Optimisasi Sistem Pengendalian Temperatur Panel Surya dengan Water spraying dan Forced Air Cooling Menggunakan Adaptive Neuro-Fuzzy Inference System (ANFIS)

Rochman, Arif Noor (2025) Optimisasi Sistem Pengendalian Temperatur Panel Surya dengan Water spraying dan Forced Air Cooling Menggunakan Adaptive Neuro-Fuzzy Inference System (ANFIS). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5009211088-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (7MB) | Request a copy

Abstract

Peningkatan efisiensi operasional dan stabilitas kinerja sistem membutuhkan pengendalian temperatur adaptif. Penelitian ini mengembangkan sistem pengendalian temperatur hibrida menggunakan kombinasi pendinginan water spraying dan forced air cooling, dikendalikan oleh Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS dipilih karena kemampuannya dalam pembelajaran adaptif dan inferensi berbasis aturan, memungkinkan sistem beradaptasi dengan perubahan kondisi. Data eksperimen dari prototipe digunakan untuk melatih dan memvalidasi model ANFIS. Didapatkan hasil Error Steady State (ESS) sebesar 0,5°C dan Root Mean Square Error (RMSE) sebesar 1°C pada kondisi steady-state yang optimal, serta kemampuan tracking yang baik terhadap perubahan setpoint dinamis. Performa ini menunjukkan keunggulan dibandingkan metode kontrol konvensional. Efisiensi daya menunjukkan peningkatan mencapai 20% daripada tanpa menggunakan sistem ANFIS, menunjukkan kontribusi positif terhadap kinerja panel surya.
===================================================================================================================================
Improving operational efficiency and system performance stability requires adaptive temperature control. This research develops a hybrid temperature control system using a combination of water spraying and forced air cooling, controlled by an Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS was selected for its adaptive learning capabilities and rule-based inference, enabling the system to adapt to changing conditions. Experimental data from the prototype was used to train and validate the ANFIS model. The results showed an Error Steady State (ESS) of 0.5°C and Root Mean Square Error (RMSE) of 1°C under optimal steady-state conditions, along with good tracking capability for dynamic setpoint changes. This performance demonstrates superiority compared to conventional control methods. Power efficiency showed an improvement of up to 20% compared to systems without ANFIS implementation, indicating a positive contribution to solar panel performance.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	ANFIS, Forced Air Cooling, Pengendalian Temperatur, Temperature Control, Water spraying.
Subjects:	Q Science > QC Physics > QC271.8.C3 Calibration Q Science > QC Physics > QC271 Temperature measurements Q Science > QC Physics > QC320 Heat transfer T Technology > T Technology (General) > T57.62 Simulation
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Arif Noor Rochman
Date Deposited:	04 Aug 2025 04:39
Last Modified:	04 Aug 2025 04:39
URI:	http://repository.its.ac.id/id/eprint/125065

Actions (login required)

View Item