Skripsi
DESAIN MODEL SMART CHARGING (SC) MENGGUNAKAN ALGORITMA ANT COLONY OPTIMIZATION (ACO) UNTUK MENENTUKAN ESTIMASI STATE OF CHARGE (SOC) LEAD ACID BATTERY (LAB).
This research presents the design of Smart Charging (SC) using the Ant Colony Optimization (ACO) algorithm in the lead acid battery charging process. The purpose of this research is to propose a new technique of energy charging system on electric vehicle batteries using smart charging system. The combination of mathematical solutions and modeling of artificial intelligence algorithms designed will be a new solution in the battery charging system to determine the State of Charge (SOC) and State of Health (SOH). The design of the Ant Colony algorithm in finding the best current pattern is done gradually and repeatedly until it gets termination in the form of the best current pattern according to the Ant Colony algorithm. The results of the algorithm design produce a current pattern consisting of 5 stages, namely: 10A, 5A, 3A, 2A, and 0A. The charging tool with this algorithm can charge lead acid batteries with a capacity of 12V 30Ah. This research shows that smart charging with Ant Colony can charge the battery safely without current fluctuations compared to charging without an algorithm, so that the amount of charging current used is not harmful to the battery. In addition, data analysis was conducted to determine the accuracy value of the SOC charging estimation using linear regression supervised learning, and (SOH) using Neural Network (NN). The results of data analysis with linear regression show that the battery SOC estimation has good accuracy with an RMSE value of 0.32 and MAE of 0.27 and the results of SOH analysis using NN produce RSME 0.004652485
No other version available