Abstract
Electric Vehicle (EV) Batteries must have high reliability to produce durable and sustainable electrical energy. Reliable electric batteries will certainly have high economic value and efficiency. Reliability can be obtained if the system and its supporting are monitored using an integrated and independent system for further analysis and observation. Battery Management System (BMS) is integrated parts of Electric Vehicle, Hybrid Electric Vehicle (HEV), or solar applications e.g. solar power plant. Its functions are to integrate many things such as voltage sampling from cell battery, cells balancing, determine State of Charge (SOC), estimate State of Health (SOH), and predict Remaining Useful Life (RUL). The key technology needed for condition-based maintenance is Prognostic and Health Management. It is a new engineering approach that allows an assessment of the system's health when the system is operating. It combines various scientific disciplines, namely: sensing technology, modern statistics, machine learning, physics of failure, and reliability engineering. It will be combined with Big Data analysis. Big data uses existing technology and contemporary architecture that is designed to efficiently take advantage of the many and varied data. Big data analytics refers to the method of analyzing huge volumes of data, high velocity of data, variety different forms of data, and veracity of uncertainty of data. The main focus in this research is the development of an integrated observation system and the ability to make error predictions. This system consists of error detection, error diagnosis, and integrated prognosis. This research is to implement Big Data analytics Platform to evaluate the reliability level of electric vehicle Battery Management System.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call