Using the social network analysis method, this paper uses the input—output table data of 42 industrial sectors in China from 2012 to 2020 to dynamically describe the structural characteristics of industrial association networks, and establishes a network dynamics model based on random actors to identify and analyze the evolution mechanism of industrial association networks. The results show that there is no significant difference in the overall index of the 42 industrial networks, and the network correlation index is greater than 0.75, and the overall network tend to be stable. Chemical products and transportation, warehousing and postal services have always been central, and the secondary industry, especially manufacturing, is at the heart of the network. From 2012 to 2015, China's industrial related network can be divided into 4 sectors (bidirectional spillover plate I, II, broker plate, net benefit plate), from 2017 to 2020, the broker plate disappeared, the main benefit plate appeared, the industrial association effect within the plate is more obvious, and each industry is more inclined to associate with the members in the same plate. Industry—related activities are mainly concentrated in the manufacturing of metal products, chemical products, communication equipment, computers and other electronic equipment, electrical machinery and equipment, metal smelting and calendering, as well as services such as wholesale and retail, transportation, warehousing and postal, information transmission, software and information technology services. The relative importance of endogenous structural factors is 53.11%, which plays an important role in the evolution of network relationships, the negative outdegree effect indicates that it is difficult to develop new relationships in industries with more correlations, the transitive effect indicates that there is a trend of continuous refinement in the industry, and the relative importance of external factors is 46.89%, of which the influence of labor is the most significant, accounting for 20.52%.