Machine learning techniques for fault detection in rotating mechanical systems

Purpose The purpose of this work is to develop and evaluate artificial intelligence (AI) models, specifically neural networks, random forest and XGBoost, for fault detection and localization in dynamic systems. By comparing the performance of these models in terms of accuracy, precision, recall and other key metrics, this study aims to identify the most effective approach for predictive maintenance in various engineering applications. The results provide insights into the strengths and limitations of each model, offering practical guidance for implementing AI-driven solutions to enhance operational reliability and efficiency in industries reliant on complex, dynamic machinery. Design/methodology/approach This study employs a comparative analysis of three machine learning algorithms – neural networks, random forest and XGBoost for fault detection in dynamic systems. The methodology includes data preprocessing, feature extraction and hyperparameter optimization using grid search and randomized search techniques. The models are trained and validated using cross-validation, with performance evaluated on accuracy, precision, recall, F1 Score and ROC AUC. Statistical tests, including ANOVA and paired T -tests, are applied to assess the significance of the differences between models. The approach ensures a rigorous evaluation of each model’s strengths and limitations for practical applications in predictive maintenance. Findings The findings reveal that XGBoost consistently outperforms neural networks and random forest in key performance metrics such as accuracy, precision and ROC AUC, demonstrating its effectiveness in fault detection for dynamic systems. The statistical analysis using ANOVA and paired T -tests confirms the significance of XGBoost’s superior performance. While random forest shows robust interpretability and neural networks perform well in certain scenarios, XGBoost’s ability to handle imbalanced data and deliver high accuracy makes it the most suitable model for predictive maintenance applications. These results provide a clear direction for selecting machine learning models in fault detection tasks. Research limitations/implications The research is limited by the use of a specific dataset and may not generalize to all dynamic systems or industrial environments. While XGBoost demonstrated superior performance, further validation is needed with diverse datasets and real-world conditions. Additionally, the study focuses on a few key metrics and does not explore other potential factors such as computational efficiency and scalability in large-scale systems. Future work should incorporate additional datasets, including real-time data and explore hybrid approaches or model ensembles to improve performance further and ensure broader applicability across various engineering applications. Practical implications This study provides practical insights for implementing AI-based fault detection in dynamic systems, particularly in predictive maintenance. By identifying XGBoost as the most effective model, industries can leverage this algorithm to improve operational reliability and reduce downtime. The findings offer a clear methodology for data preprocessing, model training and performance evaluation, which can be directly applied in sectors like manufacturing, energy and automotive. The research also highlights the importance of selecting the right model based on system requirements, offering practical guidance for engineers seeking to integrate AI solutions into their maintenance and monitoring processes. Originality/value This study offers a unique contribution by providing a comprehensive comparison of three widely-used machine learning models – neural networks, random forest and XGBoost – specifically applied to fault detection in dynamic systems. Through the use of statistical tests to validate the significance of performance differences, it offers a rigorous and objective assessment of each model’s capabilities. The findings deliver practical value to industries seeking to implement AI-driven predictive maintenance. By highlighting XGBoost’s superior performance and offering clear guidelines for model selection and implementation, this work addresses a critical gap in the literature related to AI applications in fault detection.