Jul 2026· International Conference Computing Methodologies and Communication· pp. 747-752· 0 citations· 13 references
Abstract
Predictive maintenance (PdM) in Industrial Internet of Things (IIoT) environments plays a vital role in minimizing unplanned downtime, improving operational efficiency, and spreading equipment lifespan. This paper presents a Machine Learning (ML)-based predictive maintenance basis deployed on Google Cloud AI Platform for real-time monitoring and fault prediction of manufacturing milling machine devices. The proposed system develops sensor-generated operational data, including torque, rotational speed, temperature, and tool wear, to train and evaluate multiple ML models such as Decision Tree, K-Nearest Neighbors (KNN), Gradient Boosting, Support Vector Machine (SVM), Gaussian Naïve Bayes, and Logistic Regression. The confirmed models, the Decision Tree classifier reached the highest accuracy of 99.40%, with strong cross-validation and AUC performance, indicating larger capability in detection machine failures. By fit in cloud-based AI services, the framework ensures scalable model deployment, high availability, and efficient real-time predictive analytics for manufacturing applications. Experimental findings reveal important improvements in prediction accuracy and conservation cost reduction associated to conventional reactive maintenance approaches. The study confirms the efficiency of combining IIoT sensor analytics, ML, and cloud-based AI structure for intelligent and proactive industrial conservation systems.
Analytical preservation has become an vital strategy in Industrial Internet of Things (IIoT) locations for enlightening equipment reliability, dropping unforeseen machine failures, and enlightening trade productivity. This paper suggests an AI-driven predictive maintenance framework using the Google Cloud AI Platform for smart monitoring and fault estimate of engineering refining machines. The planned framework assembles and procedures real-time device data such as vibration, temperature, turning speed, and instrument wear from IIoT-enabled plans. Three machine learning algorithms, namely Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN), are practical and assessed to classify potential equipment letdowns before disappointment occurrence. Among the manufacturing models, the XGBoost classifier achieved the highest prediction accuracy of 99.18% with strong accuracy, recall, and AUC performance, on behalf of superior ability in early fault finding and analytical analytics. The grouping of Google Cloud AI services allows walkable model training, cloud-based supply, real-time specialist care, and efficient data organization for smart manufacturing applications. New results show significant improvements in upkeep efficiency, decrease in working downtime, and lower upkeep costs associated with traditional sensitive conservation approaches. The study highlights the productivity of joining IIoT sensor analytics, cloud computation, and progressive artificial intelligence methods for evolving smart and proactive industrial conservation arrangements in Industry 4.0 surroundings.
More Praveen, A. Lakshman, V.Jyothi2 et al.· 2026 4th International Confe...· 0 citations
Experimental results demonstrate that the proposed framework achieves high fault prediction accuracy, enhances system reliability, reduces maintenance costs, and supports data-driven decision-making in industrial environments.
Govind D. More, Shreyas Hon, Piyush Kotkar et al.· International Journal of Cre...· 0 citations
Industry 4.0 has transformed manufacturing through the integration of Industrial IoT (IIoT), cyber-physical systems, cloud computing, and artificial intelligence, making predictive maintenance (PdM) a key strategy for improving equipment reliability. Unlike traditional maintenance, AI-driven PdM analyzes real-time sensor data to predict equipment failures before they occur. However, many AI models operate as black boxes, limiting trust and interpretability. The proposed Explainable AI-Based Predictive Maintenance Framework (XAI-PMF) addresses this challenge by integrating IIoT sensing, intelligent feature engineering, hybrid machine learning (Random Forest, Gradient Boosting, LSTM, and Transformers), and explainability techniques such as SHAP, LIME, and rule extraction. These methods provide transparent fault predictions and maintenance recommendations by highlighting the factors influencing equipment degradation. Continuous learning further enables adaptive model updates as new operational data become available. Overall, the framework improves prediction accuracy, reduces downtime and false alarms, enhances maintenance scheduling, and supports trustworthy, intelligent asset management for next-generation smart factories.
Narendra Karmarkar· International Journal of Mod...· 0 citations
A number of physically meaningful indicators, including thermal instability, vibration anomalies, smoke-related features, and aggregated risk scores, have a significant impact on maintenance predictions and hence provide better operational interpretability and maintenance transparency.
Chitranjanjit Kaur, S. Chopra, Chitta Ranjan Tripathy· Automation· 0 citations
Unexpected equipment failures are known to be one of the most critical causes of production losses. Such failures can result in increased maintenance cost, compromise safety of operators and increase operational inefficiency. Therefore, there is a growing interest to monitor equipment during normal operation and predict possible failure before it actually occurs. This paper describes a smart Industrial Internet of Things (IIoT) framework to monitor industrial equipment in real time using ensemble learning for failure prediction. The framework initially collects a variety of real time operating parameters of industrial equipment such as temperature, vibration, speed, torque, pressure, etc from various industrial sensors. The collected data is then preprocessed using techniques such as treatment of missing values, noise removal, feature scaling, handling of class imbalance and feature selection to select most relevant features. The preprocessed data is then fed into various machine learning models such as random forest, support vector machine, gradient boosting and multi layer perceptron. A stacking-based ensemble model is used to combine the predictions of individual models to improve the overall prediction accuracy and stability. The final output of the framework is a classification of equipment condition into normal or failure-prone, along with a probability of failure. Shapley Additive explanations (SHAP) is used to provide both global and local interpretability to the predictions made by the model. The performance of the model is evaluated using various metrics such as accuracy, precision, recall, F1-score, area under receiver operating characteristic curve, false-alarm rate and inference time. The framework has potential to provide better failure detection using combination of IIoT monitoring and explainable AI, and provide understandable reasons for failure to maintenance personnel responsible for maintenance.
Enoch Success Boakai, P. A. Mary, R. Singh et al.· International journal of com...· 0 citations
The complexity of modern industrial systems and their need for intelligent maintenance to avoid unexpected failures and to improve the efficiency of production have led to the development of Predictive Maintenance (PM) using data from Industrial Internet of Things (IIoT). PM using IIoT uses a large amount of data gathered continuously by multiple sensors installed on industrial equipment. The use of machine learning (ML) has become common in PM using IIoT. However, existing ML approaches to PM using IIoT have many restrictions, such as sensor data variability, high dimensionality of feature space, class imbalance, and lack of interpretability. This paper proposes an explainable ensemble machine learning framework that uses multi-sensor data fusion for PM using IIoT. The proposed framework consists of data preprocessing, feature engineering, ensemble learning, and explainable AI. It uses three types of ML classifiers, namely, Random Forest, XGBoost, and LightGBM, and combines them using ensemble learning to improve prediction accuracy. It uses SHAP to explain the contribution of individual sensor features to the maintenance decision and provides interpretable results. The performance of the proposed framework is evaluated using several real industrial multi-sensor datasets. The framework provides high accuracy for fault prediction, while it is also explainable. Therefore, it can support effective and reliable industrial maintenance decisions. The results of this study also show that the proposed explainable ensemble ML framework can support the development of intelligent and trustworthy PM using IIoT in Industry 4.0.
C Murugamani, P. L. Parmar, K. Manivannan et al.· International journal of com...· 0 citations