Federated Learning for Predictive Maintenance and Quality Inspection in Industrial Applications

TL;DR

This paper evaluates federated learning for predictive maintenance and quality inspection in Industry 4.0, comparing aggregation methods and introducing a new real-world dataset, highlighting FL's potential and data dependency.

Contribution

It provides a comprehensive performance comparison of federated learning methods against traditional approaches and introduces a novel real-world dataset for industrial quality inspection.

Findings

FL performance varies with data distribution among clients

In some scenarios, FL outperforms local and central training

A new real-world dataset for federated learning in industry

Abstract

Data-driven machine learning is playing a crucial role in the advancements of Industry 4.0, specifically in enhancing predictive maintenance and quality inspection. Federated learning (FL) enables multiple participants to develop a machine learning model without compromising the privacy and confidentiality of their data. In this paper, we evaluate the performance of different FL aggregation methods and compare them to central and local training approaches. Our study is based on four datasets with varying data distributions. The results indicate that the performance of FL is highly dependent on the data and its distribution among clients. In some scenarios, FL can be an effective alternative to traditional central or local training methods. Additionally, we introduce a new federated learning dataset from a real-world quality inspection setting.