基于SVR的桥梁健康监测系统缺失数据在线填补研究
|
摘要
针对桥梁健康监测系统所采集的实时数据具有不完备性,严重影响桥梁的安全评估,提出基于支持向量回归SVR(Support Vector Regression)算法的桥梁健康监测系统缺失数据实时在线预测方法。首先,分析实测数据具有时序、非线性和周期性等特点,利用变量的自相关和变量间的相关性重新构造支持向量回归模型的输入样本维数;在此基础上,根据样本在线更新的特点,采用序列最小优化算法对支持向量回归模型中的拉格朗日乘子进行实时更新,解决高精度在线填补的需求;最后,从实际问题出发,实现了支持向量回归模型的在线和离线自适应预测模式。通过对桥梁实测数据进行在线模式和离线模式预测对比,结果表明在线模式以样本更新的方式能够获得对将来值更高的预测精度。
The real-time datasets collected by the bridge health monitoring system are incomplete,and they seriously affect the safety assessment of the bridge. In this paper,the real-time online prediction model of missing data in bridge health monitoring system based on support vector regression( SVR) was proposed. The measured data has the characteristics of temporality,nonlinearity and periodicity,the input sample dimension in support vector regression model was firstly reconstructed according to the autocorrelation of variables and the correlation among variables. In order to improve the accuracy and efficiency of the prediction model for the missing datasets of bridge,the Lagrange multipliers in the support vector regression model are updated in real-time by using the sequential minimum optimization( SMO) algorithm according to the updated samples. Finally,the online adaptive prediction model of support vector regression model is put forward and realized in the practical problems. The measured missing data of bridge are predicted by online model and off-line model,the experimental results show that the online model can achieve higher prediction accuracy in the future by updating the samples.
The real-time datasets collected by the bridge health monitoring system are incomplete,and they seriously affect the safety assessment of the bridge. In this paper,the real-time online prediction model of missing data in bridge health monitoring system based on support vector regression( SVR) was proposed. The measured data has the characteristics of temporality,nonlinearity and periodicity,the input sample dimension in support vector regression model was firstly reconstructed according to the autocorrelation of variables and the correlation among variables. In order to improve the accuracy and efficiency of the prediction model for the missing datasets of bridge,the Lagrange multipliers in the support vector regression model are updated in real-time by using the sequential minimum optimization( SMO) algorithm according to the updated samples. Finally,the online adaptive prediction model of support vector regression model is put forward and realized in the practical problems. The measured missing data of bridge are predicted by online model and off-line model,the experimental results show that the online model can achieve higher prediction accuracy in the future by updating the samples.
引文
[1]Farrar C R,Worden K.An Introduction to Structural Health Monitoring[J].Philosophical Transactions,2010,365(1851):303-315.
[2]Xiao H,Gong Y,Ogai H,et al.A Data Collection System in Wireless Network Integrated WSN and ZIGBEE for Bridge Health Diagnosis[C]//Sice Conference.IEEE,2011:2024-2028.
[3]符欲梅,朱芳,昝昕武.基于支持向量机的桥梁健康监测系统残缺数据填补[J].传感技术学报,2012,25(12):1706-1710.
[4]Davey A,Savla J.Estimating Statistical Power with Incomplete Data[J].Organizational Research Methods,2008,12(2):320-346.
[5]Olinsky A,Chen S,Harlow L.The Comparative Efficacy of Imputation Methods for Missing Data in Structural Equation Modeling[J].European Journal of Operational Research,1999,151(1):53-79.
[6]樊学平,刘月飞,吕大刚.应用高斯粒子滤波器的桥梁可靠性在线预测[J].哈尔滨工业大学学报,2016,48(6):164-169.
[7]付华,代巍.基于ACPSO的PSR-MK-LSSVM瓦斯浓度动态预测方法[J].传感技术学报,2016,29(6):903-908.
[8]聂侥,吴建军.在线时间序列预测方法及其应用[J].北京工业大学学报,2017,43(3):386-393.
[9]刘双印,徐龙琴,李道亮,等.基于时间相似数据的支持向量机水质溶解氧在线预测[J].农业工程学报,2014,30(3):155-162.
[10]张大鹏.大吨位桥门式起重机主梁挠度预测方法研究[D].西南交通大学,2017.
[11]Ding S F,Bing-Juan Q I,Hong-Yan A T.An Overview on Theory and Algorithm of Support Vector Machines[J].Journal of University of Electronic Science and Technology of China,2011,40(1):2-10.
[12]乔蕾.基于支持向量机的高光谱图像分类研究[D].哈尔滨:哈尔滨工程大学,2008.
[13]Anava O,Hazan E,Mannor S,et al.Online Learning for Time Series Prediction[J].Journal of Machine Learning Research,2013,30:172-184.
[14]Gao Y,Shan X,Hu Z,et al.Extended Compressed Tracking via Random Projection Based on MSERs and Online LS-SVM learning[J].Pattern Recognition,2016,59(C):245-254.
[15]Greenhalgh J,Mirmehdi M.Real-Time Detection and Recognition of Road Traffic Signs[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(4):1498-1506.
[16]王少军,刘琦,彭喜元,等.移动通信话务量多步预测的LSSVM方法研究[J].仪器仪表学报,2011,32(6):1258-1264.
[17]Deris A M,Zain A M,Sallehuddin R.Overview of Support Vector Machine in Modeling Machining Performances[J].Procedia Engineering,2011,24(8):308-312.
[18]Chen Wei;Wang Jiale;Xie Xiaoshen,et al.Spatial Prediction of Landslide Susceptibility Using Integrated Frequency Ratio with Entropy and Support Vector Machines by Different Kernel Functions[J].Environ Earth Sci,2016,75:1344.
[19]Ardjani F,Sadouni K,Benyettou M.Optimization of SVM Multiclass by Particle Swarm(PSO-SVM)[J].International Journal of Modern Education and Computer Science,2010,2(2):1-4.
[20]王定成,方廷健,唐毅,等.支持向量机回归理论与控制的综述[J].模式识别与人工智能,2003,16(2):192-197.
[21]Tian L Y,Hu X G.Method of Parallel Sequential Minimal Optimization for Fast Training Support Vector Machine[J].Applied Mechanics and Materials,2010,29-32:947-951.
[2]Xiao H,Gong Y,Ogai H,et al.A Data Collection System in Wireless Network Integrated WSN and ZIGBEE for Bridge Health Diagnosis[C]//Sice Conference.IEEE,2011:2024-2028.
[3]符欲梅,朱芳,昝昕武.基于支持向量机的桥梁健康监测系统残缺数据填补[J].传感技术学报,2012,25(12):1706-1710.
[4]Davey A,Savla J.Estimating Statistical Power with Incomplete Data[J].Organizational Research Methods,2008,12(2):320-346.
[5]Olinsky A,Chen S,Harlow L.The Comparative Efficacy of Imputation Methods for Missing Data in Structural Equation Modeling[J].European Journal of Operational Research,1999,151(1):53-79.
[6]樊学平,刘月飞,吕大刚.应用高斯粒子滤波器的桥梁可靠性在线预测[J].哈尔滨工业大学学报,2016,48(6):164-169.
[7]付华,代巍.基于ACPSO的PSR-MK-LSSVM瓦斯浓度动态预测方法[J].传感技术学报,2016,29(6):903-908.
[8]聂侥,吴建军.在线时间序列预测方法及其应用[J].北京工业大学学报,2017,43(3):386-393.
[9]刘双印,徐龙琴,李道亮,等.基于时间相似数据的支持向量机水质溶解氧在线预测[J].农业工程学报,2014,30(3):155-162.
[10]张大鹏.大吨位桥门式起重机主梁挠度预测方法研究[D].西南交通大学,2017.
[11]Ding S F,Bing-Juan Q I,Hong-Yan A T.An Overview on Theory and Algorithm of Support Vector Machines[J].Journal of University of Electronic Science and Technology of China,2011,40(1):2-10.
[12]乔蕾.基于支持向量机的高光谱图像分类研究[D].哈尔滨:哈尔滨工程大学,2008.
[13]Anava O,Hazan E,Mannor S,et al.Online Learning for Time Series Prediction[J].Journal of Machine Learning Research,2013,30:172-184.
[14]Gao Y,Shan X,Hu Z,et al.Extended Compressed Tracking via Random Projection Based on MSERs and Online LS-SVM learning[J].Pattern Recognition,2016,59(C):245-254.
[15]Greenhalgh J,Mirmehdi M.Real-Time Detection and Recognition of Road Traffic Signs[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(4):1498-1506.
[16]王少军,刘琦,彭喜元,等.移动通信话务量多步预测的LSSVM方法研究[J].仪器仪表学报,2011,32(6):1258-1264.
[17]Deris A M,Zain A M,Sallehuddin R.Overview of Support Vector Machine in Modeling Machining Performances[J].Procedia Engineering,2011,24(8):308-312.
[18]Chen Wei;Wang Jiale;Xie Xiaoshen,et al.Spatial Prediction of Landslide Susceptibility Using Integrated Frequency Ratio with Entropy and Support Vector Machines by Different Kernel Functions[J].Environ Earth Sci,2016,75:1344.
[19]Ardjani F,Sadouni K,Benyettou M.Optimization of SVM Multiclass by Particle Swarm(PSO-SVM)[J].International Journal of Modern Education and Computer Science,2010,2(2):1-4.
[20]王定成,方廷健,唐毅,等.支持向量机回归理论与控制的综述[J].模式识别与人工智能,2003,16(2):192-197.
[21]Tian L Y,Hu X G.Method of Parallel Sequential Minimal Optimization for Fast Training Support Vector Machine[J].Applied Mechanics and Materials,2010,29-32:947-951.