基于支持向量机决策树的航空发动机轴心轨迹识别方法

摘要/Abstract

摘要： 针对航空发动机转子轴心轨迹难以准确自动识别的问题，提出了基于二维形状不变矩和支持向量机（SVM）决策树的识别方法。对信号滤波降噪和倍频提纯，形成比较清晰的轴心轨迹；利用二维形状不变矩提取轴心轨迹的图形特征，得到不变矩特征向量，进而构造特征故障的训练和测试样本；采用SVM进行训练和学习，构造SVM决策树，识别故障类别，分类正确率达93.3%以上。应用实测弹支振动应力信号对该方法的准确性进行了验证，结果表明，该方法有效地解决了航空发动机转子轴心轨迹自动识别准确率低和小样本问题。

关键词: 航空发动机, 轴心轨迹, 二维形状不变矩, 支持向量机决策树

Abstract: It was difficult to automatically and exactly identify shift orbits of aero-engine rotors, a recognition method was proposed based on two-dimensional feature invariant moments and SVM decision tree. First, the relatively clear shift orbits could be acquired after the noise reduction and frequency purification of the signals. The invariant moments were used to extract the graphic features of the shift orbits, then the invariant moment vectors were obtained, constructing the training and test samples of the characteristic faults. Finally, in order to construct SVM decision tree and identify faults, support vector machine was trained and studied. The accuracy rate of classification reaches 93.3%. The method was verified by measured signals of elastic support vibration stress. The results show that the method effectively resolve low recognition accuracy and small sample problems for shaft orbits of aero-engine rotors.

Key words: aero-engine, shift orbit, two-dimensional feature invariant moment, support vector machine（SVM） decision tree

中图分类号:

何刘海;吴桂娇;王平. 基于支持向量机决策树的航空发动机轴心轨迹识别方法[J]. 中国机械工程.

HE Liuhai;WU Guijiao;WANG Ping. Shift Orbit Recognition Method of Aero-engines Based on SVM Decision Tree[J]. China Mechanical Engineering.

参考文献

[1]李德江.旋转机械轴心轨迹的理论计算、提纯和自动识别研究[D].济南：山东大学，2007.
LI Dejiang. Calculation, Purification and Automatic Recognition of the Rotating Machinery's Orbit of Shaft Center-line[D]. Jinan:Shandong University, 2007.
[2]赵利华.旋转机械故障机理与轴心轨迹识别方法研究[D].大连：大连理工大学，2010.
ZHAO Lihua. Investigation on Failure Mechanism and Shift Orbits Recognition Methods for Rotating Machine[D].Dalian:Dalian University of Technology, 2010.
[3]袁倩，孙冬梅，范文.基于D-S证据理论的轴心轨迹自动识别方法[J].机床与液压，2017，45(7)：167-171.
YUAN Qian, SUN Dongmei, FAN Wen.Automatic Identification Method of Axis Orbits Based on D-S Evidential Theory[J]. Machine Tool ＆ Hydraulics, 2017，45(7)：167-171.
[4]许云飞，钟秉林，黄仁.轴心轨迹自动识别及其在旋机诊断中的应用[J].振动、测试与诊断，2009，29(2)：141-145.
XU Yunfei,ZHONG Binglin, HUANG Ren. Automatic Identification of Shaft Orbits and the Application in Rotary Machine Diagnosis[J]. Journal of Vibration Measurement & Diagnosis, 2009，29(2)：141-145.
[5]付波，周建中，彭兵，等.基于仿射不变矩的轴心轨迹自动识别方法[J].华中科技大学学报（自然科学版），2007，35(3)：119-122.
FU Bo, ZHOU Jianzhong, PENG Bing, et al. Auto-recognition of Shaft Orbits Using Affine Moment Invariants[J]. J. Huazhong Univ. of Sci. & Tech. (Natural Science Edition), 2007，35(3)：119-122.
[6]刘刚，李明，乔宝明，等.故障转子系统轴心轨迹的自动识别研究[J].中国测试，2014，40(1)：110-114.
LIU Gang, LI Ming, QIAO Baoming, et al. Automatic Identification of Orbits of Rotor System with Faults[J]. China Measurement & Test, 2014, 40(1):110-114.
[7]陈仁祥，汤宝平，吕中亮.EEMD滤波的转子轴心轨迹提纯方法[J].重庆大学学报，2012，35(11)：15-20.
CHEN Renxiang, TANG Baoping, LYU Zhongliang. A Method of Rotor Orbit Purification Based on Ensemble Empirical Mode Decomposition Filter[J]. Journal of Chongqing University, 2012，35(11)：15-20.
[8]陈喜阳，闫海桥，孙建平.基于PSO-BP与组合矩的水电机组轴心轨迹识别[J].振动、测试与诊断，2016，36(1)：108-114.
CHEN Xiyang, YAN Haiqiao, SUN Jianping. Shaft Orbits Identification of Hydroelectric Generators Based on PSO - BP and Combined Moment[J]. Journal of Vibration Measurement & Diagnosis, 2016，36(1)：108-114.
[9]原玥，王宏，原培新，等.一种改进的Hu不变矩算法在存储介质图像识别中的应用[J].仪器仪表学报，2016，37(5)：1042-1048.
YUAN Yue, WANG Hong, YUAN Peixin, et al. An Improved Hu Invariant Moment Algorithm for Storage Medium Image Recognition[J].Chinese Journal of Scientific Instrument,2016,37(5):1042-1048.
[10]戚大伟，牟洪波.基于Hu不变矩和BP神经网络的木材缺陷检测[J].东南大学学报(自然科学版)，2013，43(增刊1)：63-66.
QI Dawei, MU Hongbo. Detection of Wood Defects Types Based on Hu Invariant Moments and BP Neural Network[J].Journal of Southeast University(Natural Science Edition), 2013, 43(S1) :63-66.
[11]何刘海.涡轮增压器性能检测与故障预测系统的研制[D].大连：大连理工大学，2013.
HE Liuhai. Development of Performance Testing and Failure Prediction System of Turbocharger[D]. Dalian: Dalian University of Technology, 2013.
[12]王正海，方臣，何凤萍，等.基于决策树多分类支持向量机岩性波普分类[J].中山大学学报(自然科学版)，2014，53(6)：93-97.
WANG Zhenghai, FANG Chen, HE Fengping,et al. Hyperspectral Rock Spectral Classification Based on the Decision Tree-support Vector Machine(DT-SVMs)[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2014, 53(6):93-97.
[13]李宏坤，周帅，孙志辉.Hilbert谱特征提取与支持向量机的状态识别方法研究[J].振动与冲击，2009，28(6)：131-134.
LI Hongkun, ZHOU Shuai, SUN Zhihui. Investigation on Machine Condition Classification by Using Hilbert Spectrum Feature Extraction and Support Vector Machine[J]. Journal of vibration and shock, 2009, 28(6): 131-134.
[14]孙红春，张洪亭，单颖春，等.航空发动机转子的振动分析及故障诊断[J].振动与冲击，2005，24(2)：106-110.
SUN Hongchun, ZHANG Hongting, SHAN Yinchun, et al. Vibration Analysis and Fault Diagnosis of Aero-engine Rotor [J].Journal of Vibration and Shock, 2005, 24(2) :106-110.
[15]杨伟新，王平，雷沫枝，等. EMD-PCA与相关分析在航空发动机弹支动应力信号中的应用[J].噪声与振动控制，2015，35(6)：87-90.
YANG Weixin, WANG Ping, LEI Mozhi, et al. Application of EMD-PCA and Correlation Analysis in Dynamic Stress Signal Analysis of The Aero-engine Elastic Supporters[J]. Noise and Vibration Control, 2015, 35(6): 87-90.