Aluminum alloy die casting quality prediction method based on production big data

• Main Authors: CONG MING, DU YU, LIU DONG, FANG JIANRU, XIAO QINGYANG, WU XIAOXUAN, CHAI WENJIE
• Format: Patent
• Language: Chinese; English
• Published: 21.07.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses an aluminum alloy die casting quality prediction method based on production big data, and belongs to the field of automobile die casting quality prediction. Comprising the steps that (1) an equipment acquisition unit obtains production parameter data in the die casting process, a manual detection unit obtains quality index data, and the parameter data and the quality index data are integrated into an original data set; 2) preprocessing the data in combination with services, including repeated data, missing values and abnormal values, and selecting quality prediction key features; and (3) combining different machine learning algorithms by using a stacking integration method to improve the generalization ability and accuracy of the fusion model, and finally predicting the quality of the die casting according to the production data collected in real time to obtain a specific result. According to the method, the problem that manual detection of the quality of the die casting wastes time an