摘要

In order to improve productivity and global competitiveness, a novel equipment maintenance method, hybrid intelligent maintenance system (HIMS), is proposed. HIMS's key challenge is how to integrate and combine some intelligent methods, make use of their merits and avoid their demerits to forecast the incipient fault efficiently, and to prevent the fault from further deteriorating. Inspired by "divide and conquer" and "learn strong points to offset weakness", we try to simplify the complicated equipment maintenance task by decomposing the work into two subsystems: hybrid intelligent fault diagnosis system and hybrid intelligent condition forecasting system based on advanced signal processing and artificial intelligence methods. The HIMS is applied to the maintenance of the turbo-generator set in a power plant, and the simulated results show that the proposed method is very effective.