American Journal of Applied Sciences 9 (9): 1464-1471, 2012 ISSN 1546-9239 © 2012 Science Publication Corresponding Author: Chatchanayuenyong, T., Faculty of Engineering, Mahasarakham University, T. Khamriang, A. Kantarawichai, Mahasarakham, 44150, Thailand Tel: +6643754322 Ext.3004 Fax: +6643754316 1464 Design and Development of an Intelligent Control by Using Bee Colony Optimization Technique S. Tiacharoen and T. Chatchanayuenyong Faculty of Engineering, Mahasarakham University, T. Khamriang, A. Kantarawichai, Mahasarakham, 44150, Thailand Abstract: Problem statement: In the modern industrial manufacturing system, the efficiency of machine control is essential to reduce waste and increase the output. Most of the manufacturing machines employ an induction motor in their driving system. A number of induction motors must be controlled during machine operation. The more accurately these motors are controlled the higher is the quality of the finished product. Approach: This study focuses on using the Bee Colony Optimization (BCO) to find optimal fuzzy rules and membership functions of a fuzzy speed controller for an indirect field-orientated Induction Motor (IM). The BCO optimizes those quantities so that the controller can control the motor to a desired speed with the minimum rise time and speed error. The fitness function of BCO is defined as rise time and Integral Time Absolute Error (ITAE). An indirect field-orientation method for an IM drive and a description of the BCO are introduced briefly. Results: The speed tracking capability of the Proportional-Integral (PI), fuzzy and BCO optimized fuzzy controllers are compared under no-load and various load conditions with different reference speeds. Conclusion: The designed controller could track to the set point with a relatively minimum rise time and low overshoot compared to the other conventional controllers. Key words: Bee Colony Optimization (BCO), Induction Motor (IM), Integral Time Absolute Error (ITAE), speed tracking capability, conventional controllers, induction motor INTRODUCTION Manufacture of the industry components consumes resources such as materials, capital, time and energy. The manufacturing process outputs are in the form of product and waste materials. To reduce the waste, a number of process parameters must be controlled during machine operation, particularly those determining the rate of material removal. The more accurately these parameters are controlled the higher is the quality of the finished product (Waters, 1996). Automatic control has become an important and integral part of modern manufacturing and industrial processes (Ogata, 1996). For example, automatic control is essential in the numerical control of machine tool in the manufacturing industries, in the design of cars and truck in the automobile industries and in the design of aircraft parts in the aerospace industries (My et al., 2005). In process measurement and control of machine tool accuracy while increasing productivity and reduce waste (Feng et al., 2003). In a machine tool, motion (position and speed) control of the axes is necessary (Esawi and Ashby, 2003). In a turning operation, the cutting speed is directly related to the spindle speed. That relates to speed controller of spindle motor. In the manufacturing process mentioned above, the alternating current asynchronous motors or induction motors are often the preferred choice in industrial drive applications (Vas, 1999). In order to achieve the performance required by industrial drive application, these induction motors have to be controlled effectively. Fuzzy logic controller was based on the fuzzy sets theory of (Zadeh, 1965). The fuzzy logic controller consists of three parts; Fuzzification of input parameters, Inference Engine and Defuzzification of output parameter. The major problems to implement the fuzzy logic controller are the determination of the definition of the membership functions and linguistic state space of the controller rules, of which the optimal solution is always based on the human experience and time-consuming trial-and-error process. A number of optimization techniques in the literature have been employed to solve this problem. Among of these techniques are Genetic Algorithm (Jurado and Valverde, 2005), Tabu Search Algorithm (Lee, 2005),