In the context of the rapid development of intelligent manufacturing, effective quality control has become the key to improving manufacturing efficiency and product quality. Traditional quality control methods are often inadequate when faced with complex production data and changing manufacturing environments. Therefore, exploring new intelligent quality control technologies to cope with these challenges in intelligent manufacturing has become an important research direction. In view of this, the study proposed a quality control technology that combines association rules and fuzzy decision-making. Firstly, association rule mining methods are used to analyze production data and extract the relationships between key quality factors. Secondly, based on these association rules, fuzzy decision technology is used to adjust and optimize the production process, ultimately achieving quality control of products in the intelligent manufacturing production process. The data showed that when running on the training set and validation set, the research method reached a stable state at 18 and 46 iterations of the system, respectively, with a minimum cost loss function value. In both batch production lines, the detection efficiency under the operation of the research method remained at 2200 units per minute. During the process of repeating the system for 6 times, the research method consistently achieved maximum control accuracy and minimum time consumption. The satisfaction of the four experts with the operation of the research method in small batch production and large batch production was 9.32 and 9.2, respectively, significantly higher than other algorithms. The above results indicated that the proposed method can effectively improve the efficiency of product quality control, reduce production costs, and ultimately reduce the rate of defective products in the production process.
Read full abstract