Classification of Electron Gun Operation Modes Using Artificial Neural Networks

• Authors: N. Isik , A. Isik
• Languages of publication: EN

Abstracts

EN

In electron collision experiments, the seven-element electron gun is commonly used to accelerate and focus an electron beam. The main operation modes of this experimental device are afocal, zoom and broad beam-modes. Each of these operation modes can be used for producing electron beam with desired diameter. In this study, the artificial neural network classification technique (ANN) is used for classification of electron gun operation modes depending on electrostatic lens voltages. For this purpose, we investigate the focusing condition for the first three-element lens. Other ANN is employed for the second four-element lens voltages to find the electron gun operation modes. A comprehensive training data is obtained from SIMION software which uses traditional ray-tracing method. ANNs are trained with this dataset. Moreover, performance evaluations are carried out to determine the classification power of ANNs. High performance values show that the ANN can easily categorize the operation mode of the electron gun as a function of lens voltages. The proposed approach may help to adjust electron gun voltages before collision experiments. It is believed that this study will be a model for the future research in electron collision systems. Network can be trained with experimental data for practical applications.

Keywords

EN

41.85.Ne; 07.05.Rm; 84.35.+I; 07.05.Mh

Discipline

• 07.05.Rm: Data presentation and visualization: algorithms and implementation
• 07.05.Mh: Neural networks, fuzzy logic, artificial intelligence
• 41.85.Ne: Electrostatic lenses, septa

• Publisher: Institute of Physics, Polish Academy of Sciences
• Journal: Acta Physica Polonica A
• Year: 2016
• Volume: 129
• Issue: 4
• Pages: 628-630

Dates

published

2016-04

Contributors

author

N. Isik

• Mehmet Akif Ersoy University, Department of Science Education, Burdur, Turkey

author

A. Isik

• Mehmet Akif Ersoy University, Department of Computer Engineering, Burdur, Turkey

References

• [1] S. Raj, D. Sarma, Rev. Sci. Instrum. 75, 1020 (2004), doi: 10.1063/1.1647694
• [2] M. Ulu, O. Sise, M. Dogan, Rad. Phys. Chem. 76, 636 (2007), doi: 10.1016/j.radphyschem.2006.02.018
• [3] B.M. Lewis, H.T. Tran, M.E. Read, R.L. Ives, IEEE Trans. Plasma Sci. 32, 1242 (2004), doi: 10.1109/TPS.2004.827572
• [4] J. David, L. Ives, H. Tran, T. Bui, M. Read, IEEE Trans. Plasma Sci. 36, 156 (2008), doi: 10.1109/TPS.2007.913884
• [5] T.W. Barefoot, H.D. Ebinger, J.T. Yates, J. Vac. Sci. Technol. A 15, 2740 (1997), doi: 10.1116/1.580948
• [6] S.K. Mahapatra, S.D. Dhole, V.N. Bhoraskar, Nuc. Instrum. Methods Phys. Res. A 536, 222 (2005), doi: 10.1016/j.nima.2004.07.200
• [7] S.C. Johnston, W.A. Greynolds, D.Y. Wang, D.C. Dilworth, Proc. SPIE 1780, 192 (1993)
• [8] S.M. Tam, C.K. Kwong, W.H. Ip, Int. J. Comp. Appl. Techn. 13, 229 (2000), doi: 10.1504/IJCAT.2000.000243
• [9] A.A. Fadhil, Int. J. Adv. Comp. Tech. 2, 66 (2010), doi: 10.4156/ijact.vol2.issue5.7
• [10] A.H. Isik, Acta Phys. Pol. A 127, 1317 (2015), doi: 10.12693/APhysPolA.127.1317
• [11] A.H. Isik, Acta Phys. Pol. A 127, 1717 (2015), doi: 10.12693/APhysPolA.127.1717
• [12] S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice-Hall, New York 1999
• [13] Simion 3D v8.1, Scientific Instrument Services Inc., http://www.simion.com, 2012
• [14] D.W.O. Heddle, Electrostatic Lens Systems, IOP Press, London 2000
• [15] M.F. Moller, Neural Networks, 6, 525 (1993), doi: 10.1016/S0893-6080(05)80056-5

Identifiers

DOI

10.12693/APhysPolA.129.628