A comprehensive decision method of reliability probability distribution model based on the fuzzy support vector machine

Article type: Research Article

Authors: Xu, Qunhe^a | Kong, Yini^{b; *} | Zhang, Yangu^c | Wan, Yi^d

Affiliations: [a] Zhejiang Industry and Trade Vocational College, Wenzhou, Zhejiang 325000, China | [b] Zhejiang Dongfang Polytechnic, Wenzhou, Zhejiang 325000, China | [c] Ruian Department, Wenzhou Vocational and Technical College, Wenzhou, Zhejiang 325000, China | [d] College of Electrical and Electronic Engineering, Wenzhou University, Wenzhou, Zhejiang 325035, China

Correspondence: [*] Corresponding author: Yini Kong, Zhejiang Dongfang Polytechnic, Wenzhou, Zhejiang 325000, China. E-mail: [email protected].

Abstract: A fuzzy support vector machine kernel regression decision method of reliability probability distributions is presented aiming at the complexity of reliability probability distributions and disadvantage of the other regression model. The comprehensive decision model of probability distributions is built by the network design and feature extraction of the fuzzy support vector machine algorithm. A example is give for inward stress probability distribution type of a stem structural member by the model, the recognition result is Weibull distribution, the total recognition rate achieves 98.75%. The fuzzy support vector optimized algorithm has strong ability of nonlinear mapping and functional approach, it avoids availably partial minimum and overfitting, and gains high precision by comparing the numerical value of the network output with the numerical value of experiment.

Keywords: Probability distribution, fuzzy support vector machine, comprehensive decision, reliability analysis

DOI: 10.3233/JCM-193880

Journal: Journal of Computational Methods in Sciences and Engineering, vol. 20, no. 2, pp. 575-581, 2020