Multi-response non-parametric profiling using Taguchi's qualimetric engineering and neurocomputing methods: Screening a foaming process in a solar collector assembly |
| |
| Affiliation: | 1. Advanced Industrial & Manufacturing Systems Program, Mechanical Engineering Department, TEI of Piraeus, Greece;2. Advanced Industrial & Manufacturing Systems Program, Mechanical Engineering Department, Technological Education Institute of Piraeus, Attica, Greece, and Kingston University, London, UK.;1. Microsoft Research, Beijing, PR China;2. Columbia University, New York, USA;3. University of Science and Technology of China, Hefei, PR China;4. Microsoft Research, Redmond, USA;1. College of Communications Engineering, PLA University of Science and Technology, Nanjing, Jiangsu 210007, China;2. Business School, Sichuan University, Chengdu 610064, Sichuan, China |
| |
| Abstract: | Taguchi's data programming techniques in synergy with data analysis tactics based on artificial neural networks have been fruitful in illuminating intricate manufacturing phenomena. We present a non-parametric approach to treat multi-response multi-factorial datasets created with Taguchi's orthogonal-array samplers. Replicated response datasets are compressed utilizing the signal to noise ratio and then they are homogenized by simple rank-ordering. The multiple response layout is reduced to the more tractable uni-response arrangement by using the super-ranking concept to enact the fusing of the individual responses. The ‘ranked-and-fused’ dataset is subjected to conversion by linear and three-layer perceptrons. The performance of a group of examined effects is assessed according to the perceptrons’ sensitivity analysis output. Using Wilcoxon's one-sample test, statistical significance is assigned to the accumulated ranking scores obtainable from a series of independent perceptron runs. We discuss the efficiency status for each of the two engaged perceptron options on affecting prediction accuracy as well as the influence of data fusion on the SNR-compressed datasets. Our robust neurocomputing solver is elucidated in a concurrent screening of three foam characteristics which are encountered in popular solar-collector assembly operations. Seven controlling factors were profiled and it was found that the temperature of the polyol additive is the sole statistically predominant effect. Finally, through our industrial paradigm, we illustrate the superiority of the fusing principle for downsizing stochastically multiple characteristics and thus gaining faster and more accurate perceptron predictions. We show that the proposed method outperforms the outcomes obtained by the desirability analysis. We identify the points of superiority to the crisper resolution in locating effect dominance accompanied with recovered stochastic significance. |
| |
| Keywords: | Taguchi methods Artificial neural networks Robust screening Design of experiments Orthogonal array Solar collectors |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
