Technology State Control Based on Multi-source Heterogeneous Data Fusion in Manufacturing

The technology state is determined not by a single data, but by multiple data sources that has a certain degree of uncertainty and ambiguity, and even be contradictory which is difficult to support decision-making effectively. In this paper, an efficient intelligent decision-making method based on multi-source heterogeneous data fusion is proposed. Firstly, under the rough set theory, the attribute reduction method based on the improved particle swarm optimization is proposed to efficiently obtain decision-related attributes. Secondly, using the improved Dempster-Shafer (D-S) evidence theory to fuse and calculate the reduced information sources to obtain the final decision results. Finally, the production process of satellite separation station was taken as the application object to verify the feasibility of proposed technology. (C) 2020 The Authors. Published by Atlantis Press SARL.