Rancang Bangun Sistem Pengendalian Level Mini Plant Separator Tiga Fasa Menggunakan Neural Network PID Berbasis Internet of Things

Prananda, Sulthan Ariq (2022) Rancang Bangun Sistem Pengendalian Level Mini Plant Separator Tiga Fasa Menggunakan Neural Network PID Berbasis Internet of Things. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 02311840000036-Undergraduate_Thesis.pdf - Accepted Version Download (3MB)

Abstract

Proses dalam industri oil & gas terdapat proses separasi minyak mentah pada instrumen separator tiga fasa. Separator perlu dilakukan pengendalian agar produksi minyak stabil dan hasil yang maksimal. Penelitian ini dilakukan perancangan sistem pengendalian PID yang bersifat adaptif menggunakan Neural Network yang akan melakukan tuning PID secara adaptif selama proses separasi berlangsung. Sistem kendali separator ini dapat dikendalikan secara jarak jauh karena sistem dirancang dengan kombinasi antara sistem WSAN menggunakan modul Long Range (LoRa) serta Internet of Things (IoT) yang terintegrasi dengan sistem cloud database. Sistem dirancang menggunakan protokol IEEE 802.15.4g dan protokol HTTP. Hasil penelitian sistem komunikasi WSAN dengan device LoRa dapat berkomunikasi secara real-time pada jarak 100 m dengan delay time 145 ms. Pada pengendalian level campuran respon sistem menghasilkan selisih rise time 12.374 detik lebih rendah dan settling time lebih rendah 29.445 detik dari pengendali PID. Pada pengendalian level minyak respon sistem menghasilkan selisih rise time 16.768 detik lebih rendah dan settling time lebih rendah 101.052 detik dari pengendali PID. Kedua pengendali tidak memiliki perbedaan pada overshoot maksimum dan error steady state.
====================================================================================================================================
Process in oil & gas industry has separation process in a three-phase separator instrument. The separator needs to be controlled so that the oil production is stable and get maximum results. In this study, an adaptive PID control system was designed using a Neural Network which will adjust the PID adaptively during separation process. This control system can be controlled remotely because the system is designed with a combination of WSAN system using Long Range (LoRa) modules and Internet of Things (IoT) modules that are integrated with a cloud database system. The system is designed using protocol IEEE 802.15.4g and HTTP. The results showed that the WSAN communication system with LoRa devices can communicate in real-time at 100 meters with average delay time is 145 ms. When mixed level controlled, the dynamic response system produces a rise time of 12.374 seconds and a settling time of 29.445 seconds lower than the PID controller. When control oil level, the dynamic response system produces a rise time of 16.768 seconds and a settling time of 101.052 seconds lower than the PID controller. Both control systems have no difference in maximum overshoot and steady state error.

Item Type:	Thesis (Other)
Additional Information:	RSF 629.89 Pra r-1 • 2022
Uncontrolled Keywords:	IoT, Neural Network PID, Three Phase Separator, WSAN
Subjects:	Q Science > QA Mathematics > QA76.5915 Ubiquitous computing. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TJ Mechanical engineering and machinery > TJ223 PID controllers
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	- Davi Wah
Date Deposited:	02 Oct 2024 05:17
Last Modified:	02 Oct 2024 05:17
URI:	http://repository.its.ac.id/id/eprint/115717

Actions (login required)

View Item