Claim Missing Document
Check
Articles

Found 2 Documents
Search

OPTIMUM MULTILEVEL THRESHOLDING HYBRID GA-PSO BY ALGORITHM dwi taufik hidayat; Isnan .; Muhammad Ali Fauzi
Jurnal Ilmu Komputer dan Informasi Vol 6, No 1 (2013): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information)
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (482.412 KB) | DOI: 10.21609/jiki.v6i1.210

Abstract

The conventional multilevel thresholding methods are efficient for bi-level thresholding. However, these methods are computationally very expensive for use in multilevel thresholding because the search of optimum threshold do in depth to optimize the objective function. To overcome these drawbacks, a hybrid method of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), called GA-PSO, based multilevel thresholding is presented in this paper. GA-PSO algorithm is used to find the optimal threshold value to maximize the objective function of the Otsu method. GA-PSO method proposed has been tested on five standard test images and compared with particle swarm optimization algorithm (PSO) and genetic algorithm (GA). The results showed the effectiveness in the search for optimal multilevel threshold of the proposed algorithm.
DEVELOPMENT OF AN EARLY DETECTION SYSTEM FOR GAS TURBINE OIL LEAKS USING FUZZY LOGIC AND IOT Erwin Dhaniswara; Farid Budianto Putra; Dwi Taufik Hidayat; Eddy Lybrech Talakua; Tamaji
TESLA: Jurnal Teknik Elektro Vol 27 No 2 (2025): TESLA : Jurnal Teknik Elektro (IN PRESS)
Publisher : Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/tesla.v27i2.35674

Abstract

The gas turbine is one of the primary energy sources with high efficiency, where the lubrication system plays a crucial role in maintaining mechanical reliability and reducing operational risks. Oil leakage in the cooling tower can lead to overheating, reduced machine efficiency, and environmental contamination. This study aims to design an early detection system for oil leakage in a gas turbine cooling tower using fuzzy logic and the Internet of Things (IoT). The system integrates a photodiode sensor to detect light intensity changes and a DS18B20 temperature sensor, processed through an ESP32 microcontroller and displayed on an IoT-based real-time monitoring dashboard using MQTT protocol and Node-RED. The fuzzy Sugeno method classifies leakage levels into Normal, Light, Medium, and Severe categories based on the sensor readings. Laboratory testing shows that the photodiode sensor has a maximum deviation of 1.8%, while the temperature sensor error is 0.43%. The developed system successfully detects oil leakage concentration changes with latency under one second and provides accurate alerts through the IoT dashboard. This research contributes to preventive maintenance in industrial environments by enabling early oil leak detection, minimizing repair costs, and reducing environmental risks. Abstrak Turbin gas merupakan salah satu sumber tenaga utama dengan efisiensi tinggi, di mana sistem pelumasan berperan penting untuk menjaga keandalan mekanis dan mengurangi risiko operasional. Kebocoran minyak pelumas pada cooling tower dapat menyebabkan overheating, penurunan efisiensi mesin, dan pencemaran lingkungan. Penelitian ini bertujuan untuk merancang sistem deteksi dini kebocoran minyak pelumas pada cooling tower mesin gas turbin berbasis logika fuzzy dan Internet of Things (IoT). Sistem ini mengintegrasikan sensor photodioda untuk mendeteksi perubahan intensitas cahaya dan sensor suhu DS18B20, yang diproses oleh mikrokontroler ESP32 serta ditampilkan melalui dashboard pemantauan real-time berbasis IoT menggunakan protokol MQTT dan Node-RED. Metode fuzzy Sugeno digunakan untuk mengklasifikasikan tingkat kebocoran menjadi Normal, Ringan, Sedang, dan Parah berdasarkan pembacaan sensor. Pengujian laboratorium menunjukkan bahwa sensor photodioda memiliki deviasi maksimum sebesar 1,8%, sedangkan sensor suhu memiliki error sebesar 0,43%. Sistem yang dikembangkan berhasil mendeteksi perubahan konsentrasi minyak dengan latency kurang dari satu detik dan memberikan peringatan akurat melalui dashboard IoT. Penelitian ini berkontribusi pada peningkatan pemeliharaan preventif di lingkungan industri dengan memungkinkan deteksi dini kebocoran minyak pelumas, mengurangi biaya perbaikan, dan menekan risiko pencemaran lingkungan