[1]骆东松,马立东.基于深度学习的风电机组轴承诊断系统[J].机械与电子,2024,42(07):69-75.
　LUO Dongsong,MA Lidong.Deep Learning based Bearing Diagnosis System for Wind Turbines[J].Machinery & Electronics,2024,42(07):69-75.
点击复制

基于深度学习的风电机组轴承诊断系统()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
42
期数:
2024年07期
页码:
69-75
栏目:
机电一体化
出版日期:
2024-07-26

文章信息/Info

Title:
Deep Learning based Bearing Diagnosis System for Wind Turbines
文章编号:
1001-2257 ( 2024 ) 07-0069-07
作者:
骆东松; 马立东
兰州理工大学电气工程与信息工程学院,甘肃 兰州 730050
Author(s):
LUO Dongsong ;  MA Lidong
( College of Electrical and Information Engineering , Lanzhou University of Technology , Lanzhou 730050 , China )
关键词:
风电机组; 轴承; 故障诊断; 收缩网络; 残差网络
Keywords:
wind turbine ;  bearing ;  fault diagnosis ;  contraction network ;  residual network
分类号:
TM315 ; TP181
文献标志码:
A
摘要:
风电机组的轴承作为其关键部件,正常工作时常出现因磨损和裂纹而失效的状况,导致所采集到的振动数据含有其他干扰信号,而传统的诊断方法故障检测误差较大,导致诊断结果准确性较差。针对这一问题,提出了一个基于 DRSN-CW 模型的风电机组轴承诊断系统。该系统结合了软、硬件设计,算法理论和仿真结果分析,旨在提高轴承故障检测的准确性和效率。通过合适的传感器和数据采集设备进行硬件设计,构建了包括数据预处理、特征提取、模型训练和推理等模块的软件设计,实现了自动化的轴承故障诊断过程。选择 DRSN-CW 作为基础模型,结合软阈值化、残差网络和注意力机制,有效学习轴承信号中的重要特征。使用凯斯西储大学轴承振动数据进行仿真实验,并对多种不同的故障诊断算法进行了分析。实验结果表明,DRSN-CW 模型的准确率优于其他方法。
Abstract:
The bearings of wind turbines , as their key components , often fail due to wear and cracks under normal operation , resulting in the collected vibration data containing other interfering signals , and the traditional diagnostic methods have large error in fault detection , leading to poor accuracy of the diagnostic results.To address this problem , a wind turbine bearing diagnosis system based on the DRSN-CW model is proposed.The system combines software and hardware design , algorithm theory and simulation results analysis , aiming to improve the accuracy and efficiency of bearing fault detection.The hardware design is carried out by suitable sensors and data acquisition devices , and the software design including modules of data preprocessing , feature extraction , model training and inference is constructed to realize the automated bearing fault diagnosis process.DRSN CW is selected as the base model , which combines soft valorization , residual network and attention mechanism to effectively learn important features in bearing signals.Simulation experiments are conducted using Case Western Reserve University bearing vibration data , and several different fault diagnosis algorithms are analyzed.Experimental results show that the accuracy of the DRSN-CW model outperforms other methods.

参考文献/References:

[ 1 ] 南士敬,李方东,汪金伟,等 . 中国可再生能源发展水平的区域差异、分布动态与收敛性[ J ] . 资源科学, 2023 ,45 ( 7 ): 1335-1350.

[ 2 ] 朱蓉,王阳,向洋,等 . 中国风能资源气候特征和开发潜力研究[ J ] . 太阳能学报, 2021 , 42 ( 6 ): 409-418.
[ 3 ] 杨顺顺 . 中国碳排放轨迹特征、驱动因素及减排策略[ J ] . 环境科学与技术, 2020 , 43 ( 1 ): 98-104.
[ 4 ] 崔荣国,郭娟,程立海,等 . 全球清洁能源发展现状与趋势分析[ J ] . 地球学报, 2021 , 42 ( 2 ): 179-186.
[ 5 ] 赵敬娇,赵志宏,杨绍普 . 基于残差连接和 1D-CNN的滚动轴承故障诊断研究[ J ] . 振动与冲击,2021 , 40( 10 ): 1-6.
[ 6 ] 严展鸿,廖平 . 基于 LabVIEW 的大型转子监测及故障诊断系统[ J ] . 仪表技术与传感器, 2017 ( 11 ): 51-55.
[ 7 ] 史庆军,郭晓振,刘德胜 . 基于特征量融合和支持向量机的轴承故障诊断[ J ] . 电子测量与仪器学报, 2019 ,33 ( 10 ): 104-111.
[ 8 ] 余长厅,黎大健,汲胜昌,等 . 基于振动噪声及 BP 神经网络的变压器故障诊断方法研究[ J ] . 高压电器,2020 , 56 ( 6 ): 256-261.
[ 9 ] 康守强,刘哲,王玉静,等 . 基于改进 DQN 网络的滚动轴承故障诊断方法[ J ] . 仪器仪表学报, 2021 , 42 ( 3 ):201-212.
[ 10 ] 刘立,朱健成,韩光洁,等 . 基于 1D-CNN 联合特征提取的轴承健康监测与故障诊断[ J ] . 软件学报,2021 , 32 ( 8 ): 2379-2390.
[ 11 ] 魏秀业,程海吉,贺妍,等 . 基于特征融合与 ResNet 的行星齿轮箱故障诊断[ J ] . 电子测量与仪器学报,2022 , 36 ( 5 ): 213-222.
[ 12 ] 敖邦乾,曾丽娟,陈孝玉,等 . 融合注意力机制的电机故障检测系统设计[ J ] . 西南大学学报(自然科学版),2022 , 44 ( 12 ): 163-175.
[ 13 ] 夏存江,詹于游 . 基于改进的 SENet 航空发动机振动预测[ J ] . 航空动力学报, 2022 , 37 ( 12 ): 2807-2817.

相似文献/References:

[1]韩海燕,李娜娜,尚雪梅.颗粒间距及相对运动对轴承油膜压力的影响[J].机械与电子,2019,(03):27.
　HAN Haiyan,LI Nana,SHANG Xuemei.Effects of Particles Distance and Relative Motion on Oil Film Pressure of Bearing[J].Machinery & Electronics,2019,(07):27.
[2]吉 莉,卯 杰.电机转子轴承拆卸工装的研制与应用[J].机械与电子,2019,(05):46.
　.Development and Application of Disassembly Tooling for Electronic Rotationg Shaft Bearing[J].Machinery & Electronics,2019,(07):46.
[3]许 明,卢晓光,刘伟鹏,等.风电机组传动链建模及传动链频率分析[J].机械与电子,2015,(02):34.
　XU Ming,LU Xiaoguang,LIU Weipeng,et al.Modeling and Frequency Analysis for Transmission Chain of Wind Turbines[J].Machinery & Electronics,2015,(07):34.
[4]吴 鹏,许 明,卢晓光.大型风电机组变桨系统超级电容的选择及其自检策略的研究[J].机械与电子,2015,(04):36.
　WU Peng,XU Ming,LU Xiaoguang.Selection and Self-checking Control of Super Capacitor for Large-scale Wind Turbine Pitch System[J].Machinery & Electronics,2015,(07):36.
[5]祁晓笑１,耿丽红２,于永军１,等.风电机组参与调频调压对电网稳定性影响研究[J].机械与电子,2019,(11):50.
　,,et al.Study on the Grid Stability with Frequency and Voltage Regulation of Wind Turbine[J].Machinery & Electronics,2019,(07):50.
[6]王朝东,谢金娟,李松博.分散式风电机组复杂风况下阵风控制及载荷优化设计[J].机械与电子,2020,(01):62.
　,Gust Controller and Load Optimization of Distributed Wind Turbine in Complex Wind Conditions[J].Machinery & Electronics,2020,(07):62.
[7]孟庆宇.基于 ＥＥＭＤ- ＳＶＭ 的自动扶梯主驱动轴轴承故障诊断方法研究[J].机械与电子,2020,(05):51.
　Research on Fault Diagnosis Method for Main Drive Shaft Bearing of Escalator Based on EEMD-SVM [J].Machinery & Electronics,2020,(07):51.
[8]罗玉平,舒 禹,黄宜健,等.风力发电机组叶片气热法防除冰系统设计[J].机械与电子,2021,(01):34.
　LUO Yuping,SHU Yu,HUANG Yi jian,et al.Design of Antiicing / Deicing System for Wind Turbine Bladesby Air Heating Method[J].Machinery & Electronics,2021,(07):34.
[9]卢晓光１,李凤格２.基于数字孪生的风机实时载荷预估研究[J].机械与电子,2021,(06):24.
　LU Xiaoguang,LI Fengge.Real Time Load Prediction of Wind Turbine Based on Digital Twin[J].Machinery & Electronics,2021,(07):24.
[10]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(07):11.

备注/Memo

备注/Memo:
收稿日期: 2023-10-20
作者简介:骆东松 ( 1970- ),男,甘肃天水人,教授,研究方向为智能化仪表、嵌入式系统、工业以太网、现场总线、工业数据库、大型综合计算机控制系统等;马立东 ( 1992- ),男,甘肃武威人,硕士研究生,研究方向为计算机控制系统。
更新日期/Last Update: 2024-08-30