Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are unable to learn the relevant information of input data when the input gap is large. By introducing gate functions into the cell structure, the long short-term memory (LSTM) could handle the problem of long-term dependencies well. Since its introduction, almost all the exciting results based on RNNs have been achieved by the LSTM. The LSTM has become the focus of deep learning. We review the LSTM cell and its variants to explore the learning capacity of the LSTM cell. Furthermore, the LSTM networks are divided into two broad categories: LSTM-dominated networks and integrated LSTM networks. In addition, their various applications are discussed. Finally, future research directions are presented for LSTM networks.

Due to the inner deteriorating mechanism or the mutant environmental stress, the degradation systems with multi-phase features have frequently been encountered in engineering practice. The key issue for prognostics of such systems is to account for the impact of the changing-point variability and the associated degradation state at this point on the progression of the degradation process. However, current studies usually treat the degradation state at the change point as a fixed value rather a random variable. Thus, it is still challenging to predict the lifetime of such multi-phase degrading systems. To this end, we first formulate a general degradation modeling framework based on a two-phase Wiener process. In prognostics, we take into full account the uncertainty of the degradation state at the changing point and then derive the analytical expressions of the lifetime and remaining useful life under the concept of the first passage time. The derived results are distinguished from existing results limited to the fixed state at the changing point. Furthermore, we extend our approach and results to cases with unit-to-unit variability and multiple phases. To facilitate the model implementation, we propose both offline and online methods for parameter identification, which make full use of the historical data and the in-service data. Finally, a numerical simulation and a practical case study are provided for illustration.

Inter-turn short circuit (ITSC) fault is one of the critical electrical faults in induction motors that affects the reliability of many industrial applications. Although the use of data-driven fault detection techniques have gained much interest, the main deterrent in using these approaches in detecting ITSC faults is in the generalization and robustness of the diagnosis. In this paper, a data-driven on-line fault detection framework, incorporated with multi-feature extraction/selection and multi-classifier ensemble is proposed, capable of detecting ITSC faults in induction motors (IMs) that subjected to variable operating conditions. By using the synchronous time series signals collected from the machines, multiple feature extraction/selection is explored to find the sensitive faulty features, and the different types of classification strategies is used to increase the diversity of single based models. With the increased diversity of the base learners, the fault detection accuracy is expected to be enhanced and the robustness can be guaranteed. The framework was implemented and tested using real data collected from a designed test bed, with the experimental results showing the effectiveness of the framework in detecting ITSC faults in IMs.

Ship detection plays an important role in synthetic aperture radar (SAR) image interpretation. However, there are still some difficulties in SAR ship detection. First, ships often have a large aspect ratio and arbitrary directionality in SAR images. Traditional detection algorithms can cause the detection area to be redundant, which makes it difficult to accurately locate the target in complex scenes. Second, ships in ports are often densely arranged, and the effective identification of densely arranged ships is complicated. Finally, ships in SAR images exist at a variety of scales due to the multiresolution imaging modes used and ship shape variations, which pose a considerable challenge for ship detection. To solve the above problems, we propose a multiscale adaptive recalibration network (MSARN) to detect multiscale and arbitrarily oriented ships in complex scenarios. The recalibration of the extracted multiscale features through global information increases the sensitivity of the network to the target angle, thereby increasing the accuracy of positioning. In particular, we designed a pyramid anchor and a loss function to match the rotated target. In addition, we modified the rotation non-maximum suppression (RNMS) method to solve the problem of the large overlap ratio of the detection box. The proposed model combines the positioning advantage of rotation detection with the speed advantage of a single-stage framework. Experiments show that based on the SAR rotation ship detection (SRSD) data set, the proposed algorithm has a faster detection speed and higher accuracy than some state-of-the-art methods.

As the central component of prognostic and health management (PHM) field, remaining useful life (RUL) estimation approaches based on degradation modeling have played an extremely significant role in recent years. For the newly developed systems working in complex environments, the associated degradation processes not only lack historical data and prior information, but also have strong nonlinearity and three-source variability. Therefore, this paper proposes an adaptive RUL estimation approach for newly developed system based on nonlinear model. Specifically, a general nonlinear Wienerprocess-based degradation model is established to simultaneously characterize three-source variability and nonlinearity, and the associated RUL distribution is derived with an explicit form. In order to utilize the condition monitoring (CM) data of the service system up to date, we present a parameter estimation method based on the expectation maximization algorithm to adaptively estimate and update the model parameters online. As such, the RUL distribution can be updated once the new CM data are available. Finally, the effectiveness and superiority of the proposed method are demonstrated by the numerical example and empirical study for battery data. The results show that the proposed method can provide accurate and robust RUL prediction for the newly developed system.

Owing to operating condition changing, physical mutation, and sudden shocks, degradation trajectories usually exhibit multi-phase features, and the abrupt jump often appears at the changing time, which makes the traditional methods of lifetime estimation unavailable. In this paper, we mainly focus on how to estimate the lifetime of the multi-phase degradation process with abrupt jumps at the change points under the concept of the first passage time (FPT). Firstly, a multi-phase degradation model with jumps based on the Wiener process is formulated to describe the multi-phase degradation pattern. Then, we attain the lifetime’s closed-form expression for the two-phase model with fixed jump relying on the distribution of the degradation state at the change point. Furthermore, we continue to investigate the lifetime estimation of the degradation process with random effect caused by unit-to-unit variability and the multi-phase degradation process. We extend the results of the two-phase case with fixed parameters to these two cases. For better implementation, a model identification method with off-line and on-line parts based on Expectation Maximization (EM) algorithm and Bayesian rule is proposed. Finally, a numerical case study and a practical example of gyro are provided for illustration.