This paper presents a methodology to efficiently transform the existing information on the plant behaviour into knowledge that may be used to support the decision process in maintenance activities. The development of an appropriate knowledge model relating the core aspects of the process enables the extraction of new knowledge based on the past experience. The risk of a specific situation affecting the industrial plant, characterized by the symptoms, is estimated from the information stored on the system concerning probability of occurrence and its consequences. It is expected that this knowledge grows along the life-cycle of a manufacturing system. Then for each level of risk, predetermined by the industrial users, the adequate service is called for promptly react in solving the problem or avoiding critical situations. An implementation of the methodology was made in the scope of InLife project providing validation results is real industrial environments.
|Journal||Journal of Computing in Systems & Engineering|
|Publication status||Published - 1 Jan 2011|