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.
M. Indhumathi, R. Deepa, M. Rubinabegam et al.· International Conference on...· 0 citations
Rotary machines are vital in industrial and electrical systems, and prompt defect detection is crucial to prevent operational failures and financial losses. This article presents a framework using a Convolutional Neural Network (CNN) for defect detection via spectrogram images derived from simulated voltage, current, and load signals of rotary machines. The dataset, generated using MATLAB simulations and accessible on Kaggle, comprises spectrograms depicting normal operation and three fault conditions: $10 \Omega, 30 \Omega$, and $60 \Omega$. The CNN model proficiently extracts time-frequency characteristics from the spectrograms, attaining an overall classification accuracy of 96.3%, with precision, recall, and F1-scores continuously above 95% across all fault categories. The findings illustrate the model’s capacity to identify nuanced differences in machine behavior resulting from varying fault resistances. In contrast to traditional vibration- and signal-based techniques, the proposed method offers a resilient, non-invasive, and automated alternative for monitoring the state of rotary machines, facilitating predictive maintenance and mitigating the risk of unforeseen breakdowns. This research highlights the efficacy of integrating deep learning with spectrogram analysis for precise industrial problem identification.
R. Vizhi, S. Saroja, Rangarajan Dr.Sagunthala et al.· International Conference on...· 0 citations