Speed control of electric vehicle by using type-2 fuzzy neural network

Chang, Ming-Hung; Wu, Yichao

doi:10.1007/s13042-021-01475-6

Cited by 10 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Electromagnetic interference can be divided into two types, namely, conduction and radiation. Conducted electromagnetic interference refers to the interference signals transmitted to the connected circuits by conductors, while radiated interference refers to the interference signals transmitted to other circuits in space by electromagnetic fields [13]. This paper mainly studies conducted electromagnetic interference (EMI).…”

Section: Esd Transceivementioning

confidence: 99%

New Energy Vehicle Electromagnetic Compatibility Test and Closed-Loop Simulation Analysis

2022

Journal of Sensors

View full text Add to dashboard Cite

With the rapid development of new energy vehicles, electromagnetic compatibility of new energy vehicles has been widely concerned. Therefore, based on the conducted electromagnetic interference theory of electric vehicle electric drive system, a kind of electromagnetic interference transmission path is proposed, and its closed-loop simulation is carried out. The results show that the key point that has great influence on the radiation emission of the electric drive system is whether there is a torque, essentially whether the motor controller has power output, and it has little relation with the motor speed and bus voltage. In addition to the influence of whether or not the torque has on radiation emission, the torque size is further compared, set 50 Nm, 100 Nm, and 200 Nm, respectively, for comparison, and it is found that the increase of torque has no obvious influence on radiation emission. Therefore, during the test, the appropriate torque can be selected according to the actual situation, rather than the maximum torque that the component can work.

show abstract

Section: Esd Transceivementioning

confidence: 99%

New Energy Vehicle Electromagnetic Compatibility Test and Closed-Loop Simulation Analysis

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Moreover, the Gaussian-based shape for primary MF with uncertain values of mean and standard deviation, which have an interval type-2 secondary MF, could be named an interval type-2 Gaussian MF [35][36][37][38]. The mathematical expression of an interval type-2 Gaussian MF with the uncertainties in mean 𝑚 and standard deviation 𝜎 is performed as…”

Section: Fundamentals Of Interval Type-2 Fuzzy Logic Systemmentioning

confidence: 99%

Enhancement of the Tracking Performance for Robot Manipulator by Using the Feed-forward Scheme and Reasonable Switching Mechanism

Ngo

Nguyеn

2022

Journal of Robotics and Control

View full text Add to dashboard Cite

Robot manipulator has become an exciting topic for many researchers during several decades. They have investigated the advanced algorithms such as sliding mode control, neural network, or genetic scheme to implement these developments. However, they lacked the integration of these algorithms to explore many potential expansions. Simultaneously, the complicated system requires a lot of computational costs, which is not always supported. Therefore, this paper presents a novel design of switching mechanisms to control the robot manipulator. This investigation is expected to achieve superior performance by flexibly adjusting various strategies for better selection. The Proportional-Integral-Derivative (PID) scheme is well-known, easy to implement, and ensures rapid computation while it might not have much control effect. The advanced interval type-2 fuzzy sliding mode control properly deals with nonlinear factors and disturbances. Consequently, the PID scheme is switched when the tracking error is less than the threshold or is far from the target. Otherwise, the interval type-2 fuzzy sliding mode control scheme is activated to cope with unknown factors. The main contributions of this paper are (i) the recommendation of a suitable switching mechanism to drive the robot manipulator, (ii) the successful integration of the interval type-2 fuzzy sliding mode control to track the desired trajectory, and (iii) the launching of several tests to validate the proposed controller with robot model. From these achievements, it would be stated that the proposed approach is effective in tracking performance, robust in disturbance-rejection, and feasible in practical implementation.

show abstract

“…The inputs for the end-to-end learning network are not limited to image information. For longitudinal speed control of a vehicle, the error between the speed output command and the actual speed is a reasonable input [25]. Ghoniem et al [26] introduced a suspension controller to generate a valve opening signal.…”

Section: Introductionmentioning

confidence: 99%

Deviation Sequence Neural Network Control for Path Tracking of Autonomous Vehicles

Su,

Mao,

Zhang

et al. 2024

Actuators

View full text Add to dashboard Cite

Despite its excellent performance in path tracking control, the model predictive control (MPC) is limited by computational complexity in practical applications. The neural network control (NNC) is another attractive solution by learning the historical driving data to approximate optimal control law, but a concern is that the NNC lacks security guarantees when encountering new scenarios that it has never been trained on. Inspired by the prediction process of MPC, the deviation sequence neural network control (DS-NNC) separates the vehicle dynamic model from the approximation process and rebuilds the input of the neural network (NN). Taking full use of the deviation sequence architecture and the real-time vehicle dynamic model, the DS-NNC is expected to enhance the adaptability and the training efficiency of NN. Finally, the effectiveness of the proposed controller is verified through simulations in Matlab/Simulink. The simulation results indicate that the proposed path tracking NN controller possesses adaptability and learning capabilities, enabling it to generate optimal control variables within a shorter computation time and handle variations in vehicle models and driving scenarios.

show abstract

Speed control of electric vehicle by using type-2 fuzzy neural network

Cited by 10 publications

References 36 publications

New Energy Vehicle Electromagnetic Compatibility Test and Closed-Loop Simulation Analysis

New Energy Vehicle Electromagnetic Compatibility Test and Closed-Loop Simulation Analysis

Enhancement of the Tracking Performance for Robot Manipulator by Using the Feed-forward Scheme and Reasonable Switching Mechanism

Deviation Sequence Neural Network Control for Path Tracking of Autonomous Vehicles

Contact Info

Product

Resources

About