|本期目录/Table of Contents|

[1]吴智泉,路忠峰,陈克锐,等.基于BAACMD和BESDFIF的风电机组主轴承故障诊断[J].工业仪表与自动化装置,2024,(02):124-129+142.[doi:DOI:10.19950/j.cnki.CN61-1121/TH.2024.02.022]
　WU Zhiquan,LU Zhongfeng,CHEN Kerui,et al.Wind turbines based on BAACMD and BESDFIF spindle bearing damage detection[J].Industrial Instrumentation & Automation,2024,(02):124-129+142.[doi:DOI:10.19950/j.cnki.CN61-1121/TH.2024.02.022]
点击复制

基于BAACMD和BESDFIF的风电机组主轴承故障诊断(PDF)

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2024年02期
页码:
124-129+142
栏目:
出版日期:
2024-04-15

文章信息/Info

Title:
Wind turbines based on BAACMD and BESDFIF spindle bearing damage detection
文章编号:
1000-0682（2024）02-0124-06
作者:
吴智泉1; 路忠峰2; 陈克锐1; 朱 琳3; 杨智勇4
(1. 国家电投集团云南国际电力投资有限公司, 云南 昆明 650228;2. 哈尔滨能创数字科技有限公司, 黑龙江 哈尔滨 150000;3. 云南电投绿能科技有限公司， 云南 昆明 650228;4. 国家电投集团云南国际电力投资有限公司新能源开发分公司， 云南 昆明 650228)
Author(s):
WU Zhiquan1; LU Zhongfeng2; CHEN Kerui1; ZHU Lin3; YANG Zhiyong4
(1. SPIC Yunnan International Power Investment Co., Ltd, Yunnan Kunming 650228, China;2.Harbin Energy Innovation Digital Technology Co, Ltd., Heilongjiang Haerbin 15000, China;3.Yunnan Power Investment Green Energy Technology Co., Ltd， Yunnan Kunming 650228, China;4.SPIC Yunnan International New Energy Development Branch， Yunnan Kunming 650228, China)
关键词:
风电机组主轴承; 秃鹰优化算法; 直接快速迭代滤波; 故障诊断
Keywords:
wind turbine main bearing;  bald eagle searh;  direct fast iterative filtering;  fault diagnosis
分类号:
TH17
DOI:
DOI:10.19950/j.cnki.CN61-1121/TH.2024.02.022
文献标志码:
A
摘要:
针对风电机组主轴承故障难以诊断的问题，提出一种基于BAACMD和BESDFIF的故障诊断方法。首先采用加权频谱趋势法准确划分信号频段，诊断各频段的有效成分，随后利用模型拟合方法确定ACMD方法中惩罚因子和初始中心频率f，并通过BAACMD方法实现对故障信号进行处理实现故障特征信息的提取；其次利用秃鹰优化算法对DFIF方法中影响参数及分量选取过程进行寻优；最后使用最优滤波区间参数的BESDFIF方法对所得分量进行分解降噪处理，从中诊断出微弱的风电机组主轴承故障特征频率成分。现场数据分析结果表明，所研究方法可以有效诊断风电机组主轴承的微弱故障特征，实现风电机组主轴承的故障诊断。
Abstract:
Aiming to solve the problem that it is difficult to diagnose the main bearing fault of wind turbine, a fault diagnosis method based on BAACMD and BESDFIF is proposed. Firstly, the weighted spectrum trend method is used to accurately divide the signal frequency band and diagnose the effective components of each frequency band, the penalty factor and the initial center frequency f in the ACMD method are determined by the model fitting method, and the fault feature information is extracted by processing the fault signal by the BAACMD method. Then the vulture optimization algorithm is used to optimize the filter interval parameters in the DFIF method. Finally, the BESDFIF method with optimal filtering interval parameters is used to decompose and reduce the noise of the obtained components, from which the weak fault characteristic frequency components of wind turbine main bearings are diagnosed. The field data analysis results show that the research method can effectively diagnose the weak fault characteristics of the wind turbine main bearing and realize the fault diagnosis of the wind turbine main bearing.

参考文献/References:

[1]凌永志,鲁纳纳,孙启涛等.风电机组主轴轴承故障的分析与预测[J].风能,2020(04):74-78.

[2]党存禄,杜小波.粒子群优化变论域模糊PID控制在风电机组变桨距中的应用[J].工业仪表与自动化装置,2017(05):97-100.
[3]石志标,姜红阳. 基于IEM-FA优化LSSVM的风机主轴轴承故障诊断研究[J]. 组合机床与自动化加工技术,2019(1):90-93.
[4]张博,程珩.倒频谱在直驱风机主轴轴承故障诊断中的应用[J].机械设计与制造,2014(07):265-267.
[5]王振亚,伍星,刘韬,等.奇异谱分解联合互信息的主轴轴承故障特征提取研究[J].振动与冲击,2023,42(15):23-30+47.
[6]王春梅.基于深度置信网络的风电机组主轴承故障诊断方法研究[J].自动化仪表,2018,39(05):33-37.
[7]王桂兰,赵洪山,米增强.XGBoost算法在风机主轴承故障预测中的应用[J].电力自动化设备,2019,39(01):73-77+83.?/div>
[8]CHEN S， GUO L， FAN J， et al. Bandwidthaware adaptive chirp mode decomposition for railway bearing fault diagnosis[J]. Structural Health Monitoring， 2023: 14759217231174699.
[9]ALMONACID B， SOTO R. Andean condor algorithm for cell formation problems[J]. Natural Computing， 2019， 18: 351-381.
[10]CICONE A， LIU J， ZHOU H. Adaptive local iterative filtering for signal decomposition and instantaneous frequency analysis[J]. Applied and Computational Harmonic Analysis， 2016， 41(2): 384411.
[11]LIU Y， YUAN D， GONG Z， et al. Adaptive spectral trend based optimized EWT for monitoring the parameters of multiple power quality disturbances[J]. International Journal of Electrical Power & Energy Systems， 2023， 146: 108797.
[12]李华，伍星，刘韬,等.基于信息熵优化变分模态分解的滚动轴承故障特征提取[J].振动与冲击，2018，37(23).
[13]JACEK D. Diagnosing of rollingelement bearings using amplitude levelbased decomposition of machine vibration signal[J]. Measurement，2018，126：413153.
[14]LI C， LIU Y， LIAO Y， et al. A VME method based on the convergent tendency of VMD and its application in multifault diagnosis of rolling bearings[J]. Measurement， 2022， 198: 111360.
[15]王建国，刘冀韬，张文兴.自适应MCKD和VMD在行星齿轮箱早期故障诊断中的应用[J].机械设计与制造，2022，(6):130-133.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：2023-11-17第一作者：吴智泉（1974—），男，汉族，湖北武汉人，博士，正高级工程师，主要从事可再生能源发电技术研究。E-mail：aaa111201116@163.com
更新日期/Last Update: 1900-01-01