Federated Learning for Secure AI-Driven Predictive Maintenance in Smart Manufacturing

Abstract

Background: In the Industry 4.0 landscape, integrating artificial intelligence (AI) with smart manufacturing is essential for enhancing automated monitoring, predictive maintenance, and system optimization. However, traditional centralized AI model training poses critical risks to data privacy, security, and scalability, especially when sensitive operational data from factory machines is shared across platforms. Methods: This study proposes a decentralized, intelligent framework designed for real-time machine monitoring that enhances fault detection accuracy while safeguarding data privacy. The approach begins with real-time sensor data acquisition—capturing vibration, temperature, and acoustic signals from distributed factory units via edge devices. These signals undergo preprocessing and advanced feature extraction using Wavelet Transform and Empirical Mode Decomposition (EMD) to reveal critical fault characteristics. Results: A hybrid deep learning model that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks is used for classification. CNNs are responsible for extracting spatial features, whereas LSTMs identify temporal dependencies in time-series. With the federated learning (FL) framework, model training can be done collaboratively across edge devices without the need to transfer sensitive raw data. Conclusion: This ensures security and enhances model generalization. Results from experiments indicate that the suggested FL-based hybrid model exceeds centralized architectures regarding detection accuracy, computational efficiency, and adaptability. This research provides a scalable and secure solution that enhances intelligent monitoring for Industry 4.0 systems.