International Journal of Soft Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-1, March 2012 417 Abstract — This paper provides the design for air conditioning system using fuzzy logic as well as neuro-fuzzy method. Inputs taken for the air conditioning system are from temperature and humidity sensors and the output is to control the compressor speed. The simulation results of both systems using fuzzy logic and neuro-fuzzy are shown as well as compared to signify better of the two. Index Terms— air conditioning system, fuzzy logic control, neuro-fuzzy, rule base. I. INTRODUCTION Nowadays, air conditioning systems are commonly found in homes and in public enclosed spaces to create a comfortable environment [1]. Air conditioning has developed to be an integrated industry including environment, energy, machinery, electronics, and automatic control technology, so that its several major trends of development would be health, environmental protection, energy saving, intelligence and diversity. Air conditioning is not only a name of the product, but by using the ideas and methods of air conditioning to create comfort and natural living environment while at the same time reduce the ravages of nature and achieve the real sense harmony of human and nature to maximum extent [2].Air conditioning system is a control system that have complex interactions between physical variables and is too nonlinear. Conventional design methods require the development of a mathematical model of the control system and then use of this model to construct the controller that is described by the differential equations. Mathematical model is an abstraction and cannot perfectly represent all possible dynamics of any physical process. Even if a relatively accurate model of a dynamic system can be developed, it is often too complex to use for development of controller, especially for many conventional design procedures as they require restrictive assumptions for the plant, e.g. linearity. As opposed to conventional control design, fuzzy logic control focus on gaining an intuitive understanding of how to best control the process or plant [3]. Manuscript Received February 26, 2012 Arshdeep Kaur, Pursuing M.Tech., University College Of Engineering, Patiala (Punjab), India (Email: arshdeep_24@yahoo.in) Amrit Kaur, Assistant Professor, Punjabi University, Patiala (Punjab), India (Email: amrit_aks@yahoo.ca) Fuzzy logic control appears very useful when linearity and time invariance of the controlled process cannot be assumed, when the process lacks a well posed mathematical model, or when human understanding of the process is very different from its model [4]. Fuzzy logic control provides a formal methodology for representing, manipulating and implementing a human‟s experience based knowledge about how to control a system [3]. Fuzzy logic uses human knowledge and expertise to deal with uncertainties in the process of control [5]. Fuzzy controller block diagram is shown in Fig.1. It has four main parts: (i) Fuzzification interface, simply modifies and converts inputs into suitable linguistic values so that can be compared to the rules in the rule base. (ii) Rule base, holds the knowledge in the form of a set of rules, of how best to control the system. (iii) Inference mechanism, evaluates which control rules are relevant at current time and then decides what the input to the plant should be. (iv) Defuzzification interface, converts the conclusions reached by the inference mechanism into crisp ones. Fig.1. Block diagram of Fuzzy controller The affectivity of the fuzzy models representing non linear input-output relationships depends on the fuzzy partition of the input output spaces. Therefore, the tuning of membership functions becomes an important issue in fuzzy modeling. Since this tuning task can be viewed as an optimization problem neural networks offer a possibility to solve this problem [6]. A neuro-fuzzy system is a fuzzy system that uses a learning algorithm derived from or inspired by neural network theory to determine its parameters by processing data samples. The rest of the paper is organized as follows: Section 2 gives the fuzzy logic control algorithm and Section 3 neuro-fuzzy algorithm for air conditioning system. Section 4 provides the results. Section 5 Conclusion. COMPARISON OF FUZZY LOGIC AND NEURO FUZZY ALGORITHMS FOR AIR CONDITIONING SYSTEM Arshdeep Kaur, Amrit Kaur