Intelligent Decision-Making Technology of Automobile Gearbox Parts Process Based on Knowledge Graph

With the development of modern manufacturing industry, the traditional automobile gearbox processing mode is faced with the problems of strong coupling of process parameters, fragmentation of knowledge and lagging response of working conditions. In this study, knowledge graph technology is integrated into the processing of automobile gearbox parts, and a “fourth-order construction model” is proposed to solve the problem of semantic integration of multi-source heterogeneous data and construct a full-factor knowledge graph. A deep reinforcement learning framework with enhanced knowledge constraints is designed to achieve multi-objective collaborative optimization, which improves the processing efficiency by 16.5% and shortens the process debugging cycle by 21.9%. Combined with the generative AI industrial model, the knowledge map is expected to become the “cognitive center” of the manufacturing industry, promote the digital transformation of the manufacturing industry, and help realize the strategy of “manufacturing power”.