Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling

Masoumeh Mohamadian; Hossein Afarideh; Mitra Ghergherehchi

doi:10.1088/1674-1137/41/1/017003

Chinese Physics C> 2017, Vol. 41> Issue(1) : 017003 DOI: 10.1088/1674-1137/41/1/017003

Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling

1.
Energy Engineering and Physics Department, Amirkarbir University of Technology, Tehran, 15857-4413 Iran
2.
College of Information and Communication Engineering, Sungkyunkwan University, Suwon 440-746, Korea

Abstract
HTML
Reference
Related

PDF

Abstract：
The cyclotron cavity presented in this paper is modeled by a feed-forward neural network trained by the authors' optimized back-propagation (BP) algorithm. The training samples were obtained from simulation results that are for a number of defined situations and parameters and were achieved parametrically using MWS CST software; furthermore, the conventional BP algorithm with different hidden-neuron numbers, structures, and other optimal parameters such as learning rate that are applied for our purpose was also used here. The present study shows that an optimized FFN can be used to estimate the cyclotron-model parameters with an acceptable error function. A neural network trained by an optimized algorithm therefore shows a proper approximation and an acceptable ability regarding the modeling of the proposed structure. The cyclotron-cavity parameter-modeling results demonstrate that an FNN that is trained by the optimized algorithm could be a suitable method for the estimation of the design parameters in this case.
- cyclotron cavity ,
- CST ,
- modeling ,
- neural network

References

[1]	M. S. Livingston, J. P. Blewett, Particle Accelerators (New York:McGraw-Hill, 1962)
[2]	J. Xia, Rusli, A. S. Kumta, IEEE T Plasma SCI, 38(2):142-148(2010)
[3]	M. Abd El-Kawy, M. Shaker Ismail, M. Abdel-Bary, M. M. Ouda, Arab J. Nucl. Science and App., 45(3):(2012)
[4]	R. Fletcher, Practical Methods of Optimization (UK:Chichester Wiley, 1987)
[5]	L. Fausett, Fundamentals of Neural Networks (New York:Prentice Hall 1994)
[6]	J. Y. F. Yam, T. W. S. Chow, IEEE T Neural Networks, 8:806-811, (1997)
[7]	J. L. McClelland, D. E. Rumelhart, Explorations in Parallel Distributed Processing-a Handbook of Models, Programs, and Exercises (MIT Press, Cambridge, 1988), p. 126-130
[8]	P. J. Werbos, The Roots of Backpropagation From Ordered Derivatives to Neural Networks and Political Forecasting (New York, NY:John Wiley Sons, 1994)
[9]	M. Mohamadian, H. Afarideh, F. Babapour, IAENG Int. J of Com. Science, 42(3):265-274(2015)
[10]	S. I. Gallant, Neural Network Learning and Expert Systems (MIT Press, Cambridge, 1993)
[11]	Y. Jongen et al, Proc of Cyclotrons, China (2010)
[12]	CST Studio Suite 2014(CST Microwave Studio)
[13]	M. Mohamadian, M. Salehi, H. Afarideh, M. Ghergherechi, J. Chai, Proc. 12th International Computational Accelerator Phys. Conf., China, (2015)
[14]	A. W. Chao, K. H. Mess, M. Tigner, F. Zimmermann, Handbook of Accelerator Physics and Engineering (2nd Edition, World Scientific Publishing Co., 2013)
[15]	S. L. Ozesmi, U. Ozesmi, Ecological Modelling, 116:15-31(1999)
[16]	O. M. Ibrahim, J Applied Sciences Research, 9(11):5692-5700(2013)
[17]	S. Tonidandel, J. M. LeBreton, J. B. Psychol, J Business and Psychology, 26(1):1-9(2011)
[18]	G. D. Garson, Artificial Intelligence Expert, 6:46-51(1991)
[19]	R. Gunawan, Y. Cao, L. Petzold, Biophys J., 88(4):2530-2540(2005)

[1]	Ying-Hua Dang , Jun-Sheng Li , Dong-Hai Zhang . Predicting ²⁸Si projectile fragmentation cross sections with Bayesian neural network method. Chinese Physics C, 2024, 48(12): 124102. doi: 10.1088/1674-1137/ad6c0a
[2]	Zehan Wu , Dehua Wen . From masses and radii of neutron stars to EOS of nuclear matter through neural network. Chinese Physics C, 2024, 48(2): 024101. doi: 10.1088/1674-1137/ad0e04
[3]	Kai-Fang Pu , Han-Lin Li , Hong-Liang Lü , Long-Gang Pang . Solving Schrodinger equations using a physically constrained neural network. Chinese Physics C, 2023, 47(5): 054104. doi: 10.1088/1674-1137/acc518
[4]	Tian-Liang Zhao , Hong-Fei Zhang . A neural network approach based on more input neurons to predict nuclear mass. Chinese Physics C, 2022, 46(4): 044103. doi: 10.1088/1674-1137/ac3e5b
[5]	Zilong Yuan , Dachuan Tian , Jian Li , Zhongming Niu . Magnetic moment predictions of odd-A nuclei with the Bayesian neural network approach. Chinese Physics C, 2021, 45(12): 124107. doi: 10.1088/1674-1137/ac28f9
[6]	Halil Mutuk . Neural network study of hidden-charm pentaquark resonances. Chinese Physics C, 2019, 43(9): 093103. doi: 10.1088/1674-1137/43/9/093103
[7]	Kai Zhou , Yun-Tao Song , Kai-Zhong Ding , Jian Ge , Kai Yao . Analytical solution of transverse oscillation in cyclotron using LP method. Chinese Physics C, 2018, 42(3): 037001. doi: 10.1088/1674-1137/42/3/037001
[8]	Mei-Qi Song , Qing-Min Zhang , Yu-Hang Guo , Kai Li , Hai-Xiao Deng . Numerical modeling of thermal loading of diamond crystal in X-ray FEL oscillators. Chinese Physics C, 2016, 40(4): 048101. doi: 10.1088/1674-1137/40/4/048101
[9]	Cai-Xun Zhang , Shin-Ted Lin , Jian-Ling Zhao , Xun-Zhen Yu , Li Wang , Jing-Jun Zhu , Hao-Yang Xing . Discrimination of neutrons and γ-rays in liquid scintillator based on Elman neural network. Chinese Physics C, 2016, 40(8): 086204. doi: 10.1088/1674-1137/40/8/086204
[10]	ZHANG Hua , HUANG Kui-Dong , SHI Yi-Kai , XU Zhe . Point spread function modeling and image restoration for cone-beam CT. Chinese Physics C, 2015, 39(3): 038202. doi: 10.1088/1674-1137/39/3/038202
[11]	LI Lin , FANG Wen-Cheng , WANG Chao-Peng , GU Qiang . Modeling and analysis of SLED. Chinese Physics C, 2015, 39(4): 047002. doi: 10.1088/1674-1137/39/4/047002
[12]	M. Ghergherehchi , Y. H. Yeon , J. W. Kim , J. S. Chai . Simulation of electron behavior in PIG ion sourcefor 9 MeV cyclotron. Chinese Physics C, 2014, 38(12): 127004. doi: 10.1088/1674-1137/38/12/127004
[13]	DAI Jin-Hua , DENG Hai-Xiao , DAI Zhi-Min . Numerical modeling of a high power terahertzsource in Shanghai. Chinese Physics C, 2012, 36(7): 648-652. doi: 10.1088/1674-1137/36/7/014
[14]	LIANG Li-Zhen , HU Chun-Dong , XIE Yuan-Lai , XIE Ya-Hong , NBI-Team . Modeling process of the neutral beam re-ionization loss. Chinese Physics C, 2010, 34(7): 972-977. doi: 10.1088/1674-1137/34/7/008
[15]	YAO Hong-Juan , ZHANG Tian-Jue , GUAN Feng-Ping , ZHONG Jun-Qing . Vertical focusing study in the central region of the CYCIAE-100 cyclotron. Chinese Physics C, 2009, 33(S2): 39-41. doi: 10.1088/1674-1137/33/S2/010
[16]	WANG Si-Guang , MAO Ya-Jun , YE Hong-Xue . An artificial neural network for proton identification in HERMES data. Chinese Physics C, 2009, 33(3): 217-223. doi: 10.1088/1674-1137/33/3/011
[17]	ZHANG Meng , ZHAO Ming-Hua . Study of multipacting effect in superconducting cavity. Chinese Physics C, 2008, 32(10): 846-848. doi: 10.1088/1674-1137/32/10/016
[18]	XU Ye , HOU Jian , ZHU Kai-En . Applying Bayesian neural networks to identify pion, kaon and proton in BESⅡ. Chinese Physics C, 2008, 32(3): 201-204. doi: 10.1088/1674-1137/32/3/008
[19]	ZHANG Kun-Shi , LIU Lian-Shou . On the Identification of Quark and Gluon Jets Using Artificial Neural Network Method. Chinese Physics C, 2004, 28(11): 1141-1145.
[20]	Zhang Ziping , Chen Hongfang , Ye Shuwei , Zhao Jiawei . Identification of e,μ,π by Neural Network in BES. Chinese Physics C, 1997, 21(4): 297-303.

Access

Get Citation

Masoumeh Mohamadian, Hossein Afarideh and Mitra Ghergherehchi. Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling[J]. Chinese Physics C, 2017, 41(1): 017003. doi: 10.1088/1674-1137/41/1/017003

RIS(for EndNote,Reference Manager,ProCite)

BibTex

Txt

Milestone

Received: 2016-02-29
Revised: 2016-05-12

Article Metric

Article Views(1705)
PDF Downloads(37)
Cited by(0)

Policy on re-use

To reuse of subscription content published by CPC, the users need to request permission from CPC, unless the content was published under an Open Access license which automatically permits that type of reuse.

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling

Corresponding author: Hossein Afarideh, hafarideh@aut.ac.ir

Corresponding author: Mitra Ghergherehchi, hafarideh@aut.ac.ir

1. Energy Engineering and Physics Department, Amirkarbir University of Technology, Tehran, 15857-4413 Iran

2. College of Information and Communication Engineering, Sungkyunkwan University, Suwon 440-746, Korea

Received Date: 2016-02-29

Accepted Date: 2016-05-12

Available Online: 2017-01-05

Abstract: The cyclotron cavity presented in this paper is modeled by a feed-forward neural network trained by the authors' optimized back-propagation (BP) algorithm. The training samples were obtained from simulation results that are for a number of defined situations and parameters and were achieved parametrically using MWS CST software; furthermore, the conventional BP algorithm with different hidden-neuron numbers, structures, and other optimal parameters such as learning rate that are applied for our purpose was also used here. The present study shows that an optimized FFN can be used to estimate the cyclotron-model parameters with an acceptable error function. A neural network trained by an optimized algorithm therefore shows a proper approximation and an acceptable ability regarding the modeling of the proposed structure. The cyclotron-cavity parameter-modeling results demonstrate that an FNN that is trained by the optimized algorithm could be a suitable method for the estimation of the design parameters in this case.

HTML

Reference (19)

Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling

Abstract：

References

Access

Article Metrics

Metrics

通讯作者: 陈斌, bchen63@163.com

Email This Article