Estimation of Soc and Soh Using Mixed Neural Network and Coulomb Counting Algorithm
Abhash Ganeshan1, R. Shanmughasundaram2
1Abhash Ganeshan, Department of Electrical and Electronics Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, India.
2R. Shanmughasundaram, Assistant prof. (Sr. Gr), Department of Electrical and Electronics Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, India
Manuscript received on 02 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 2557-2561 | Volume-8 Issue-10, August 2019 | Retrieval Number: J13080881019/19©BEIESP | DOI: 10.35940/ijitee.J1308.0881019
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The Lithium ion battery is widely used in most of the battery powered electronics and automotive products like mobile phones, laptop, wall watch, calculator and other. The Battery provides power to devices with the facility of movability. On the other hand, it also provides power backup to devices. The Battery State of charge (SOC) and state of health (SOH) are the key terms by which the available charge and its life span can be estimated. In this paper, SOC is estimated using a back-propagation neural network with 3 inputs namely, voltage, current, and temperature of the battery. Coulomb counting method is used to find the new or remaining capacity of the battery which will notify about its SOH. The whole setup is implemented in PIC16F877A with the voltage, current and temperature sensors.
Keywords: Back-Propagation, SOC, SOH, PIC16f877A, Coulomb Counting.
Scope of the Article: Coulomb Counting