.png){kind=icon}
.png){kind=icon}
Return
Process-oriented optimization of gate and vent systems in silicone rubber rapid tooling for complex wax pattern manufacturing
.png){kind=icon}
PRE
AI
C
Z
Y
A
S
DOI：10.1016/j.cirpj.2026.07.013.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Based on years of practical experience, silicone rubber mold (SRM) is the most commonly used technology for the reproduction of wax patterns with complex geometries. The key to successfully reproducing wax patterns with complex geometries lies in whether the SRM has excellent filling and ventilation capability. Numerical simulation techniques are widely used in rapid tooling design to reduce physical trials and quantify filling behavior and potential defect locations. However, optimization of gate and vent systems for highly complex geometries, such as thin-walled structures or deep cavities, still heavily relies on designers’ experience. This study develops an artificial intelligence (AI)-driven framework for optimizing gate and vent systems in silicone rubber rapid molds. The framework integrates 3D geometric data with Moldex3D simulations and constructs a deep learning surrogate model to predict molten wax flow. It determines optimal gate and vent configurations, replaces experience-based design, and correlates mold parameters with casting quality. Multiple scenarios validate robustness under complex geometries. Integrating AI with rapid tooling enhances efficiency, reproducibility, and standardization, supporting precise wax pattern production and industrial small-batch applications. The back-propagation artificial neural network (BP-ANN) surrogate model achieves high predictive accuracy with coefficient of determination values of 0.987 for training data, 0.942 for boundary validation data, and 0.778 for blind test data across a filling time range from 0.1 s to 5.5 s. AI-optimized design reduces filling time by approximately 10% compared with experience-based design. Experimental verification confirms improved flow uniformity and defect reduction, demonstrating the feasibility of the intelligent rapid tooling framework. The proposed framework supports sustainable intelligent manufacturing and aligns with the sustainable development goals advocated by the United Nations by improving process efficiency, reducing material waste, and enhancing precision rapid tooling development.
Journal
IF:
5.4
Papers:
283
Citations:
4.8K
Organization
Cited Papers