Submarine Cable Vibration Signal Identification Method Based on VMD-BSA-SVM

Qiufeng Shang; Jiaxing Guo

doi:10.3788/LOP202259.1701001

Laser & Optoelectronics Progress, Volume. 59, Issue 17, 1701001(2022)

Submarine Cable Vibration Signal Identification Method Based on VMD-BSA-SVM

Qiufeng Shang^1,2,3 and Jiaxing Guo^1、*

¹Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, Hebei , China

²Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, Hebei , China

³Baoding Key Laboratory of Optical Fiber Sensing and Optical Communication Technology, North China Electric Power University, Baoding 071003, Hebei , China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Flow chart of the VMD-BSA-SVM

Download full size

Fig. 2. Composition of the experimental system

Download full size

Fig. 3. Vibration signals. (a) Scouring signal; (b) anchor smashing signal; (c) friction signal

Download full size

Fig. 4. VMD results of the signal. (a) Scouring signal; (b) friction signal; (c) anchor smashing signal

Download full size

Fig. 5. Classification results of BSA-SVM. (a) Fitness curve; (b) accuracy of the test set

Download full size

Fig. 6. Classification results of different algorithms. (a) PSO-SVM algorithm; (b) GA-SVM algorithm; (c) GS-SVM algorithm

Download full size

Table 1. Signal characteristics

View table

Table 1. Signal characteristics

IMF	Category	Scour	Friction	Anchor smashing
IMF 1	energy	0.1937	0.0087	0.0004
	kurtosis	0.1025	0.1601	0.2398
	energy entropy	0.318	0.0415	0.0029
IMF 2	energy	0.3739	0.0082	0.0006
	kurtosis	0.0492	0.1878	0.3074
	energy entropy	0.3678	0.0396	0.0044
IMF 3	energy	0.0458	0.0121	0.0006
	kurtosis	0.2292	0.1301	0.1807
	energy entropy	0.1411	0.0533	0.0045
IMF 4	energy	0.0009	0.0208	0.0019
	kurtosis	0.2507	0.2868	0.2198
	energy entropy	0.0061	0.0805	0.0121
IMF 5	energy	0.0007	0.3804	0.0038
	kurtosis	0.2793	0.1445	0.0211
	energy entropy	0.0053	0.3677	0.0212
IMF 6	energy	0.385	0.5697	0.9927
	kurtosis	0.0889	0.0907	0.0313
	energy entropy	0.3675	0.3205	0.0073

Table 2. Comparison results of four types of algorithms
View table
Table 2. Comparison results of four types of algorithms
Algorithm Accuracy /% Running time /s
BSA-SVM 99.17 67.32
GA-SVM 97.50 74.96
PSO-SVM 96.67 81.84
GS-SVM 95.83 49.27

Tools

Get Citation

Copy Citation Text

Qiufeng Shang, Jiaxing Guo. Submarine Cable Vibration Signal Identification Method Based on VMD-BSA-SVM[J]. Laser & Optoelectronics Progress, 2022, 59(17): 1701001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites