Fuzzy logic controller of indoor air quality monitoring and control system for risk reduction of Covid-19 transmission

• Main Authors: Hishamuddin, Muhammad Izharuddin, Mansor, Hasmah, Zahaba, Maryam, Md Yusoff, Nelidya, Gunawan, Teddy Surya
• Format: Conference or Workshop Item
• Language: English
• Published: Institute of Electrical & Electrical Engineers 2022
• Subjects: T Technology (General)
• Online Access: http://irep.iium.edu.my/100956/1/100956_Fuzzy%20logic%20controller%20of%20indoor.pdf; http://irep.iium.edu.my/100956/; https://ieeexplore.ieee.org/document/9929189
• Institution: Universiti Islam Antarabangsa Malaysia

The risk of Coronavirus disease (COVID-19) was reported to be higher in the indoor environment due to poor ventilation systems. A good and efficient ventilation system in enclosed spaces can help reduce the risk of infection. Thus, it is important to monitor the efficiency of the ventilation system. Therefore, this research aims to develop an indoor air quality (IAQ) monitoring and control system using the fuzzy logic controller (FLC). Three IAQ parameters were selected in this study (temperature, relative humidity (RH), and carbon dioxide (CO2) concentration). In addition, benchmark testing was done to test the efficiency of the IAQ monitoring and control system. The system's engine is a microcontroller, which collects data on IAQ parameters, and is equipped with an exhaust fan as the ventilation strategy. The device aids in monitoring IAQ parameters and is equipped with an exhaust fan as the ventilation strategy. The device, which aids in monitoring IAQ, was created using a machine learning technique, fuzzy logic controller. The performance of the proposed air quality monitoring and control system was also investigated and validated through several experiments. The system was tested by modifying each parameter individually while keeping the controlled parameters safe. In addition, the tests were changed to include the existence of a controller in the system to see how ventilation affects the measured metrics. The test revealed that without the controller, the parameters take a long time to return to their initial values, however with the controller, the readings return to their original values faster than normal. The system also demonstrated that by following the fuzzy rules set, it is capable of handling two parameters at the same time.