AI-Driven Predictive Maintenance for Manufacturing and Aerospace Systems

Abstract

The age of intelligent engineering and Industry 5.0 has made the use of artificial intelligence (AI), machine learning (ML) and predictive maintenance (PM) increasingly common to boost the performance, sustainability and resilience of manufacturing and aerospace systems. Traditional maintenance strategies focus on scheduled checks or remedial maintenance, introducing the risk of unforeseen equipment failures, higher operating expenses, downtime, and system vulnerabilities. In this research, we introduce an intelligent and sustainable engineering framework by combining advanced machine learning methods with predictive maintenance strategies, aiming to enhance decision-making and operational efficiency in next-generation manufacturing and aerospace systems, while also leveraging asset management. To demonstrate the validity of the proposed framework, two benchmark datasets were used to the AI4I 2020 Predictive Maintenance Dataset, which is for smart manufacturing environments, and the NASA C-MAPSS Turbofan Engine Degradation Dataset, which is for aerospace engine health monitoring and remaining useful life prediction. The created methodology consists of data preprocessing, feature engineering, feature selection, developing machine learning models, optimizing hyperparameters, and comparing the performance of the models. Models such as Artificial Neural Networks, Random Forest, Support Vector Machine, XGBoost, LightGBM, CatBoost and Long Short-Term Memory (LSTM) networks are used for manufacturing failure prediction, and models like Random Forest Regressor, XGBoost Regressor and Long Short-Term Memory (LSTM) networks are applied for the estimation of remaining useful life (RUL) in the aerospace industry. The accuracy, precision, recall, f1 score, roc-auc, mean absolute error (mae), root mean square error (rmse), and coefficient of determination (r2) are used to evaluate the performance of the model. The proposed framework will be expected to increase the accuracy of fault detection, optimize maintenance scheduling, minimize equipment downtimes, increase energy efficiency, and extend operational life of critical equipment. This study highlights the potential of AI-driven predictive maintenance across diverse industries, including manufacturing and aerospace, providing a unified solution for sustainable industrial practices, digital transformation, and data-driven decision-making. The results will also be relevant to the researchers and industry practitioners who want to deploy a reliable, scalable and intelligent maintenance system in future smart manufacturing and aerospace systems.