Aug 2026· Journal of Intelligent Decision Making and Information Science· 0 citations· 20 references
TL;DR
This study proposes a machine learning-based predictive maintenance framework for machine failure prediction and fault diagnosis using the AI4I 2020 Predictive Maintenance Dataset, and identified torque, torque–speed ratio, and tool wear as the most influential predictors of machine failure.
Abstract
Predictive maintenance has become a critical component of Industry 4.0 by enabling intelligent mechanical systems to minimize unexpected equipment failures, reduce maintenance costs, and improve operational reliability. This study proposes a machine learning-based predictive maintenance framework for machine failure prediction and fault diagnosis using the AI4I 2020 Predictive Maintenance Dataset. The dataset comprises 10,000 machine observations with operational parameters, including air temperature, process temperature, rotational speed, torque, tool wear, and machine type. A comprehensive comparative analysis was conducted using Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Extreme Gradient Boosting (XGBoost). To address the highly imbalanced failure distribution, multiple evaluation metrics, including Accuracy, Precision, Recall, F1-score, Receiver Operating Characteristic–Area Under the Curve (ROC–AUC), and Matthews Correlation Coefficient (MCC), were employed. The experimental results demonstrated that XGBoost achieved the best predictive performance, obtaining an accuracy of 98.95%, an F1-score of 82.93%, a ROC–AUC of 98.00%, and an MCC of 0.8289, outperforming the remaining machine learning models. Furthermore, SHapley Additive exPlanations (SHAP) identified torque, torque–speed ratio, and tool wear as the most influential predictors of machine failure, providing transparent model interpretation and supporting informed maintenance decision-making. The proposed framework offers an accurate and interpretable solution for predictive maintenance, contributing to enhanced equipment reliability, reduced downtime, and intelligent maintenance strategies in modern manufacturing environments.
Predictive maintenance has become an important means of increasing the reliability of machines and reducing unexpected failures in industrial systems. This paper proposes a machine learning-based framework for machine failure prediction using operational data. The AI4I 2020 Predictive Maintenance Dataset is used, which contains 10,000 samples with a binary target variable indicating machine failure. The dataset was preprocessed by dropping irrelevant attributes, encoding categorical variables, and standardizing numerical features. Two approaches were investigated: Support Vector Machine (SVM) as a supervised classification model and Isolation Forest as an unsupervised anomaly detection model. The performance of both methods was evaluated using accuracy, precision, recall, F1score, and confusion matrix analysis. Experimental results show that the SVM model achieves 99.45% accuracy with 96% recall for the failure class, while Isolation Forest achieves 97.25% accuracy but only 49% recall for failures, missing over half of the actual failure cases. These findings demonstrate that supervised classification with SVM is significantly more effective than unsupervised anomaly detection for failure prediction in imbalanced predictive maintenance datasets, supporting its adoption in intelligent maintenance systems aimed at reducing downtime and improving operational efficiency.
In the context of Industry 4.0, predictive maintenance increasingly relies on machine learning models to anticipate equipment failures and reduce unplanned downtime. This makes the selection of the most suitable ML model a multidimensional and complex decision problem, since models with comparable predictive performance may differ substantially in terms of failure detection, false positives (FP), false negatives (FN), and computational requirements. This paper proposes a reproducible multicriteria decision-making framework that integrates objective Entropy-based weighting with the TOPSIS method for ML model selection in predictive maintenance applications. Logistic Regression (LR), Random Forest (RF), XGBoost, and LightGBM are evaluated using two predictive-maintenance datasets: the MetroPT dataset, representing real industrial time-series data from an air production unit in a metro system, and the AI4I 2020 Predictive Maintenance dataset from the UCI Machine Learning Repository. The experimental protocol incorporates leakage-aware temporal evaluation for MetroPT, stratified repeated evaluation for AI4I, controlled hyperparameter optimization, statistical significance analysis, and separate assessment of predictive and computational performance. The resulting model rankings are further examined using the VIKOR method and a systematic weight-sensitivity analysis covering 56 perturbation scenarios at ±20% and ±50%. The results show that XGBoost achieves the highest TOPSIS closeness coefficient on MetroPT (Ci = 0.6097), whereas LightGBM ranks first on AI4I (Ci = 0.9837). The VIKOR analysis produces the same ranking as TOPSIS on MetroPT (Spearman ρ = 1.000) and shows a strong but not perfect agreement on AI4I (ρ = 0.800). The sensitivity analysis indicates that the MetroPT ranking remains unchanged across all ±20% perturbation scenarios, while three ranking reversals occur under the ±50% perturbations. For AI4I, the top-ranked model remains unchanged across the tested perturbation scenarios, although the complete ranking can vary under changes in criterion weighting. These findings demonstrate that ML model selection in predictive maintenance should not rely solely on conventional predictive metrics, and that the proposed framework provides a structured decision-support approach for jointly considering predictive and operational performance.
Zouhair Marmoucha, Mohamed El Khaili, A. Soulhi et al.· Applied Sciences· 0 citations
Findings show that digital twin–enabled predictive maintenance supports proactive maintenance planning, human-centered decision-making, and operational efficiency, bridging the gap between Industry 4.0 automation and Industry 5.0 human–AI collaboration.
Ifebadiofu Matthew Okoro, Perseverance Omoh Agbi· International journal of res...· 0 citations
Machine learning-powered fault detection systems are the backbone of modern predictive maintenance solutions in the context of Industry 4.0, as they allow organizations to prevent expensive breakdowns and unnecessary machine downtime. Still, it is a known fact that machine learning systems are prone to model drift, which happens when a learning model performs worse due to changes in input data patterns. In dynamic industrial environments where machines operate under varying conditions, such changes are frequent and inevitable. Therefore, predictive maintenance systems must have built-in self-learning and self-healing mechanisms that allow them to adapt to new patterns and maintain the desired performance level. This paper proposes a Self-Healing Machine Learning System for Fault Detection to perform these tasks and demonstrates the concept’s feasibility within the Python/Flask environment. The proposed system utilizes Scikit-learn and the AI4I 2020 Predictive Maintenance Dataset to train an isolated random forest classifier and test its healing mechanism’s performance. The results demonstrate that the proposed approach can keep the random forest classifier’s performance stable by re-training it with new data whenever the performance metric falls below a certain threshold. Therefore, the self-healing ML system described in this paper can be a viable solution for industrial applications, as it ensures continuous learning and adaptability in the ever-changing environment of Industry 4.0.
A. V, Kumar Siddamallappa U, Shreedevi Prakash Gotur· World Journal of Advanced En...· 0 citations
Results show that using statistical vibration features with ensemble classifiers is a good way to diagnose multi-class bearing faults and establishes a comprehensive benchmark for ML- and DL-based rolling bearing FDD.
M. I. Quamar, Abdulrazaq Nafiu Abubakar, Ali Nasir· Journal of Vibration Enginee...· 0 citations
The proposed Explainable AI-Based Predictive Maintenance Framework (XAI-PMF) addresses this challenge by integrating IIoT sensing, intelligent feature engineering, hybrid machine learning, and explainability techniques such as SHAP, LIME, and rule extraction.
Narendra Karmarkar· International Journal of Mod...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
