doi: 10.4304/jsw.9.1.63-69
Hybrid Intelligent Recommending System for Process Parameters in Differential Pressure Vacuum Casting
- 1 Rapid Manufacturing Engineering Center, Shanghai University, Shanghai, China
- 2 Rapid Manufacturing Engineering Center, Shanghai University, Shanghai, China
Abstract
The determination of process parameters in Differential Pressure Vacuum Casting (DPVC) process depends on the technologist’s experience, and thus the optimized ones are usually determined through repeated molding trial and repairing process. However, this can result in problems of long production period and high cost. So, combining case based reasoning (CBR), neural network 、agent model and fuzzy inference, a hybrid intelligent model is proposed herein to solve this problem. First, the CBR strategy is adopted for setting the initial process parameters by simulating the technologist’s reaction where technologists determines the optimized parameters by referencing highly similar case from past experience. If the CBR fails, the neural network reasoning (NNR) strategy is applied to determine the initial process parameters by imitating technologist’s “experience reasoning” process; if no similar case exists, the agent model reasoning (AMR ) strategy is applied to determine the initial parameters. Finally, a fuzzy inference (FI) based on expert knowledge is developed for revising defects and optimizing process parameters during the molding trial process until the part quality can meet the requirements. Based on the intelligent model, the corresponding software system is developed, and the experiment results show that the system is effective and can be applied to practical production.
Keywords
- Differential pressure vacuum casting
- Ca
How to Cite
Zhuangya Zhang, Haiguang Zhang, Yuanyuan Liu, and Qingxi Hu, "Hybrid Intelligent Recommending System for Process Parameters in Differential Pressure Vacuum Casting," Journal of Software, vol. 9, no. 1, pp. 63-69, 2014. https://doi.org/ 10.4304/jsw.9.1.63-69
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).