Indonesian Journal of Electrical Engineering and Computer Science Vol. 19, No. 2, August 2020, pp. 586~592 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v19.i2.pp586-592  586 Journal homepage: http://ijeecs.iaescore.com Thermal comfort control via air conditioning system using fuzzy neural network feedback controller Somaye A. Mohamadi, Abdulraheem J. Ahmed Department of Information Technology, Zakho Technical Institute, Duhok Polytechnic University, Iraq Article Info ABSTRACT Article history: Received Dec 24, 2019 Revised Feb 26, 2020 Accepted Mar 13, 2020 Despite their complexity and uncertainty, air conditioning systems should provide the optimal thermal conditions in a building. These controller systems should be adaptable to changes in environmental parameters. In most air conditioning systems, today, there are On/Off controllers or PID in more advanced types, which, due to different environmental conditions, are not optimal and cannot provide the optimal environmental conditions. Controlling thermal comfort of an air conditioning system requires estimation of thermal comfort index. In this study, fuzzy controller was used to provide thermal comfort in an air conditioning system, and neural network was used to estimate thermal comfort in the feedback path of the controller. Fuzzy controller has a good response given the non-linear features of air conditioning systems. In addition, the neural network makes it possible to use thermal comfort feedback in a real-time control. Keywords: Air conditioning Fuzzy controller Neural network Thermal comfort Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Somaye A. Mohamadi, Duhok Polytechnic University, 61 Zakho Road, Duhok, Iraq. Email: abdulraheem.ahmed@dpu.edu.krd 1. INTRODUCTION Today, modern heating, purification and air conditioning systems should provide comfort of the occupants in addition to optimal energy consumption [1]. The conventional controllers used in air conditioning systems are On/Off switch type, which, in addition to being non-optimal, do not provide optimal environmental conditions [2]. Modern air conditioning systems can manage the power consumption more efficiently[3]. In addition, the proportional-integral-derivative (PID) controllers are Preferred in air conditioning systems because of their simplicity, structure, ease of use, good stability, high reliability and zero steady-state error. Yet, the process of setting up an air conditioning system may take up to a few days to find the appropriate PID mode for the controller. This condition becomes much more difficult when there is a need for re-rendering, especially when the air conditioning system is large [4]. Many control loops are not properly set up in effect due to the lack of adequate knowledge of the control engineers of the process. This non-optimal setting increases energy consumption and, at the same time, leads to improper performance of the system under different conditions, and thus, in addition to being non- optimal, it does not provide optimal environmental conditions [5]. This is very important when it is necessary to maintain an environment in particular conditions (such as museums and sterilized rooms). On the other hand, due to the complexity and uncertainty in the variables, which is one of the main characteristics of the dynamic behavior of these systems, the use of more advanced controllers in this field is expanding. Therefore, the developing a mountable technology on air conditioning systems is very important [6-10]. Various controllers have been proposed in this regard. Some of these controllers are used to adjust the available PID controllers. In this case, depending on various conditions, the function of PID controller's gain factor is determined by the fuzzy logic. In some others, given the above-mentioned properties for air conditioning systems, several multi-input multi-output systems have been controlled using a central fuzzy controller [11].