[Retracted] Application of Reinforcement Learning Algorithm Model in Gas Path Fault Intelligent Diagnosis of Gas Turbine

Table 3

Statistical data reference value of gas path fault diagnosis experiment.

Air circuit failure index	Pneumatic fault reference value
Number of samples	4000
Characteristic number	3596
Accuracy	0.95
Number of categories	30
Domain representation	18
Reinforcement learning type	Strategy-centered and step-by-step reinforcement learning
Fault diagnosis model	Press surge, ignition failure, combustion failure, high lubricating oil temperature and bending of the main shaft of the gas turbine, etc.
Number of neural network layers	33
Number of neural network nodes	107