Nowadays, modern manufacturing systems are becoming increasingly complex. They are exposed to more frequent and unpredictable risks of change and disruption, both external and internal. Reconfiguration is an important way for the manufacturing system to maintain stability, so we propose a reconfigurable digital twin system to enable it to cope with increasing uncertainty and instability. This paper investigates a unified description template for digital twin foundation components, enabling the fusion of digital objects at the layer of foundation components. On this basis, the methods for adjustment of internal and external changes are proposed. Also, a rapid development and simulation method based on reconfiguration strategies and similarity matching algorithms is proposed to support the reconfiguration of the digital twin. Finally, the proposed architecture is illustrated and validated with a case study of a manufacturing workshop for intelligent navigation vehicles.

There are many factors involved in the complex manufacturing production process (CMP). It is necessary to identify key processes and features in the CMP. A CE-ND-based algorithm is proposed to provide an effective data-based scheme to identify key features in CMP. Nonparametric Copula Entropy (CE) is applied to estimate the correlation between features and establish a correlation relational network; network deconvolution (ND) is applied to eliminate the influence of transfer effects in the relational network. Abundant experiments in the analysis of industrial production process data are conducted, which indicate that our proposed method outperforms other methods.

Laser weeding is a non-chemical, non-contact precision weeding method particularly suited for inter-row operations during the crop seedling stage. However, maintaining precise laser targeting on weed stems during dynamic field operation remains challenging. This task requires close coordination among perception, control, and actuation modules, while vehicle vibration from uneven terrain further degrades strike precision on the move. This paper presents a fully autonomous laser weeding robot for inter-row operation in cotton seedling fields, integrating weeding control, automatic mode switching, and autonomous navigation into a coordinated multi-process architecture. Vibration-induced strike deviation is mitigated by STCF-Net (Spatio-Temporal Cross-modal Fusion Network), a cross-modal prediction framework that fuses forward-looking depth maps with historical IMU signals to forecast vibration severity over a 3 s horizon. The prediction enables the control system to proactively adjust travel speed and weeding mode before encountering rough terrain, balancing precision and efficiency under dynamic field conditions. Field experiments validated weeding performance in static and dynamic scenarios and demonstrated that STCF-Net-guided predictive switching reduced operational time by 11.5% to 13.9% compared with a conservative baseline in two controlled experiments, with only a marginal reduction in weeding precision. This study reports the system-level design of a fully autonomous laser weeding robot and introduces feedforward vibration prediction to the laser weeding domain, providing a practical reference for integrating predictive algorithms into field-deployable weeding systems.