원문정보
초록
영어
This study first analyzes the features and defects of each product design evaluation method. Then radial basis function (RBF) network is used for the modeling for sowing machines. Considering the characteristics of sowing machines and the general method of design evaluation of electromechanical equipments, 7 primary evaluation indicators for sowing machines are identified, including overall design, form, human-machine interface and color. These primary evaluation indicators were subdivided into 18 secondary indicators. Survey on these indicators was performed by professionals and the scores are assigned to 18 indicators collected from 26 samples. Thus the comprehensive evaluation score of the indicators is calculated using image scale method. The scores of the evaluation indicators are taken as input and the comprehensive evaluation score as the output, then the RBF network for design evaluation is built. After training and verification using 26 samples, it is found that the RBF-based design evaluation model achieves better prediction performance than the BP-based model.
목차
1. Introduction
2. Evaluation Indicator System for Sowing Machine Design
2.1. Evaluation Indicators
2.2. Evaluation Indicators
3. Building Comprehensive Design Evaluation Model Based On RBF Network
3.1. An Introduction of RBF Network
3.2. Principle of RBF Network
3.3. RBF Network Learning
3.4. RBF-Based Evaluation Model
4. Simulation using RBF-Based Model
4.1. Sample Data
4.2. Simulation and Verification
5. Conclusion
References