Formability Prediction Using Machine Learning Combined with Process Design for High-Drawing-Ratio Aluminum Alloy Cups

Area of Science:

• Materials Science and Engineering
• Manufacturing Processes
• Artificial Intelligence in Manufacturing

Background:

• Deep drawing is a widely used metal forming process in manufacturing.
• Traditional methods for determining formable regions are time-consuming and complex.
• Advancements in artificial intelligence (AI) offer new possibilities for process optimization.

Purpose of the Study:

• To investigate the effects of geometric and process parameters on deep drawing of aluminum alloy A7075.
• To establish AI-driven prediction models for identifying sound product regions.
• To validate the feasibility and reliability of machine learning (ML) in optimizing deep drawing processes.

Main Methods:

• Utilizing finite element simulation to create a comprehensive database of forming results.
• Training and validating machine learning models using the generated database.
• Conducting experimental validation to compare predicted and actual forming outcomes.

Main Results:

• Development of an AI prediction model capable of rapidly determining forming results based on input parameters.
• Successful identification of formable regions for sound products under various conditions.
• Experimental validation confirmed the accuracy and reliability of the AI prediction model.

Conclusions:

• Machine learning is a feasible and reliable tool for optimizing the deep drawing process of aluminum alloy A7075.
• The developed AI model significantly enhances the speed and accuracy of predicting optimal forming parameters.
• This approach facilitates the efficient production of sound deep-drawn products.