New Rules Generation From Measurement Data Using an Expert System in a Power Station

The integration of artificial-intelligence techniques in traditional real-time systems is a promising approach to cope with the growing complexity of real-world applications. Real-time expert systems are online knowledge-based systems that combine analytical process models with conventional process control to monitor complex industrial processes and to assist in problem identification. The expert system interfaces with the external distributed control system (DCS) via an object linking and embedding for process control module which acquires measurement data and identifies processes alarms for diagnosis. This paper proposes generating new rules from the plant measurement data using a learning engine. We present an efficient algorithm that generates all significant rules based on the data. The association-based algorithms were compared and those best suited for this process application were selected. The application for the learning system is studied in a powerplant application This innovative approach should assist in sustainable growth of automation in the power sector.