Toward an evolvable digital twin: a knowledge-driven architecture for optical manufacturing

Area of Science:

• Manufacturing Engineering
• Artificial Intelligence
• Optical Science

Background:

• Optical manufacturing faces challenges in high precision and empirical dependency.
• Current digital twin models lack dynamic knowledge integration and adaptability.
• Need for intelligent systems in advanced manufacturing processes.

Purpose of the Study:

• To propose a novel bionic digital twin model for optical manufacturing.
• To enhance knowledge integration, causal reasoning, and cognitive adaptability.
• To enable real-time decision-making and self-evolving capabilities.

Main Methods:

• Developed a plant-growth-inspired bionic digital twin.
• Implemented a multi-vascular knowledge network for computable causal reasoning.
• Utilized a dual-loop (growth and metabolic) cognitive architecture for knowledge evolution.

Main Results:

• Validated the model through continuous polishing cases.
• Demonstrated enhanced surface form error convergence and parameter optimization.
• Achieved sustained cognitive adaptability via continuous knowledge updates.

Conclusions:

• The proposed bionic digital twin offers a pathway to adaptive, self-evolving systems.
• This model addresses limitations in dynamic knowledge integration for optical manufacturing.
• Enables intelligent and responsive manufacturing processes for high-precision applications.