A machine learning based approach of robust parameter design
A machine learning based approach of robust parameter design
- Author(s): Cui Qing'an ; He Zhen ; Cui Nan
- DOI: 10.1049/cp:20060802
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
International Technology and Innovation Conference 2006 (ITIC 2006) — Recommend this title to your library
Thank you
Your recommendation has been sent to your librarian.
- Author(s): Cui Qing'an ; He Zhen ; Cui Nan Source: International Technology and Innovation Conference 2006 (ITIC 2006), 2006 p. 443 – 448
- Conference: International Technology and Innovation Conference 2006 (ITIC 2006)
- DOI: 10.1049/cp:20060802
- ISBN: 0 86341 696 9
- Location: Hangzhou, China
- Conference date: 6-7 Nov. 2006
- Format: PDF
Dual response surface methodology (DRSM) and nonparametric methodology (NPM) are main approaches used to achieve robust parameter design (RPD) of industrial processes and products. When the relationship between influential input factors and output quality characteristic of a process is very complex, both approaches have their limitations. For DRSM, it fails to fit the real response surfaces of process mean and variance by using the second order polynomial models. For NPM, it is hard to optimize parameters of fitting equation, and it needs more experiments as well. From a machine learning perspective, this paper generalizes RPD as a restricted active learning problem and proposes a new approach to achieve it. It fits process mean and variance responses by support vector machines (SVM), and then optimizes levels of design parameters by genetic algorithm. In order to reduce experiment times, the influence of priori knowledge on generalized error of fitting model is studied. Then a prior knowledge based experiment design is developed. Moreover, the approach selects the form of kernel function and optimizes parameters in SVM by comparing the upper bounds of generalized error of different SVM models without extra samples. The example given in the paper shows that, the generalized error and the experiment times of the approach decrease by no less than 45% and 39% respectively, compared with traditional approaches. All these results demonstrate the adaptability and superiority of the approach proposed in the paper.
Inspec keywords: response surface methodology; learning (artificial intelligence); manufacturing processes; genetic algorithms; support vector machines; polynomials
Subjects: Algebra; Learning in AI (theory); Systems theory applications; Optimisation; Interpolation and function approximation (numerical analysis); Optimisation techniques; Algebra; Numerical analysis; Systems theory applications in industry
Related content
content/conferences/10.1049/cp_20060802
pub_keyword,iet_inspecKeyword,pub_concept
6
6