Prediksi Remaining Useful Lifetime Dari Sel Baterai Lithium-Ion NMC 18650 Menggunakan Support Vector Machine

Imani, Andira Rahman (2023) Prediksi Remaining Useful Lifetime Dari Sel Baterai Lithium-Ion NMC 18650 Menggunakan Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 02111740000025-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (4MB) | Request a copy

Abstract

Peningkatan kebutuhan akan energi menghasilkan inovasi penting seperti baterai lithium-ion. Baterai tersebut merupakan solusi penyimpanan energi yang paling umum digunakan saat ini, mulai dari perangkat elektronik pribadi hingga kendaran listrik dan pembangkit daya terbaharui. Namun, dalam penggunaannya sel baterai lithium-ion akan mengalami penurunan kapasitas akibat ketidaksempurnaan pada reaksi kimianya. Memprediksi perilaku degradasi kapasitas tersebut dapat membantu meningkatkan efisiensi penggunaan, perbaikan, dan penggantian sel baterai lithium-ion. Salah satu cara untuk memahami perilaku tersebut adalah menggunakan metode data-driven seperti machine learning. Pada penelitian ini, akan dilakukan prediksi dari Remaining Useful Lifetime (RUL) dari sebuah sel baterai lithium-ion tipe NMC dengan faktor bentuk 18650 menggunakan aloritma machine learning yakni Support Vector Machine (SVM) untuk melihat performa algoritma tersebut. Data yang digunakan merupakan data sekunder dari institusi Sandia National Laboratories yang menguji berbagai jenis sel baterai lithium di beberapa kondisi untuk meneliti perilaku degradasi sel baterai lithium-ion. Dataset yang digunakan dibatasi di laju pengisian kapasitas sebesar 0.5C. Dataset tersebut kemudian digunakan untuk melatih dan menguji sejumlah model machine learning yang menggunakan algoritma SVM dengan variasi fungsi kernel seperti kernel linear, kernel polinomial, kernel radial-basis function, dan kernel sigmoid, sebelum dan sesudah penyesuaian hyperparameter menggunakan random search grid. Performa model-model tersebut kemudian dihitung dan dibandingkan untuk mencari model dengan performa terbaik. Indeks performa yang digunakan adalah Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Coefficient of Determination (R2), Root Mean Squared Logarithmic Error (RMSLE), dan Mean Absolute Percentage Error (MAPE). Performa terbaik dari model SVM dalam memprediksi RUL sebuah sel baterai lithium-ion NMC 18650 adalah sebagai berikut, MAE senilai 1.347,4521, MSE senilai 3.729.987,2910, RMSE sebesar 1.931,3175, R2 sebesar 0,6944, RMSLE sebsar 0,8844, dan MAPE sebesar 2,0422. Performa tersebut didapatkan dengan menggunakan model SVM dengan hyperparameter seperti berikut, fungsi kernel radial-basis function, nilai C sebesar 9,596, dan nilai epsilon sebesar1,9. Untuk hyperparameter dari radial-basis function itu sendiri menggunakan konstanta gamma yang bernilai 0.10000000024877526.
===============================================================================================================================
The rise of energy needs of humans brought forth important innovations such as the lithium-ion battery. Said innovation has become one of the most common energy storage solutions of today, powering things from personal electronic devices to electric vehicles and renewable energy power grids. However, in its usage the lithium-ion battery cells would experience a capacity drop due to imperfections in the chemical reactions. Predicting that capacity degradation behavior would help improve the efficiency of the usage, maintenance, and replacement of said lithium-ion battery cells. One of the many ways to predict said behavior is by using data-driven methods such as machine learning. In this research, prediction of a lithium-ion battery cell’s Remaining Useful Lifetime (RUL) with the NMC cathode type and the 18650 form-factor using a machine learning algorithm known as Support Vector Machine (SVM) will be conducted to assess the performance of said algorithm. The data used in this research is a secondary dataset acquired from a study conducted at the Sandia National Laboratory which tests numerous types of lithium-ion battery cells under several conditions to study the general degradation behavior of lithium-ion battery cells. The dataset used is limited to certain conditions such as a charging rate of 0.5C. The dataset will then be used to train and test several models each with varying kernel functions such as the linear kernel, polynomial kernel, radial-basis function kernel, and sigmoid kernel, before and after their hyperparameters are tuned using the random search grid methods. The acquired performances of predicting the RUL would then be compared with each other to find the best performing models. The performance indexes used in this experiment are the Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Coefficient of Determination (R2), Root Mean Squared Logarithmic Error (RMSLE), and Mean Absolute Percentage Error (MAPE). The best performance from the SVM model predicting the RUL of a lithium-ion NMC 18650 battery cell ar as follows, MAE score of 1,347.4521, MSE score of 3,729,987.2910, RMSE score of 1,931.3175, R2 score of 0.6944, RMSLE score of 0.8844, and MAPE score of 2.0422. That performance was achieved using an SVM model with hyperparemeters as follows, radial-basis function for the kernel function, C value of 9.596, and an epsilon value of 1.9. For other hyperparameters of radial-basis function kernel itself uses the gamma constant of 0.10000000024877526.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Baterai Lithium-Ion NMC 18650, Lithium-Ion NMC 18650 Battery, Remaining Useful Lifetime, Support Vector Machine
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. T Technology > TJ Mechanical engineering and machinery > TJ165 Energy storage. T Technology > TJ Mechanical engineering and machinery > TJ174 Maintenance and repair of machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2921 Lithium cells.
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Industrial Engineering > 26201-(S1) Undergraduate Thesis
Depositing User:	Andira Rahman Imani
Date Deposited:	05 Sep 2023 03:32
Last Modified:	05 Sep 2023 03:32
URI:	http://repository.its.ac.id/id/eprint/104343

Actions (login required)

View Item