Klasifikasi Kondisi Baterai Berdasarkan Tegangan dan Arus Menggunakan Metode Decision Tree pada Battery Management System.

Rachman, Muhammad Azis (2026) Klasifikasi Kondisi Baterai Berdasarkan Tegangan dan Arus Menggunakan Metode Decision Tree pada Battery Management System. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2040221045-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Baterai lithium-polymer memerlukan battery management system (BMS) untuk menjaga keamanan selama proses pengisian karena kondisi overcharge dapat menyebabkan penurunan performa hingga memicu thermal runaway. Selain itu, BMS konvensional umumnya hanya memberikan respons penghentian pengisian tanpa mampu menginformasikan fase pengisian baterai. Oleh karena itu, penelitian ini bertujuan merancang dan merealisasikan battery management system (BMS) berbasis ESP32 DevKit V1 yang mampu memantau tegangan, arus, dan state of charge (SoC), menerapkan proteksi overcharge, serta mengklasifikasikan kondisi baterai menggunakan metode Decision Tree. Sistem dikembangkan menggunakan sesnor INA219, voltage divider, ADS1115, relay, dan LCD. Model decision tree dilatih menggunakan pembagian data 80% data latih dan 20% data uji, kemudian diimplementasikan pada ESP32 DevKit V1 dalam bentuk aturan if-else untuk klasifikasi real-time. Hasil penelitian menunjukkan bahwa sistem berhasil melakukan monitoring tegangan, arus, dan state of charge (SoC) secara real-time serta menghentikan proses pengisian secara otomatis pada tegangan sekitar 12,61 V dengan arus sekitar 0,05 A, sementara tegangan maksimum yang tercatat sebesar 12,614 V, masih berada di bawah batas overcharge 12,75 V. Selain itu, metode decision tree berhasil mengklasifikasikan kondisi baterai ke dalam tiga fase pengisian, yaitu Pengisian Awal, Mendekati Penuh, dan Penuh, dengan akurasi sebesar 99,83%. Hasil tersebut menunjukkan bahwa sistem yang dikembangkan mampu meningkatkan keamanan proses pengisian sekaligus memberikan informasi kondisi baterai secara real-time dengan tingkat akurasi yang tinggi.
===================================================================================================================================
Lithium-polymer batteries require a battery management system (BMS) to ensure safety during the charging process, as overcharging can lead to a decline in performance and even trigger thermal runaway. Furthermore, conventional BMS typically only provide a charging termination response without being able to indicate the battery’s charging phase. Therefore, this study aims to design and implement a battery management system (BMS) based on the ESP32 DevKit V1 that is capable of monitoring voltage, current, and state of charge (SoC), implementing overcharge protection, and classifying battery conditions using the Decision Tree method. The system was developed using an INA219 sensor, a voltage divider, an ADS1115, a relay, and an LCD. The decision tree model was trained using a data split of 80% training data and 20% test data, then implemented on the ESP32 DevKit V1 in the form of if-else rules for real-time classification. The research results show that the system successfully monitored voltage, current, and state of charge (SoC) in real time and automatically stopped the charging process at a voltage of approximately 12.61 V with a current of approximately 0.05 A, while the maximum recorded voltage of 12.614 V remained below the overcharge threshold of 12.75 V. In addition, the decision tree method successfully classified battery status into three charging phases Initial Charging, Nearly Full, and Full with an accuracy of 99,83%. These results indicate that the developed system is capable of enhancing the safety of the charging process while providing real-time information on battery status with a high degree of accuracy.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Battery Management System (BMS), Decision Tree, ESP32 DevKit V1, Overcharge, State of Charge (SOC). Battery Management System (BMS), Decision Tree, ESP32 DevKit V1, Overcharge, State of Charge (SOC).
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2943 Battery chargers.
Divisions:	Faculty of Vocational > 36304-Automation Electronic Engineering
Depositing User:	Muhammad Azis Rachman
Date Deposited:	05 Aug 2026 02:33
Last Modified:	05 Aug 2026 02:33
URI:	http://repository.its.ac.id/id/eprint/142234

Actions (login required)

View Item