An intelligent tutoring system for turbine startup training of electrical power plant operators

摘要

Training is a critical issue for operators responsible for the efficient operation of complex dynamic systems. Consequently, the number of utilities that have invested in simulator-based programs has grown and the necessity of extending the availability of simulator-based training, beyond the limited use of simulators has emerged. Trying to increase the training effectiveness of simulators, intelligent training systems (ITS) are being developed. The objective of an ITS is to increase the training effectiveness, providing a means to have additional training time. It benefits the utility by cutting down operational costs of a training simulator and improving the training methodology of the simulator. This paper describes an ITS designed for the operators' training of fossil-fuelled electrical power plants. The system consists of a real time simulation of a 300 MW turbine from zero to rated speed, a computer model of a turbine operator expert and other components that allow for evaluation and coaching of a turbine operator engineer. The rationale for such a system is presented. The architectural design, procedure and approach taken in constructing such a system for practical application are described. Instructional content and strategies to teach a novice operator how to supervise and control the turbine startup are included.