AN INTELLIGENT BATTERY MANAGEMENT

SYSTEM FOR ELECTRIC AND HYBRID

ELECTRIC BATTERY MEASUREMENTS AND
MODELING FOR SOC INDICATION
ALGORITHM
CONTENT

• Abstract
• Introduction
• Literature
• Proposed system
• Block diagram
• Working procedure
• Advantages
• Application
• Conclusion
• Referances
ABSTRACT

• The purpose of this project is to acquire the remote electrical parameters like
Voltage, Current and Frequency The durability and reliability of battery management
systems in electric vehicles to forecast the state of charge (SoC) is a tedious task.
• As the process of battery degradation is usually non-linear, it is extremely
cumbersome work to predict SoC estimation with substantially less degradation.
This paper presents the SoC estimation of lithium-ion battery systems using six
machine learning algorithms for electric vehicles application..
• This project is also designed to protect the electrical circuitry by operating an
Electromagnetic Relay. This Relay gets activated whenever the electrical parameters
exceed the predefined values. The Relay can be used to operate a Circuit Breaker to
switch off the main electrical supply.
INTRODUCTION

• The transport industry accounts for the bulk of greenhouse gas emissions and
pollution to the environment. The transport sector can be improved by the
introduction of the e-mobility applications such as electric vehicles (EVs) , hybrid
locomotives and other battery-energy storage systems . The energy storage system
is one of the most significant parts of EVs and smart grid technologies.
• The smart grid technology is the emerging technology in electricity transmission
and distribution lines. Numerous batteries are available in the market for various
energy storage applications. Specifically, lithium-ion batteries are selected as an
energy storage technology for EVs due to its gravimetric and volumetric density,
high hour’s efficiency, and long life.
• However, thermal management of batteries for EV application is important.
LITERATURE

• The development of data-driven algorithms such as machine learning

methods has taken a major step in recent years to improve the accuracy
of state of charge (SoC) measurements with improved generalization
performance, improved learning capabilities for high accuracy and
convergence . The battery’s performance is estimated based on state of
health (SOH) and remaining useful life (RUL).
• The SOH and RUL of the battery can be predicted by artificial
intelligence such as machine learning and the deep learning approach
which are intelligent and adaptive. However, estimation and prediction
outcomes are subjected to the collection of trained data continue…
• In the present work, the SoC of lithium-ion batteries is
predicted based on the six machine learning algorithms using
data derived from the electric vehicle BMS. The algorithms
used in the studies are artificial neural network (ANN),
support vector machine (SVM), linear regression (LR),
Gaussian process regression (GPR), and ensemble bagging
(EBa), and ensemble boosting (EBo) algorithm. Finally, all
six algorithms are compared with performance indices.
PROPOSED SYSTEM

• First, the suggested machine learning (ML) algorithm is used according to

known partial data to construct a predictive model of the state of charge
(SoC) for forecasting the complete charging curve. The flow chart of the
proposed SoC method. The overall SoC diagnostics framework is based on
short-term charging results.
• The battery model applied in the developed SoC indication algorithm
describes the battery EMF and overpotential behavior, neither of which
can be measured directly. The EMF and overpotential curves have been
measured with an accurate battery tester and implemented in the Battery
Management System (BMS) using mathematical-function approximations
BLOCK DIAGRAM
WORKING PROCEDURE

•  
• So far BMSs with different architectures were designed and built. And they
were used for different applications based on their specific advantages and
disadvantages. BMSs can be categorized based on the cost, size and scalability
to three groups of centralized, distributed and modular BMS architectures.
• In the centralized architectures, battery cells are controlled and monitored in
BMS by a main control board. Centralized BMSs are cost effective and simple
for some applications in which battery packs have low number of cells.
However, all wires of battery cells and sensors are connected to the main
board of centralized BMSs. Therefore, the bigger size of battery pack leads to
having more complexity and difficulty in wiring.
• In the distributed architectures, for each cell in the battery pack, a node is assigned for
controlling and monitoring data of each cell. These nodes considered as slaves have
serial communication with a master node in which the transferred data are interpreted
and monitored. Although the distributed BMS architectures are relatively expensive, but
they can be installed and scaled up easily.
• In the modular architecture, BMS is designed based on combination of both centralized
and distributed BMS architectures. Modular BMSs contain several slave devices and a
master device in which each slave can control and monitor more than one cell.
• This architecture has flexibility and can be scaled up since a daisy chain connection is
applied to connect the salves to the master controlling and monitoring process. The
modular BMS architecture is a good option for large battery packs containing many
cells.
ADVANTAGES

• 1. Devices can be operated from anywhere in the world.

• 2. Feedback of the devices being operated is present.
• 3. Efficient and low cost design.
• 4. Low power consumption.
• 5. Real time monitoring.
APPLICATION

•  
• 1. This system can be implemented in industries.
• 2. This system can be used to monitoring and controlling
the home appliances.
• 3. major application is electrical vehicles
• 4. electric bikes and scooters.
•  
CONCLUSION

• Battery models have many applications in battery management

systems including battery performance analysis, fault detection,
SOC and SOH estimations. Some main factors such as SOC, and the
operating temperature have impact on the battery model parameters.
• Due to these parameter variations in ECM, model-based fault
diagnosis methods which are not equipped with adaptive battery
models, may lead to erroneous fault detections in the battery system.
Moreover, the accuracy of SOC and SOH estimation depends on the
accuracy of the battery model.
REFERANCES

•  
• [1] Zubi, G., Dufo-López, R., Carvalho, M. and Pasaoglu, G., 2018. The lithium-ion battery: State of the art
and future perspectives. Renewable and Sustainable Energy Reviews, 89, pp.292-308.
• [2] Liu, K., Liu, Y., Lin, D., Pei, A. and Cui, Y., 2018. Materials for lithium-ion battery safety. Science
advances, 4(6), p.eaas9820.
• [3] Lu, L., Han, X., Li, J., Hua, J. and Ouyang, M., 2013. A review on the key issues for lithium-ion battery
management in electric vehicles. Journal of power sources, 226, pp.272-288.
• [4] Jia, Y. and Rajashekara, K., 2017. An induction generator-based ac/dc hybrid electric power generation
system for more electric aircraft. IEEE Transactions on Industry Applications, 53(3), pp.2485-2494.
• [5] Voskuijl, M., Van Bogaert, J. and Rao, A.G., 2018. Analysis and design of hybrid electric regional
turboprop aircraft. CEAS Aeronautical Journal, 9(1), pp.15-25.
• [6] Xie, S., Hu, X., Qi, S., Tang, X., Lang, K., Xin, Z. and Brighton, J., 2019. Model predictive energy
management for plug-in hybrid electric vehicles considering optimal battery depth of discharge. Energy, 173,
pp.667-678.
Thank you