Xichun Luo

Modern industries impose numerous challenges on manufacturing technologies and systems due to stringent quality requirements, the adoption of difficult-to-machine materials, high demands on miniaturization, mass customization, high productivity, and sustainability targets

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.

Microvibrations caused by airflow self-excitation within pressurized air films significantly degrade the dynamic stability of aerostatic bearings. However, effectively controlling supersonic flow velocity, which is critical for suppressing the turbulent airflows that cause this self-excitation, remains a significant challenge in the current designs of aerostatic bearings. To address this gap, a novel aerostatic restrictor inspired by the Laval nozzle principle is proposed to enhance the dynamic stability of bearings by decelerating supersonic pressurized airflows. Computational fluid dynamics (CFD) simulations are conducted to elucidate the underlying mechanism by which the proposed restrictor improves performance (i.e., by suppressing turbulent airflows by mitigating adverse pressure gradients). On the basis of the CFD simulation results, the key geometrical parameters of the newly designed restrictor are identified. The effectiveness of the proposed restrictor is evaluated through experimental testing, with the results indicating that it achieves improved dynamic stability and reduced vibration amplitude compared with a conventional aerostatic restrictor design. This work is expected to advance the theory of restrictor design by enhancing the dynamic stability of aerostatic bearings.