An Improved BP Algorithm Based on Global Revision Factor and Its Application to PID Control

Lei, Lin; Wang, Houjun; Yu-fang, Cheng

doi:10.1007/11760023_150

Cited by 2 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…denotes the weight increment in nth iteration. Weight value adjusting expressions of BP neural network is as follow [5]:…”

Section: Microwave Power Soft-measurement Based On Ibpmentioning

confidence: 99%

“…According to the input and output of object to construct a nonlinear function, BP neural network can be used to learn adaptive according to the new data swatch coming from mechanism model and practical running object. The method of soft-measuring based on IBP [5] can be simulated by Matlab language. The sample data can be divided into two parts.…”

Section: B Microwave Power Soft-measuring Based On Ibp Algorithmmentioning

confidence: 99%

“…All the exiting microwave power measurement techniques can not only measure exactly online but also real-timely [3,4]. So, we adopt microwave power measurement technique synthetically that exist now, a new method based on improved BP (IBP) neuron network [5] has been presented to carry out the microwave power measurement. The basic method is using technique of soft-measuring [6] based on IBP and the self-learning function of neuron network, meanwhile the sample data of microwave power signal can be used to carry out microwave power measurement, the new measurement is wide frequency and big dynamic.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Microwave Power Real-Time Soft-Measuring Based on Improved BP Neural Network

Lei

Ouyang

2011

AMR

Self Cite

View full text Add to dashboard Cite

There are many faults in microwave power measurement in the working spots. In this paper, the novel technique of microwave power measurement and Schottky detector and the technique of soft-measuring based on improved BP neural network are presented. Making use of directional coupler, the part of power of microwave signal in transmission line was taken in the certain proportion. Then, the microwave power meter indicated the magnitude of power. The microwave power measurement system was composed of tuneable attenuator, directional coupler, matching load, peak-peak value detector, oscillograph, thermocouple, soft-measuring algorithm and so on. The low microwave power meter obtained the sample data of training BP neuron network. Then, the output of trained BP neural network may represent the result of high microwave power measurement. The experiments and applications in practice project prove that this new method has many advantages.

show abstract

“…denotes the weight increment in nth iteration. Weight value adjusting expressions of BP neural network is as follow [5]:…”

Section: Microwave Power Soft-measurement Based On Ibpmentioning

confidence: 99%

Section: B Microwave Power Soft-measuring Based On Ibp Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Microwave Power Real-Time Soft-Measuring Based on Improved BP Neural Network

Lei

Ouyang

2011

AMR

Self Cite

View full text Add to dashboard Cite

show abstract

“…At present, BP-PID has been widely used in various industrial fields, Ren et al proposed an active anti-disturbance pitch controller using BP-PID algorithm for different working conditions of wind turbines to meet the engineering needs [9], and BP-PID has also been applied to the lateral stability control of electric vehicles [10], DC electronic load systems [11] and so on. However, its control performance is affected by two factors: the parameter settings (learning rate and inertia coefficient) [12] and the susceptibility of the BP algorithm to gradient vanishing Error! Reference source not found.. Adaptive controllers with extremely irrational parameter settings can adapt to different operating conditions, but it will lead to its long control time, so predicting roughly reasonable parameters through different operating conditions can effectively shorten the control time of the BP-PID controller [14], and Adithiyaa et al have already proved the ability of KNN to predict the parameters [15]; and Wang et al…”

Section: Introductionmentioning

confidence: 99%

ATKB-PID: An adaptive control method for micro tension under complex hot rolling conditions

Xinkai,

Xiangrong,

Zheng

2024

Preprint

View full text Add to dashboard Cite

At present, the controller parameters in hot rolling roughing microtension control cannot be adaptively adjusted according to the changes of working conditions, which affects the width accuracy as well as the stability of production. Therefore, an ATKB-PID adaptive micro tension control method is proposed in this paper. A linear attention layer is added to the BP-PID controller and a KNN method is established to predict the optimal learning rate and inertia coefficient under actual working conditions. In addition, the objective function is designed according to the production index to improve the performance of the model. Through the comparison experiments with the widely used RBF-BP control and BP-PID control, it is verified that the ATKB-PID control method proposed in this paper has small steady state error and short adjustment time. The ATKB-PID control method can meet the complex and variable micro tension control conditions in thermal roughing, and has good application prospects.

show abstract

An Improved BP Algorithm Based on Global Revision Factor and Its Application to PID Control

Cited by 2 publications

References 4 publications

Microwave Power Real-Time Soft-Measuring Based on Improved BP Neural Network

Microwave Power Real-Time Soft-Measuring Based on Improved BP Neural Network

ATKB-PID: An adaptive control method for micro tension under complex hot rolling conditions

Contact Info

Product

Resources

About