CNN-Based Intelligent Fault-Tolerant Control Design for Turbofan Engines With Actuator Faults

In this paper, the problem of fault-tolerant control is investigated for turbofan engines with actuator faults. The controller involvement has repressed effects faults on controlled outputs engines, making difficult. To solve problem, internal gas-path data introduced to provide conducive fault information. Besides, useful property convolution neural network (CNN) explored and utilized in control. Based analysis faults, by using Lyapunov stability L 2 -gain like theorems, a novel CNN-based intelligent system proposed, including diagnosis module nonlinear corresponding reconfiguration unit. advantages reducing accuracy requirements mathematical description engines. Furthermore, proposed can diagnose reduce adverse Finally, simulation results are presented demonstrate efficiency designed method.