Rotatory Machine Fault Detection Using CNNs on Spectrogram Signal Data

A convolutional neural network (cnn)-based classification of rotary machine vibration and acoustic signals

Multi-sensor configurations incorporating acoustic data demonstrated faster convergence while maintaining perfect classification performance, achieving high classification accuracy across multiple sensor configurations, including single-sensor and fused measurements.

1D-CNN-Based Fault Diagnosis for Traction Motors Using Vibration and Current Signals

Accurate defect detection of traction motors is essential for preserving the performance and safety of electric cars and industrial gear. This research presents a onedimensional convolutional neural network (1D-CNN) architecture for the automated identification of faults using vibration and current information obtained from a 150 kW traction motor operating under varying load and speed circumstances. The proposed technique concurrently analyses time-series vibration and current data, allowing the model to detect both mechanical and electrical irregularities. The dataset includes several defect kinds and healthy operating settings, offering a realistic basis for training and assessment. Experimental findings indicate that the 1D-CNN model attains a classification accuracy of 98.7% with just vibration signals, 97.5% with only current inputs, and 99.4% when both modalities are integrated. The precision, recall and F1-score of the integrated signal model are above 99 percent in all types of faults, which shows good performance even in varying operations. The findings underscore the efficacy of multi-signal 1D-CNN architectures for the prompt and precise detection of traction motor faults, reducing dependence on human feature extraction and facilitating predictive maintenance tactics. The proposed method provides a scalable and generalizable solution for practical traction systems, enhancing operating dependability and decreasing maintenance expenses.

Explainable CNN–GRU learning on Mel-spectrogram acoustic signals for bearing fault diagnosis under small-sample experimental conditions

Reliable bearing fault diagnosis is essential for predictive maintenance of rotating machinery, particularly in applications where contact-based vibration sensors are difficult to install or maintain. This study proposes an explainable acoustic fault diagnosis framework based on Mel-spectrogram representations and a hybrid Convolutional Neural Network–Gated Recurrent Unit (CNN–GRU) architecture. Acoustic emission signals collected from a controlled bearing fault simulator are first segmented and transformed into Mel-spectrograms to represent the time–frequency structure of normal and faulty bearing conditions. The CNN module extracts localized spectral patterns from the Mel-spectrogram images, while the GRU module models temporal dependencies along the spectrogram time axis with fewer recurrent parameters than conventional LSTM-based designs. To address the interpretability limitations of deep learning models, Grad-CAM, Integrated Gradients, and SHAP are employed to analyze the frequency–time regions contributing to the model decisions. In addition, the explanation maps are compared with fault-relevant spectral regions derived from fault characteristic frequency analysis to evaluate whether the model focuses on physically meaningful patterns rather than arbitrary image regions. The proposed framework achieved an high accuracy of in the initial experiment and was further evaluated through repeated validation to assess performance stability under small-sample conditions. The results demonstrate that acoustic sensing combined with explainable CNN–GRU learning can provide a non-contact and interpretable alternative for bearing fault diagnosis. However, the limited dataset size remains an important constraint, and future studies should validate the framework on larger record-level and cross-domain datasets.

A visual interpretation-based intelligent fault diagnosis framework for switch machines based on sound signal

Switch machines are critical components in rail transit signal systems, ensuring the safe, efficient, and smooth operation of trains. However, due to the harsh working conditions, they are the most failure-prone among all ground signal devices. Existing studies mainly pursue higher diagnostic accuracy via specialized models, often at the expense of interpretability, diagnostic transparency, and adaptability to different signal representations. In this article, a visual interpretation-based intelligent fault diagnosis framework is developed for switch-machine fault diagnosis using acoustic signals. A flexible time-frequency transformation module is used to convert signals into time-frequency representations, which are then input into a convolutional neural network for fault classification. Heatmaps obtained by the gradient-weighted class activation mapping (Grad-CAM) method are employed to visually explain the fault diagnosis results. To enhance both accuracy and interpretability, an entropy-regularized composite loss function is introduced by combining cross-entropy loss with a Grad-CAM-derived two-dimensional local information entropy term. This design encourages the model to form more compact fault-related saliency distributions while maintaining classification accuracy. Experimental results on the constructed laboratory dataset show that the framework achieves high diagnostic accuracy under different time–frequency representations, with several configurations reaching 100% accuracy under the current evaluation protocol. These results demonstrate the feasibility of visual interpretation for acoustic-based switch-machine fault diagnosis.

Acoustic signal - based misfire detection in internal combustion engines using machine learning techniques

Neural network-supported vibration analysis of turbomachinery for early fault prediction

A new hybrid deep learning architecture, combining one-dimensional convolutional neural networks (1D-CNN) with bidirectional long short-term memory (BiLSTM) networks to the problem of automatic detection and early forecasting of mechanical faults based on raw vibration signals is suggested.