INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 9, ISSUE 04, APRIL 2020 ISSN 2277-8616 IJSTR©2020 2096 Design and Development of a Fire Evacuation System Using Fuzzy Logic Control Allie B. Villanueva, Ralph Sherwin A. Corpuz Abstract— Fires are among the worst disasters that can happen anywhere, anytime, and to anyone, for so many reasons. The risks are even higher for highly-congested areas and public buildings where evacuation schemes are not effectively planned and implemented. There is a wide-range of fire-sensing technologies available in the market to prevent fire incidents, however, the extent of flexibility and reliability of these devices are still subject for further improvements. This paper presents the design and development of a Fire Evacuation System (FES) using Mamdani-type Fuzzy Logic Control (FLC) with the main intent to improve responsiveness and reliability of fire detection. The authors compared two types of smoke sensors then interfaced with a microcontroller unit, relay drivers, Light Emitting Diodes (LED) indicators, and other system peripherals to simulate the existence of smoke and to indicate the evacuation map. The authors further implemented the FLC rules using C programming language in an Arduino Integrated Development Environment (IDE). Testing results revealed that there is no significant difference on the responsiveness of the two smoke sensors with independent T-test value of t (26.131) = -0.026 and p = 0.979. Likewise, test results further proved that there is no significant difference on the reliability performance of the smoke sensors and LED indicators with dependent T-test value of tA_ON (19) = -0.847; pA_ON = 0.408; tA_OFF (19) = 0.678; pA_OFF = 0.506; tB_ON (19) = -0.764; pB_ON = 0.454; tB_OFF (19) =1.212; pB_OFF = 0.240 in activated and deactivated modes, respectively. These results confirmed that the prototype is responsive and reliable, and the use of FLC is effective for the design and development of fire evacuation systems. Index Terms— Fuzzy Logic Control, fire evacuation map, microcontroller applications, Mamdani FLC, fire management system —————————— u —————————— 1 INTRODUCTION IRES are among the hazardous incidents that can happen to any people, properties, or location. Ineffective interventions on fires can result to significant damages, injuries, and even deaths [1]. In the Philippines, fires usually happen in highly- densed areas, such as Metro Manila, in which the most common root-causes are attributed to faulty electrical connections, lit cigarette butts, and open flames from unattended stoves [2]. According to the Bureau of Fire Protection, there are 72,318 recorded incidents; 4,091 injuries; 1,203 deaths; and PhP 18.8 billion estimated damages for the year 2012-2016 alone [3]. Trends show that there is an increasing rate of fire incidents in the country year after year, which causes an alarm among authorities and common people alike. Despite being potentially disastrous to humanity and to the community, fires are also controllable to certain extents, hence, the implementation of preventive programs, activities and methodologies, such as evacuation plans and drills, are helpful for people to avoid the risks and other emergencies [4]. Similarly, the utilization of various fire-fighting facilities also have positive impacts in managing fires for household, work, or public use. Today, there is a wide range of commercially-available sensors used for fire detection. These sensors can be categorized in terms of their capability to detect levels of temperature, humidity, carbon monoxide, smoke, Liquified Petrolium Gas (LPG), etc. [5]. These sensors are found to be effective for specific applications, can work as stand-alone units, or can also be integrated with existing fire alarm systems [6], wireless multiple sensors [7], GSM networks [8], multi-thread embedded systems [9], etc. In designing the frameworks of these technologies, Artificial Intelligence (AI) is one of the most recently-explored approaches for fire management purposes [6]. The common AI techniques used are neural networks [10], image processing [11], fuzzy logic control [12], support vector machines [13], Internet of Things (IOT) [6], etc. While each technique has its own strengths and weaknesses, the most common issues still persist due to the verity of certain factors, such as the uncertainty of fire system structures, mutation of fire sources, inefficiency of existing controls, and the nature of working conditions. Particularly, these issues are more prevalent in public organizations or buildings, such as state universities, which have larger internal area and population size, more complex channel setting and structure design, overloaded electrical system, and inefficient evacuation schemes, thus resulting to higher risks of fires and emergencies [6]. With the above-mentioned AI techniques, Fuzzy Logic Control (FLC) is one of the most popular approaches studied extensively for fire management purposes [14], [15], [16], [17]. FLC is a mathematical tool used to handle logic of imprecision, analogous to the capabilities of the human brain [15, 18]. Shown on Fig. 1 is the FLC process model, which has five basic sub- processes, namely: fuzzification, application of fuzzy operations, implication, aggregation, and defuzzification. In F ———————————————— • Allie B. Villanueva, Assistant Professor, Electronics Engineering Technology Department, Technological University of the Philippines, Manila, Philippines. E-mail: allie_villanueava@tup.edu.ph • Ralph Sherwin A. Corpuz, Associate Professor, Electronics Engineering Technology Department, Technological University of the Philippines, Manila, Philippines. E-mail: ralphsherwin_corpuz@tup.edu.ph