Machine Learning Approaches for Predictive Maintenance in Industrial Operations
Author:
- 22 December 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 365-372
Abstract
Predictive maintenance (PdM) has emerged as a transformative approach for enhancing industrial efficiency and reliability, leveraging machine learning (ML) techniques for real-time data analysis and anomaly detection. This study proposes a hybrid PdM framework integrating advanced ML models, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Autoregressive Integrated Moving Average (ARIMA), Isolation Forest, and One-Class SVM. Using IoT-enabled sensor data capturing parameters like vibration, temperature, and pressure, the framework demonstrates significant improvements. Key findings reveal that CNNs achieved 92% accuracy in early anomaly detection, while the combined LSTM-ARIMA model provided forecasting accuracy of 87% and reduced errors by 25% compared to standalone models. Isolation Forest and One-Class SVM achieved anomaly detection precision of 93% and recall of 88%. The framework reduced unplanned downtime by 54% and maintenance costs by 32% across tested scenarios. This study contributes to the existing body of knowledge by presenting a robust hybrid modeling approach that integrates statistical and deep learning methods to address fault prediction and maintenance scheduling limitations. Practical implications include improved maintenance efficiency, extended equipment lifespan, and enhanced industry decision-making capabilities, making the framework highly relevant for Industry 4.0 applications.Keywords
This publication has 23 references indexed in Scilit:
- Enhancing machine failure prediction with a hybrid model approachIAES International Journal of Artificial Intelligence (IJ-AI), 2024
- Enhancing Predictive Maintenance Hyperparameter Optimization and Adopted Strategies2024
- TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance FrameworkIEEE Internet of Things Journal, 2024
- Digital Twin Applied to Predictive Maintenance for Industry 4.0Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems, 2024
- ML-based failure detection approach for predictive maintenance in an industry 4.0 oriented web manufacturing control application2024
- A New Predictive Maintenance Approach: novel integration of GMM-LSTM for prediction of latent state and failure location of Rotating Machinery2024
- Deep Learning-based Predictive Maintenance for Industrial IoT Applications2024
- A hybrid deep learning approach to integrate predictive maintenance and production planning for multi-state systemsJournal of Manufacturing Systems, 2024
- Predictive maintenance in Industry 4.0: A systematic multi-sector mappingCIRP Journal of Manufacturing Science and Technology, 2024
- The advance of digital twin for predictive maintenance: The role and function of machine learningJournal of Manufacturing Systems, 2023