Open AccessPrediction of Process Parameters of New Injection Molding Products Based on Historical Qualified Product Data
Author(s) -
Shiyin Niu,
Jin Yu,
Hongbing Zhan,
Rui Wang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2025/1/012085
Subject(s) - process (computing) , product (mathematics) , artificial neural network , computer science , injection molding machine , field (mathematics) , molding (decorative) , productivity , manufacturing engineering , industrial engineering , production (economics) , new product development , perspective (graphical) , process engineering , mechanical engineering , engineering , mathematics , machine learning , artificial intelligence , materials science , business , marketing , economics , mold , geometry , pure mathematics , composite material , macroeconomics , operating system
In the field of thermoplastic injection molding, there are a large number of qualified product data, mining and analyzing these data is of great significance to enterprise production. At present, most scholars do optimization research around given process parameters, and cannot fundamentally solve the problem of process parameter setting values. To this end, this article proposes a new method, through the analysis of the material, structure and process of historical qualified products, from the perspective of the product, find the factors that affect the process parameters, and use the BP neural network model to train the non-linear mapping relationship between the product and several main process parameters, and predict the main process parameter values of the new product. For inexperienced manufacturers of injection products, this method can greatly improve their productivity.