There are some problems such as uncertain thresholds, high dimension of monitoring parameters and unclear parameter relationships in the anomaly detection of aero-engine gas path. These problems make it difficult for the high accuracy of anomaly detection. In order to improve the accuracy of aero-engine gas path anomaly detection, a method based on Markov Transition Field and LSTM is proposed in this paper. The correlation among high-dimensional QAR data is obtained based on Markov Transition Field and hierarchical clustering. According to the correlation analysis of high-dimensional QAR data, a multi-input and multi-output LSTM network is constructed to realize one-step rolling prediction. A Gaussian mixture model of the residuals between predicted value and true value is constructed. The three-sigma rule is applied to detect outliers based on the Gaussian mixture model of the residuals. The experimental results show that the proposed method has high accuracy for aero-engine gas path anomaly detection.

The aero-engine is the heart of an aircraft; its performance deteriorates rapidly due to the high temperature and high-pressure environment during flights. It is necessary to predict the remaining useful life (RUL) to improve the reliability of aero-engines and provide security for reliable flights. In previous flights, the sensors collected a lot of performance parameter data and formed a database regarding the aero-engine degradation process. These performance parameters cannot reflect the degradation process directly. In this paper, fuzzy clustering is applied to divide the degradation stages of the aero-engine, construct the health indicator, and describe the degradation process. Time-series decomposition modeling is applied to predict the degradation process of the health indicator. Based on the idea of similarity comparison, the RUL is predicted by comparing the similarity of time series through example learning. The method is verified and analyzed on the dataset published by National Aeronautics and Space Administration (NASA), and the mean square error (MSE) is 528. The result is better than the comparative method.

Remaining useful life (RUL) prediction is the main approach to guarantee the reliability of lithium-ion batteries. This paper proposes an interpretable hybrid method to predict the RUL distribution with changeable form. The method integrates prior knowledge from the statistical model and regular patterns learned from monitoring data based on the data-driven model. The predicted compound distribution provides more information compared to point estimation and distribution with fixed form. The general hybrid framework contains a component learner, a fusion model with a stacking strategy, and a prognostic distribution algorithm with adaptive sampling weights. The stacking fusion model is implemented by a one-dimensional convolution neural network. The sampling weights are estimated by optimal estimation. The statistical model describes the individual capacity degradation path based on the Wiener process. The data-driven model learns the degradation process from historical data based on convolutional gated recurrent neural network (CNN-GRU) and Monte Carlo dropout simulation. The comparative experiments between the proposed method and existing methods were carried out. The experiment results show that the proposed hybrid method performs well.

An Inertial Measurement Unit (IMU) is a significant component of a spacecraft, and its fault diagnosis results directly affect the spacecraft’s stability and reliability. In recent years, deep learning-based fault diagnosis methods have made great achievements; however, some problems such as how to extract effective fault features and how to promote the training process of deep networks are still to be solved. Therefore, in this study, a novel intelligent fault diagnosis approach combining a deep residual convolutional neural network (CNN) and a data preprocessing algorithm is proposed. Firstly, the short-time Fourier transform (STFT) is adopted to transform the raw time domain data into time–frequency images so the useful information and features can be extracted. Then, the Z-score normalization and data augmentation strategies are both explored and exploited to facilitate the training of the subsequent deep model. Furthermore, a modified CNN-based deep diagnosis model, which utilizes the Parameter Rectified Linear Unit (PReLU) as activation functions and residual blocks, automatically learns fault features and classifies fault types. Finally, the experiment’s results indicate that the proposed method has good fault features’ extraction ability and performs better than other baseline models in terms of classification accuracy.

Metal roof sheathings are widely employed in large-span buildings because of their light weight, high strength and corrosion resistance. However, their severe working environment may lead to deformation, leakage and wind-lift, etc. Thus, predicting these damages in advance and taking maintenance measures accordingly has become important to avoid economic losses and personal injuries. Conventionally, the health monitoring of metal roofs mainly relies on manual inspection, which unavoidably compromises the working efficiency and cannot diagnose and predict possible failures in time. Thus, we proposed a novel damage monitoring scheme implemented by laying bend sensors on vital points of metal roofs to precisely monitor the deformation in real time. A fast reconstruction model based on improved Levy-type solution is established to estimate the overall deflection distribution from the measured data. A standing seam metal roof under wind pressure is modeled as an elastic thin plate with a uniform load and symmetrical boundaries. The superposition method and Levy solution are adopted to obtain the analytical model that can converge quickly through simplifying an infinite series. The truncation error of this model is further analyzed. Simulation and experiments are carried out. They show that the proposed model is in reasonable agreement with the experimental results.