A Drift Handling Approach for Self-Adaptive ML Software in Scalable Industrial Processes

TL;DR

This paper presents an importance weighting-based drift handling approach to enable self-adaptation of machine learning software in scalable industrial processes, demonstrated through an electroslag remelting use case.

Contribution

It introduces an automated, adaptive drift handling technique for ML systems in industrial settings, addressing scalability and integration challenges.

Findings

Improved ML performance with the proposed drift handling approach.

Effective adaptation to new industrial conditions and equipment.

Demonstrated success in a real-world steel manufacturing process.

Abstract

Most industrial processes in real-world manufacturing applications are characterized by the scalability property, which requires an automated strategy to self-adapt machine learning (ML) software systems to the new conditions. In this paper, we investigate an Electroslag Remelting (ESR) use case process from the Uddeholms AB steel company. The use case involves predicting the minimum pressure value for a vacuum pumping event. Taking into account the long time required to collect new records and efficiently integrate the new machines with the built ML software system. Additionally, to accommodate the changes and satisfy the non-functional requirement of the software system, namely adaptability, we propose an automated and adaptive approach based on a drift handling technique called importance weighting. The aim is to address the problem of adding a new furnace to production and enable the adaptability attribute of the ML software. The overall results demonstrate the improvements in ML software performance achieved by implementing the proposed approach over the classical non-adaptive approach.