A Fault Diagnosis Approach for Electromechanical Actuators with Simulating Model under Small Experimental Data Sample Condition

Electromechanical actuators (EMAs) have shown a high efficiency in flight surface control with the development of more electric aircraft. In order to identify abnormalities and potential failures EMA, methodology for fault diagnosis is developed. A simulating model EMA first built perform different working states. Based on modeling corresponding faults are then simulated re-generate data. Afterwards, gated recurrent unit (GRU) co-attention-based approach proposed classify states EMA. Experiments conducted satisfying classification accuracy data obtained. Furthermore, an actual system performed. The experimental results demonstrate that method has efficiency.