Adaptive Inverse Control of Flexible Link Robot Using ANFIS Based on Type-2 Fuzzy

journal of Artificial Intelligence in Electrical Engineering

مقاله 2، دوره 5، شماره 19، بهمن 2016، صفحه 11-19   

نوع مقاله: Original Article

نویسندگان

Saeed Barghandan^{* 1}؛ Mohammad Esmael Akbari²؛ Hamid Ghadiri^{* 3}

¹Department of Electrical Engineering, Ahar Branch, Islamic Azad University, Ahar, Iran

²Department of Electrical Engineering. Ahar Branch, Islamic Azad University, Ahar, Iran

³Department of Electrical, Biomedical and Mechatronics Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran

چکیده

This paper presents a novel adaptive neuro-fuzzy inference system based on interval Gaussian type-2 fuzzy sets in the antecedent part and Gaussian type-1 fuzzy sets as coefficients of linear combination of input variables in the consequent part. The capability of the proposed ANFIS2 for function approximation and dynamical system identification is remarkable. The structure of ANFIS2 is very similar to ANFIS but in ANFIS2, a layer is added for purpose to type reduction. An adaptive learning rate based back propagation with convergence guaranteed is used for parameter learning. Finally, the proposed ANFIS2 is used to control of a flexible link robot arm. Simulation results shows the proposed ANFIS2 with Gaussian type-1 fuzzy set as coefficients of linear combination of input variables in the consequent part has good performance and high accuracy but more training time.

کلیدواژه‌ها

ANFIS؛ Interval Type-2 Fuzzy Sets؛ Inverse Control؛ Flexible Link Robot