abstract

On-line monitoring and fault diagnosis based on artificial intelligence (AI) technology is an important Al application. Hazardous accidents and equipment failures always result in environmental pollution and poor product quality, and jeopardize the safety of equipment and human resources. As a result, accidents cost money, decrease productivity and profits. In this article, a generic integrated distributed intelligent multimedia system architecture for process monitoring, fault diagnosis and maintenance is discussed. The architecture consists of four individual modules: data calibration, condition monitoring, fault diagnosis, and maintenance assistance. It integrates different AI techniques such as heuristic reasoning, case-based reasoning and hypermedia. An industrial application using the architecture is presented which is used to implement an intelligent operation support system (IPMS) using rich knowledge representation and hybrid reasoning strategy. The functional requirements and desired features for IPMS are defined. The human operator's recognition behavior is analyzed. It is shown that a hybrid reasoning environment that combines case-based reasoning (CBR), model-based reasoning (MBR) and rule-based reasoning (RBR) is consistent with operator's problem solving. A multidimensional problem solving model is proposed to incorporate these requirements and human recognition behavior. IPMS is designed by using the problem solving model as the guide. The implementation of IPMS in a pulp production process is presented.