Rolling Bag Station Motor Decoupling Control Based on Multi-Agent on Automobile Safety Airbag

Niao Na Zhang; Guo Liang Wang

doi:10.4028/www.scientific.net/AMM.668-669.370

Paper Titles

Motion Model of Two-Wheel Differential Drive Mobile Robot under Variable Load
p.352

Research and Design of Auxiliary Power Supply for Motor Controller in Electric Vehicles
p.357

Research on the Kinematics of Line Heating Robot Based on SVM
p.361

Setting-Up Wireless Communication System for Mine Rescue Robots
p.366

Rolling Bag Station Motor Decoupling Control Based on Multi-Agent on Automobile Safety Airbag
p.370

Entering Direction Analysis of Matching Area of Underwater Terrain Aided Navigation Based on Variation Function
p.374

The Stewart Platform Dynamic Model Coupling Characteristic Analysis
p.379

Topological Map Building Based on Thinning
p.384

Survey of Cooperative Path Planning for Multiple Unmanned Aerial Vehicles
p.388

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 668-669Rolling Bag Station Motor Decoupling Control Based...

Rolling Bag Station Motor Decoupling Control Based on Multi-Agent on Automobile Safety Airbag

Abstract:

This paper based on multi-agent technology, according to automobile safety airbag roll bag station production technology, at first adopt TS fuzzy neural regression network to distributed modeling for the controlled object, the methods of combining supervision learning and reinforcement learning are used, according to multi-agent external reinforcement signals and the value function of evaluate network ,using adaptive genetic co-evolution algorithm to optimize the action network, so can adapt to the mutational environment, and engineering application supply the proof about the effectiveness of the control strategy.

You might also be interested in these eBooks

Mechanical Components and Control Engineering III

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 668-669)

Pages:

370-373

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.668-669.370

Citation:

Cite this paper

Online since:

October 2014

Authors:

Niao Na Zhang, Guo Liang Wang

Keywords:

Distributed Reinforcement Learning Algorithm, Genetic Algorithm (GA), Multi-Agent, Safety Airbag

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Bin Qin, Min Wu, Xin Wang. MAS based distributed decoupling control for the pressure of gas collectors of coke ovens[J]. Control Theory and Applications. 2006, 23(6): 961-966. In Chinese.

Google Scholar

[2] Bennian Wang , Yang Gao, Zhaoqian Chen. RLGA: A Reinforcement Learning Ba sed Genetic Algorithm [J]. Chinese Journal of Electronics. 2006 , 34(5): 856-866. In Chinese.

Google Scholar

[3] Bin Qin, Min Wu, Xin Wang. Multi-Level Coordination Control Based on Multi-Agent Reinforcement Learning for the Pressure of Gas Collectors of Coke Ovens [J]. Chinese Journal of Electronics. 2006, 34(10): 1847-1851. In Chinese.

Google Scholar

[4] Kulkarni A J, Tai K. Probability collectives: A decentralized, distributed optimization for multi-agent systems [J]. Advances in Intelligent and Soft Computing, 2009: 58: 441-450.

DOI: 10.1007/978-3-540-89619-7_43

Google Scholar

[5] Xing L N. Research on knowledge-based intelligent optimization approaches and its application [D]. Changsha: College of Information System and Management, National University of Defense Technology, (2009).

Google Scholar

[6] Yang Gao, Shifu Chen, Xin Lu. Research on Reinforcement Learning Technology: A Review[J]. ACTA AUTOMATICA SINICA. 2004, 30(1): 86-100. In Chinese.

Google Scholar

[7] Nan Wang, Tianjiang Hu, Jing Chen, Lincheng Shen. Probability collectives with compensate sampling and smooth factors [J]. Control and Decision. 2012, 27(4): 519-530. In Chinese.

Google Scholar