D-S证据理论及其在燃气轮机系统诊断中的应用研究

Due to the complex and changeable operating conditions of gas turbine bearings and insufficient utilization of measurement point information, the detection, diagnosis, operation and maintenance of gas turbine bearings have always been the focus of research.In recent years, multi-source information fusion technology has been widely used, and gradually become the key to ensure the safe operation of industrial equipment. In view of the problems of the insufficient utilization of multi-source monitoring data, the difficulty of eliminating sensor signal uncertainty, and the need to improve diagnosis accuracy existed in current gas turbine bearing monitoring diagnosis, Dempster-Shafer (DS) evidence theory is a concise and efficient decision-level multi-source information fusion method, which has huge application potential in gas turbine condition monitoring and fault diagnosis. The traditional D-S evidence theory is introduced, and in view of its shortcomings, the research status of evidence theory in the field of gas turbine fault diagnosis is systematically summarized. Focusing on the actual industrial application scenarios of gas turbines, the characteristics of D-S evidence theory are analyzed and concluded, and the future development trend of D-S evidence theory and gas turbine fault diagnosis is pointed out.