基于D-S证据理论的柴油机故障诊断

D-S证据理论已经广泛应用于各种故障诊断中,但基本概率分配是证据理论的重要一步.运用典型样本的数据融合方法对柴油机供油系统的3种故障进行诊断,避免了D-S证据理论应用中基本概率赋值难以分配的问题,减少了方法的主观性.实践结果表明,该方法可以有效的判别出柴油机故障类型,具有工程实用价值.

Fusion Diagnosis of Diesel Engine Based on a D-S Evidence Theory

Demmpster -Shafer theory of evidence had good performance in dealing with many kinds of fault diagnosis. However, basic probability assignment was important for evidence theory. In this paper, the typical swatch-based method data fusion was used in three diesel engine faults of fuel supply system. This method avoided the problem that it is difficult to determine the basic probability assignment during the use of D-S evidence theory, thus reducing subjectivity. The practice shows that the method can effectively recognize various types of Diesel engine faults and be practical value in engineering applications.