Aug 2026· Italian National Conference on Sensors· Vol 26, pp. 5379· 0 citations· 150 references
TL;DR
Examining explainable artificial intelligence for rotating machinery fault diagnosis classifies existing methods into ante hoc and post hoc approaches according to their integration with model architectures according to physical interpretability, applicable fault scenarios, explanation quality, computational overhead, robustness, and edge-deployment potential are critically compared.
Abstract
Rotating machinery is essential to energy, aerospace, manufacturing, and other safety-critical industries. Although deep-learning-based fault diagnosis has achieved high accuracy, its black-box nature limits trust, verification, and industrial deployment. This review examines explainable artificial intelligence for rotating machinery fault diagnosis and classifies existing methods into ante hoc and post hoc approaches according to their integration with model architectures. Their physical interpretability, applicable fault scenarios, explanation quality, computational overhead, robustness, and edge-deployment potential are critically compared. Quantitative criteria, including fidelity, stability, robustness, localization, and physical consistency are discussed to support objective evaluation of explanations. The review further highlights the gap between laboratory validation and industrial operation, particularly under sensor degradation, electromagnetic interference, variable working conditions, limited computing resources, and scarce fault data. It also discusses how model-relative explanations can be mapped to calibrated vibration quantities, fault-characteristic frequencies, industrial diagnostic standards, and actionable maintenance decisions. The distinction between correlation-based attribution and causal root-cause analysis is clarified, together with the role of digital twins and human-in-the-loop decision support. Finally, future research priorities are identified in standardized benchmarking, robust lightweight models, causal reasoning, and human-centered industrial deployment.
The increasing adoption of smart manufacturing technologies has intensified the need for reliable predictive maintenance solutions to reduce unexpected equipment failures and production downtime. Rotating machinery, including bearings, electric motors, gearboxes, pumps, and turbines, represents a critical class of industrial assets whose degradation directly affects manufacturing productivity, operational safety, and maintenance costs. This study presents a trustworthy AI-driven framework for condition monitoring and Remaining Useful Life (RUL) prediction of rotating machinery in smart manufacturing environments. The proposed framework integrates multi-sensor condition monitoring using vibration, temperature, acoustic emission, pressure, and motor current measurements with machine learning and deep learning models for intelligent fault diagnosis and prognostics. To improve transparency and industrial trust, the framework incorporates Explainable Artificial Intelligence (XAI) techniques, including SHAP and LIME, to identify the operational factors influencing prediction outcomes. In addition, Digital Twin technology and Physics-Informed Artificial Intelligence are integrated to enhance prediction reliability and maintain consistency with engineering knowledge. The framework is evaluated using benchmark datasets and standard classification and regression metrics, including Accuracy, Precision, Recall, F1-Score, MAE, RMSE, and RUL prediction error. The results demonstrate that the integration of multi-sensor monitoring, explainable AI, and Digital Twin-assisted analysis improves diagnostic reliability, prediction consistency, and maintenance decision support. The proposed approach offers practical benefits for Industry 4.0 applications by reducing unplanned downtime, optimizing maintenance scheduling, improving equipment availability, and enhancing the trustworthiness of AI-based predictive maintenance systems for critical rotating machinery.
Umme Habiba Aesha, Reyan Hridoy Bhuiyan, Yeasir Arafat Ayan· International Journal of Eng...· 0 citations
Fault diagnosis is a critical discipline within modern engineering that ensures the operational reliability, structural safety, and maximum availability of complex mechatronic systems. As contemporary automated processes become deeply integrated with mechanical, electrical, and computational sub-units, tracking internal health status transitions from an operational preference to a fundamental necessity. This paper provides an exhaustive, large-scale review of fault diagnosis methodologies, focusing explicitly on the architecture of model-based systems. Model-based fault diagnosis leverages high-fidelity mathematical and topological representations of physical processes to detect, isolate, and identify faults by evaluating analytical discrepancies, or residuals, between actual system responses and anticipated model states. This comprehensive review systematically categorizes these methodologies into qualitative approaches—including abstraction hierarchies, fault tree models, signed directed graphs, and fuzzy logic formulations—and quantitative mathematical techniques, encompassing analytical redundancy, parity spaces, Kalman filtering frameworks, parametric estimation algorithms, and diagnostic observer topologies. Furthermore, complementary architectural considerations, such as hardware redundancy and history-based data analytics, are investigated to build an integrated view of modern industrial developments. A detailed taxonomic synthesis highlights current system implementation hurdles, trade-offs between mathematical precision and computational complexity, and future diagnostic research paradigms for safety-critical systems.
R. Ekanayake, T. K. U. S. Bandara· Sri Lankan Journal of Applie...· 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
Ensuring reliable equipment operations are critical for production efficiency and safety compliance in manufacturing industries. Unexpected machine breakdowns not only disrupt operations but also increase maintenance costs and safety risk. Traditional approaches — whether reactive or preventive — often fail to incorporate real-time equipment data and often overlook early fault indicators. Predictive maintenance strategies based on artificial intelligence models, address these shortcomings by monitoring machine conditions in real time, detect anomalies and forecast failures. Thus, this study proposes a refined deep neural network to classify machine health and estimate failure probability, thereby emphasizing Remaining Useful Life (RUL) prediction as a strategy for optimizing maintenance scheduling. In this study, the AI4I 2020 Predictive Maintenance dataset, which contains 10,000 records of machine operating conditions, including air and process temperatures, rotational speed, torque, tool wear, product type, and failure status was used for the evaluation of the proposed model. To improve the proposed model's performance, detailed preprocessing steps were deployed on the dataset. These steps include some preliminary categorical encoding and feature standardization on the dataset while class weighting, SMOTE and focal loss were deployed for handling class imbalance issues. According to the results achieved, the proposed model performed better across all metrics considered in comparison with similar models including baseline models. By integrating data-driven AI techniques with predictive maintenance strategies, this research study demonstrates how manufacturing plants can reduce downtime, extend machine lifespan, and minimize unnecessary maintenance interventions.
O. A. Alimi, O.C. Tshidavhu, N. Khanyile et al.· 2026 6th International Confe...· 0 citations
The results show that the proposed Condition Monitoring (CM) approach significantly reduces resource waste and prevents costly downtime, offering a practical and scalable asset management model for industrial applications.
A. Oner, Meral Bayraktar· Italian National Conference...· 0 citations
This paper proposes a knowledge-based input configuration to inform deep learning models for both electrical and mechanical fault diagnosis, rather than increasing model complexity, and confirms that, while conventional feature processing techniques perform well for electrical fault diagnosis, only the proposed FFT-informed input effectively captures both electrical and mechanical fault patterns.
Jingyi Yan, Hariram Arni, Bin Jou et al.· Measurement· 1 citation