High Power Laser and Particle Beams, Volume. 36, Issue 9, 099002(2024)
Prediction of system-level electric field radiated emission based on ANN reverse model
Figures & Tables(13)
Table 1. Validation dataset
View tableView in ArticleTable 1. Validation dataset
No. f/MHz x1 y1 z1 E1/(dBuV/m) x2 y2 z2 E2/(dBuV/m) x3 y3 z3 E3/(dBuV/m) Etotal/(dBuV/m) 1 30 0 0 −100 4.3 1000 120 −100 4.3 1050 310 −750 42.2 31.939571 2 70 0 0 −100 10.9 1000 120 −100 3.2 1050 310 −750 39.4 40.123183 3 100 0 0 −100 9.2 1000 120 −100 10.7 1050 310 −750 45.2 53.036382 4 130 0 0 −100 30.5 1000 120 −100 11.5 1050 310 −750 45.3 60.507379 5 160 0 0 −100 19.9 1000 120 −100 11.6 1050 310 −750 48.3 64.899009 6 200 0 0 −100 20.9 1000 120 −100 17.3 1050 310 −750 57.2 77.367965 7 30 0 100 −200 4.3 900 200 −200 4.3 1000 400 −600 42.2 35.062737 8 70 0 100 −200 10.9 900 200 −200 3.2 1000 400 −600 39.4 43.601726 9 100 0 100 −200 9.2 900 200 −200 10.7 1000 400 −600 45.2 56.07834 10 130 0 100 −200 30.5 900 200 −200 11.5 1000 400 −600 45.3 62.877408 … … … … … … … … … … … … … … … 25 30 −200 0 −400 4.3 1200 150 −150 4.3 1200 200 −800 42.2 32.92811 26 70 −200 0 −400 10.9 1200 150 −150 3.2 1200 200 −800 39.4 40.90428 27 100 −200 0 −400 9.2 1200 150 −150 10.7 1200 200 −800 45.2 54.0078 28 130 −200 0 −400 30.5 1200 150 −150 11.5 1200 200 −800 45.3 61.66204 29 160 −200 0 −400 19.9 1200 150 −150 11.6 1200 200 −800 48.3 65.79797 30 200 −200 0 −400 20.9 1200 150 −150 17.3 1200 200 −800 57.2 77.72475
Table 2. Validation error and relative coefficient of different number of training dataset
View tableView in ArticleTable 2. Validation error and relative coefficient of different number of training dataset
number of training dataset validation error/% relative coefficient 30 7.7008 0.85303 100 0.8713 0.87193 200 0.4159 0.95546 500 0.0059 0.99809 1000 3.4247E-5 0.99977 10000 2.2718E-5 0.99991
Table 3. Alternative neural network
View tableView in ArticleTable 3. Alternative neural network
No. alternative neural network validation error/% 1 x1,c=fann,1(y, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.149589782 2 x2,c=fann,2(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.000017400 3 x3,c=fann,3(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.096499053 4 x4,c=fann,4(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.003367234 5 x5,c=fann,5(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 3.945121882 6 x6,c=fann,6(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.000000768 7 x7,c=fann,7(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.20383497 8 x8,c=fann,8(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.000812276 9 x9,c=fann,9(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 26.19090216 10 x10,c=fann,10(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 8.284504188 11 x11,c=fann,11(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.061618247 12 x12,c=fann,12(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 0.430195851 13 x13,c=fann,13(x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13) 10.20954216
Table 4. Comparison of prediction results
View tableView in ArticleTable 4. Comparison of prediction results
No. Etotal/(dBμV·m−1) CST simulation traditional LM-BP ANN ANN reverse model (conjugate gradient method) ANN reverse model (regular-falsi method) 1 31.94 45.64 30.34 31.04 2 40.12 52.91 38.11 39.00 3 53.04 56.41 52.91 51.55 4 60.51 48.03 60.33 58.81 5 64.90 58.98 65.98 63.08 6 77.37 60.86 76.63 75.20 7 35.06 54.04 26.02 34.08 8 43.60 55.38 36.43 42.38 9 56.08 60.12 49.31 54.51 10 62.88 56.28 65.89 61.11 11 67.58 60.84 66.36 65.68 12 80.09 63.85 74.17 77.84 13 33.37 60.00 33.68 32.44 14 40.88 62.78 41.72 39.73 15 53.74 60.13 53.21 52.23 16 60.87 61.54 60.15 59.17 17 65.84 65.62 66.13 63.99 18 78.86 68.21 78.36 76.65 19 32.80 47.91 27.05 31.88 20 41.02 53.70 37.33 39.87 21 53.80 55.91 48.49 52.29 22 61.09 52.69 59.88 59.38 23 65.67 59.85 60.61 63.83 24 78.14 64.56 65.75 75.95 25 32.93 58.02 31.77 32.00 26 40.90 57.64 38.76 39.76 27 54.01 56.90 53.70 52.49 28 61.66 60.12 60.52 59.93 29 65.80 61.43 67.04 63.95 30 77.72 66.63 77.63 75.55
Tools
Get Citation
Copy Citation Text
Luyao Liu, Xiao Jin, Jinliang Cai. Prediction of system-level electric field radiated emission based on ANN reverse model[J]. High Power Laser and Particle Beams, 2024, 36(9): 099002
Paper Information
Category: Advanced Interdisciplinary Science
Received: May. 24, 2024
Accepted: Jul. 22, 2024
Published Online: Oct. 15, 2024
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20