Neural Network Based Computer-Aided Process Design System for Wire Bonding Quality Improvement

2010 ◽  
Vol 97-101 ◽  
pp. 2496-2499
Author(s):  
Jian Gao ◽  
Chuan Wei Li ◽  
Ke Tian Li ◽  
Ze Xiang Li ◽  
Xin Chen

The relationship between the process parameters and bonding quality is very complicated due to the features of non-linear and coupling relation. It’s therefore hard to express their relationship in an exact mathematic model and very difficult to obtain an reasonable parameters setting to get high bonding quality. In this paper, a wire bonding process model based on BP(Back Propagation) neural network is proposed, and based on this model a computer-aided process design system for bonding quality improvement is developed through VC++6.0. Based on the training data from design of experiments (DoE), the BP network is built. The system is validated by test data and the testing result shows that the predicted error is samll and reasonable and the system developed can be used for parameter optimization and quality improvement.

2013 ◽  
Vol 347-350 ◽  
pp. 3460-3464
Author(s):  
Hong Hui Huang ◽  
Ling Yun Wang

This paper takes UGNX6.0 as the development platform, by using its UG/KF development tools, fusing feature and knowledge together, so as to realize the process associated with the geometric design knowledge and stamping process design. Based on the features of stamping process, the classification of stamping process knowledge has been studied. With the object-oriented method, the rule-based and instance-based technology for expressing and acquiring the stamping process knowledge is discussed. Based on this, the stamping process model driven by knowledge has been established. It showed the importance of the CAD technology in designing of relatively complex progressive dies. Based on the knowledge engineering process designed, the degree of intelligence stampings process design has been enhanced, design quality and efficiency has been improved, and the dependence of the process design experience of designers has been reduced.


1992 ◽  
Vol 25 (24) ◽  
pp. 189-195
Author(s):  
Yuji Naka ◽  
Hiroshi Takiyama ◽  
Eiji O'Shima

2013 ◽  
Vol 340 ◽  
pp. 833-836
Author(s):  
Ling Yu

According to the concept of computer aided design system and color matching colors based on color solid theory, color coordination guide designers great tools its realization process, and give users more than free choice. This article through the emotional color that quantitative puts forward nine tones the concept of the emotional tone. Finally, this paper summarizes the Buddha tonal coordination than process, design optimization method in a certain extent color according to the comparison of the new and old model of configuration. This method should be widely used in new cases of urban planning management, the color. Thanks to the building should be improved and color should adapt to test the feasibility of in a different environment, improve computer aided design and color of the update other areas, color design.


1976 ◽  
Vol 9 (3) ◽  
pp. 59-67
Author(s):  
R.S. Ahluwalia ◽  
J. Lopez ◽  
A.I. Johnson ◽  
R. Millares

2017 ◽  
Vol 2017 ◽  
pp. 1-6 ◽  
Author(s):  
Junhua Zhang ◽  
Hongjian Li ◽  
Liang Lv ◽  
Yufeng Zhang

Objective. To develop a computer-aided method that reduces the variability of Cobb angle measurement for scoliosis assessment. Methods. A deep neural network (DNN) was trained with vertebral patches extracted from spinal model radiographs. The Cobb angle of the spinal curve was calculated automatically from the vertebral slopes predicted by the DNN. Sixty-five in vivo radiographs and 40 model radiographs were analyzed. An experienced surgeon performed manual measurements on the aforementioned radiographs. Two examiners used both the proposed and the manual measurement methods to analyze the aforementioned radiographs. Results. For model radiographs, the intraclass correlation coefficients were greater than 0.98, and the mean absolute differences were less than 3°. This indicates that the proposed system showed high repeatability for measurements of model radiographs. For the in vivo radiographs, the reliabilities were lower than those from the model radiographs, and the differences between the computer-aided measurement and the manual measurement by the surgeon were higher than 5°. Conclusion. The variability of Cobb angle measurements can be reduced if the DNN system is trained with enough vertebral patches. Training data of in vivo radiographs must be included to improve the performance of DNN. Significance. Vertebral slopes can be predicted by DNN. The computer-aided system can be used to perform automatic measurements of Cobb angle, which is used to make reliable and objective assessments of scoliosis.


2011 ◽  
Vol 291-294 ◽  
pp. 2296-2301
Author(s):  
Kang Liu ◽  
Yan Li ◽  
Wu Zhao ◽  
Wen Qiang Li

A process model FPBS for conceptual design is put forward. The function and behavior etc about the model are defined and analyzed, and the expressions are analyzed too. The relationships of elements, the application of model are discussed and analyzed. The model can be effective used to guide conceptual design and applied to construct computer aided conceptual design system.


Sign in / Sign up

Export Citation Format

Share Document