Fault Diagnosis Method for Aircraft EHA Based on FCNN and MSPSO Hyperparameter Optimization

Abstract

Contrapose the highly integrated, multiple types of faults and complex working conditions of aircraft electro hydrostatic actuator (EHA), to effectively identify its typical faults, we propose a fault diagnosis method based on fusion convolutional neural networks (FCNN). First, the aircraft EHA fault data is encoded by gram angle difference field (GADF) to obtain the fault feature images. Then we build a FCNN model that integrates the 1DCNN and 2DCNN, where the original 1D fault data is the input of the 1DCNN model, and the feature images obtained by GADF transformation are used as the input of 2DCNN. Multiple convolution and pooling operations are performed on each of these inputs to extract the features. Next these feature vectors are spliced in the convergence layer, and the fully connected layers and the Softmax layers are finally used to attain the classification of aircraft EHA faults. Furthermore, the multi-strategy hybrid particle swarm optimization (MSPSO) algorithm is applied to optimize the FCNN to obtain a better combination of FCNN hyperparameters; MSPSO incorporates various strategies, including an initialization strategy based on homogenization and randomization, and an adaptive inertia weighting strategy, etc. The experimental result indicates that the FCNN model optimized by MSPSO achieves an accuracy of 96.86% for identifying typical faults of the aircraft EHA, respectively, higher than the 1DCNN and the 2DCNN by about 16.5% and 5.7%. By comparing with LeNet-5, GoogleNet, AlexNet, and GRU, the FCNN model presents the highest diagnostic accuracy, less time in training and testing. The comprehensive performance of the proposed model is demonstrated to be much stronger. Additionally, the FCNN model improved by MSPSO has a higher accuracy rate when compared to PSO.