RANCANG BANGUN SISTEM DETEKSI KONDISI PANEL SURYA BERBASIS ESP32-CAM DAN MODEL YOLOv8

Anwar, Muhammad Choirul (2026) RANCANG BANGUN SISTEM DETEKSI KONDISI PANEL SURYA BERBASIS ESP32-CAM DAN MODEL YOLOv8. Undergraduate thesis, Universitas Nusantara PGRI Kediri.

	Text (Full text) RAMA_55201_2213020110.pdf - Accepted Version Restricted to Registered users only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text (Similarity) RAMA_55201_2213020110_SIMILARITY.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (6MB)
	Text (Cover sd BAB 1 + References) RAMA_55201_2213020110_0707079001_0710018501_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (865kB)
	Text (BAB 2) RAMA_55201_2213020110_0707079001_0710018501_02.pdf - Accepted Version Restricted to Registered users only Available under License Creative Commons Public Domain Dedication. Download (545kB) | Request a copy
	Text (BAB 3) RAMA_55201_2213020110_0707079001_0710018501_03.pdf - Accepted Version Restricted to Registered users only Available under License Creative Commons Public Domain Dedication. Download (870kB) | Request a copy
	Text (BAB 4) RAMA_55201_2213020110_0707079001_0710018501_04.pdf - Accepted Version Restricted to Registered users only Available under License Creative Commons Public Domain Dedication. Download (818kB) | Request a copy
	Text (BAB 5) RAMA_55201_2213020110_0707079001_0710018501_05.pdf - Accepted Version Restricted to Registered users only Available under License Creative Commons Public Domain Dedication. Download (190kB) | Request a copy
	Text (References) RAMA_55201_2213020110_0707079001_0710018501_06_ref.pdf - Bibliography Available under License Creative Commons Public Domain Dedication. Download (169kB)
	Text (Lampiran) RAMA_55201_2213020110_0707079001_0710018501_07_lamp.pdf - Accepted Version Restricted to Registered users only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Penelitian ini mengembangkan sistem monitoring kondisi panel surya berbasis arsitektur hybrid dua tahap untuk mengidentifikasi 7 kelas kondisi secara real-time dan hemat bandwidth. Menggunakan model Waterfall dan metode kuantitatif, sistem diuji menggunakan dataset Roboflow sebanyak 6.218 citra yang mencakup kelas Bird Drop, Defective, Dust, Leaf, Non-Defective, Physical Damage, dan Snow. Hasil pengujian menunjukkan integrasi ESP32-CAM dengan metode Frame Difference sebagai pre-detector lokal sukses memangkas transmisi data dengan hanya mengirimkan frame anomali ke server. Pada server, model YOLOv8 Nano (~6,2 MB) berhasil melakukan klasifikasi multi-kelas dengan waktu inferensi cepat 85,4 ms/frame pada CPU laptop menengah. Evaluasi sistem menghasilkan presisi 72,80%, recall 68,66%, F1-Score 70,67%, dan mAP50 68,13%, membuktikan sistem ini andal, responsif, dan efisien untuk monitoring nirkabel.

Available Versions of this Item

• RANCANG BANGUN SISTEM DETEKSI KONDISI PANEL SURYA BERBASIS ESP32-CAM DAN MODEL YOLOv8. (deposited UNSPECIFIED)
  • RANCANG BANGUN SISTEM DETEKSI KONDISI PANEL SURYA BERBASIS ESP32-CAM DAN MODEL YOLOv8. (deposited UNSPECIFIED) [Currently Displayed]

Actions (login required)

View Item