Bearings are indispensable and key components in rotating machinery. To ensure the safe and reliable operation of rotating machinery, bearing fault diagnosis plays a crucial role. To explore the spatial and temporal information in vibration signals, a novel bearing fault diagnosis method is proposed by combining a deep residual shrinkage network (DRSN) and bidirectional long short-term memory (Bi-LSTM) network in this study. Firstly, a DRSN is employed to extract the spatial features from noise-related vibration signals. Then, a Bi-LSTM network is adopted to further address the long-term dependencies problem in vibration signals, where the temporal information is exploited. By integrating DRSN and Bi-LSTM, the spatial and temporal information of vibration signals is fully extracted. Finally, a fully connected layer with Softmax is used to offer the diagnostic results. Experimental results using two case studies demonstrate the effectiveness of the proposed method by comparison with other state-of-the-art methods.

Insufficient and imbalanced samples pose a significant challenge in bearing fault diagnosis, leading to low diagnosis accuracy. However, the fault characteristics of vibration signals are weak and difficult to extract when faults occur in the early stage. This paper proposes an effective fault diagnosis method that addresses small and imbalanced sample problems under noise interference. First, the number of faulty samples in the form of 1D signals is increased mainly by the sliding split sampling method. The preprocessed data are used to create 2D time–frequency diagrams using the continuous wavelet transform (CWT), which can extract effective features to improve the data quality. Subsequently, the minority samples are oversampled by combining synthetic minority oversampling technique to realize time–frequency conversion augmented oversampling. Moreover, the clustering method and random undersampling method are introduced to prevent the overfitting and underfitting problems respectively. Then, we propose a hybrid attention mechanism to enhance the extraction of effective feature information. This combination, integrating CWT with a multicolumn modified deep residual network, effectively extracts fault characteristics and suppresses noise effects. The experimental results demonstrate the effectiveness of the proposed method by comparison with other advanced methods using two case studies of bearing datasets.

Rate-dependent hysteresis nonlinearity in piezoelectric actuators severely limits micro- and nanoscale system performance. It is necessary to establish a dynamic model to describe the full behavior of rate-dependent hysteresis. In this article, the Elman neural network–based hysteresis model is developed for piezoelectric actuators. An improved dynamic hysteretic operator is proposed to transform the multi-valued mapping of hysteresis into one-to-one mapping on a newly constructed expanded input space. Then, Elman neural network incorporated with the improved dynamic hysteretic operator is utilized to approximate the behavior of rate-dependent hysteresis. The combination of Elman neural network and the improved dynamic hysteretic operator can dually embody the dynamic property and is capable of fully extracting the characteristics of rate-dependent hysteresis. The experimental results are presented to illustrate the potential of the proposed modeling technique.

Magnetorheological dampers are promising vibration control devices that are widely used for vibration mitigation applications. However, due to the inherent hysteresis of magnetorheological dampers, achieving high performance is a challenging issue because it requires the development of models that can accurately describe the unique characteristics of this hysteresis. In this article, first, a generalized hysteretic biviscous operator is proposed to roughly describe the hysteretic property. Then, the superposition of the weighted generalized hysteretic biviscous operators is performed to model the magnetorheological damper, and modified particle swarm optimization is utilized to regulate the weights. This methodology provides the hybrid model with the advantages of both parametric and non-parametric models. Moreover, the model has a rather simple architecture and can be easily determined. The experimental results demonstrate the feasibility of the proposed method.