The instability of lithium-ion batteries may result in system operation failure and cause safety accidents, thus predicting the remaining useful life (RUL) accurately is helpful for reducing the risk of battery failure and extending its useful life. In this paper, a hybrid model based on TCN-GRU-DNN and dual attention mechanism is proposed for enhancing the RUL prediction accuracy of lithium-ion batteries. Firstly, the Temporal Convolutional Network (TCN) with a feature attention mechanism is applied to form an encoder module to capture the battery capacity regeneration phenomenon, and then a Gated Recurrent Unit (GRU) with a temporal attention mechanism is denoted as a decoder module for better characterizing the decay trend of the capacity series. Finally, the final prediction results are output through a Deep Neural Network (DNN). We conducted experiments on two data sets NASA and CALCE. The prediction errors are presented in subsequent experiments under different evaluation standards such as absolute error (AE), root mean square error (RMSE), mean absolute error (MAE), and R-squared error (R²). The experimental results demonstrate that the proposed model can achieve a more accurate prediction for RUL on lithium-ion batteries, with RMSE does not exceed 2.407% in the NASA dataset and does not exceed 0.897% in the CALCE lithium-ion battery dataset respectively.

A large amount of labeled data are important to enhance the performance of deep-learning-based methods in the area of fault diagnosis. Because it is difficult to obtain high-quality samples in real industrial applications, federated learning is an effective framework for solving the problem of sparse samples by using the distributed data. Its global model is updated by the local client without sharing data at each round. Considering computing resources and communication loss of multiple clients, an efficient method based on stacked sparse autoencoders (SSAEs) and Siamese networks is proposed to detect interturn short-circuit (ITSC) faults in permanent magnet synchronous motors. In this article, to achieve an accurate ITSC fault detection, an SSAE was employed to extract sparse features in a limited number of samples, and Siamese networks were used to determine the similarity between the given samples. The problem of fault diagnosis is transformed into a classification problem under few-shot learning. Furthermore, the proposed method is trained successfully in the frameworks of centralized learning and decentralized structure. The experimental results indicate that the proposed method achieved high fault diagnosis accuracy. Moreover, it is suitable for deployment in smart manufacturing systems.

Due to the diverse equipment and uneven load distribution in industrial environments, data regarding faults are often unbalanced. Moreover, data and models from clients may become contaminated or damaged, affecting diagnostic performance. To overcome these problems, this study proposes a stacking model for diagnosing interturn short circuit (ITSC) faults in permanent magnet synchronous motors (PMSMs). Federated learning (FL) is used to train the model to increase data security and overcome data islanding in distributed scenarios. Moreover, an improved verification strategy was adopted to select appropriate client models in each round to update the FL global model. We created a secondary server-side data set to validate the client weightings. The data set contains clean sample data for all ITSC fault categories. By calculating the fault diagnosis accuracy of the global model on the auxiliary data set, the model eliminates low-quality clients with uneven fault distributions. The improved particle swarm optimization (PSO) is used to optimize the weight coefficients of clients involved in aggregation, improving the robustness of the aggregation strategy under a joint learning system. In evaluation experiments, compared with the federated average (FedAvg) model, the proposed dynamic verification model exhibited the better diagnostic accuracy in situations of data imbalance, incurred lower communication costs, and prevented local oscillations in the model.

Smart manufacturing, which is increasingly popular worldwide, is aided by time-series forecasting. As the volume of historical data increases, powerful forecasting techniques that reveal unknown relationships between past and future values are required to provide accurate forecasts of production and sales. Thus, in this article, a composite gate recurrent unit (GRU)-Prophet model with an attention mechanism was constructed to predict sales volume. In this composite model, Prophet model and GRU model with attention mechanism were used to capture linear and nonlinear features, respectively. The composite model was experimentally determined to be more applicable and to provide more accurate predictions than did recurrent neural network, long short-term memory, gate recurrent unit, Prophet, and autoregressive integrated moving average models. This article's composite model is suited to rapid changes in market demand and helps enterprises be more competitive in the field of smart manufacturing.

Accurately predicting the remaining useful life (RUL) of lithium-ion batteries enables their timely replacement and ensures the proper operation of equipment. This study presents a novel hybrid approach for predicting nonlinear and nonsmooth battery capacity sequences. To develop this approach, first, the original battery capacity sequence was adaptively decomposed through Northern Goshawk Optimization (NGO)-Variational Mode Decomposition (VMD). NGO-VMD could efficiently extract useful information at different scales and could considerably reduce the complexity of the battery capacity sequence. Second, the decomposed sequences were grouped into high- and low-frequency components on the basis of the over-zero rate. A convolutional neural network-bidirectional long short-term memory model was then constructed to predict the low-frequency components, and a temporal convolutional network-attention mechanism-deep neural network model was developed to predict the high-frequency components. In addition, a tensor-based transfer learning approach was employed to predict the low-frequency components of capacity sequences from same-type batteries. The RUL prediction errors of the proposed approach did not exceed 2 cycles, which was fewer than those of other comparable approaches. Accordingly, the proposed approach has favorable generalizability and robustness.

With the rapid development of artificial intelligence, deep learning has become widely used to monitor the state of permanent magnet synchronous motors (PMSMs). However, to achieve accurate condition detection, datasets with large quantities of labeled data must be used for model training. Accuracy decreases considerably when the quantity of labeled data is insufficient. To address this problem, a fault diagnosis method based on an improved deep Q-network (DQN) is designed in this study to detect inter-turn short circuit (ITSC) faults. In this method, first, a one-dimensional group convolutional neural network–based conditional generative adversarial network is used to expand the collected dataset. Subsequently, a DQN-based fault diagnosis method is applied. A one-dimensional deep residual shrinkage network and the prioritized experience replay strategy are introduced into the original network structure, and the sampling strategy of the original network is optimized. Finally, the fault diagnosis capability of the proposed method was evaluated in several experiments. The proposed method considerably outperformed competing algorithms: it had a diagnosis rate of 98.49% for the ITSC faults of PMSMs and a diagnosis rate of 99.50% on the bearing dataset of Case Western University with certain generalizations. The proposed method is promising for use in circuit fault detection.