Claims:The scope of the invention is defined by the following claims:

Claims:
1. A method to control speed of bldc motor in electric vehicles comprising the following steps:
a) The Fuel cell provides power to the DC-DC Converter which is interconnected to the Inverter, this power is given as input, to drive the Brushless DC motor
b) A circuit has closed loop system for speed control of BLDC motor and it is achieved using Adaptive neuro fuzzy interface system, Fuzzy PID and PI Controller.
c) The speed of the BLDC motor is controlled by the dc bus voltage through pulse width modulation based voltage inverter
2. As per claim 1, the control signal and the switching logic is given to the three phase PWM voltage inverter, the feedback error signal generate through the output of the brushless DC motor and the reference speed of the BLDC motor is given to controller block.
3. According to claim 1, structure of adaptive fuzzy controller is a five layer network which has two inputs (error and change in error), three membership functions and one output. The Mamdani Fuzzy Inference system is considered for Fuzzy PID Control , Description:Field of Invention
The proposed system aims at developing an Adaptive Neuro Fuzzy system based soft computing controller and it is implemented to control the speed in Electric Vehicles.
Background of the Invention
Now a days, saving of electric energy has attracted a lot of researchers due to continuous exhaustion of fossil elements and rapid rise in greenhouse gas emissions. Because of this, there is growing interest among researchers to concentrate on technologies related to energy savings.[ Chan, C.C., “The state of the art of electric and hybrid vehicles”, Proc. IEEE, 90(2): 247–275, (2002)] Taking this into account, the automobile industry has focused on alternative energy sources other than petrol or diesel for fueling vehicles which resulted in the usage of electric vehicles. Therefore, the development of Electric Vehicles (EVs) is taking a quick pace in marketing. The EVs have certain advantages like low weight, low CO2 emissions, easy cooling, excellent speed-torque characteristics, low protection cost, high reliability, simple drive train systems and high-energy conversion efficiency. Configuration of EVs is more flexible compared to Internal Combustion Engine Vehicles (ICEVs). [Leduc, P., Dubar, B., “Downsizing of gasoline engine: an efficient way to reduce CO2 emissions”. Oil Gas Science Technology, 58: 115–27, (2003).]Some of the applications are implementation in short-range transportations, motorized wheelchairs, and patrolling vehicles.
In future EVs can be preferred for public transportations. The performances of the EVs rely on three factors. They are energy source, vehicle expectation, and constraints. In electric propulsion system Permanent Magnet (PM), brushless (BLDC) motors and induction motors are mostly used.[ Wang, J., Atallah, K., Zhu, Z. Q., Howe, D., “Modular 3-phase permanent magnet brushless machines for in-wheel applications”, IEEE Vehicle Power and Propulsion Conference,1-6, (2006).] The Brush less DC motor is explained as synchronous motor have trapezoidal back EMF, which is used broadly in numerous applications like robotics, chemical industries, aeronautics, and electric vehicles. etc. Since they require no mechanical commutators, it would have certain amenities such as easier control, high power density, produce require torque and more efficiency. In the proposed system, BLDC motors are considered. In EVs, the controller plays a crucial role to obtain the maximum accelerated performance. Because EV’s run on different road conditions and also the operating parameters always variable in nature. Therefore, control of EV’s plays a vital role. In process industries, chemical industries, and also various electrical control applications PI/PID controllers are used because it is easy to design. For nonlinear and complex systems of EVs, the PI/PID controllers do not give optimal performance. Later a hybrid PID controller applied for the nonlinear system is proposed. The fuzzy logic controller is convenient to apply for electric vehicles because EVs operate at complex conditions.

A control technique called ANFIS controller is used in numerous applications such as maximum power extraction in solar panels and inertia control of wind turbines, silicone rubber mechanical properties approximation, robotic gripper control, human musculoskeletal arm, anti-lock braking system, underwater vehicles, control of nonlinear industrial process and batch process, estimation of system forecasting, estimation of open lens system parameters.[ Petković, D., Pavlovic, N.T., Samshirband, S., Kiah, M.L.M., Anuar, N.B., Idris, M.Y.I., “Adaptive neuro-fuzzy estimation of optimal lens system parameters”, Optical Laser Engineering, 55: 84-93, (2014).] The ANFIS controller is used for speed control of permanent magnet excitation transverse flux linear motor and BLDC motor. This ANFIS gives satisfactory performance under load varying conditions. In the proposed system, an ANFIS controller has been implemented for speed control of EVs. In this controller, the training data for the ANFIS is obtained from the performance of fuzzy PID controller. The proposed controller has certain advantage that it gives better performance in uncertain conditions also.[K. Harshavardhana REDDY(2021) ,Implementation of Adaptive Neuro Fuzzy Controller for Fuel cell based Electric vehicles, 34(1) 112-126,https://doi.org/10.35378 gujs.698272]

Summary of the Invention
A soft computing based ANFIS method has been proposed to execute the rapid speed response in electric vehicle. Here, Brushless DC motor was used as a propulsion system to drive the vehicle. Electric Vehicle is basically a time variant system, whose operating parameters and road conditions vary continuously. To address these uncertainties, a novel control strategy is proposed. The fuel cell battery is used as the auxiliary power supply for the electric vehicle.
Brief Description of Drawings
The invention will be described in detail with reference to the exemplary embodiments shown in the figures wherein:
Figure 1: Pictorial representation of Electric Vehicle
Figure 2: Simulation model for speed control of BLDC motor in Electric Vehicle
Figure 3: Pictorial representation of Mamdani Fuzzy Inference System
Figure 4: Structure of Adaptive Neuro Fuzzy Inference System Controller
Figure 5: Performance of Controllers at constant 25km/h speed and ECE 15 Cycle Test
Detailed Description of the Invention
To model the Electric Vehicle dynamics, the factors considered to design road condition are hill climbing, acceleration and aerodynamic drag etc. The BLDC motor has certain advantages compared to other motors like lower electromagnetic interference (EMI), lower maintenance costs and higher reliability. The overall block diagram to simulate the electric vehicle is depicted in Figure 1. It comprises of a fuel cell battery to supply the power using DC-DC converter and an inverter and the electric motor is connected to EV.
The speed control of brushless DC motor using adaptive neuro fuzzy interface system, Fuzzy PID and PI Controller is shown in Figure 2. The circuit has a closed loop system to control the speed of the BLDC motor. The speed of the BLDC motor is controlled by the dc bus voltage through pulse width modulation based voltage inverter. The control signal and the switching logic is given to the three phase PWM voltage inverter, the feedback error signal generate through the output of the brushless DC motor and the reference speed of the BLDC(US5563980A). To control the speed of EV, an ANFIS controller is proposed and it is mixture of ANN with fuzzy interface system.
The ANFIS is a very good learning technique to take over an issue on uncertainties in any system. This controller is based on framing fuzzy IF-Then rules that produces specific input-output with the help of membership functions. The learning process of ANFIS consists of three stages; first is the rule base, second is the membership functions and the third is the reasoning mechanism. For the proposed controller the data of error and change in error of fuzzy PID plus PD controller data set is used. The structure of adaptive fuzzy controller, generated by the MATLAB code is a five layer network as shown in Figure 4. It has two inputs (error and change in error), one output and three membership functions.(US6446054B1). The proposed controller performance for the EV is studied and its efficiency is evaluated based on the obtained results that are compared with conventional controller. The Vehicle parameters are listed in Table 1.The mass of the vehicle is 800(kg) and its area being 1.8(m2).Its air density being 1.25(kg/m3) and its drag vaue is 0.3.The angle of hill climbing being 0 (deg) with a rollng resistance of 0.015.The tyre radius being 0.025m and its gearing ratio is 11.
The performance of the proposed controller is compared with PI and Fuzzy PID controller when operating at constant speed of 25 Km/h as depicted in Figure 5. It is observed that the proposed control method achieved enhanced response in short period of time. In order to validate the speed control of EVs for the proposed controller an ECE 15 cycle profile obtained for a speed of 50 km/h is considered as shown in Figure 6. From the results, it is evident that the tracking performance of proposed controller is better than the PI and Fuzzy PID controller for ECE 15 cycles as shown in Figure 7. To evaluate the performance of the proposed controller the same ECE 15 test cycle is considered for large time of 400 seconds as illustrated in Figure 8. It is realized that for large time based ECE test cycle, the Proposed ANFIS Controller achieved good response compared with the PI and Fuzzy PID Controller.