Fault Identification Method of High‑speed Railway Noise Barriers Based on KNN Algorithm and φ‑OTDR System

Daliang FU; Yuanyuan YAO; Huaru LIU; Qianyi GAO; Ying LI; Xuping ZHANG; Chengcheng DAI; Ningmu ZOU; Yixin ZHANG

doi:10.19453/j.cnki.1005-488x.2023.03.013

Optoelectronic Technology, Volume. 43, Issue 3, 261(2023)

Fault Identification Method of High‑speed Railway Noise Barriers Based on KNN Algorithm and φ‑OTDR System

Daliang FU¹, Yuanyuan YAO², Huaru LIU¹, Qianyi GAO², Ying LI¹, Xuping ZHANG^2,3, Chengcheng DAI¹, Ningmu ZOU⁴, and Yixin ZHANG^2,3

Author Affiliations

¹China Railway Fifth Survey and Design Institute Group Co., Ltd, Beijing 02600, CHN

²College of Engineering and Applied Sciences, Nanjing University, Nanjing 1003, CHN

³Nanjing Fiber Photonics Technology Co., Ltd, Nanjing 21115, CHN

⁴College of Engineering, Texas State University, San Marcos78666, United States

show less

Abstract Get PDF(in Chinese)

Figures & Tables(1)

Table 1. Common characteristics in time domain， frequency domain and information domain

View table

View in Article

Table 1. Common characteristics in time domain， frequency domain and information domain

特征类型	特征名称	定义	含义
时域	最大值	$X_{P K} = m a x (x)$	信号幅度的最大值
	最小值	$X_{m i n} = m i n (x)$	信号幅度的最小值
	峰峰值	$X_{P K - P K} = m a x (x) - m i n (x)$	幅度最高值和最低值之间的差值
	方差	$X_{v a r} = \frac{1}{n} \cdot {\sum_{i = 1}^{n} (x_{i} - \bar{x})}^{2}$	能量的动态分量
频域	重心频率	$F C = \frac{\sum_{i = 1}^{m} f_{i} \cdot p_{i}}{\sum_{i = 1}^{m} p_{i}}$	信号在频谱中分量较大的信号成分的频率
	均方频率	$M S F = \frac{\sum_{i = 1}^{m} {f_{i}}^{2} \cdot p_{i}}{\sum_{i = 1}^{m} p_{i}}$	描述功率谱主频带位置分布
	均方根频率	$R M S F = \sqrt[]{M S F}$	均方频率的算数平方根
	频率方差	$V F = \frac{\sum_{i = 1}^{m} {(f_{i} - F C)}^{2} \cdot p_{i}}{\sum_{i = 1}^{m} p_{i}}$	描述功率谱能量分布的分散程度
	频率标准差	$R V F = \sqrt[]{V F}$	频率方差的算数平方根
信息域	功率谱熵	$p s d E = - \sum_{i = 1}^{n} (\frac{p_{i}}{\sum_{i = 1}^{n} p_{i}} \cdot l n (\frac{p_{i}}{\sum_{i = 1}^{n} p_{i}}))$	表示信号能量在功率谱划分下的不确定性
	奇异谱熵	$s v d E = - \sum_{i = 1}^{n} (\frac{s v d_{i}}{\sum_{i = 1}^{n} s v d_{i}} \cdot l n (\frac{s v d_{i}}{\sum_{i = 1}^{n} s v d_{i}}))$	对信号序列进行奇异谱分解后，获取其内在复杂性特征
	能量熵	$e E = - \sum_{i = 1}^{n} (\frac{i m f_{i}}{\sum_{i = 1}^{n} i m f_{i}} \cdot l n (\frac{i m f_{i}}{\sum_{i = 1}^{n} i m f_{i}}))$	信号分解后各个分量的能量，得到其概率密度函数计算信息熵

Tools

Get Citation

Copy Citation Text

Daliang FU, Yuanyuan YAO, Huaru LIU, Qianyi GAO, Ying LI, Xuping ZHANG, Chengcheng DAI, Ningmu ZOU, Yixin ZHANG. Fault Identification Method of High‑speed Railway Noise Barriers Based on KNN Algorithm and φ‑OTDR System[J]. Optoelectronic Technology, 2023, 43(3): 261

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category:

Received: Dec. 21, 2022

Accepted: --

Published Online: Mar. 21, 2024

The Author Email:

DOI:10.19453/j.cnki.1005-488x.2023.03.013

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology