Digital twin (DT) technology has evolved beyond static physical mapping into a dynamic intelligence layer for smart manufacturing. We argue that three capabilities are now decisive for advancing DT production lines in complex industrial environments: data-driven quality correction through nonlinear feature learning, real-time edge vision for surface defect sensing, and deep time-series modeling for predictive maintenance. We further contend that the next inflection point lies not in individual algorithmic improvements, but in the cognitive integration of structured engineering knowledge-such as Manufacturer Knowledge Packages (MKP) and the Theory of Inventive Problem Solving (TRIZ)-with gene... More >

In the field of high-end precision manufacturing, quality control in production processes has long been challenged by both spatiotemporal data sparsity and error lag. Traditional offline sampling methods struggle to capture the dynamic fluctuations in production, while single-dimensional feedback controls fall short in addressing the nonlinear coupling between multi-dimensional process parameters and final product quality. To address these challenges, this paper proposes a production quality management system based on multi-dimensional data learning and an active error elimination method. First, to tackle the issue of sparse sampling, an Adaptive Gaussian Process Regression (AGPR) algorithm... More >