Affiliations: [a]
Jiangsu Key Laboratory of Advanced Manufacturing Technology, Huaiyin Institute of Technology, Huai’an, China
| [b]
School of Hydropower and Information Engineering, Huazhong University of Science and Technology, Wuhan, China
Correspondence:
[*]
Corresponding authors. Nan Zhang and Xiaoming Xue, Huaiyin Institute of Technology, Huaian, Jiangsu 223003, China. E-mail: [email protected] (Nan Zhang); E-mail: [email protected] (Xiaoming Xue).
Abstract: This paper proposes a novel Takagi–Sugeno fuzzy model identification method by combining fuzzy c-regression model clustering (FCRM), least squares support vector machine (LSSVM) and intelligent optimization algorithm. Firstly, in order to improve the performance of FCRM for the complex nonlinear dataset, in this paper the method of FCRM based on LSSVM (FCRM-LSSVM) is proposed to discover the data structure and obtain the antecedent parameters. And then, a newly developed intelligent optimization algorithm by hybridizing Harris hawks optimization and moth-flame optimization algorithm (IHHOMFO) is proposed to further optimize the antecedent membership function parameters obtained by the FCRM-LSSVM. Finally, the proposed novel T-S fuzzy model identification combines FCRM, LSSVM and IHHOMFO for solving actual model identification problems. Experiments on five different datasets demonstrate that the proposed method is more efficient than conventional methods, such as T-S model identification based on fuzzy c-means (FCM), FCRM and FCRM-LSSVM, in standard measurement indexes. This study thus demonstrates that the proposed method is a credible and competitive fuzzy model identification method. The novel method contributes not only to the theoretical aspects of fuzzy model, but is also widely applicable in data mining, image recognition and prediction problems.
Keywords: T-S fuzzy model, fuzzy c-regression
model, least squares support vector machine, hybrid
optimization algorithm
