Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{156889,
        author = {N. Sivaraj and B. Rajagopal },
        title = {High Accuracy LSTM Classifier for Induction Motor Fault Monitoring System},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {9},
        number = {5},
        pages = {282-287},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=156889},
        abstract = {Motors are one of the most critical components in industrial processes due to their reliability, low cost and robust performance. Motor failure will lead to the shutdown of a whole production line and cause great loss. Therefore, accurate, reliable and effective motor fault diagnosis must be performed. Currently, motors fault diagnosis has gained much attention to guarantee safe motor operations. In this paper a fault diagnosis method is proposed for three-phase asynchronous motor using Long Short-Term Memory (LSTM) neural network, which possesses the capacity to learn meaningful representations from raw signal without any feature engineering. Firstly, the acceleration signals of different fault motors were collected. Then, the raw data were directly fed into LSTM neural network to establish the relationship between the raw vibration signals and fault states. The whole proposition was experimentally demonstrated and discussed by carrying out the tests of six three-phase asynchronous motors under different fault conditions in the drivetrain diagnostics simulator system. Performances of other classification methods such as LR, SVM, MLP, and basic RNN, are tested and contrasted. Results show that the proposed approach achieves the highest fault diagnosis accuracy.},
        keywords = {LSTM, Motor, Fault},
        month = {},
        }