SISTEM EARLY WARNING INDUSTRIAL HYGIENE BERBASIS IOT DENGAN PREDIKSI KONDISI BAHAYA MENGGUNAKAN ARTIFICIAL NEURAL NETWORK-MULTI LAYER PERCEPTRON (ANN-MLP)

KHIYAR QOLBA SHIDIQ, . (2026) SISTEM EARLY WARNING INDUSTRIAL HYGIENE BERBASIS IOT DENGAN PREDIKSI KONDISI BAHAYA MENGGUNAKAN ARTIFICIAL NEURAL NETWORK-MULTI LAYER PERCEPTRON (ANN-MLP). Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text File_COVER.pdf Download (1MB)
	Text File_BAB 1.pdf Download (256kB)
	Text FILE_BAB 2.pdf Restricted to Registered users only Download (727kB) | Request a copy
	Text File_BAB 3.pdf Restricted to Registered users only Download (738kB) | Request a copy
	Text File_BAB 4.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text File_BAB 5 .pdf Restricted to Registered users only Download (230kB) | Request a copy
	Text File_DAFTAR PUSTAKA.pdf Download (233kB)
	Text File_LAMPIRAN.pdf Restricted to Registered users only Download (768kB) | Request a copy

Abstract

Penelitian ini bertujuan untuk merancang dan membangun sistem monitoring industrial hygiene berbasis Internet of Things (IoT) menggunakan komunikasi Modbus RTU, mengimplementasikan metode Artificial Neural Network Multi Layer Perceptron (ANN-MLP) untuk memprediksi kondisi bahaya satu jam ke depan, serta mengetahui performa sistem dalam melakukan monitoring suhu dan tingkat kebisingan secara real-time. Metode penelitian yang digunakan adalah metode rekayasa teknik (Forward Engineering) yang meliputi analisis kebutuhan, perancangan sistem, pengembangan sistem, implementasi sistem, serta pengujian dan evaluasi.. Sistem dikembangkan menggunakan Raspberry Pi 3 B+ sebagai perangkat edge computing, sensor suhu SHT20, sensor kebisingan RT-ZS-BZ-485, komunikasi Modbus RTU, basis data Supabase, dashboard Grafana, serta model ANN-MLP berbasis TensorFlow Lite. Hasil penelitian menunjukkan bahwa sistem berhasil melakukan monitoring suhu dan tingkat kebisingan secara real-time, mengirimkan data ke basis data, serta menampilkan informasi melalui dashboard Grafana dan LCD I2C. Hasil pengujian sensor menunjukkan nilai Mean Absolute Error (MAE) sebesar 0,91°C untuk sensor suhu dan 2,78 dB untuk sensor kebisingan. Model ANN-MLP menghasilkan akurasi prediksi di atas 90% pada kondisi ruangan stabil maupun tidak stabil sehingga mampu memberikan prediksi kondisi lingkungan satu jam ke depan sebagai early warning system. Berdasarkan hasil tersebut, sistem yang dikembangkan dinyatakan layak digunakan sebagai sistem monitoring industrial hygiene berbasis IoT dengan kemampuan prediksi kondisi bahaya secara real-time.***** This study aims to design and develop an Internet of Things (IoT)-based industrial hygiene monitoring system using Modbus RTU communication, implement the Artificial Neural Network Multi-Layer Perceptron (ANN-MLP) method to predict hazardous conditions one hour ahead, and evaluate the system's performance in real-time temperature and noise monitoring. The research employed the engineering method (Forward Engineering), consisting of requirements analysis, system design, implementation, testing, and evaluation. The developed system utilizes a Raspberry Pi 3 Model B+ as an edge computing device, an SHT20 temperature sensor, an RT-ZS-BZ-485 noise sensor, Modbus RTU communication, a Supabase database, a Grafana dashboard, and an ANN-MLP model implemented using TensorFlow Lite. The results show that the system successfully performs real-time monitoring of temperature and noise levels, transmits data to the database, and displays monitoring information through the Grafana dashboard and LCD I2C. Sensor testing produced a Mean Absolute Error (MAE) of 0.91°C for temperature measurement and 2.78 dB for noise measurement. The ANN-MLP model achieved prediction accuracy of over 90% under both stable and unstable environmental conditions, enabling one-hour-ahead environmental condition prediction as an early warning system. Therefore, the developed system is considered feasible for IoT-based industrial hygiene monitoring with real-time hazardous condition prediction capability.

Item Type:	Thesis (Sarjana)
Additional Information:	1). Ir. Heri Firmansyah, S.T., M.T. 2). Churnia Sari, S.T., M.T.
Subjects:	Teknologi dan Ilmu Terapan > Teknik Energi > Energi Listrik Teknologi dan Ilmu Terapan > Teknologi (umum) Teknologi dan Ilmu Terapan > Teknik Elektronika Teknologi dan Ilmu Terapan > Teknik Energi Teknologi dan Ilmu Terapan > Manufaktur
Divisions:	FT > D IV Teknologi Rekayasa Otomasi
Depositing User:	Users 34205 not found.
Date Deposited:	05 Aug 2026 04:51
Last Modified:	05 Aug 2026 04:51
URI:	http://repository.unj.ac.id/id/eprint/68503

Actions (login required)

View Item