A data-driven health evaluation method for engine test-beds

Abstract

A novel strategy by using relevance vector machine (RVM) coupled with fuzzy comprehensive evaluation method is proposed for the health evaluation of engine test-bed system. Based on our previous work, the concept of health reliability degree (HRD) is reviewed to indicate a quantitative health level from the perspectives of single parameter, some subsystems and the whole test-bed system. The relationship among multiple parameters are fully considered, which is different from traditional qualitative fault detection. The fuzzy evaluation method is used to evaluate the health condition of test-bed system under different fuzzy evaluating criterion sets. The HRD is calculated by using the RVM-based multi-variable fusion method. To verify the proposed strategy, a simulated experimental system is designed. The health evaluation of test-bed system with different health levels have been discussed under different working conditions. Results show that the proposed method provides a better solution to health evaluation of test-bed system.