以风力发电机高速齿轮磨损故障为研究对象,提出基于独立成分分析的高速齿轮磨损故障趋势预测方法。构建混合信息模型,应用独立成分分析方法将各独立成分信息的近似成分信息从混合信号中分离出来,并以纯净的近似故障源信号特征为依据找到有用成分;根据近似故障源信号与故障源信号互为相似形,利用正态总体均值区间估计方法估计相似形放大倍数值域;确定连续且单向变化的放大倍数值域与旋转部件故障程度的对应关系,建立故障程度判别标准,结合高速齿轮全生命周期故障源信号能量变化趋势图,对故障程度及趋势做出判断及预测。应用以上方法对工业现场采集到的高速齿轮磨损故障数据进行处理,结果表明,该方法对于处理以周期性突变为特征的磨损故障信号具有较理想的趋势预测效果。
Abstract
Constructs the mixing information model, separates the independent components from the mixing signals by using the independent component analysis method, and finds useful component with the features of the pure approximate fault source signal as the basis. Based on the similarity between the approximate fault source signal and fault source signal, estimates the value domain of the magnification time of the similar shape by using the normal general mean interval estimation method, identifies the mapping between continuous and one-way varying magnification time domain and rotary component fault degree, establishes the fault degree judgment standard, and determines and predicts the fault degree and trend based on the energy change trend diagram of the whole-lifecycle fault source signal of the high-speed gear. The above method is used to process the wear failure data of the high-speed gear which is collected in industrial field. The results show that the above method has an ideal trend forecast effect in processing the wear fault signal characterized by periodic mutation.
关键词
风力发电机 /
独立成分分析 /
旋转机械 /
信号处理 /
特征提取
Key words
wind turbine generators /
independent component analysis /
rotating machinery /
signal processing /
feature extraction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 徐小力, 王红军. 大型旋转机械运行状态趋势预测[M].北京: 科学出版社, 2011: 1-381.
XU X L, WANG H J.Large rotating machinery running state trend forecasting[M]. Beijing: Science Press, 2011: 1-381.
[2] 冯浩楠, 付胜, 胥永刚. 基于BN-1DCNN的旋转机械故障诊断研究[J]. 振动与冲击, 2021, 40(19): 302-308.
FENG H N, FU S, XU Y G.Fault diagnosis of rotating machinery based on BN-1DCNN model[J]. Journal of vibration and shock, 2021, 40(19): 302-308.
[3] 陈菲, 杨峥, 张志成, 等. 面向无标签数据的旋转机械故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(11): 2514-2522.
CHEN F, YANG Z, ZHANG Z C, et al.Fault diagnosis method of rotating machinery for unlabeled data[J]. Journal of Jilin University(engineering and technology edition), 2022, 52(11): 2514-2522.
[4] 姜万录, 李满, 张培尧, 等. 基于全矢增强深度森林的旋转设备智能故障诊断方法[J]. 中国机械工程, 2022, 33(11): 1324-1335.
JIANG W L, LI M, ZHANG P Y, et al.Intelligent fault diagnosis method for rotating equipment based on full vector enhanced deep forest[J]. China mechanical engineering, 2022, 33(11): 1324-1335.
[5] 刘颉, 杨超颖, 周凯波. 基于图数据深度挖掘的旋转机械故障诊断[J]. 华中科技大学学报(自然科学版), 2021, 49(9): 1-5.
LIU J, YANG C Y, ZHOU K B.Fault diagnosis of rotating machinery based on graph data deep mining[J]. Journal of Huazhong University of Science and Technology(natural science edition), 2021, 49(9): 1-5.
[6] 丁小飞, 曹航, 冯国全, 等. 航空发动机转子盘腔积油振动故障分析[J]. 航空动力学报, 2021, 36(2): 341-351.
DING X F, CAO H, FENG G Q, et al.Vibration fault analysis of aeroengine rotor disk cavity filled with oil[J]. Journal of aerospace power, 2021, 36(2): 341-351.
[7] 李志农, 朱亚静, 王冬. 机械振动数估计的四线性平行因子方法研究[J]. 振动工程学报, 2021, 34(3): 619-625.
LI Z N, ZHU Y J, WANG D.Quadrilinear parallel factor method for estimating the number of mechanical vibration sources[J]. Journal of vibration engineering, 2021, 34(3): 619-625.
[8] 马宝泽, 张天骐, 安泽亮, 等. 基于张量分解的卷积盲源分离方法[J]. 通信学报, 2021, 42(8): 52-60.
MA B Z, ZHANG T Q, AN Z L, et al.Convolutive blind source separation method based on tensor decomposition[J]. Journal of communications, 2021, 42(8): 52-60.
[9] 石少帅, 曹天宇, 许新骥, 等. 隧道凿岩台车破岩震源三臂混合先导信号盲源分离方法与工程应用[J]. 应用基础与工程科学学报, 2021, 29(5): 1124-1139.
SHI S S, CAO T Y, XU X J, et al.Three-arm mixed pilot signal blind source separation method and engineering application of rock breaking seismic source of tunnel rock drilling rig[J]. Journal of basic science and engineering,2021, 29(5): 1124-1139.
[10] GERAMIFARD O, XU J X, ZHOU J H, et al.Continuous health condition monitoring: a single hidden semi-markov model approach[C]//2011 IEEE Conference on Prognostics and Health Management, Denver, CO, USA, 2011: 1-10.
[11] LYU K H, QIU J, LIU G J,et al.Real-time health state assessment method for MOSFET based on time stress analysis[C]//2011 Prognostics and System Health Management Conference, Shenzhen, China, 2011.
[12] 张小丽, 陈雪峰, 李兵, 等. 机械重大装备寿命预测综述[J]. 机械工程学报, 2011, 47(11): 100-116.
ZHANG X L, CHEN X F, LI B, et al.Review of life prediction for mechanical major equipments[J]. Journal of mechanical engineering, 2011, 47(11): 100-116.
[13] 李钢, 周东华. 基于SPM的多变量连续过程在线故障预测方法[J]. 化工学报, 2008(7): 1829-1833.
LI G, ZHOU D H.SPM-based online fault prediction approach for multivariate continuous processes[J]. CIESC Journal, 2008(7): 1829-1833.
[14] XU X L, CHEN T, MINAMI M.Intelligent fault prediction system based on internet of things[J]. Computers & mathematics with applications, 2012, 64(5): 833-839.
基金
北京市教委科技一般项目（KM202011232001）; 国家自然科学基金（51275052）
PDF(1906 KB)
