[1]袁武民,邢建平,杨 栋.基于改进 Stacking 模型的铁路信号设备故障率预测[J].机械与电子,2024,42(01):41-46.
　YUAN Wumin,XING Jianping,YANG Dong.Prediction of Railway Signal Equipment Failure Rate Based on Improved Stacking Model[J].Machinery & Electronics,2024,42(01):41-46.
点击复制

基于改进 Stacking 模型的铁路信号设备故障率预测()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
42
期数:
2024年01期
页码:
41-46
栏目:
自动控制与检测
出版日期:
2024-01-25

文章信息/Info

Title:
Prediction of Railway Signal Equipment Failure Rate Based on Improved Stacking Model
文章编号:
1001-2257 ( 2024 ) 01-0041-06
作者:
袁武民 1 ; 邢建平 2 ; 杨 栋 3
1. 兰州深蓝图形技术有限公司,甘肃 兰州 730010 ;
2. 中国铁路兰州局集团有限公司兰州高铁基础设施段,甘肃 兰州 730050 ;
3. 中国铁路兰州局集团有限公司银川电务段,宁夏 银川 750021
Author(s):
YUAN Wumin 1 ;  XING Jianping 2 ;  YANG Dong3
( 1.Lanzhou Sunland Graphics Technology Co. , Ltd. , Lanzhou 730010 , China ;
2.Lanzhou High Speed Railway Infrastructure Section , China Railway Lanzhou Bureau Group Co. , Ltd. , Lanzhou 730050 , China ;
3.Yinchuan Electricity Section , China Railway Lanzhou Bureau Group Co. , Ltd. , Yinchuan 750021 , China )
关键词:
机器学习; 融合模型; 时间序列; 铁路信号设备; 故障率预测
Keywords:
machine learning ;  fusion model ;  time series ;  railroad signal equipment ;  failure rate prediction
分类号:
U284.92
文献标志码:
A
摘要:
针对单一机器学习模型在预测设备故障率的应用场景中存在误差大、精度低的问题,提出一种基于改进 Stacking 融合模型对铁路信号设备进行故障率预测的方法。采用 XGBoost 、 LightGBM 、 CatBoost 和逻辑回归方法构建基本 Stacking 模型,在此基础上引入 Prophet 时间序列预测模型,将 Prophet 模型提取的时序特征与基本 Stacking 模型逐级融合,构建改进后的 Stacking Prophet 预测模型。最后以某单位信号设备数据为例,验证预测模型有效性。实验结果表明,相较单一预测模型, Stacking-Prophet 预测模型均方根误差( RMSE )平均降低了 94.14% ,预测精度有较大的提升,对设备运维有一定的参考价值。
Abstract:
To address the problems oflarge errors and low accuracy with single machine learning models for predicting the failure rate of equipment , a prediction method based on improved Stacking fusion model is proposed.The basic Stacking fusion model is constructed by selecting XGBoost , LightGBM , CatBoost and the logistic regression model.On this basis , the Prophet time series prediction model is introduced , and the features extracted by the Prophet model are fused with the basic Stacking model level by level to construct the improved Stacking-Prophet prediction model.Finally , the validity of the prediction model is verified by taking the signal equipment data of a unit as an example.The experimental result shows that compared with the single prediction model , the Stacking-Prophet prediction model reduces the root mean square error ( RMSE ) by 94.14% on average , and the prediction accuracy is greatly improved.It is of a certain reference value for equipment operation and maintenance.

参考文献/References:

[ 1 ] 李刚,卢佩陵 . 基于数据驱动的高速铁路信号智能运维技术研究[ J ] . 铁道运输于经济, 2021 , 43 ( 10 ): 61-67.

[ 2 ] 李莉,熊玮,邹晓松,等 . 基于小波变换和 ARMA 模型的电力设备故障率预测方法[ J ] . 贵州大学学报(自然科学版),2016 , 33 ( 4 ): 49-51 , 63.
[ 3 ] 王瑞奇,逯程 . 基于 EMD 与 RVM-GM 模型的故障率预测[ J ] . 兵器装备工程学报, 2018 , 39 ( 7 ): 127-130.
[ 4 ] BELYI D , POPOVA E , MORTON D P , et al.Bayesian failure-rate modeling and preventive maintenance optimization [ J ] .European journal of operational research , 2017 , 262 ( 3 ): 1085-1093.
[ 5 ] SHIRZAD A , SAFARI M J S.Pipe failure rate prediction in water distribution networks using multivariate adaptive regression splines and random forest techniques [ J ] .Urban water journal , 2019 , 16 ( 9 ):653-661.
[ 6 ] 陆航,杨涛存,刘洋,等 . 基于 LSTM 的动车组故障率预测模型[ J ] . 中国铁路, 2020 ( 7 ): 61-66.
[ 7 ] 郭朝有,许喆,姚乾 . 基于 Stacking 的机舱设备剩余寿命预测方法[ J ] . 中国舰船研究, 2022 , 17 ( 6 ): 118-125.
[ 8 ] 姜万录,赵岩,李振宝,等 . 多模型 Stacking 集成学习的旋转机械故障诊断方法[ J ] . 液压与气动, 2023 , 47 ( 4 ):46-58.
[ 9 ] WOLPERT D H.Stacked generalization [ J ] .Neural networks , 1992 , 5 ( 2 ): 241-259.
[ 10 ] 史佳琪,张建华 . 基于多模型融合 Stacking 集成学习方式的负荷预测方法[ J ] . 中国电机工程学报, 2019 , 39 ( 14 ): 4032-4042.
[ 11 ] CHEN T Q , GUESTRIN C.XGBoost : a scalable tree boosting system [ C ]// The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , 2016 : 785-794.
[ 12 ] KE G L , MENG Q , FINLEY T , et al.Lightgbm : a highly efficient gradient boosting decision tree [ C ]// The 31st International Conference on Neural Information Processing Systems , 2017 : 3149-3157.
[ 13 ] PROKHORENKOVA L , GUSEV G , VOROBEV A , et al.CatBoost : unbiased boosting with categorical features [ C ]// The 32nd International Conference on Neural Information Processing Systems , 2018 : 6639-6649.
[ 14 ] 王献志,曾四鸣,周雪青,等 . 基于 XGBoost 联合模型 的光伏发电功率预测[ J ] . 太阳能学报, 2022 , 43 ( 4 ):236-242.
[ 15 ] 柴琴琴,陈舒迪,王武,等 . 基于改进 GWO-LightGBM 的滚动轴承未知故障诊断[J ] . 航空动力学报,2022 , 37 ( 4 ): 848-855.
[ 16 ] ZHANG Y X , ZHAO Z G , ZHENG J H.CatBoost : A new approach for estimating daily reference crop evapotranspiration in arid and semi-arid regions of Northern China [ J ] .Journal of hydrology , 2020 , 588 : 125087.
[ 17 ] TAYLOR S J , LETHAM B.Forecasting at scale [ J ] . The American statistician , 2017 , 72 ( 1 ): 37-45.
[ 18 ] LI J D , CHENG K W , WANG S H , et al.Feature selection : a data perspective [ J ] .ACM Computing surveys , 2017 , 50 ( 6 ): 1-45.
[ 19 ] WONG T T , YEH P Y.Reliable accuracy estimates from k-fold cross validation [ J ] .IEEE Transactions on knowledge and data engineering , 2019 , 32 ( 8 ):1586-1594.
[ 20 ] 丁思云,李香,沈宗沼,等 . 基于专家经验法的机械密 封基本事件失效概率分析方法[ J ] . 液压气动与密封,2020 , 40 ( 2 ): 31-35.
[ 21 ] 杜聪,邵建华,杨薇,等 . 网格搜索法优化的支持向量机室内可见光定位 [ J ] . 激光杂志, 2021 , 42 ( 3 ):104-109.
[ 22 ] 王家天 . 基于随机搜索策略的特征选择算法研究[ D ] . 大连:大连理工大学,2017.

相似文献/References:

[1]李鸿奎,程昭龙,周 蕾,等.智能变电站设备管控大数据分析系统研究[J].机械与电子,2020,(10):72.
　LI Hongkui,CHENG Zhaolong,ZHOU Lei,et al.Big Data Analysis System of Intelligent Substation Equipment Management and Control[J].Machinery & Electronics,2020,(01):72.
[2]周岳斌,杨 沫,曹煜晖.无线视频监控系统人脸跟踪功能的实现[J].机械与电子,2021,(06):35.
　ZHOU Yuebin,YANG Mo,CAO Yuhui.Realization of Face Tracking Function in Wireless Video Surveillance System[J].Machinery & Electronics,2021,(01):35.
[3]原 军,张 凯,药 炜,等.基于机器学习的分组交换电力光网络流量异常检测[J].机械与电子,2021,(09):47.
　YUAN Jun,ZHANG Kai,YAO Wei,et al.Anomaly Detection of Packet Switching Power Optical Network[J].Machinery & Electronics,2021,(01):47.
[4]刘 哲,闫佳文,陈长金,等.电力线图像检测方法研究[J].机械与电子,2022,(03):54.
　LIU Zhe,YAN Jiawen,CHEN Changjin,et al.Research on Power Line Image Detection Method[J].Machinery & Electronics,2022,(01):54.
[5]范子铭,田富君,胡子翔,等.基于机器学习的回流焊焊点形貌预测[J].机械与电子,2023,41(01):53.
　FAN Ziming,TIAN Fujun,HU Zixiang,et al.Topography Prediction of Reflow Solder Joints Based on Machine Learning[J].Machinery & Electronics,2023,41(01):53.
[6]宾世杨,张 振,唐俊杰,等.基于机器学习的风电机组机械传动系统故障诊断研究[J].机械与电子,2024,42(01):11.
　BIN Shiyang,ZHANG Zhen,TANG Junjie,et al.Research on Fault Diagnosis of Wind Turbine Mechanical Transmission System Based on Machine Learning[J].Machinery & Electronics,2024,42(01):11.
[7]郭文升,李建平.基于机器学习的煤矿输送带 RFID 健康监测方法[J].机械与电子,2025,(04):64.
　GUO Wensheng,LI Jianping.Machine Learning Based RFID Enabled Health Monitoring of Coal Mine Conveyor Belt[J].Machinery & Electronics,2025,(01):64.

备注/Memo

备注/Memo:
收稿日期: 2023-07-10
基金项目:甘肃省中小企业创新基金项目( 22CX3GA029 )
作者简介:袁武民 ( 1991- ),男,甘肃武威人,高级工程师,研究方向为机器学习与计算机应用、计算机视觉。
更新日期/Last Update: 2024-01-16