Knowledge modelling for rule-based supervision and control of production facilities

摘要

The technological complexity of modern production facilities and the increasing demands on operation procedures result in new tasks and requirements for automation solutions and operating staff qualification. On the one hand, supervision and control systems must assign tasks which have been carried out by operators-e.g. operative planning of resources, scheduling of maintenance, operation tuning. On the other hand, the operating principles and techniques must become more objective; operating experience and knowledge should be more easily collected, conserved and disseminated. The general objective of this paper is to develop methods and techniques for these issues. The studied approach is based on integrated use of several formalizations of facility operation knowledge-mathematical modelling, data-driven methods, and scenario-oriented supervision and control routines. Here, facility events in the past are classified by means of Data Mining. Cause-and-effect relations between process states and phenomena are expressed by equations. Facility operation routines are modelled in the form of 'if-then' scenarios. The functional chain, which begins with operator knowledge acquisition and moves to knowledge and facility modelling and finally to their integration into a real Supervisory Control and Data Acquisition system, have been implemented and tested for a water treatment and supply plant.