A novel hybrid explainable artificial intelligence modelling approach for smart manufacturing

TL;DR

The paper introduces a new hybrid AI framework that combines physics-based models with explainable AI to improve accuracy and transparency in manufacturing processes.

Contribution

The novel framework intrinsically integrates physics-based models with explainable AI, avoiding black-box components.

Findings

The hybrid framework achieves high accuracy and transparent decision-making in manufacturing.

A case study demonstrates its effectiveness in predicting cutting tool positions during ultra-precision diamond turning.

Abstract

Modelling complex manufacturing processes presents significant challenges related to accuracy and explainability. Physics-based models, while interpretable and generalizable, often suffer from reduced accuracy due to simplifications and incomplete system understanding. On the other hand, purely data-driven models are typically more accurate but lack transparency, limiting their trust and adoption in critical manufacturing applications. Existing hybrid approaches attempt to address these issues but often retain black-box AI components that compromise interpretability. In this study, we propose a novel hybrid modelling framework that intrinsically integrates physics-based models with explainable AI, to correct for modelling inaccuracies. This approach offers both high accuracy and transparent, traceable decision-making. Its effectiveness is demonstrated through a case study predicting the real-time position of cutting tools from accelerometer signals during ultra-precision diamond turning.

Figures