Electric vehicles (EVs) enabled by high efficiency
electric motors and controllers and powered by alternative energy
sources provide the means for a clean, efficient, and
environmentally friendly system. The power demanded by an EV
is very variable. Hence HESS (Hybrid energy storage system) as
an alternative source have been investigated with the objective of
improving the storage of electrical energy. In these systems, two
(or more) energy sources work together to create a superior device
in comparison with a single source. In batteries and
ultra-capacitors have complementary characteristics that make
them attractive for a hybrid energy storage system. But the result
of this combination is fundamentally related to how the sources
are interconnect and controlled. Hybrid Electric Vehicle (HEV) is
the most advance technology in automobile industries but long
drive range in HEV is still a problem due to limited battery life.
For increasing of battery life, two methods are widely used in
HEV; one is with fuzzy logic-based battery management strategy
and second is through improvement in regenerative braking
system. Regenerative braking system used in HEV is to give
backup power in deceleration mode which not only make HEV to
drive longer but also increase the battery life cycle by charging of
ultra-capacitor. The present work is for controlling the source of
the motor present in the EV during different driving load
conditions and storage of energy by implementing regenerative
braking. In the proposed control action, motor speed plays a
major role in switch the energy sources in HESS. To attain the
objective, another controller has been designed with four math
functions corresponding to the speed of the motor termed as Math
Function Based (MFB) controller. The MFB controller works
based on the motor’s speed and this controller creates the closed
loop operation of the overall system with smooth operation
between the energy sources. Thereafter the designed MFB
controller combined with a Fuzzy Logic controller applied to the
entire circuit at different load conditions. In the same way, MFB
with Artificial Neural Network controller also applied to the
circuit. Finally, comparative analysis has been done between two
controllers. The motor has been applied with 6 different types of
load and simulated. The MATLAB results of MFB with FLC and
MFB with ANN has been attained and compared, discussed.