Accurate prediction of wind power generation is of great significance for the efficient operation of wind farms. However, traditional deep learning-based methods predict the wind power without simultaneously considering the temporal features of wind power and spatial features between variables, which leads to low prediction accuracy. This article proposes a novel wind power forecasting approach based on a graph convolution network (GCN) and a multiresolution convolution neural network (CNN), combining spatial features and temporal features. In this approach, GCN merged with maximum information coefficient (MIC) is proposed to extract the spatial correlation features between input variables, which considers the effects of multiple variables on wind power and provides interpretability for deep learning-based forecasting. On the other hand, multiresolution CNN combines multiscale convolution kernels with a new self-attention mechanism to understand local and long-term temporal features, which enables simultaneous prediction of wind power and other variables. Experiments on a real dataset prove that the proposed method is effective and accurate in short-term wind power forecasting. Comparisons with the other three state-of-the-art methods and ablation experiments also reveal the advantages of the proposed approach.

The telemetry data obtained from an on-orbit spacecraft contain important information to indicate anomaly of the spacecraft. However, the large number of monitoring variables and the large amount of data points, as well as the lack of prior knowledge about anomaly due to complicated structure of spacecraft and its working conditions, pose great challenge to the anomaly detection. This article proposes an anomaly detection algorithm based on a spatial-temporal generative adversarial network (GAN) for the anomaly detection in telemetry data. This algorithm establishes a GAN-based model combining convolutional neural network (CNN) and long short-term memory (LSTM) to extract spatial and temporal features of the telemetry data, which facilitates the automatic and simultaneous representation of nonnegligible time-related characteristics of a monitoring variable and complex correlation between variables. Using these features, many kinds of anomalies including multivariate anomalies and contextual anomalies can be detected. Moreover, an anomaly score specifically designed to fit the GAN-based algorithm is also proposed to evaluate the possibility of anomaly by weighted fusion of the generator metric and the discriminator metric, which is proved to be significantly helpful to the accuracy of anomaly detection. Finally, experiments on one real telemetry data set and two public telemetry data sets are conducted, by which the proposed anomaly algorithm is demonstrated to be effective and accurate in detecting outliers in telemetry data. Comparison with three other state-of-the-art methods also reveals the advantages of our proposed algorithm.

Voltage fault diagnosis is critical for detecting and identifying the lithium (Li)-ion battery failure. This article proposes a voltage fault diagnosis algorithm based on an equivalent circuit model-informed neural network (ECMINN) method for Li-ion batteries, which aims to learn the voltage fault observer by embedding the equivalent circuit model (ECM) into neural network structures. This method directly embeds the deterministic mechanism part in the ECM and designs the uncertain part into neural networks, which takes advantage of the high precision of the physical model and the strong nonlinear processing ability of the neural network to improve the fault diagnosis effect. In this method, the voltage prediction module and residual-based parameter calibration module are developed to describe state space equations and automatically learn the state parameters and model parameters, respectively. Moreover, a fault score specifically designed by combining the identified model parameters is presented, which is proved to be effectively in detecting different fault types. Finally, experiments on two public datasets are conducted, by which the proposed ECMINN method is demonstrated to be effective and accurate in predicting voltage data and detecting faults. Comparison with three other state-of-the-art methods also reveals the advantages of the proposed ECMINN method.

Remaining useful life (RUL) prediction of rolling bearings brings benefits for maintenance of spacecrafts. Vibration signals are widely used for RUL prediction. However, under some situations such as high-speed rotation of bearings, vibration signals are quite easily disturbed by noise and might be tough to collect due to inappropriate installation of accelerometers. Therefore, in this paper, stator current signals are considered as health indicator for bearing RUL prediction. Based on stator current signals, feature extraction and trajectory tracking of signals suffer two challenges: 1) degradation tracking of downlinked stator current data is restricted due to low-frequency downlink from spacecrafts to stations; 2) the accuracy of health state estimation is constrained by artificial feature selection and prior knowledge about bearings. To overcome these issues, a novel RUL prediction approach is proposed in this work. An adaptive feature selection strategy based on autoregression model and backpropagation neural network is applied. Finally, an improved RUL prediction framework is introduced under down-sampled signals, which combines compressed sensing and deep learning model. A case from Paderborn university and a case from life test of bearing on control moment gyro were investigated. Experimental results support the validity of proposed approach in terms of lower prediction error than related works.

Efficient anomaly detection in telemetry time series is of great importance to ensure the safety and reliability of spacecraft. However, traditional methods are complicated to train, have a limited ability to maintain details, and do not consider temporal-spatial patterns. These problems make it still a challenge to effectively identify anomalies for multivariate time series. In this paper, we propose Denoising Diffusion Time Series Anomaly Detection (DDTAD), an unsupervised reconstruction-based method using a denoising diffusion probabilistic model. Our model offers the advantages of training stability, flexibility, and robust high-quality sample generation. We employ 1D-U-Net architecture to capture both temporal dependencies and inter-variable information. We restore the anomalous regions from the noise-corrupted input while preserving the precise features of the normal regions intact. Anomalies are identified as discrepancies between the original time series input and its corresponding reconstruction. Experiments on two public datasets demonstrate that our method outperforms the current dominant data-driven methods and enables the accurate detection of point anomalies, contextual anomalies, and subsequence anomalies.