Implementasi Metode Electronic Nose Pada Sistem Kontrol Gas Hidrogen Dalam Ruangan

Sudama, Kadek Ari (2022) Implementasi Metode Electronic Nose Pada Sistem Kontrol Gas Hidrogen Dalam Ruangan. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6022201043-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2024. Download (6MB) | Request a copy

Abstract

Kebocoran gas hidrogen pada ruangan tertutup dapat menimbulkan bahaya kebakaran serta kualitas udara yang buruk. Konsentrasi gas hidrogen 4-75% di udara sangat mudah terbakar dan dapat menyebabkan ledakan. Penggunaan gas hidrogen telah banyak diaplikasikan baik di industri atau perkantoran. Pada industri pengolahan minyak pelumas, gas hidrogen digunakan dalam proses pemurnian produk yang dihasilkan dalam skala besar melalui proses Steam Methane Reforming (SMR) dari gas natural yang berpotensi menyebabkan bahaya kebakaran dan ledakan. Gas hidrogen juga dimanfaatkan untuk menunjang pengamatan udara atas oleh Badan Meteorologi Klimatologi dan Geofisika (BMKG). Dalam pengamatannya gas hidrogen digunakan sebagai pengisi balon untuk radiosonde dan pilot balon. Proses pengisian dilakukan dalam ruangan khusus yang dapat menyebabkan kebakaran akibat bocornya gas. Suatu sistem kontrol gas hidrogen memerlukan metode pengklasifikasian jenis gas untuk menghindari false alarm yang mengakibatkan sistem kontrol aktif karena keberadaan jenis gas lainnya. Sistem electronic nose yang terdiri dari deret sensor gas dan neural network telah dibangun untuk mendeteksi kebocoran gas hidrogen di dalam ruangan. Data dari masing-masing sensor digunakan sebagai inputan untuk klasifikasi gas pada neural network. Kontrol Proportional-Integral-Derivative (PID) digunakan untuk mengontrol exhaust fan untuk menghilangkan kebocoran gas hidrogen di dalam ruangan. Electronic nose dan kontrol PID diimplementasikan pada mikrokontroller Arduino Nano. Hasil eksperimen menunjukkan bahwa sistem ini dapat mengklasifikasikan beberapa jenis gas seperti gas hidrogen, asap kendaraan dan parfum dengan tingkat keberhasilan klasifikasi sebesar 86,67 %. Kontrol PID menjadi aktif ketika gas hidrogen dengan konsentrasi di atas 200 ppm telah diklasifikasi. Monitoring dan peringatan dini berbasis Internet of Things (IoT) digunakan pada sistem untuk mengetahui kondisi gas hidrogen secara realtime. Hasil ini dapat meminimalisir kecelakaan kebocoran hidrogen serta menjaga kualitas udara yang baik.
================================================================================================
Hydrogen gas leaks in a closed room can pose a fire hazard and poor air quality. The concentration of hydrogen gas of 4-75% in the air is highly flammable and can cause explosions. The use of hydrogen gas has been widely applied in both industry and offices. In the lubricating oil processing industry, hydrogen gas is used in the purification process of products produced on a large scale through the Steam Methane Reforming (SMR) process from natural gas which causes fire and explosion hazards. Hydrogen gas is also used to monitor observations of the Meteorology, Climatology and Geophysics Agency (BMKG). In his observations hydrogen gas was used as a balloon filler for radiosondes and balloon pilots. The filling process is carried out in a special room which can cause fires due to gas leaks. A hydrogen gas control system requires a gas type classification method to avoid false alarms that result in the control system being active due to the presence of other types of gas. An electronic nose system consisting of gas sensors array and a neural network has been built to detect hydrogen gas leaks in a room. Data from each sensor is used as input for the classification of gases on the neural network. Proportional-integral-derivative (PID) method is applied to control the exhaust fan to eliminate hydrogen gas leaks in the room. The electronic nose and PID control are implemented on the Arduino Nano microcontroller. The experiment results showed that this system could classify several gases such as hydrogen gas, vehicle smoke, and perfume with a success rate of 86,67%. The PID control becomes active when hydrogen gas with concentrations above 200 ppm has been classified. Internet of Things (IoT) based monitoring and early warning is used in the system to determine the condition of hydrogen gas in real time. These results can minimize and prevent hydrogen gas leaks and maintain good indoor air quality.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	air quality, electronic nose, hydrogen gas leak, PID control, kebocoran gas hidrogen, kontrol PID, kualitas udara
Subjects:	Q Science Q Science > Q Science (General) Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis
Depositing User:	Kadek Ari Sudama Kadek Ari Sudama
Date Deposited:	08 Jul 2022 08:57
Last Modified:	08 Jul 2022 08:57
URI:	http://repository.its.ac.id/id/eprint/94973

Actions (login required)

View Item