Implementasi Tinyml Berbasis Esp32 Untuk Prediksi Kerusakan Motor Aerator Tambak Udang Vaname Menggunakan Analisis Vibrasi Real-Time Di Pesisir Sumatera Utara

  • Ahmad Arif Universitas Al-Azhar
  • Gunawan Sihombing universitas amir hamzah
Keywords: TinyML, ESP32, Predictive Maintenance, Vibration, Aerator Motor, Vaname Shrimp Pond

Abstract

The aerator motor is an important component in vaname shrimp ponds because it functions to maintain dissolved oxygen levels in the pond water. Undetected aerator motor damage can cause a decrease in water quality and increase the risk of shrimp mortality. This study aims to design and implement a TinyML-based predictive maintenance system using an ESP32 microcontroller and vibration sensors to detect aerator motor damage in real-time. Vibration data was obtained using an MPU6050 sensor in several motor conditions, namely normal, damaged bearings, misalignment, unbalance, and light overload. The data was then processed using a feature extraction method and trained using an Artificial Neural Network (ANN) model based on TensorFlow Lite for Microcontroller. The results showed that the system was able to classify motor conditions with an accuracy of 95.2%, precision of 94.8%, recall of 95.1%, and F1-score of 94.9%. The TinyML implementation on ESP32 was able to work in real-time with an average inference time of 1.2 seconds and low power consumption of ±2.8 Watts. This research proves that TinyML can be an effective and inexpensive solution for predictive maintenance of aerator motors in vaname shrimp ponds in coastal areas

References

Z. Abidin Et Al., Agribisnis Perikanan Era 4.0. Universitas Brawijaya Press, 2026.

A. R. Ramadhani, “Pengaruh Jumlah Kincir Air (Padhel Wheel) Terhadap Pertumbuhan Pada Budidaya Udang Vannamei (Litopenaeus Vannamei) Secara Intensif Di Pt. Bumi Subur Iii Desa Wotgalih Kecamatan Yosowilangun Kabupaten Lumajang Provinsi Jawa Timur,” 2022.

A. Gunawan, “Rancang Bangun Turbin Angin Savonius Untuk Aerator Tambak Udang (Pengujian),” 2021, Politeknik Negeri Sriwijaya.

A. Perawito, “Rancang Bangun Turbin Angin Savonius Untuk Aerator Tambak Udang (Perawatan Dan Perbaikan),” 2020, Politeknik Negeri Sriwijaya.

K. P. J. Timur, P. K. Lapang Iii, I. Arditya, And K. K. D. A. N. Perikanan, “Efektifitas Penggunaan Kincir Air (Paddle Wheel) Pada Tambak Udang Vannamei Di Upt Bapl Bangil”.

W. Wardana, “Kajian Dan Analisa Sistem Aerator Tipe Furrower Berpenggerak Plts Untuk Tambak Udang Ukuran 50 M× 40 M,” 2022, Universitas Lampung.

J. Fadhilah And F. M. Rusman, “Rancang Bangun Sistem Monitoring Kualitas Air Pada Tambak Berbasis Internet Of Things (Iot),” 2023, Politeknik Negeri Ujung Pandang.

Y. Syahra And J. Tanjung, “Sistem Pengelolaan Sampah Cerdas: Inovasi Tempat Sampah Iot Dengan Otomatisasi Dan Mekanisme Keamanan Modern,” Blend Sains J. Tek., Vol. 4, No. 3, Pp. 639–647, 2026.

R. P. Laksana, S. Wahyu, And Q. H. Hidayah, “Sistem Cerdas Iot Untuk Pemantauan Cuaca Real-Time Dan Prediksi Kondisi Lingkungan Pada Aplikasi Jemuran Pakaian Otomatis,” Juki J. Komput. Dan Inform., Vol. 7, No. 2, Pp. 259–271, 2025.

K. Riyanto And I. G. N. Suryantara, “Implementasi Model Lstm Pada Mikrokontroler Untuk Prediksi Iklim Mikro Jakarta Utara Secara Real-Time Menggunakan Tinyml,” Jati (Jurnal Mhs. Tek. Inform., Vol. 10, No. 1, Pp. 970–977, 2026.

B. H. Reader, T. W., Flin, R., Mearns, K., & Cuthbertson, “Scholar (17),” 2009.

J. Leckenby Et Al., “Scholar (18),” 2014. Doi: 10.1163/_Q3_Sim_00374.

D. P. Akbar, “Pengaruh Unbalance Pada Mesin Beputar Terhadap Pengukuran Getaran: Menggunakan Alat Modal Analysis Testing Dan Vibration Meter,” 2024, Fakultas Teknik Universitas Sultan Ageng Tirtayasa.

M. D. Apriliya, I. Supriyono, And S. T. Joko Sedyono, “Sistem Monitoring Berbasis Iot Untuk Predictive Maintenance Generator Set Menggunakan Machine Learning,” 2025, Universitas Muhammadiyah Surakarta.

A. Fitriansyah And R. A. Nugroho, Internet Of Things Dan Machine Learning. Minhaj Pustaka, 2026.

Published
2026-04-30

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.