A Method for Gas Turbine Fault Diagnosis Based on Bayesian Network
Aiming at the phenomenon that there are small amount of fault samples of existing power station gas turbine,and the previous fault diagnosis methods rely on a large amount of data with fault labels,which is difficult to obtain the expected diagnosis effect in actual operation,this paper presents a method to identify the cause of gas turbine failure by using Bayesian network counterfactual reasoning.This paper first introduces the basic principle of Bayesian network,then applies failure mode and effects analysis as well as fault tree analysis to the construction of Bayesian network,and finally verifies the effectiveness of this method through the actual case analysis.The fault diagnosis method proposed in this paper can analyze possible faults and corresponding fault causes according to abnormal phenomena in the operation of gas turbines,help operation and maintenance personnel to discover and eliminate faults in time,and make up for the lack of professional knowledge support of data-driven fault diagnosis methods,and provides a flexible,efficient and reliable new option for fault diagnosis of gas turbines.
gas turbinefault diagnosisBayesian networkcounterfactual reasoningfailure mode and effects analysis
NETL
NSTL
万方数据
维普
