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{174493,
        author = {S. VENKATA SAI NIKITH and SAMMETA. RAM CHARAN and SHAIK. SHER AHAMED and D. TEJOVANTH and Mr.S.Ramadoss},
        title = {MACHINE FAILURE DETECTION IN INDUSTRIES USING LSTM AND LIGHTGBM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {3993-3999},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174493},
        abstract = {By analyzing real-time sensor data such as temperature, rotational speed, torque, and tool wear, our model predicts potential failures before they occur, helping reduce downtime and maintenance costs. Machine failures in automated industries result in downtime, reduced productivity, and increased costs, creating a demand for effective predictive maintenance solutions. The framework combines Long Short- Term Memory (LSTM) networks for capturing time-based patterns and LightGBM for identifying critical features to build a robust predictive maintenance system.
The system analyzes sensor data in real-time to predict machine failures, assess their severity, and trigger alarms based on the level of urgency. The hybrid model enhances predictive accuracy, reduces false alarms, optimizes maintenance schedules, and ensures minimal downtime for seamless industrial operations. In factories and industries, machines sometimes break down unexpectedly. This leads to: Downtime (machines stop working), Lower productivity (less work gets done), Higher costs (repairs and losses in production). To prevent these failures, industries need a better way to predict when a machine about to fail.},
        keywords = {Predictive Maintenance, Real-Time sensor data, Machine failure prediction, LSTM, LightGBM, Maintenance prediction, Sensor data analysis, Time-based patterns, Alarm triggers, Predictive Accuracy},
        month = {April},
        }