Quality Defect Recognition Method Based on Variable Precision Rough Set and Deep Belief Network.

Aiming at the problem of how to quickly identify the types of quality defects in the quality control of mechanical products in the manufacturing process, a quality defect identification method in the manufacturing process based on variable precision rough set and deep belief network is proposed. The variable precision rough set is used to reduce the dimension of quality characteristics influencing factor data, and the quality defect recognition model is established combined with the deep belief network algorithm to classify the quality defects of the quality problems in the manufacturing process of mechanical products. Finally, the feasibility and effectiveness of the model are verified by an example of crankshaft machining.