With the development of unmanned aerial vehicle (UAV) technology, a UAV is gradually applied to a variety of civil fields, such as photography, power line inspection, and environmental monitoring. At the same time, the safety and reliability of a UAV also attract wide attention. Anomaly detection is one of the key technologies to improve the safety of an UAV. The structure of the UAV system is complex, and there are complex spatio-temporal correlations among the high-dimensional flight data with many parameters. However, the existing methods often ignore the spatio-temporal correlation of data and lack parameter selection, which is used to abandon the parameters without a positive impact on anomaly detection results. This article proposes a spatio-temporal correlation based long short-term memory (LSTM) method for anomaly detection and recovery prediction of UAV flight data. First, an artificial neural network correlation analysis is proposed to preliminarily mine the spatio-temporal correlation in flight data and to obtain the correlation parameter sets. Second, the LSTM model is established, and the mapping among different parameters is realized. Finally, anomaly detection and recovery prediction are carried out based on parameter sets mapping model. The effectiveness of the proposed method is verified by generating sample sets with anomaly injection on real UAV flight data.

Benefited from the sampling signal from monitoring sensors installed in electro-mechanical actuator (EMA), data-driven methods, such as deep learning models that can mine adaptive features from monitoring signal, have received wide attention in EMA fault diagnosis. A generalized hypothesis accepted by previous efforts on EMA fault diagnosis, is that target domain datasets (i.e., testing monitoring signal) are drawn from the same distribution with source domain datasets (i.e., training monitoring signal). However, except for the different working loads and velocities, various driving signal waveforms also exits in EMA, which further increase the domain discrepancy challenge and decrease the performance of those deep learning models. Therefore, this paper proposes a deep learning domain adaptation method that introduces joint maximum mean discrepancy (JMMD) into convolutional neural network (CNN), which aims to reduce the domain difference between labeled source domain datasets and unlabeled target domain datasets. In order to simulate domain discrepancy phenomenon, the NASA EMA datasets, sampled from acceleration sensors under variable driving waveforms with different working loads and velocities, are considered in this paper. Experiment results indicate that CNN-JMMD method can reduce the distribution difference and improve the diagnosis accuracy in source and target domains. In comparison with several available methods, extensive experimental evaluations on six domain tasks indicate the effectiveness of the proposed method. In addition, better performance has been obtained by selecting the proper trade-off factor between CNN and JMMD.

In a complex system, condition monitoring (CM) can collect the system working status. The condition is mainly sensed by the pre-deployed sensors in/on the system. Most existing works study how to utilize the condition information to predict the upcoming anomalies, faults, or failures. There is also some research which focuses on the faults or anomalies of the sensing element (i.e., sensor) to enhance the system reliability. However, existing approaches ignore the correlation between sensor selecting strategy and data anomaly detection, which can also improve the system reliability. To address this issue, we study a new scheme which includes sensor selection strategy and data anomaly detection by utilizing information theory and Gaussian Process Regression (GPR). The sensors that are more appropriate for the system CM are first selected. Then, mutual information is utilized to weight the correlation among different sensors. The anomaly detection is carried out by using the correlation of sensor data. The sensor data sets that are utilized to carry out the evaluation are provided by National Aeronautics and Space Administration (NASA) Ames Research Center and have been used as Prognostics and Health Management (PHM) challenge data in 2008. By comparing the two different sensor selection strategies, the effectiveness of selection method on data anomaly detection is proved.

Electro-Mechanical Actuators (EMA) have attracted growing attention with their increasing incorporation in More Electric Aircraft. The performance degradation assessment of EMA needs to be studied, in which EMA motor voltage is an essential parameter, to ensure its reliability and safety of EMA. However, deviation exists between motor voltage monitoring data and real motor voltage due to electromagnetic interference. To reduce the deviation, EMA motor voltage estimation generally requires an accurate voltage state equation which is difficult to obtain due to the complexity of EMA. To address this problem, a Feature-aided Kalman Filter (FAKF) method is proposed, in which the state equation is substituted by a physical model of current and voltage. Consequently, voltage state data can be obtained through current monitoring data and a current–voltage model. Furthermore, voltage estimation can be implemented by utilizing voltage state data and voltage monitoring data. To validate the effectiveness of the FAKF-based estimation method, experiments have been conducted based on the published data set from NASA’s Flyable Electro-Mechanical Actuator (FLEA) test stand. The experiment results demonstrate that the proposed method has good performance in EMA motor voltage estimation.

Electro-Mechanical Actuator (EMA) is a key component in the flight control actuation of the more electric aircraft. The degradation of EMA has a significant influence on its performance. Hence, the degradation estimation of EMA need to be studied, which is an important part of the health monitoring of EMA. However, the multiple failure modes of EMA bring much difficulty for implementing degradation estimation. To solve this problem, a fusion degradation estimation method based on Continuous Hidden Markov Model (CHMM) and Generalized Linear Model (GLM) (i.e., Multiple CHMMGLM) is proposed for EMA with multiple failure modes. Firstly, Health Indicator (HI) extraction models are formulated based on CHMM for multiple failure modes to extract HIs, which can be used to indicate the degradation degree of EMA. Secondly, the fusion degradation model for EMA with multiple failure modes is formulated based on the extracted HIs and GLM, in which the nonlinearity of a single HI and the coupling among multiple HIs are both considered. Finally, the output of the fusion degradation model is regarded as a HI to indicate the degradation degree of EMA. This study provides a new way for the degradation estimation of EMA with multiple failure modes, which can contribute to the Prognostics and Health Management (PHM) development of EMA. To evaluate the effectiveness of the proposed method, experiments are conducted utilizing EMA simulation and practical data. Experimental results show that the proposed method has a good performance in the degradation estimation for EMA with multiple failure modes.