With the widespread application of deep learning in Internet of Things (IoT), remarkable achievements have been made especially in rolling bearing fault diagnosis in rotating machinery. However, such complex models commonly have high demand for a large number of parameters and computational resources, and with insufficient interpretability, which restrict their extensive application in real-world industrial applications. To improve efficiency and interpretability, this study innovatively fuses a quadratic neural network (QNN) with a bidirectional long and short-term memory network (Bi-LSTM) to develop a novel hybrid model for quick and accurate diagnosis of rolling bearing faults. The results show that the model fully utilizes the multilayer feature extraction of QNN and the sensitivity of Bi-LSTM to the dynamic evolution of signals to significantly improve the accuracy and speed of fault diagnosis. By visualizing the convolutional kernel response map, the Qttention mapping of QNN, and the hidden states of Bi-LSTM, this study makes progress in interpretability and successfully demonstrates the model’s attention to different features of the bearing signals, which provides users with a more reasonable understanding of the interpretation of the model results.

Due to the complex changes in physicochemical properties of lithium-ion batteries during the process from degradation to failure, it is difficult for methods based on physical or data-driven models to fully characterize this nonlinear process, and existing methods that hybridize physical and data-driven models suffer from ambiguous hybridization, which results in the vast majority of existing methods for predicting the remaining useful life (RUL) of lithium-ion batteries suffering from a lack of accuracy and robustness. In this study, a novel hybrid approach based on empirical modeling and data-driven techniques is proposed for predicting the RUL of lithium-ion batteries. To better capture its complexity, stochasticity, and state transition, and improve the modeling accuracy and RUL prediction precision, Gamma stochasticity and state-space modeling are used to empirically model the complex Li-ion battery degradation process. Moreover, the expectation maximization (EM) method of particle filtering (PF) was used to estimate the hidden parameters of the empirical model, and the estimated parameters were corrected using an optimized support vector regression (SVR) method to enhance the generalization performance and robustness of the data-driven model. The results show that the gamma state-space model is effective in capturing the inherent stochastic properties of the battery degradation and the proposed hybrid method outperforms the existing prediction methods in RUL prediction. The experiments show that the sparrow search algorithm (SSA) optimized SVR is considered to be the most effective correction method for the estimated parameters, while the new EM-PF-SSA-SVR hybrid method provides better performance for state assessment and RUL prediction of lithium-ion batteries. It is indicated that the proposed EM-PF-SSA-SVR method with Gamma stochastic process has hybrid validity and superior performance with equal performance and less parameter computation relative to the existing state-of-the-art deep learning RUL prediction methods.

With the rapid development of fault prognostics and health management (PHM) technology, more and more deep learning algorithms have been applied to the intelligent fault diagnosis of rolling bearings, and although all of them can achieve over 90% diagnostic accuracy, the generality and robustness of the models cannot be truly verified under complex extreme variable loading conditions. In this study, an end-to-end rolling bearing fault diagnosis model of a hybrid deep neural network with principal component analysis is proposed. Firstly, in order to reduce the complexity of deep learning computation, data pre-processing is performed by principal component analysis (PCA) with feature dimensionality reduction. The preprocessed data is imported into the hybrid deep learning model. The first layer of the model uses a CNN algorithm for denoising and simple feature extraction, the second layer makes use of bi-directional long and short memory (BiLSTM) for greater in-depth extraction of the data with time series features, and the last layer uses an attention mechanism for optimal weight assignment, which can further improve the diagnostic precision. The test accuracy of this model is fully comparable to existing deep learning fault diagnosis models, especially under low load; the test accuracy is 100% at constant load and nearly 90% for variable load, and the test accuracy is 72.8% at extreme variable load (2.205 N·m/s–0.735 N·m/s and 0.735 N·m/s–2.205 N·m/s), which are the worst possible load conditions. The experimental results fully prove that the model has reliable robustness and generality.

This study proposes an efficient rolling bearing fault diagnosis model of a hybrid neural network with a lightweight attention mechanism. Firstly, to achieve the low complexity of deep learning (DL) computation, data reduction and denoising are performed by sparse convolutional network (principal component analysis and improved complete ensemble empirical modal decomposition of adaptive noise), then processed data is imported to the hybrid neural network model with convolutional block attention module. The bi-directional long short-term memory and sparse convolutional networks are used in the backbone of the model. A lightweight, generalized attention mechanism is introduced to the last layer of the model for enhancing feature learning, which can further improve the diagnostic accuracy and efficiency. Compared with existing DL fault diagnosis models, In simulating the most realistic cross-conditions and cross-platform conditions, which leads to the random nature of fault generation and makes model diagnosis more complex, the proposed method still maintains less running time and excellent diagnostic accuracy. Finally, the experimental results fully prove that the model has reliable robust and efficient, and it achieves the best balance of diagnostic accuracy and diagnostic efficiency of the hybrid DL model.

As the most popular power source equipment in commercial aviation, turbofan engines face problems such as difficulties in data acquisition and unbalanced data sets. In addition, it is enormously challenging to construct a realistic remaining useful life (RUL) prediction model that can be applied because of the complex physical mechanisms involved in turbofan engine operation and the strong nonlinear properties of the data collected by multiple sensors. Moreover, most of the existing RUL prediction models lack interpretability. Therefore, in this study, a 3D Attention-enhanced hybrid neural network is proposed to solve the RUL prediction problem of turbofan engines. The model employs a convolutional network to extract local features from sensor data and uses a bi-directional long short-term memory (BiLSTM) framework to learn long-dependent nonlinear features. To enhance the learning capability of the model, this study incorporates a 3D attention module capable of balancing space and channels to visualize and analyze the action weights learned by the neural network through the attention mechanism, and the proposed attention module is found to have good robustness and generalization performance with good interpretability. In addition, handcrafted features with degradation trend coefficients and average degradation values are used as auxiliary inputs for all-round learning of the hybrid model in this study. Finally, tested on a real C-MAPSS benchmark dataset, the proposed method in this study has the most superior performance and better practical application compared with existing advanced RuL prediction methods.