SETIAWAN, HARIS TRI (2026) DETEKSI GELEMBUNG PADA FLOW METER BUBBLE MENGGUNAKAN METODE DEEP LEARNING BERBASIS ANDROID. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
COVER.pdf Download (740kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
BAB 1.pdf Restricted to Registered users only Download (642kB) |
|
|
Text (BAB II)
BAB 2.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB IV)
BAB 4.pdf Restricted to Registered users only Download (692kB) |
|
|
Text (BAB III)
BAB 3.pdf Restricted to Registered users only Download (2MB) |
|
|
Text (BAB V)
BAB 5.pdf Restricted to Registered users only Download (554kB) |
|
|
Text (DAFTAR PUSTAKA)
DAFPUS.pdf Restricted to Registered users only Download (567kB) |
|
|
Text (LAMPIRAN)
LAMPIRAN.pdf Restricted to Registered users only Download (729kB) |
Abstract
Gas flow measurement is an important aspect in various industrial and laboratory activities, particularly to ensure process accuracy and efficiency. One commonly used method for measuring low flow rate gas is the bubble flow meter, which operates based on the travel time of bubbles within a tube. However, manual measurement methods have several limitations, including dependency on operator accuracy, potential measurement errors, and low result consistency. This study aims to develop a bubble detection system for a bubble flow meter based on an Android application using a deep learning approach. The system utilizes a smartphone camera to capture bubble movement in real-time, and processes image data using a deep learning model integrated through TensorFlow Lite. The application is developed using the Flutter framework to provide a responsive user interface and efficient data processing. The expected results of this study include the system’s ability to automatically detect and track bubble movement, calculate bubble travel time, and improve measurement accuracy and consistency compared to manual methods. In addition, the system is expected to operate in real-time with stable performance on mobile devices while maintaining visual data security. Therefore, this research is expected to contribute to the development of measurement systems based on computer vision and deep learning, as well as provide a more efficient, accurate, and practical solution for gas flow measurement using a bubble flow meter. Keywords: bubble flow meter, deep learning, Android, computer vision, bubble detection, real-time. Pengukuran laju aliran gas merupakan aspek penting dalam berbagai kegiatan industri dan laboratorium, khususnya untuk menjamin akurasi dan efisiensi proses. Salah satu metode yang umum digunakan untuk mengukur aliran gas berdebit rendah adalah bubble flow meter, yang bekerja berdasarkan waktu tempuh gelembung dalam tabung. Namun, proses pengukuran secara manual masih memiliki keterbatasan, seperti ketergantungan pada ketelitian operator, potensi kesalahan pengukuran, serta rendahnya konsistensi hasil. Penelitian ini bertujuan untuk mengembangkan sistem deteksi gelembung pada bubble flow meter berbasis aplikasi Android menggunakan metode deep learning. Sistem memanfaatkan kamera smartphone untuk menangkap pergerakan gelembung secara real-time, kemudian memproses data citra menggunakan model deep learning yang diintegrasikan melalui TensorFlow Lite. Aplikasi dikembangkan menggunakan framework Flutter untuk menghasilkan antarmuka yang responsif serta mendukung pemrosesan data secara efisien. Hasil yang diharapkan dari penelitian ini adalah kemampuan sistem dalam mendeteksi dan melacak pergerakan gelembung secara otomatis, menghitung waktu tempuh gelembung, serta meningkatkan akurasi dan konsistensi pengukuran dibandingkan metode manual. Selain itu, sistem juga diharapkan mampu bekerja secara real-time dengan performa yang stabil pada perangkat mobile, serta memperhatikan aspek keamanan data visual pengguna. Dengan demikian, penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan sistem pengukuran berbasis computer vision dan deep learning, serta menjadi solusi alternatif yang lebih efisien, akurat, dan praktis dalam pengukuran laju aliran gas menggunakan bubble flow meter. Kata kunci: bubble flow meter, deep learning, Android, computer vision, deteksi gelembung, real-time.
Actions (login required)
 |
View Item |
