基于VMD与AdaBoost-SCN的海缆振动信号识别方法

尚秋峰1,2,3,黄达1,巩彪1

振动与冲击 ›› 2023, Vol. 42 ›› Issue (19) : 231-239.

PDF(3066 KB)
PDF(3066 KB)
振动与冲击 ›› 2023, Vol. 42 ›› Issue (19) : 231-239.
论文

基于VMD与AdaBoost-SCN的海缆振动信号识别方法

  • 尚秋峰1,2,3,黄达1,巩彪1
作者信息 +

Submarine cable vibration signal identification method based on VMD and AdaBoost-SCN

  • SHANG Qiufeng1,2,3, HUANG Da1, GONG Biao1
Author information +
文章历史 +

摘要

海底光缆的在线监测和振动信号识别是保证其正常运行的关键技术。搭建了基于布里渊光时域分析系统,模拟不同工况下的海缆振动信号。针对海缆振动信号信息丰富、信噪比低,使用单一随机配置网络(Stochastic Con¬figuration Network, SCN)模型对信号识别准确率不高的问题,提出了自适应增强(Adaptive Boosting, AdaBoost)算法优化的随机配置网络(AdaBoost-SCN)识别方法。首先用变分模态分解(Varia¬tional Modal Decomposition,VMD)算法分解海缆振动信号,构建特征向量;然后采用AdaBoost-SCN算法对振动信号分类。结果表明,所提方法有着很高的精度,并且具有很强的鲁棒性与泛化能力,提高了布里渊光时域分析系统振动信号识别的有效性。

Abstract

Online monitoring and vibration signal identification of submarine cables are the key technologies to en¬sure their normal operation. Based on brillouin optical time domain analysis system, the vibration signal of submarine cable under different working conditions was simulated. Aiming at the problem that the signal recognition accuracy of the stochastic configuration network (SCN) model is not high, the adaptive boosting (AdaBoost) algorithm optimization (Ada-Boost-SCN) is proposed. Firstly, the variational modal decomposition (VMD) algorithm is used to decompose the vibration signal of the submarine cable and construct the eigenvector. Then, the AdaBoost-SCN algorithm is used to classify the vibration signal. The results show that the proposed method has high accuracy, robustness and generalization ability, which improves the effectiveness of vibration signal recognition in brillouin optical time domain analysis system.

关键词

信号识别 / 变分模态分解 / 随机配置网络 / 自适应增强算法

Key words

signal identification / varia¬tional modal decomposition (VMD) / stochastic configuration network (SCN) / AdaBoost algorithm (AdaBoost)

引用本文

导出引用
尚秋峰1,2,3,黄达1,巩彪1. 基于VMD与AdaBoost-SCN的海缆振动信号识别方法[J]. 振动与冲击, 2023, 42(19): 231-239
SHANG Qiufeng1,2,3, HUANG Da1, GONG Biao1. Submarine cable vibration signal identification method based on VMD and AdaBoost-SCN[J]. Journal of Vibration and Shock, 2023, 42(19): 231-239

参考文献

[1] 徐朗, 蔡德所. 基于最小二乘平滑滤波与CEEMDAN的光纤陀螺信号处理研究[J]. 振动与冲击, 2020,39(10) (10):269-278.
XU Lang, CAI Desuo. Research on Fiber Optic Gyro Signal Processing Based on Least Squares Smoothing Filtering and CEEMDAN[J]. Journal of Vibration and Shock, 2020, 39(10):269-278.
[2] 詹君, 程龙生, 彭宅铭. 基于VMD和改进多分类马田系统的滚动轴承故障智能诊断[J]. 振动与冲击, 2020, 39(2):32-39.
ZHAN Jun, CHENG Longsheng, PENG Zhaoming. Intelligent diagnosis of rolling bearing faults based on VMD and im¬proved multi-classification Martin system[J]. Journal of Vibration and Shock, 2020, 39(2):32-39.
[3] 尚秋峰, 巩彪. 基于BOTDA的海缆监测系统振动信号降噪方法研究[J]. 半导体光电, 2021, 42(5):760-766.
SHANG Qiufeng, GONG Biao. Research on Vibration Signal Noise Reduction Method of Submarine Cable Monitoring Sys-tem Based on BOTDA[J]. Semiconductor Optoelectronics, 2021, 42(5):760-766.
[4] 窦希杰, 王世博, 谢洋,等. 基于IMF能量矩和SVM的煤矸识别[J]. 振动与冲击, 2020, 39(24):39-45.
DOU Xijie, WANG Shibo, XIE Yang, et al. Gangue Identification Based on IMF Energy Moment and SVM[J]. Journal of Vibration and Shock, 2020, 39(24):39-45.
[5] 焦敬品, 李勇强, 吴斌,等. 基于BP神经网络的管道泄漏声信号识别方法研究[J]. 仪器仪表学报, 2016, 37(11): 2588-2596.
JIAO Jingpin, LI Yongqiang, WU Bin, et al. Research on acoustic signal recognition method of pipeline leakage based on BP neural network[J]. Chinese Journal of Scientific Instru-ment, 2016, 37(11):2588-2596.
[6] CHEN T, HONG C. Universal approximation to nonlinear operators by neural networks with arbitrary activation func-tions and its application to dy¬namical systems[J]. IEEE Transactions on Neural Networks, 1995, 6(4):911-917.
[7] IGELNIK B, PAO Y H. Stochastic choice of basis functions in adaptive function approximation and the functional-link net[J]. IEEE Transactions on Neural Networks, 1995, 6(6):1320-1329.
[8] WANG D, MING L. Stochastic Configuration Networks: Fun¬damentals and Algorithms[J]. IEEE Transactions on Cybernetics, 2017, 47(10):3466-3479.
[9] 盛智勇, 孙成斌, 张远. 基于TSVD-SCN的光纤入侵信号识别算法研究[J]. 光电子•激光, 2019, 30(5): 494-502.
SHENG Zhiyong, SUN Chengbin, ZHANG Yuan. Research on Optical Fiber Intrusion Signal Recognition Algorithm Based on TSVD-SCN[J]. Optoelectronics & Lasers, 2019, 30(5): 494-502.
[10] LI W, ZENG Z, QU H, et al. A Novel Fiber Intrusion Signal Recognition Method for OFPS Based on SCN With Dropout[J]. Journal of Lightwave Technology, 2019, 37(20): 5221-5230.
[11] 曲洪权,吉祥,盛智勇,等.基于AdaBoost集成学习的光纤振动信号识别分类方法[J].激光与光电子学进展,2022, 59(13):229-236.
QU Hongquan, JI Xiang, SHENG Zhiyong, et al. Research on Optical Fiber Vibration Signal Iden¬tification Classification Method Based on AdaBoost Integrated Learning[J]. Advances in Laser and Optoelectronics, 2022, 59(13):229-236.
[12] FREUND Y. A decision-thoretic generalization of on-line learning and an application to boosting[J]. Journal of Com-puter and System Sciences, 1997, 55(1): 119-139.
[13] VALLE C, NANCULEF R , ALLENDE H , et al. LocalBoost: A Parallelizable Approach to Boosting Classifiers[J]. Neural processing letters, 2019, 50(1):19-41.
[14] 冯雨珊,尚秋峰,吕安强.波浪力作用下光纤复合海底电缆动力学有限元分析[J].光通信研究,2017(4):30-34.
FENG Yushang, SHANG Qiufeng, LV Anqiang. Dynamic finite element analysis of optical fiber composite submarine cable under wave force [J]. Optical communication research, 2017 (4): 30-34.
[15] 柳小花.光纤复合海底电缆扭转与磨损特性的有限元分析[D].华北电力大学.2017.
LIU Xiaohua. Finite element analysis of torsion and wear characteristics of optical fiber composite submarine cable [D]. North China Electric Power University. 2017.
[16] 尚秋峰,巩彪,郑国强.锚砸作用下光纤复合海底电缆的振动特性分析[J].光通信研究,2021(5):45-49+56.
SHANG Qiufeng, GONG Biao, ZHENG Guoqiang. Analysis of vibration characteristics of optical fiber composite submarine cable under anchor impact [J]. Optical communication research, 2021 (5): 45-49+56.
[17] 樊凤杰,白洋,纪会芳.基于EEMD-ICA的脑电去噪算法研究[J].计量学报,2021,42(3):395-400.
FAN Fengjie, BAI Yang, JI Huifang. Research on EEG based EEMD-ICA denoising algorithm[J]. Acta of Metrology, 2021,42(3):395-400.
[18] SUMREDDEE P, HAY E H, TOGHIANI S, et al. Grid search approach to discriminate between old and recent inbreeding using phenotypic, pedigree and genomic information[J]. BMC Genomics, 2021, 22(1):538-538.
[19] 梅比,汪旭光,杨仁树.基于Adaboost-SVM组合算法的爆破振动强度预测研究[J].振动与冲击,2019,38(18):231-235.
MEI Bi, WANG Xuguang, YANG Renshu. Research on blasting vibration intensity prediction based on Adaboost-SVM combination algorithm[J]. Journal of Vibration and Shock,2019,38(18):231-235.
[20] 付乐天,李鹏,高莲,等.基于遗传算法与BP_ Adaboost的故障检测方法[J].计算机仿真,2022,39(08):109-114.
FU Letian, LI Peng, GAO Lian, et al. Fault detection method based on genetic algorithm and BP_ Adaboost[J].Computer Simulation,2022,39(08):109-114.

PDF(3066 KB)

Accesses

Citation

Detail

段落导航
相关文章

/