Perancangan Sistem Monitoring Kadar CO2 Di Udara Pada Steel Calendar Room Menggunakan Machine Learning Dengan Metode Algoritma k-NN Berbasis IoT Di PT X

Putra, Aditya Samratna (2023) Perancangan Sistem Monitoring Kadar CO2 Di Udara Pada Steel Calendar Room Menggunakan Machine Learning Dengan Metode Algoritma k-NN Berbasis IoT Di PT X. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title]
Preview
Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (16kB) | Preview
[thumbnail of Abstract]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (109kB) | Preview
[thumbnail of ToC]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (141kB) | Preview
[thumbnail of Chapter1] Text (Chapter1)
Chapter1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (41kB)
[thumbnail of Chapter2] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (319kB)
[thumbnail of Chapter3] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (142kB)
[thumbnail of Chapter4] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (856kB)
[thumbnail of Chapter5] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (464kB)
[thumbnail of Chapter6] Text (Chapter6)
Chapter6.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (31kB)
[thumbnail of Bibliography]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (101kB) | Preview
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)

Abstract

PT X merupakan perusahaan manufaktur yang memproduksi ban sebagai komoditas penjualan utamanya. Dalam proses pembuatan ban yaitu proses pelapisan antara struktur kawat dan compound terjadi proses pemanasan di suatu mesin calendar yang menimbulkan bau yang menyengat dan berindikasi memiliki kadar polutan yang dapat membahayakan pekerja. Dalam skripsi ini dirancang dan dibuat sistem monitoring kadar CO2 berbasis IoT dengan menggunakan beberapa sensor yang keluarannya diolah dengan algoritma machine learning K-NN. Pengujian sistem dilakukan pada chamber dengan men-trigger kelima sensor tersebut dengan gas dari steel calendar. Kemudian mikrokontroler akan memproses gas tersebut dengan algoritma k-NN. Output dari algoritma k-NN tersebut akan ditampilkan pada LCD 16x2 yang secara bersamaan juga akan menampilkan safety status antara “safe” atau “warning”. Selain ke LCD output data juga akan terekam di database dan tertampil di dashboard Blynk. Proses pengambilan data dilakukan dengan kadar ppm gas yang berbeda-beda, yaitu 25 sampai dengan 200 ppm. Setiap kadar gas dilakukan test pembacaan sebanyak 10 kali untuk setiap masing-masing kadar gas. Berdasarkan pengujian tersebut maka didapatkan bahwa hasil pengujian blackbox untuk sistem monitoring mencapai tingkat keberhasilan 100% terhadap uji fungsionalitas dari pembacaan sensor, kalkulasi nilai sensor, algoritma k-NN, komunikasi serial dari mikrokontroler ke modul komunikasi, menampilkan hasil ke display LCD 16x2, dashboard Blynk, database Google sheets, dan pilot lamp, serta menyimpan dan menambah data di database Google sheets. Hasil tes kadar gas dari ruangan steel calendar dari kadar 25 ppm sampai dengan 200 ppm, dinyatakan aman bagi pekerja. Hasil tes akurasi menunjukkan bahwa hasil ukur antara alat air quality detector KKMOON JSM-131 komersial dengan sistem monitoring yang dibangun memiliki kecocokan yang baik, dengan tingkat akurasi sebesar 99.61%. / PT X is a manufacturing company that produces tires as its main sales commodity. In the tire manufacturing process, namely the coating process between wire structure and compound, a heating process occurs in a calender machine which causes a smelly air indicating that it has pollutant levels that can endanger workers. In this thesis we report the designed and construction of IoT-based CO2 level monitoring system using several sensors which output is processed with a K-NN machine learning algorithm. The results of the gas extraction were tested in the monitoring system chamber with the k-NN algorithm processing so to detect on the amount of CO2 gas levels in ppm in the steel calendar room. System testing is carried out in the chamber by triggering the five sensors with gas from a steel calendar. Then the microcontroller processed the results with the k-NN algorithm. The output of the k-NN algorithm were displayed on a 16x2 LCD which will simultaneously display a safety status between "safe" or "warning". In addition to the LCD, the output will also be recorded in the database and displayed on the Blynk dashboard. The data collection process was carried out with different levels of gas, namely 25 to 200 ppm. Each gas content was tested for readings 10 times. Based on these tests, the blackbox testing results for the monitoring system achieved a 100% success rate on functionality tests from sensor readings, sensor value calculations, k-NN algorithms, serial communication from the microcontroller to the communication module, displaying results to a 16x2 LCD display, Blynk dashboard, Google sheets database, pilot lamp, store and add data to the Google sheets database. The results of the gas level test from the steel calendar room, from 25 ppm to 200 ppm, were declared safe for workers. The accuracy test show that the results of commercial air quality detector KKMOON JSM-131 and the developed monitoring system has a good agreement with an accuracy rate of 99.61%.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Putra, Aditya Samratna
NIM01035200005
adityasamratna17@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Uranus, Henri P
NIDN0302126304
henri.uranus@uph.edu
Uncontrolled Keywords: kadar CO2; sensor MQ; Arduino mega 2560; algoritma k-NN; nodeMCU ESP8266; Google sheets; Blynk
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Electrical Engineering
Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Electrical Engineering
Depositing User: Aditya Samratna Putra
Date Deposited: 17 Feb 2023 11:14
Last Modified: 17 Feb 2023 11:17
URI: http://repository.uph.edu/id/eprint/54502

Actions (login required)

View Item
View Item