基于PCA和随机森林的故障趋势预测方法研究
|
摘要
故障预测和健康管理技术(PHM)在现代工程系统中能够在系统具备较高复杂度的情况下,有效保障其可靠性和安全性;在机械故障诊断中对于采集到的原始数据的高维特征量的处理较为复杂,并且在实际应用中趋势预测的精度要求较高,针对该问题提出一种基于主成分分析(PCA)与随机森林算法的轴承故障趋势预测方法;该方法利用PCA对提取的原始轴承数据特征量进行线性降维,并选取其中主成分特征量,输出非线性时间序列数据;原始数据经过PCA处理得到非线性时间序列,将该序列作为随机森林算法的输入进行故障趋势预测,并把预测结果与BP神经网络模型预测的结果进行对比,结果表明随机森林在故障趋势预测上在精度相较于BP神经网络有显著提高,是一种有效的故障趋势预测方法。
Fault prediction and health management system(PHM)can effectively guarantee the reliability and safety of modern engineering system under the condition of high complexity.In mechanical fault diagnosis with high dimensional characteristic quantity of raw data collected for the more complex,and in the practical application trend prediction precision,this paper presents a method based on principal component analysis(PCA)method to predict bearing fault trend and random forests algorithm.The method uses PCA to reduce the characteristic data of the original bearing data,and selects the principal component characteristic quantity to output the nonlinear time series data.The original data are processed by PCA nonlinear time series,the sequence as a random forest algorithm input fault trend prediction,and the prediction results were compared with the BP neural network model prediction results,results show that the random forest in the fault trend prediction in precision compared with the BP neural network is improved,is a method of forecasting an effective fault trend.
Fault prediction and health management system(PHM)can effectively guarantee the reliability and safety of modern engineering system under the condition of high complexity.In mechanical fault diagnosis with high dimensional characteristic quantity of raw data collected for the more complex,and in the practical application trend prediction precision,this paper presents a method based on principal component analysis(PCA)method to predict bearing fault trend and random forests algorithm.The method uses PCA to reduce the characteristic data of the original bearing data,and selects the principal component characteristic quantity to output the nonlinear time series data.The original data are processed by PCA nonlinear time series,the sequence as a random forest algorithm input fault trend prediction,and the prediction results were compared with the BP neural network model prediction results,results show that the random forest in the fault trend prediction in precision compared with the BP neural network is improved,is a method of forecasting an effective fault trend.
引文
[1]王晓勇.故障预测和健康管理(PHM)及其应用[J].中国电子商务,2013(3):120-120.
[2]刘恩朋,杨占才,靳小波.国外故障预测与健康管理系统开发平台综述[J].测控技术,2014,33(9):1-4.
[3]曾声奎,Pecht M G,吴际.故障预测与健康管理(PHM)技术的现状与发展[J].航空学报,2005,26(5):626-632.
[4]续媛君,潘宏侠.设备故障趋势预测的分析与应用[J].振动、测试与诊断,2006,26(4):305-308.
[5]李斌,章卫国,宁东方,等.基于神经网络技术的飞机舵面故障趋势预测研究[J].系统仿真学报,2008(21):5840-5842.
[6]Feng Z,Chu F,Song X.Application of general regression neural network to vibration trend prediction of Rotating machinery[M].Advances in Neural Networks-ISNN 2004.Springer Berlin Heidelberg,2004:367-371.
[7]Hajnayeb A,Ghasemloonia A,Khadem S E,et al.Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis[J].Expert Systems with Applications,2011,38(8):10205-10209.
[8]谢松汕,许宝杰,吴国新,等.基于HMM/SVM的风电设备故障趋势预测方法研究[J].计算机测量与控制,2014,22(1):39-41.
[9]李波,赵洁,郭晋.设备故障评估新指标及基于ARMA的预测系统[J].系统工程与电子技术,2011,33(1):98-101.
[10]Rauber T W,Boldt F D A,Varej2o F M.Heterogeneous Feature Models and Feature Selection Applied to Bearing Fault Diagnosis[J].IEEE Transactions on Industrial Electronics,2015,62(1):637-646.
[11]李兵,张培林,任国全,等.基于互信息的滚动轴承故障特征选择方法[J].测试技术学报,2009,23(2):183-188.
[12]张恒,赵荣珍.故障特征选择与特征信息融合的加权KPCA方法研究[J].振动与冲击,2014,33(9):89-93.
[13]Surhone L M,Tennoe M T,Henssonow S F,et al.Random Forest[J].Machine Learning,2010,45(1):5-32.
[14]Tipping M E,Bishop C M.Probabilistic Principal Component Analysis[J].Journal of the Royal Statistical Society,2010,61(3):611-622.
[15]Quinlan J R.Induction on decision tree[J].Machine Learning,1986,1(1):81-106.
[2]刘恩朋,杨占才,靳小波.国外故障预测与健康管理系统开发平台综述[J].测控技术,2014,33(9):1-4.
[3]曾声奎,Pecht M G,吴际.故障预测与健康管理(PHM)技术的现状与发展[J].航空学报,2005,26(5):626-632.
[4]续媛君,潘宏侠.设备故障趋势预测的分析与应用[J].振动、测试与诊断,2006,26(4):305-308.
[5]李斌,章卫国,宁东方,等.基于神经网络技术的飞机舵面故障趋势预测研究[J].系统仿真学报,2008(21):5840-5842.
[6]Feng Z,Chu F,Song X.Application of general regression neural network to vibration trend prediction of Rotating machinery[M].Advances in Neural Networks-ISNN 2004.Springer Berlin Heidelberg,2004:367-371.
[7]Hajnayeb A,Ghasemloonia A,Khadem S E,et al.Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis[J].Expert Systems with Applications,2011,38(8):10205-10209.
[8]谢松汕,许宝杰,吴国新,等.基于HMM/SVM的风电设备故障趋势预测方法研究[J].计算机测量与控制,2014,22(1):39-41.
[9]李波,赵洁,郭晋.设备故障评估新指标及基于ARMA的预测系统[J].系统工程与电子技术,2011,33(1):98-101.
[10]Rauber T W,Boldt F D A,Varej2o F M.Heterogeneous Feature Models and Feature Selection Applied to Bearing Fault Diagnosis[J].IEEE Transactions on Industrial Electronics,2015,62(1):637-646.
[11]李兵,张培林,任国全,等.基于互信息的滚动轴承故障特征选择方法[J].测试技术学报,2009,23(2):183-188.
[12]张恒,赵荣珍.故障特征选择与特征信息融合的加权KPCA方法研究[J].振动与冲击,2014,33(9):89-93.
[13]Surhone L M,Tennoe M T,Henssonow S F,et al.Random Forest[J].Machine Learning,2010,45(1):5-32.
[14]Tipping M E,Bishop C M.Probabilistic Principal Component Analysis[J].Journal of the Royal Statistical Society,2010,61(3):611-622.
[15]Quinlan J R.Induction on decision tree[J].Machine Learning,1986,1(1):81-106.