Development of Progressive Fuzzy Logic and ANFIS Control for Energy Management of Plug-In Hybrid Electric Vehicle

Abstract

Hybrid electric vehicles are an effective alternative to the conventional fuel engine vehicles and thus efficient and intelligent energy management is the key for establishing a significant market for the hybrid electric vehicles globally. Recent developments in the field of intelligent techniques and demand to make the energy systems intelligent have become a means to develop energy efficient hybrid electric vehicles. The energy management issue becomes vital in order to enhance the autonomy of hybrid electric vehicles and to reduce the costs. Therefore, a novel approach with intelligent techniques, to control the plug-in hybrid electric vehicles, in front of different customer profiles has been presented. This paper presents the battery performance improvement of a plug-in hybrid electric vehicle using fuzzy logic controller and neural fuzzy logic controller with battery state of charge as a deciding parameter and consequently comparing the performance of both cases. The battery state of charge and engine speed as input has been selected and based on their values the advanced controller decides the accurate torque required to be converted to energy which could be used to charge the battery and this can be achieved by controlling the forward gain value. For this, an advanced fuzzy controller and advanced adaptive nuero fuzzy inference system controller are used to decide the value of forward gain. Simulink environment is used to simulate the performance of the proposed system. This could be helpful in deciding which type of intelligent system is to be used for the power efficient operation of the hybrid electric vehicle. The results of both the control techniques are compared and the better controller is recommended for energy management of a plug-in electric vehicles. The results indicate that advanced control techniques provide the good performance and improving the fuel budget of hybrid electric vehicles.

Fuzzy adaptive singular value decomposition cubature Kalman filtering algorithm for lithium‐ion battery state‐of‐charge estimation

“…Reasonable fuzzy rules can reduce the amount of calculation. 48,49 The larger the number of fuzzy rules, the greater the amount of calculation, considering the trade-off between computational complexity and accuracy; the fuzzy rules are established as shown in Table 1.…”

Battery Energy Management Techniques for an Electric Vehicle Traction System

“…The work in [17] created an intelligent energy management system that monitors the torque signal and the battery SOC then generates the electric throttle signal to regulate the motor speed. Furthermore, [18] introduced a neural FLC to manage regenerative braking in a hybrid EV. The controller monitors the engine speed and power delivered then accurately determines the required torque for the application [18].…”

“…Furthermore, [18] introduced a neural FLC to manage regenerative braking in a hybrid EV. The controller monitors the engine speed and power delivered then accurately determines the required torque for the application [18]. Once the delivered power exceeds the required value, the regenerative braking system starts charging the battery bank using the excess power generated by the engine [18].…”

“…The controller monitors the engine speed and power delivered then accurately determines the required torque for the application [18]. Once the delivered power exceeds the required value, the regenerative braking system starts charging the battery bank using the excess power generated by the engine [18]. A common aspect in the literature is the utilization of the FLC's ability to incorporate the user's expertise to dictate the system's operation without requiring an accurate system model [19].…”

Advanced Fuzzy-Based Smart Energy Auditing Scheme for Smart Building Environment With Solar Integrated Systems

“…Smart buildings will be smarter when techniques used are intelligent and cost effective. Fuzzy logic uses different membership functions and then rules are made to get the desired output [22]. Fuzzy logic control, in this study, is used for smart energy auditing by making use of energy requirement data during different times of the day.…”