[1]姜 楠,张健穹,臧杰锋,等.基于 GWO-CFDP 算法的速度传感器干扰源识别[J].机械与电子,2025,(03):74-80.
　JIANG Nan,ZHANG Jianqiong,ZANG Jiefeng,et al.Speed Sensor Interference Source Identification Based on GWO-CFDP Algorithm[J].Machinery & Electronics,2025,(03):74-80.
点击复制

基于 GWO-CFDP 算法的速度传感器干扰源识别()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2025年03期
页码:
74-80
栏目:
机电一体化
出版日期:
2025-03-25

文章信息/Info

Title:
Speed Sensor Interference Source Identification Based on GWO-CFDP Algorithm
文章编号:
1001-2257 ( 2025 ) 03-0074-07
作者:
姜 楠; 张健穹; 臧杰锋; 李相强; 王庆峰
西南交通大学物理科学与技术学院,四川 成都 610031
Author(s):
JIANG Nan ;  ZHANG Jianqiong ;  ZANG Jiefeng ;  LI Xiangqiang ;  WANG Qingfeng
( School of Physics Science and Technology , Southwest Jiaotong University , Chengdu 610031 , China )
关键词:
速度传感器; 密度峰值聚类; 灰狼算法; 稀疏自编码; 核主成分分析
Keywords:
speed sensors ;  peak density clustering ;  grey wolf algorithm ;  sparse self-coding ;  kernel principal component analysis
分类号:
TM86
文献标志码:
A
摘要:
为了准确判断列车行驶时 TCU 速度传感器的干扰来源,提出了基于灰狼算法( GWO )改进的密度峰值快速聚类( CFDP )算法。首先,对列车实测干扰信号进行特征分析;然后,通过采用 2 层稀疏自编码网络连同核主成分分析,对预处理后的信号完成特征的自提取与降维;最后,利用所提出的 GWO-CFDP算法实现 4 种干扰工况的分类识别。实验结果表明,所提出的干扰源识别算法对 4 种干扰工况的识别准确率达到 99.0% ,验证了该算法在干扰源识别领域的有效性和实用价值。
Abstract:
In order to accurately identify the sources of interference affecting the TCU speed sensors during train operation , an improved Density Peak Fast Clustering ( CFDP ) algorithm based on Grey Wolf Optimizer ( GWO ) was proposed.Initially , the actual interference signals of the train were subject to feature analysis ; following this , feature auto extraction and dimensionality reduction were performed on the preprocessed signals using a two-layer sparse autoencoder network along with kernel principal component analysis ; subsequently , the classification and identification of four types of interference conditions were realized using the proposed GWO-CFDP algorithm.The experimental results demonstrate the interference source identification algorithm proposed in this paper achieved an identification accuracy of 99.0 percent for the four interference conditions , thereby validating the effectiveness and practical value of the algorithm in the field of interference source identification.

参考文献/References:

[ 1 ] 张国芹,高国强 . 车体过电压对动车组轴端速度传感器的影响机理[ J ] . 城市轨道交通研究, 2019 , 22 ( 2 ): 60-65.

[ 2 ] 鲁进军,吴萌岭,牛刚 . 轨道交通制动系统速度传感器的故障诊断方法研究[ J ] . 铁道学报, 2021 , 43 ( 1 ): 85-93.
[ 3 ] 张翔,温熙圆,曹宏发,等 . 基于迭代学习的速度传感器故障诊断研究 [ J ] . 铁道科学与工程学报,2021 , 18( 11 ): 3006-3012.
[ 4 ] 刘尧 . 基于迭代学习的地铁车辆速度传感器故障识别[ J ] . 自动化与仪表, 2023 , 38 ( 4 ): 107-111.
[ 5 ] 牛刚,曹雪杰,秦肖肖 . 高速列车双通道速度传感器故障检测与隔离研究[ J ] . 仪器仪表学报,2019 , 40 ( 1 ):158-165.
[ 6 ] 吕红运 . 配电网弧光接地过电压与铁磁谐振过电压识别方法研究[ D ] . 长沙:湖南大学,2016.
[ 7 ] 蒋懿波,刘会家,吴田 . 基于改进残差网络的输电线路雷击过电压识别研究[ J ] . 广西师范大学学报(自然科学版),2023 , 41 ( 4 ): 74-83.
[ 8 ] LONG F , XU H , ZHAN W , et al.Recognition of internal overvoltage in distribution network based on convolutional neural network [ J ] .Electrica , 2022 , 22 ( 3 ):342-350.
[ 9 ] 李文艺,彭跃辉,刘坤亮,等 . 基于小波变换和随机森林算法的高压断路器机构机械特性监测技术研究[ J ] . 高压电器,2022 , 58 ( 10 ): 75-82.
[ 10 ] 何婷,乔俊强,包建勤,等 . 基于 EMD 和 SVM 的电力系统故障分类识别[ J ] . 仪表技术, 2022 ( 4 ): 64-69.
[ 11 ] ZHU J P , YUAN Y , WU H.Key factor identification of over-voltage in renewable-rich distribution network based on spectral clustering [ C ] ∥2020 12th IEEE PES Asia-Pacific Power and Energy Engineering Conference ( APPEEC ),2020 : 1-5.
[ 12 ] PENG X S , YANG F , WANG G J , et al.A convolutional neural network-based deep learning methodology for recognition of partial discharge patterns from high-voltage cables [ J ] .IEEE Transactions on power delivery , 2019 , 34 ( 4 ): 1460-1469.
[ 13 ] 陈富昭 . 基于多传感器融合的高速列车牵引变流器故障智能诊断技术研究 [ D ] . 北京:北京交通大学,2021.
[ 14 ] 贾君宜,吴命利,宋可荐,等 . 基于短时傅里叶变换和深度学习的牵引网过电压辨识[ J ] . 电气技术, 2021 ,22 ( 10 ): 1-10.
[ 15 ] 崔芮华,李英男,王传宇,等 . 基于小波能量矩的航空交流串联电弧故障识别算法研究[ J ] . 电工电能新技术,2019 , 38 ( 11 ): 1-9.
[ 16 ] WANG J H , HUANG Z , LENG Y.Identification technology of substation lightning overvoltage based on wavelet transform research and application [ C ] ∥2020 5th Asia Conference on Power and Electrical Engineering ( ACPEE ), 2020 : 1746-1750.
[ 17 ] MIRJALILI S , MIRJALILI S M , LEWIS A.Grey wolf optimizer [ J ] .Advances in engineering software , 2014 , 69 : 46-61.
[ 18 ] 陈敏,陈晔,牛兴龙,等 . 求解全局优化问题的多策略改进灰狼算法[ J ] . 国外电子测量技术, 2022 , 41 ( 11 ): 22-29.
[ 19 ] 刘再涛,王震,贺建军,等 . 基于灰狼算法优化的多隐层径向基神经网络铅锌烧结返粉料水分预测[ J ] . 中南大学学报(自然科学版),2023 , 54 ( 2 ): 754-764.
[ 20 ] 曹轲,谭冲,刘洪,等 . 基于改进灰狼算法优化 BP 神经网络的无线传感器网络数据融合算法[ J ] . 中国科学院大学学报(中英文),2022 , 39 ( 2 ): 232-239.
[ 21 ] 刘松,陈克,王楷焱 . 基于 IGWO BP 神经网络的车内声品质预测[ J ] . 沈阳理工大学学报, 2023 , 42 ( 5 ):88-94.
[ 22 ] 管雪梅,杨渠三,吴言 . 基于灰狼算法优化支持向量回归模型的木材染色配色算法研究 [ J ] . 林产工业,2023 , 60 ( 7 ): 27 33.
[ 23 ] RODRIGUEZ A , LAIO A.Clustering by fast search and find of density peaks [ J ] .Science , 2014 , 344 ( 6191 ): 1492-1496.

备注/Memo

备注/Memo:
收稿日期: 2024-03-20
基金项目:四川省科技厅重点研发项目( 22ZDYF3091 );中央高校基本科研业务费(2682021ZT039 , 2682021ZTPY128 )
作者简介:姜 楠 ( 1999- ),男,吉林长春人,硕士研究生,研究方向为电磁兼容;张健穹 ( 1983- ),男,四川成都人,教授,博士研究生导师,研究方向为电磁兼容、天线理论与技术、智能检测技术,通信作者。
更新日期/Last Update: 2025-04-08