Health monitoring of electro-mechanical actuator (EMA) is critical to ensure the security of airplanes. It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA. The autoencoder based on reconstruction loss is a popular model that can carry out anomaly detection with only consideration of normal training data, while it fails to capture spatio-temporal information from multivariate time series signals of multiple monitoring sensors. To mine the spatio-temporal information from multivariate time series signals, this paper proposes an attention graph stacked autoencoder for EMA anomaly detection. Firstly, attention graph convolution is introduced into autoencoder to convolve temporal information from neighbor features to current features based on different weight attentions. Secondly, stacked autoencoder is applied to mine spatial information from those new aggregated temporal features. Finally, based on the benchmark reconstruction loss of normal training data, different health thresholds calculated by several statistic indicators can carry out anomaly detection for new testing data. In comparison with traditional stacked autoencoder, the proposed model could obtain higher fault detection rate and lower false alarm rate in EMA anomaly detection experiment.

As one of the hydraulic control systems of an aircraft, the hydraulic drive system of the aircraft cabin door can cause severe impact on the safe operation of the plane once failed. In order to enhance the safety and reliability of the hydraulic drive system of the aircraft cabin door, this paper takes the rotary hydraulic drive system of the aircraft cabin door as the research object, and analyzes its working principle. Additionally, five types of potential failures are summarized, including gain reduction fault in angular displacement sensors, blockage fault in flow control valves, air pollution fault, leakage fault in motor plungers, and motor plunger failure fault. Using the AEMSim software to establish a fault simulation model, the fault characteristics of the system under various fault conditions can be studied, which can effectively reduce the cost of physical simulation and testing, improve design efficiency and provide simulation data for other research.

A common necessity for prior unsupervised domain adaptation methods that can improve the domain adaptation in unlabeled target domain dataset is access to source domain dataset and target domain dataset simultaneously. However, data privacy makes it not always possible to access source domain dataset and target domain dataset in actual industrial equipment simultaneously, especially for aviation component like Electro-Mechanical Actuator (EMA) whose dataset are often not shareable due to the data copyright and confidentiality. To address this problem, this paper proposes a source free unsupervised domain adaptation framework for EMA fault diagnosis. The proposed framework is a combination of feature network and classifier. Firstly, source domain datasets are only applied to train a source model. Secondly, the well-trained source model is transferred to target domain and classifier is frozen based on source domain hypothesis. Thirdly, nearest centroid filtering is introduced to filter the reliable pseudo labels for unlabeled target domain dataset, and finally, supervised learning and pseudo label clustering are applied to fine-tune the transferred model. In comparison with several traditional unsupervised domain adaptation methods, case studies based on low- and high-frequency monitoring signals on EMA indicate the effectiveness of the proposed method.