Research On Quality Control Of Mechanical Product Manufacturing Under The IoT Manufacturing Environment

Quality is the foundation of an enterprise’s survival,and quality control is an important part of the product life cycle.It is of great significance for improving the market competitiveness of products and reducing the life cycle cost of products.The traditional method of quality control by sampling inspection and statistical process control usually has the problem of control delay,and can not feedback the health status of the product in time according to the quality data monitored by the quality system.With the rapid development of the Internet of Things and big data technology,quality control technologies such as quality diagnosis and quality prediction during product manufacturing have received extensive attention and development.By monitoring the factors affecting the quality characteristics of products and the status of processing elements in the manufacturing process,using data mining and artificial intelligence methods for quality diagnosis and prediction is of great significance for improving product quality.The quality control process of the mechanical product manufacturing process and the architecture of the Industrial Internet of Things are analyzed,and the architecture of the quality control system of the mechanical product manufacturing process under the IoT manufacturing environment is established.The key technologies in the system operation process are pointed out.In view of the problem of rationally setting up quality inspection stations on the production line of the mechanical product manufacturing process,through the analysis of the product process,total production cost and total processing time,an optimized setting model of the production line quality inspection station is constructed and solved,and the crankshaft is used for machining The process is taken as an example to verify the validity of the model set by the quality inspection station.Aiming at the diagnosis of product quality defect types in the manufacturing process of mechanical products,by collecting data on the influencing factors of product quality characteristics in the manufacturing process,using variable precision rough sets to process the influencing factors of quality characteristics,combined with deep confidence networks to establish a quality diagnosis model The quality defects in the product manufacturing process were classified into quality defects,and the crankshaft forging process was used as an example to verify the effectiveness of the model.In view of the reasonably adjusting and controlling the processing elements to improve the quality of products,through monitoring and analysis of the processing elements,collecting the data of the processing elements,using the principal component analysis method to reduce the data of the processing elements,and combining the convolutional neural network to establish the quality prediction The model uses the influence of the processing process elements on the product quality characteristics to predict the product quality,so as to adjust the processing process elements in real time to ensure product quality.The impact performance and wear performance of the crankshaft forging process are used as examples to verify the effectiveness of the model.In order to effectively realize the quality control of the manufacturing process of mechanical products,real-time online monitoring of product quality and intelligent control of processing elements have been designed,and a product quality control system has been designed to optimize the settings of quality inspection stations,quality diagnosis,quality prediction,and real-time monitoring of product quality status.,Equipment management and other functions,the quality control prototype system in the product manufacturing process was developed to verify the effectiveness of the model.