Forming Parameter Optimization based on Kriging Model and Genetic Algorithm
- Resource Type
- Conference
- Authors
- Tang, Junxiong; You, Dongdong; Li, Fenglei; Cheng, Yong
- Source
- 2023 IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC) Information Technology and Mechatronics Engineering Conference (ITOEC), 2023 IEEE 7th. 7:343-346 Sep, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Manufacturing industries
Costs
Mechatronics
Machine learning algorithms
Optimization methods
Metals
Predictive models
Hydroforming machining
Kriging model
Genetic algorithm
Finite element
- Language
- ISSN
- 2693-289X
When optimizing the processing parameters for hydraulic forming of sheet metal, improving the process parameters based on actual experiments will increase costs, while finite element simulation will lengthen the design cycle. This study proposes a feasible solution by using a Kriging predictive surrogate model to replace the time-consuming finite element model and combining it with multi-objective genetic algorithm for parameter optimization. The optimal process parameters obtained from the simulation validation of finite element analysis prove the feasibility of this solution. This integrated approach of using machine learning and optimization algorithms is practical and promising for improving efficiency and reducing costs in the manufacturing industry.