A Centralized Federated Learning Algorithm based Multi classification Predictive Maintenance in Industrial Internet of Things System
Ruaa W. Abdalah, Osamah Fadhil Abdulateef, Ali Hussein Hamad · Journal Européen des Systèmes Automatisés · 2025
Predictive maintenance (PdM) is essential for maintaining sustained operation for Industry 4.0 systems.Using artificial intelligence is crucial when PdM is required.However, there are several difficulties because of growing requirements for secure learning when uploading and downloading data in cloud servers.This led to the use of a training algorithm that preserves the privacy and security of the dataset.This work proposed a Federated Learning (FL) algorithm in PdM emphasizing its benefits in terms of quicker training time, lower latency, low power consumption, and, mainly, more security and privacy.The proposed system uses FL with deep neural network (DNN) model for both client and global models.Three client systems are represented by three AC motors equipped with different sensors, such as temperature, vibration, and current, which have been interfaced with Raspberry Pi through the I2C communication protocol.The weight values for the models are uploaded and downloaded between the local model and the global model in the cloud server using the MQTT Internet of Things (IoT) protocol.Results show good training performance metrics enhancement for the FL algorithm over the local model training without FL, where the accuracy has been increased from (0.9915) to (0.9983) in FL while the loss is decreased from (0.0232) to (0.0104) in FL.