半球谐振陀螺仪寿命的一种长周期预测方法
|
摘要
为了缩短半球谐振陀螺仪寿命实验周期,降低实验成本,提出了一种针对漂移数据的残差修正ARGM(1,1)(Autoregressive GM(1,1))寿命预测方法。该方法利用神经网络与支持向量机中的自回归方式改进灰色模型,提高了模型的自适应能力,增强了模型的学习能力与预测能力,降低了模型回归学习的时间消耗和数据量要求,提高了预测效率。采用小波包络分析预处理某型号半球谐振陀螺仪的漂移数据,利用提出的预测方法对处理后的数据进行长周期预测,并结合灰色关联分析方法,分析失效阶段并最终预测出半球谐振陀螺仪的寿命。实验表明,残差修正ARGM(1,1)模型对半球谐振陀螺仪漂移数据的长期预测精度高于传统GM(1,1)模型、BP神经网络与支持向量机,结果也表明了研究方法的正确性和有效性。
In order to shorten the test duration and cut down test cost for a hemispherical resonator gyroscope( HRG),a long-term lifetime prediction method of residual modified ARGM( 1,1)( Autoregressive GM( 1,1)) based on drift data is proposed. In the method,the autoregressive process used in neural network and support vector machine is utilized to improve the grey model,which not only enhances the self-adaptive ability and the prediction performance,but also lowers the demands for modeling data and improves the prediction efficiency. First,wavelet-envelope analysis is adopted to preprocess drift data,and then the processed data are used to forecast several periodic prediction sequences for the HRG.At last,a grey correlation analysis method is employed to evaluate the HRG's failure stage and then finally achieves the HRG's lifetime prediction. The experimental results show the residual modified ARGM( 1,1) model with preprocessed drift data has the highest accuracy in long-term prediction among the conventional GM( 1,1),BP neural network and support vector machine,and the results also indicate the method is reliable.
In order to shorten the test duration and cut down test cost for a hemispherical resonator gyroscope( HRG),a long-term lifetime prediction method of residual modified ARGM( 1,1)( Autoregressive GM( 1,1)) based on drift data is proposed. In the method,the autoregressive process used in neural network and support vector machine is utilized to improve the grey model,which not only enhances the self-adaptive ability and the prediction performance,but also lowers the demands for modeling data and improves the prediction efficiency. First,wavelet-envelope analysis is adopted to preprocess drift data,and then the processed data are used to forecast several periodic prediction sequences for the HRG.At last,a grey correlation analysis method is employed to evaluate the HRG's failure stage and then finally achieves the HRG's lifetime prediction. The experimental results show the residual modified ARGM( 1,1) model with preprocessed drift data has the highest accuracy in long-term prediction among the conventional GM( 1,1),BP neural network and support vector machine,and the results also indicate the method is reliable.
引文
[1]Rozelle D M.The hemispherical resonator gyro:from wineglass to the planets[C].19th AAS/AIAA Space Flight Mechanics Meeting,Savannah,USA,2009.
[2]杨建业,汪立新,张胜修,等.半球谐振陀螺旋转惯导系统误差抑制机理研究[J].宇航学报,2010,31(10):2321-2327.[Yang Jian-ye,Wang Li-xin,Zhang Sheng-xiu,et al.Depression mechanism of systematic errors for HRG-based rotating inertial navigation system[J].Journal of Astronautics,2010,31(10):2321-2327.]
[3]Xu W,Wu W Q,Fang Z.Temperature drift compensation for hemispherical resonator gyro based on natural frequency[J].Sensors,2012,12(5):6434-6446.
[4]周小刚,汪立新,佘嫱,等.半球谐振陀螺温度补偿与实验研究[J].宇航学报,2010,31(4):1083-1087.[Zhou Xiaogang,Wang Li-xin,She Qiang,et al.HRG temperature compensation and experiment research[J].Journal of Astronautics,2010,31(4):1083-1087.]
[5]Deng J.Introduction to grey system theory[J].The Journal of Grey System,1989,1(1):1-24.
[6]Yin M S,Tang H W.On the fit and forecasting performance of grey prediction models for China’s labor formation[J].Mathematical and Computer Modelling,2013,57(3/4):357-365.
[7]Chang T S,Ku C Y,Fu H P.Grey theory analysis of online population and online game industry revenue in Taiwan[J].Technological Forecasting and Social Change,2013,80(1):175-185.
[8]Li G D,Masuda S,Nagai M.The prediction model for electrical power system using an improved hybrid optimization model[J].International Journal of Electrical Power&Energy Systems,2013,44(1):981-987.
[9]Kayacan E,Ulutas B,Kaynak O.Grey system theory-based models in time series prediction[J].Expert Systems with Applications,2010,37(2):1784-1789.
[10]Arhami M,Kamali N,Rajabi M M.Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations[J].Environmental Science and Pollution Research International,2013,20(7):4777-4789.
[11]Wong C,Versace M.CARTMAP:a neural network method for automated feature selection in financial time series forecasting[J].Neural Computing&Applications,2012,21(5):969-977.
[12]Meilani D,Richardo I.Currency exchange rate forecasting using artificial neural networks backpropagation method[J].International Journal of Green Computing,2012,3(2):14-33.
[13]Ilic S A,Vukmirovic S M,Erdeljan A M,et al.Hybrid artificial neural network system for short-term load forecasting[J].Thermal Science,2012,16(suppl.1):S215-S225.
[14]Shen C,Chen X Y.Improved forward linear prediction algorithm based on AGO for fiber optic gyroscope[J].Journal of Grey System,2012,24(3):251-260.
[15]Ma T,Wang L X.Application of neural network based on improved hierarchical genetic algorithms to the simulation and prediction of dynamically tuned gyroscope drift[J].Journal of Projectiles,Rockets,Missiles and Guidance,2008,28(4):42-44,58.
[16]Hou Q J,Wang H L.Random error coefficient prediction of laser gyro based on LSSVM[J].Infrared Laser Engineering,2008,37(5):802-805.
[17]Shiau J K,Ma D M,Huang C X,et al.MEMS gyroscopes null drift and compensation based on neural network[J].Advanced Materials Research,2011(255-260):2077-2081.
[18]Zhang Y S,Yang T.Modeling and compensation of MEMS gyroscope output data based on support vector machine[J].Measurement,2012,45(5):922-926.
[2]杨建业,汪立新,张胜修,等.半球谐振陀螺旋转惯导系统误差抑制机理研究[J].宇航学报,2010,31(10):2321-2327.[Yang Jian-ye,Wang Li-xin,Zhang Sheng-xiu,et al.Depression mechanism of systematic errors for HRG-based rotating inertial navigation system[J].Journal of Astronautics,2010,31(10):2321-2327.]
[3]Xu W,Wu W Q,Fang Z.Temperature drift compensation for hemispherical resonator gyro based on natural frequency[J].Sensors,2012,12(5):6434-6446.
[4]周小刚,汪立新,佘嫱,等.半球谐振陀螺温度补偿与实验研究[J].宇航学报,2010,31(4):1083-1087.[Zhou Xiaogang,Wang Li-xin,She Qiang,et al.HRG temperature compensation and experiment research[J].Journal of Astronautics,2010,31(4):1083-1087.]
[5]Deng J.Introduction to grey system theory[J].The Journal of Grey System,1989,1(1):1-24.
[6]Yin M S,Tang H W.On the fit and forecasting performance of grey prediction models for China’s labor formation[J].Mathematical and Computer Modelling,2013,57(3/4):357-365.
[7]Chang T S,Ku C Y,Fu H P.Grey theory analysis of online population and online game industry revenue in Taiwan[J].Technological Forecasting and Social Change,2013,80(1):175-185.
[8]Li G D,Masuda S,Nagai M.The prediction model for electrical power system using an improved hybrid optimization model[J].International Journal of Electrical Power&Energy Systems,2013,44(1):981-987.
[9]Kayacan E,Ulutas B,Kaynak O.Grey system theory-based models in time series prediction[J].Expert Systems with Applications,2010,37(2):1784-1789.
[10]Arhami M,Kamali N,Rajabi M M.Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations[J].Environmental Science and Pollution Research International,2013,20(7):4777-4789.
[11]Wong C,Versace M.CARTMAP:a neural network method for automated feature selection in financial time series forecasting[J].Neural Computing&Applications,2012,21(5):969-977.
[12]Meilani D,Richardo I.Currency exchange rate forecasting using artificial neural networks backpropagation method[J].International Journal of Green Computing,2012,3(2):14-33.
[13]Ilic S A,Vukmirovic S M,Erdeljan A M,et al.Hybrid artificial neural network system for short-term load forecasting[J].Thermal Science,2012,16(suppl.1):S215-S225.
[14]Shen C,Chen X Y.Improved forward linear prediction algorithm based on AGO for fiber optic gyroscope[J].Journal of Grey System,2012,24(3):251-260.
[15]Ma T,Wang L X.Application of neural network based on improved hierarchical genetic algorithms to the simulation and prediction of dynamically tuned gyroscope drift[J].Journal of Projectiles,Rockets,Missiles and Guidance,2008,28(4):42-44,58.
[16]Hou Q J,Wang H L.Random error coefficient prediction of laser gyro based on LSSVM[J].Infrared Laser Engineering,2008,37(5):802-805.
[17]Shiau J K,Ma D M,Huang C X,et al.MEMS gyroscopes null drift and compensation based on neural network[J].Advanced Materials Research,2011(255-260):2077-2081.
[18]Zhang Y S,Yang T.Modeling and compensation of MEMS gyroscope output data based on support vector machine[J].Measurement,2012,45(5):922-926.