Perancangan Aplikasi Object Recognition guna Mengidentifikasi Komponen Alat Berat Industri menggunakan Metode Deep Learning

Pradana, Argya (2025) Perancangan Aplikasi Object Recognition guna Mengidentifikasi Komponen Alat Berat Industri menggunakan Metode Deep Learning. Bachelor thesis, Institut Teknologi Kalimantan.

	Text 04211010_cover.pdf Restricted to Repository staff only until 4 October 2027. Download (325kB) | Request a copy
	Text 04211010_statement_of_authenticity.pdf Restricted to Repository staff only until 4 October 2027. Download (6MB) | Request a copy
	Text 04211010_publishing_agreement.pdf Restricted to Repository staff only until 4 October 2027. Download (5MB) | Request a copy
	Text 04211010_approval_sheet.pdf Restricted to Repository staff only until 4 October 2027. Download (5MB) | Request a copy
	Text 04211010_preface.pdf Restricted to Repository staff only until 4 October 2027. Download (10MB) | Request a copy
	Text 04211010_abstract_id.pdf Restricted to Repository staff only until 4 October 2027. Download (35kB) | Request a copy
	Text 04211010_abstract_en.pdf Restricted to Repository staff only until 4 October 2027. Download (102kB) | Request a copy
	Text 04211010_table_of_content.pdf Restricted to Repository staff only until 4 October 2027. Download (255kB) | Request a copy
	Text 04211010_illustrations.pdf Restricted to Repository staff only until 4 October 2027. Download (162kB) | Request a copy
	Text 04211010_tables.pdf Restricted to Repository staff only until 4 October 2027. Download (131kB) | Request a copy
	Text 04211010_notations.pdf Restricted to Repository staff only until 4 October 2027. Download (199kB) | Request a copy
	Text 04211010_chapter_1.pdf Restricted to Repository staff only until 4 October 2027. Download (342kB) | Request a copy
	Text 04211010_chapter_2.pdf Restricted to Repository staff only until 4 October 2027. Download (1MB) | Request a copy
	Text 04211010_chapter_3.pdf Restricted to Repository staff only until 4 October 2027. Download (2MB) | Request a copy
	Text 04211010_chapter_4.pdf Restricted to Repository staff only until 4 October 2027. Download (3MB) | Request a copy
	Text 04211010_conclusions.pdf Restricted to Repository staff only until 4 October 2027. Download (163kB) | Request a copy
	Text 04211010_bibliography.pdf Restricted to Repository staff only until 4 October 2027. Download (132kB) | Request a copy
	Text 04211010_enclosure.pdf Restricted to Repository staff only until 4 October 2027. Download (2MB) | Request a copy
	Text 04211010_paper.pdf Restricted to Repository staff only until 4 October 2027. Download (501kB) | Request a copy
	Text 04211010_Form. TA-020.pdf Restricted to Repository staff only until 4 October 2027. Download (4MB) | Request a copy
	Text 04211010_presentation.pdf Restricted to Repository staff only until 4 October 2027. Download (2MB) | Request a copy

Abstract

Hydraulic Cylinder merupakan sistem kemudi pada kendaraan alat berat yang membantu pengemudi mengatur arah kendaraan dengan memanfaatkan mekanisme hidrolik atau elektrik. Penelitian ini mengembangkan sistem pengenalan terhadap object part Steering Cylinder berbasis Deep Learning dengan memanfaatkan algoritma YOLOv8 dan Convolution Neural Network (CNN) dalam mendeteksi part dalam Steering Cylinder Komatsu HD785 tersebut. Sistem ini menggunakan Aplikasi melalui software Android Studio untuk User Interface (UI) yang telah di learning dengan Kaggle Notebook untuk Algoritma Deep Learning. Dataset yang digunakan terdiri dari 1.194 gambar yang kemudian dianotasikan kedalam 8 kategori, dibagi kedalam data pelatihan (70%), validasi (20%), dan pengujian (10%) melalui Roboflow. Hasil pengujian selama satu minggu menunjukkan akurasi rata-rata 74.75% (10 cm), 73.5% (30 cm), dan 55.75% (50 cm). Saat pelatihan, seluruh part dikenali 100% kecuali Bolt (90%). Waktu deteksi tercepat adalah 0.35 detik, terlama 1.14 detik, dengan rata-rata pengiriman data ke server 5.57 detik. Hal ini secara garis besar meningkatkan performa deteksi objek, serta memberikan solusi efektif guna mengidentifikasi part yang menjadi bagian dari unit HD785 walaupun jarak dan intensitas cahaya menjadi poin obstacle dari pengenalan objek.

Item Type:	Thesis (Bachelor)
Subjects:	A General Works > AI Indexes (General) T Technology > TJ Mechanical engineering and machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Jurusan Teknologi Industri dan Proses > Teknik Elektro
Depositing User:	Mr. Argya Pradana
Date Deposited:	11 Jul 2025 03:17
Last Modified:	11 Jul 2025 03:17
URI:	http://repository.itk.ac.id/id/eprint/24259

Actions (login required)

View Item