A backpropagation neural network controller trained using PID for digitally-controlled DC-DC switching converters

Liu, Jianfu; Wei, Tingcun; Chen, Nan; Liu, Wei; Wu, Jiayu; Xiao, Peilei; Luo, Yongbo

doi:10.1109/iciea51954.2021.9516423

Cited by 7 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This characteristic turns out to be interesting in the case of non-linear models that are difficult to model mathematically. Thus, thanks to its learning and approximation faculties, the neural command reproduce the behavior of the PI controller already developed using the matlab environment and proceeding as follows: [18] Figure 6. Efficiency versus load curve.…”

Section: Neural Control Boost Choppermentioning

confidence: 99%

Performance of the Boost Chopper, Comparative Study between PI Control and Neural Control to Regulate Its Output Voltage

Gueye¹,

Sall²,

Kebe³

2023

SGRE

View full text Add to dashboard Cite

In this study, we investigate the performance of a boost converter regulating its output voltage using two control methods: Proportional-Integral (PI) control and neural control. Both methods are implemented on a simulation platform (Matlab/Simulink) and evaluated in terms of accuracy, response speed, and robustness to disturbances. Indeed, the output voltage of converters exhibits imperfections that require a control method to optimize efficiency when applying a variable load. Results show that neural control offers superior performance in terms of accuracy and response time, with faster and more precise regulation of the output voltage. On the other hand, PI control proves to be more robust against disturbances. These findings can help guide the selection of the appropriate control method for a boost converter based on the specific requirements of each application.

show abstract

Section: Neural Control Boost Choppermentioning

confidence: 99%

Performance of the Boost Chopper, Comparative Study between PI Control and Neural Control to Regulate Its Output Voltage

Gueye¹,

Sall²,

Kebe³

2023

SGRE

View full text Add to dashboard Cite

show abstract

“…As an advanced control algorithm, their powerful knowledge extraction ability, superior learning ability, and strong robustness in the field of control have all led to their increasing application in modern research. Reference (Maruta and Hoshino, 2019;Liu, 2021) proposes the use of neural networks to control the converter. In reference (Kurokawa et al, 2010), the author identified a control object implemented using a DC/DC converter as the algorithm, delved into neural network algorithms, and proposed a neural network predictive controller to improve the dynamic output response of the converter.…”

Section: Motivation and Challengesmentioning

confidence: 99%

A robust voltage control of dual active full bridge converter based on RBF neural network sliding mode control with reduced order modeling approach

Wang

Sun

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

This paper presents a control method of dual active full bridge (DAB) DC/DC converter based on neural network Sliding mode control under the reduced order modeling method, which is used to enhance the output voltage regulation and improve the system robustness. Sliding mode control (SMC) is famous for its robustness and improving the dynamic performance of nonlinear systems. However, it includes drawbacks such as complex modeling, chattering, and decreased tracking performance. Therefore, through the method of reduced order modeling, the Radial Basis Function neural network algorithm is selected to modify and design the traditional sliding mode variable structure controller, completing the design of neural network approximation terms and adaptive laws. The proposed reduced order modeling and RBF(Radial Basis Function Neural Network)-SMC scheme simplifies the dual active full bridge modeling process, completes the parameter approximation of the sliding mode controller, and eliminates the chattering problem. Firstly, through simulation and comparative analysis of commonly used modeling methods for dual active full bridge, a reduced order modeling method was adopted to simplify the design process. Then, by ingeniously designing the sliding mode surface and Radial Basis Function control law, and using neural network to modify the Sliding mode control technology, the chattering problem, load disturbance and voltage fluctuation influence of the sliding mode controller are improved. The stability of the control method is proved by Lyapunov stability theory. Finally, the proposed RBF-SMC method is compared with PI linear control and classical Sliding mode control methods through simulation and experiments to verify the effectiveness of the proposed control method.

show abstract

“…Literature [9] proposes a design method for an expert adaptive PID controller, which is tuned online by expert rules to make the control performance smoothly converge to the expectation, but the controller requires a large amount of a priori knowledge as well as rules. Neural network has the ability to change its own performance to adapt to environmental changes, literature [10] use this characteristic, using BP neural network algorithm to optimize the PID parameters, however the process converges slowly, making real-time control difficult. As the fundamental building block of a neural network, a single neuron also has that property common to neural networks and also has the advantage of a simple structure and low computational effort [11] .…”

Section: Introductionmentioning

confidence: 99%

Study on boost converter control strategy based on particle swarm optimization single neuron PID

Yang,

Huang,

et al. 2024

Ninth International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023)

View full text Add to dashboard Cite

Aiming at the poor effect of conventional PID control in boost converter with nonlinear and time-varying characteristics, this work suggests a boost converter control technique based on Particle Swarm Optimization Single Neuron PID (PSO-SNPID). First, the ability of self-learning and self-adaptation of single neurons is utilized to adjust the weights online by learning rules, which in turn achieves the purpose of online rectification of PID parameters; Second, the learning rate and gain coefficient of the Single Neuron PID (SNPID) are optimized by the PSO algorithm as a way to improve the accuracy of the model; Finally, simulation experiments were carried out in Matlab/Simulink platform, and the results proved that the proposed method avoids the difficulty of manual parameterization and has better tracking performance and stronger robustness than the conventional PID control and Single Neuron PID control.

show abstract

A backpropagation neural network controller trained using PID for digitally-controlled DC-DC switching converters

Cited by 7 publications

References 9 publications

Performance of the Boost Chopper, Comparative Study between PI Control and Neural Control to Regulate Its Output Voltage

Performance of the Boost Chopper, Comparative Study between PI Control and Neural Control to Regulate Its Output Voltage

A robust voltage control of dual active full bridge converter based on RBF neural network sliding mode control with reduced order modeling approach

Study on boost converter control strategy based on particle swarm optimization single neuron PID

Contact Info

Product

Resources

About