Collaborative Manufacturability Assessment and Autonomous Control for Intelligent Milling Lines Via Knowledge-Data Fusion

To address the limitations of autonomous decisionmaking in complex industrial environments, this study proposes a knowledge-data fusion-driven framework for Collaborative Manufacturability Assessment (CMA) and autonomous control. Utilizing Digital Twin (DT) technology, we establish a multidimensional semantic perception layer that enables the deep decoupling and real-time mapping of multi-source heterogeneous data across the machining lifecycle. The core innovation lies in the development of a fuzzy inference system based on Interval Type-2 Fuzzy Logic (IT2 FL), which synergistically harmonizes expert heuristics, physical simulation models, and historical machining data to effectively quantify cognitive uncertainties and resolve decision conflicts. Furthermore, an autonomous rule-evolution mechanism based on the FP-Growth algorithm is introduced, facilitating a transition from manually defined knowledge to datadriven strategy generation. Experimental results indicate that this architectural improvement significantly enhances decision-making robustness, yielding a 79.5 % increase in machining accuracy and a 79.2 % reduction in processing time, providing a novel closed-loop path for high-precision intelligent manufacturing.