Applied Soft Computing 28 (2015) 226–236 Contents lists available at ScienceDirect Applied Soft Computing j ourna l ho me page: www.elsevier.com/locate /asoc Sugeno fuzzy PID tuning, by genetic-neutral for AVR in electrical power generation Abdullah J.H. Al Gizi a,b,∗ , M.W. Mustafa a , Nasir A. Al-geelani c , Malik A. Alsaedi c a Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Johor, Malaysia b Foundation of Technical Education, Institute of Technology Baghdad, Iraq c Institute of High Voltage and High Current, Universiti Teknologi Malaysia, 81310 Johor, Malaysia a r t i c l e i n f o Article history: Received 23 October 2013 Received in revised form 23 September 2014 Accepted 22 October 2014 Available online 9 December 2014 Keywords: AVR system Develop the rule base Design a PID controller GA RBF-NN Sugeno fuzzy logic a b s t r a c t We report a novel design method for determining the optimal proportional-integral-derivative (PID) controller parameters of an automatic voltage regulator (AVR) system, using a combined genetic algo- rithm (GA), radial basis function neural network (RBF-NN) and Sugeno fuzzy logic approaches. GA and a RBF-NN with a Sugeno fuzzy logic are proposed to design a PID controller for an AVR system (GNFPID). The problem for obtaining the optimal AVR and PID controller parameters is formulated as an optimiza- tion problem and RBF-NN tuned by GA is applied to solve the optimization problem. Whereas, optimal PID gains obtained by the proposed RBF tuning by genetic algorithm for various operating conditions are used to develop the rule base of the Sugeno fuzzy system and design fuzzy PID controller of the AVR system to improve the system’s response (∼0.005 s). The proposed approach has superior features, including easy implementation, stable convergence characteristic, good computational efficiency and this algorithm effectively searches for a high-quality solution and improve the transient response of the AVR system (7E-06). Numerical simulation results demonstrate that this is faster and has much less computational cost as compared with the real-code genetic algorithm (RGA) and Sugeno fuzzy logic. The proposed method is indeed more efficient and robust in improving the step response of an AVR system. © 2014 Elsevier B.V. All rights reserved. 1. Introduction The AVR is utilized for controlling the terminal voltage by reg- ulating the exciter voltage of the generator, while the AVR system optimal control is performed by the PID inside the AVR. The PID is in charge of the optimal control of AVR system possessing differential, proportional and integral coefficients. The real-coded genetic algorithm (RGA) is applied to generate the optimal PID parameters for the formulation of the fuzzy rules [1]. The AVR system has differential, proportional, and integral coefficients [2]. Minglin proposed a method for designing PID- like fuzzy controller with FPGAV. The feed forward fuzzy PID controller has been used to [3] improve the performance of high pressure common rail system. The performance of current hybrid fuzzy PID controller is somewhat poor and the changes in the system parameters require a new adjustment variable of PID controller. To overcome this difficulty, Sinthipsomboon et al. [4] developed a hybrid system of fuzzy and fuzzy self-tuning PID ∗ Corresponding author. Tel.: +60 162410406; fax: +60 162410406. E-mail address: abdullh969@yahoo.com (A.J.H. Al Gizi). controller. An improved fuzzy PID controller is employed [5,6] to control brushless DC motor speed. An adaptive-network-based fuzzy logic power system stabilizer (PSS) is proposed by [7,8]. In this research a novel power system stabilizer for damping both local and global modes of an interconnected system based on neuro fuzzy (hybrid) system is developed [9]. This paper is concerned with the application of an adaptive fuzzy logic controller to both single and multi-machine power system simulations. Jinwook et al. [10] proposed the design and stability analysis of Takagi–Sugeno–Kang (TSK)-type full-scale fuzzy proportional-integral-derivative (PID) controller. The fluctuation in temperature is further improved by self-setting fuzzy PID control algorithm [11]. An improved fuzzy PID controller algorithm based on DSP is introduced [12]. Zhang et al. [13] designed a new algorithm of vehicle stability adaptive PID control with single neuron network. Kun et al. [14] used radi- cal basis function (RBF) to develop an optimal PID controller called direct-drive permanent magnet linear synchronous motor (PMSM). A linear-quadratic regulator (LQR) method is implemented to improve the PID controller for a universal second-order system [15] which required a good selection of weighting functions for accept- able performance. Computational techniques such as GA and fuzzy logic are used for analytic solution [6,10–12] which resulted the http://dx.doi.org/10.1016/j.asoc.2014.10.046 1568-4946/© 2014 Elsevier B.V. All rights reserved.