Aero-engine Air Path Fault Diagnosis via FGO-1DCNN-LSTM

Abstract

To address the shortcomings of existing fault diagnosis models for aero-engine gas path components, such as weak feature extraction capabilities and low diagnostic accuracy, this paper proposes a fault diagnosis model underpinned by the Fungal Growth Optimization (FGO) algorithm (FGO-1DCNN-LSTM). This model integrates a 1D convolutional neural network (1DCNN) and a long short-term memory network (LSTM). LSTM's strength in extracting temporal features compensates for the limitations of 1DCNN in processing time-series data. A split-path convolutional fusion module is introduced into the 1DCNN, enabling parallel input of sensor data, thus enhancing both the network's extraction capabilities and efficiency. Simultaneously, the FGO algorithm is incorporated to tackle the issue of hyperparameter optimization. To validate the model's performance, training and validation experiments were conducted using the N-CMAPSS dataset, which covers fault data under three typical operating conditions: low-altitude low-velocity, higher-altitude and higher-velocity, and high-altitude high-velocity. Experimental results indicate that the FGO-1DCNN-LSTM model attains fault diagnosis accuracies of 90.74%, 91.67%, and 94.44% under three operating conditions, significantly outperforming the 1DCNN and LSTM models. In comparison with the unoptimized 1DCNN-LSTM model, its diagnostic accuracy is improved by 2.78%, 10.19%, and 3.7%, respectively. The results provide evidence that the FGO-1DCNN-LSTM model can effectively achieve accurate identification and diagnosis of faults in aero-engine gas path components.