Data-driven ensemble deep learning approach for rolling bearing failures monitoring using multiple source data

An improved CNN–Transformer–ELM framework with residual shrinkage networks for bearing fault diagnosis

Deep Learning Approaches for Bearing Fault Diagnosis Using Motor Current Signals

Motor Current Signature Analysis (MCSA) is a non-invasive technique that enables the detection of bearing faults in rotating electrical machines without the need for additional sensors. In this study, the Paderborn University bearing dataset was utilized to perform a two-stage analysis. In the first stage, motor current data were processed directly using 1-Dimensional Convolutional Neural Networks (1D-CNN). In the second stage, scalogram images obtained via Continuous Wavelet Transform (CWT) were used to train five different deep learning models, with the ResNet18-based 2D-CNN model providing the best performance. To prevent data leakage, the training and testing sets were partitioned based on individual bearings to ensure complete isolation. The experimental results demonstrated that both 1D-CNN and ResNet18-based 2D-CNN methods achieved 100% accuracy in detecting outer race faults. However, it was observed that the impact of inner race faults on the stator current remains weak due to the complex physical transmission path of the fault signal, resulting in significantly lower detection rates.

Unsupervised Hybrid Deep Learning for Unknown Bearing Fault Diagnosis and Severity Assessment

An unsupervised hybrid deep learning framework for unknown bearing fault diagnosis and severity assessment using vibration signals that combines Continuous Wavelet Transform, Convolutional Neural Networks, and Long Short-Term Memory autoencoders is presented.

A Hybrid CNN-BiLSTM Deep Learning Framework for Predictive Maintenance in Industry 4.0 Using Multivariate Time-Series Sensor Data

Unplanned equipment failure remains one of the costliest problems in modern manufacturing, driving research toward Predictive Maintenance (PdM) strategies that anticipate failures before they occur using real-time sensor data. This paper proposes a hybrid deep learning framework combining Convolutional Neural Networks (CNN) for local spatial feature extraction and Bidirectional Long Short-Term Memory (BiLSTM) networks with a temporal attention mechanism for capturing long-range degradation trends in multivariate time-series sensor data. The framework is designed to estimate Remaining Useful Life (RUL) and detect early fault signatures in Industry 4.0 environments equipped with IoT-based condition-monitoring sensors. We formulate the problem as a windowed sequence-to-value regression task, describe a sliding-window feature pipeline, and benchmark the framework's data pipeline against classical machine learning regressors (Random Forest, Gradient Boosting, Support Vector Regression, and a Multi-Layer Perceptron) on a run-to-failure sensor dataset. Experimental results show that ensemble tree-based models achieve strong baseline performance (RMSE as low as 9.96 cycles, R2 = 0.946), establishing a validated pipeline and baseline for the full CNN-BiLSTM-Attention model. The proposed architecture, evaluation protocol, and ablation plan are presented in full so the framework can be reproduced and extended on industrial-scale datasets such as NASA C-MAPSS or live plant telemetry.

An ensemble attention-based residual convolutional neural network for rolling bearing fault diagnosis

Rolling bearings are essential components in mechanical systems, whose fault diagnosis is vital for operational efficiency. But in real industrial environments, the harsh conditions, including noise, missing data, and compound faults, severely limit the diagnostic performance of the algorithm. Thus, we propose an ensemble attention-based residual convolutional neural network (CNN) optimized by the vortex search algorithm. First, a new residual CNN with the improved residual structure, the separable convolution, and the global average pooling layer is designed to extract features from the vibration signals automatically. Second, a residual cooperative attention mechanism is presented. To guarantee the difference between the base models, different base models are constructed employing multiple convolutional kernels, activation functions, as well as attention mechanisms, respectively. And different training sets are allocated to each base model by Bootstrap. Third, a new exponential threshold decision fusion strategy is put forward to achieve ensemble learning. Eventually, the vortex search algorithm is employed to optimize the parameters of the decision fusion strategy. The noise, missing data, and compound fault datasets constructed separately using data from two rolling bearing experiments reveal that the proposed ensemble model can effectively overcome the limitations of individual models and achieve superior fault identification performance than existing methods under many types of severe conditions.

Domain-generalized multi-channel fusion for bearing fault diagnosis under variable operating conditions

To address the issues of low accuracy and insufficient generalization capabilities in traditional methods for diagnosing bearing faults under variable operating conditions, we propose a vision-temporal bimodal multi-channel feature fusion method for rolling bearing fault diagnosis based on domain generalization (DG). This approach constructs a parallel architecture for extracting bimodal features: on one hand, multiple signal processing techniques are employed to transform raw vibration signals into multi-perspective two-dimensional visual feature maps as visual modality input, while simultaneously employing variational modal decomposition to decompose vibration signals into a series of eigenmode functions constituting the temporal modality input. At the model level, a multi-channel large-kernel convolutional network and a global attention-enhanced bidirectional gated recurrent unit network are designed to extract deep features from the visual and temporal modalities, respectively. Subsequently, feature vectors from each channel are concatenated in the feature dimension, with fault classification performed via a progressive dimensionality reduction classifier. Experiments conducted using bearing datasets from case western reserve university and the University of Paderborn in Germany demonstrate that this method can diagnose bearing failures under cross-conditions—even when trained solely on source-domain data and without exposure to target-domain data during training—and that its DG accuracy outperforms that of existing mainstream advanced methods.