基于改进型BP神经网络的导引头测高性能评估
|
摘要
武器装备性能评估贯穿于装备发展的全寿命过程,对于装备定型与实战化运用具有重要意义。针对传统反向传播(back propagation,BP)神经网络模型易陷入局部最优、武器装备评估数据少等问题,提出了基于数据包络分析和Bootstrap法的改进型BP神经网络模型。利用数据包络分析处理原始指标得到3项优化参数,结合Bootstrap法对其进行扩充,再通过BP神经网络建立评估模型。实验表明,改进模型得到的合成孔径雷达(systemic aperture radar,SAR)导引头测高性能评估结果,其决定系数和误差系数均有明显改善。该模型不仅规避了模糊综合评判法主观性强、精确度不高等问题,同时有效解决了传统BP神经网络模型易陷入局部最优和武器装备评估数据少的两个问题。
The performance evaluation of weapon equipment runs through the whole life process of equipment development,which is important to equipment finalization and practical application.In view of that the traditional back propagation(BP)neural network is prone to local optimal and weapon equipment evaluation data are a small sample type,this paper proposes an improved BP neural network model based on data envelopment ana-lysis and the Bootstrap method.Three optimized parameters are obtained by data envelopment analysis,and expanded by the Bootstrap method,and then an evaluation model is established by the BP neural network.The experimental results show that the determination coefficient and error coefficient of the systemic aperture radar seeker are improved obviously.This model not only avoids the problems of strong subjectivity and low accuracy of the fuzzy comprehensive evaluation method,but also solves two shortcomings of the traditional BP neural network model which is prone to be involved in local optimization and the lack of weapon equipment data.
The performance evaluation of weapon equipment runs through the whole life process of equipment development,which is important to equipment finalization and practical application.In view of that the traditional back propagation(BP)neural network is prone to local optimal and weapon equipment evaluation data are a small sample type,this paper proposes an improved BP neural network model based on data envelopment ana-lysis and the Bootstrap method.Three optimized parameters are obtained by data envelopment analysis,and expanded by the Bootstrap method,and then an evaluation model is established by the BP neural network.The experimental results show that the determination coefficient and error coefficient of the systemic aperture radar seeker are improved obviously.This model not only avoids the problems of strong subjectivity and low accuracy of the fuzzy comprehensive evaluation method,but also solves two shortcomings of the traditional BP neural network model which is prone to be involved in local optimization and the lack of weapon equipment data.
引文
[1]SAATY T L,SHANG J S.An innovative orders of magnitude approach to AHP based multicriteria decision making:prioritizing divergent intangible humane acts[J].European of Operation Research,2011,214(3):703-715.
[2]AJAY G,SENTHIL K.Analysis on critical success factors for agile manufacturing evaluation in original equipment manufacturing industryan AHP approach[J].Chinese Journal of Mechanical Engineering,2016,29(5):880-888.
[3]LI W,MAO N,PAN W.The effectiveness evaluation model of radar jamming system based on WSEIAC model[C]∥Proc.of the IEEE Control and Decision Conference,2008:1848-1852.
[4]BAO M,DAI Y W.Analysis and evaluation of the viability of redundant systems[J].Control and Decision,2009,24(12):1873-1876.
[5]BOUTHONNIER V,LEVIS A H.Effectiveness analysis of C3systems[J].IEEE Trans.on System and Cybermetics,1984,14(1):48-54.
[6]LEVIS A H,WANGENHALS L W.Advances in C4ISR architectures[M].Fairfax County:George Mason University Press,2002.
[7]ZHOU Z Q,ZHANG T T.Artificial neural network is used to analyze the quality of edible oil by direct ionization mass spectrometry[J].Chinese Journal of Analytic Chemistry,2011,39(11):1665-1669.
[8]CAO J X,LU J P.Genetic algorithm-Bayes B-P neural network fitting titration of organic acids in molasses[J].Chinese Journal of Analytica Chemistry,2011,39(5):743-747.
[9]肖恭伟,欧吉坤.基于改进的BP神经网络构建区域精密对流层延迟模型[J].地球物理学报,2018,61(8):3139-3148.XIAO G W,OU J K.Regional precision tropospheric delay model is built based on improved BP neural network[J].Chinese Journal of Geophysics,2018,61(8):3139-3148.
[10]刘东,李帅.基于KHA优化BP神经网络的地下水水质综合评价方法[J].农业机械学报,2018,49(9):275-284.LIU D,LI S.Comprehensive evaluation method of groundwater quality based on KHA optimized BP neural network[J].Tran-sactions of the Chinese Society for Agricultural Machinery,2018,49(9):275-284.
[11]秦玉亮.弹载SAR制导技术研究[D].长沙:国防科学技术大学,2008.QIN Y L.Research on missile-borne SAR guidance technology[D].Changsha:Journal of National University of Defense Technology,2008.
[12]李莹莹,吴昊.基于星载光学和SAR影像的多视立体定位误差分析[J].光学学报,2018,38(5):0528003.LI Y Y,WU H.Multi-visual stereo positioning error analysis based on spaceborne optics and SAR image[J].Acta Optica Sinica,2018,38(5):0528003.
[13]JESSICA M,MICHAEL K.Comparison of L-band and X-band differential interferometric synthetic aperture radar for mine subsidence monitoring in central utah[J].International Journal of Mining Science and Technology,2017,27:159-163.
[14]杨立波,高仕博.合成孔径雷达相干与非相干干扰性能分析[J].系统工程与电子技术,2018,40(11):2444-2449.YANG L B,GAO S B.Analysis of SAR coherent and incoherent interference performance[J].Systems Engineering and Electronics,2018,40(11):2444-2449.
[15]LIU T,CUI H G.Novel estimators of equivalent of looks in polarimetric SAR imagery based on sub-matrices[J].Science China,2016,59(6):062309.
[16]DING S F,SU C Y,YU J Z.An optimizing BP neural network algorithm based on genetic algorithm[J].Artificial Intelligence Review,2011,36(2):153-162.
[17]GUO H J,BING S,YU Q L.On the application of improved back propagation neural network in real-time forecast[C]∥Proc.of the IEEE International Conference on Neural Computation,2007:541-542.
[18]LONG J Q,LAN F C,CHEN J Q.Mechanical properties prediction of the mechanical clinching joints based on genetic algorithm and BP neural network[J].Chinese Journal of Mechanical Engineering,2009,22(1):36-41.
[19]SHU Z H,FANG S.Property screening based on regularization network-genetic algorithm and its application in chemical pattern recognition[J].Chinese Journal of Analytics Chemistry,2003,31(10):1169-1172.
[20]WANG Y,JIANG G P.Assessment of coal mining and environmental management efficiency based on envelope analysis of network data[J].Journal of China University of Mining,2018,47(2):421-427.
[21]CASTELLI L,PESENTI R.Network,shared flow and multilevel models:a critical review[J].Springer US,2014,208:329-376.
[22]TOLOO M,EMROUZNEJAD A.A linear relational DEA model to evaluate two-stage processes with shared inputs[J].Computational&Applied Mathematics,2017,37(1):1-37.
[23]郭清娥,王雪青,位珍.基于DEA交叉评价的模糊综合评价模型及其应用[J].控制与决策,2012,27(4):575-583.GUO Q E,WANG X Q,WEI Z.Fuzzy comprehensive evaluation model based on DEA cross evaluation and its application[J].Control and Decision,2012,27(4):575-583.
[24]WANG Y Q,WANG Z Y.Gray bootstrap method for estimating frequency-varying random vibration signal with small samples[J].Chinese Journal of Aeronautics,2013,24(2):383-389.
[25]CHEN S,LI Y X.Constructing confidence intervals of extreme rainfall quantiles using Bayesian,bootstrap,and profile likelihood approaches[J].Science China,2016,34(4):573-585.
[26]ZHANG W,HU C H.Bootstrap-adaptive chaotic clone network and gyroscopic drift prediction[J].Acta Electronica Sinica,2009,37(9):2035-2040.
[2]AJAY G,SENTHIL K.Analysis on critical success factors for agile manufacturing evaluation in original equipment manufacturing industryan AHP approach[J].Chinese Journal of Mechanical Engineering,2016,29(5):880-888.
[3]LI W,MAO N,PAN W.The effectiveness evaluation model of radar jamming system based on WSEIAC model[C]∥Proc.of the IEEE Control and Decision Conference,2008:1848-1852.
[4]BAO M,DAI Y W.Analysis and evaluation of the viability of redundant systems[J].Control and Decision,2009,24(12):1873-1876.
[5]BOUTHONNIER V,LEVIS A H.Effectiveness analysis of C3systems[J].IEEE Trans.on System and Cybermetics,1984,14(1):48-54.
[6]LEVIS A H,WANGENHALS L W.Advances in C4ISR architectures[M].Fairfax County:George Mason University Press,2002.
[7]ZHOU Z Q,ZHANG T T.Artificial neural network is used to analyze the quality of edible oil by direct ionization mass spectrometry[J].Chinese Journal of Analytic Chemistry,2011,39(11):1665-1669.
[8]CAO J X,LU J P.Genetic algorithm-Bayes B-P neural network fitting titration of organic acids in molasses[J].Chinese Journal of Analytica Chemistry,2011,39(5):743-747.
[9]肖恭伟,欧吉坤.基于改进的BP神经网络构建区域精密对流层延迟模型[J].地球物理学报,2018,61(8):3139-3148.XIAO G W,OU J K.Regional precision tropospheric delay model is built based on improved BP neural network[J].Chinese Journal of Geophysics,2018,61(8):3139-3148.
[10]刘东,李帅.基于KHA优化BP神经网络的地下水水质综合评价方法[J].农业机械学报,2018,49(9):275-284.LIU D,LI S.Comprehensive evaluation method of groundwater quality based on KHA optimized BP neural network[J].Tran-sactions of the Chinese Society for Agricultural Machinery,2018,49(9):275-284.
[11]秦玉亮.弹载SAR制导技术研究[D].长沙:国防科学技术大学,2008.QIN Y L.Research on missile-borne SAR guidance technology[D].Changsha:Journal of National University of Defense Technology,2008.
[12]李莹莹,吴昊.基于星载光学和SAR影像的多视立体定位误差分析[J].光学学报,2018,38(5):0528003.LI Y Y,WU H.Multi-visual stereo positioning error analysis based on spaceborne optics and SAR image[J].Acta Optica Sinica,2018,38(5):0528003.
[13]JESSICA M,MICHAEL K.Comparison of L-band and X-band differential interferometric synthetic aperture radar for mine subsidence monitoring in central utah[J].International Journal of Mining Science and Technology,2017,27:159-163.
[14]杨立波,高仕博.合成孔径雷达相干与非相干干扰性能分析[J].系统工程与电子技术,2018,40(11):2444-2449.YANG L B,GAO S B.Analysis of SAR coherent and incoherent interference performance[J].Systems Engineering and Electronics,2018,40(11):2444-2449.
[15]LIU T,CUI H G.Novel estimators of equivalent of looks in polarimetric SAR imagery based on sub-matrices[J].Science China,2016,59(6):062309.
[16]DING S F,SU C Y,YU J Z.An optimizing BP neural network algorithm based on genetic algorithm[J].Artificial Intelligence Review,2011,36(2):153-162.
[17]GUO H J,BING S,YU Q L.On the application of improved back propagation neural network in real-time forecast[C]∥Proc.of the IEEE International Conference on Neural Computation,2007:541-542.
[18]LONG J Q,LAN F C,CHEN J Q.Mechanical properties prediction of the mechanical clinching joints based on genetic algorithm and BP neural network[J].Chinese Journal of Mechanical Engineering,2009,22(1):36-41.
[19]SHU Z H,FANG S.Property screening based on regularization network-genetic algorithm and its application in chemical pattern recognition[J].Chinese Journal of Analytics Chemistry,2003,31(10):1169-1172.
[20]WANG Y,JIANG G P.Assessment of coal mining and environmental management efficiency based on envelope analysis of network data[J].Journal of China University of Mining,2018,47(2):421-427.
[21]CASTELLI L,PESENTI R.Network,shared flow and multilevel models:a critical review[J].Springer US,2014,208:329-376.
[22]TOLOO M,EMROUZNEJAD A.A linear relational DEA model to evaluate two-stage processes with shared inputs[J].Computational&Applied Mathematics,2017,37(1):1-37.
[23]郭清娥,王雪青,位珍.基于DEA交叉评价的模糊综合评价模型及其应用[J].控制与决策,2012,27(4):575-583.GUO Q E,WANG X Q,WEI Z.Fuzzy comprehensive evaluation model based on DEA cross evaluation and its application[J].Control and Decision,2012,27(4):575-583.
[24]WANG Y Q,WANG Z Y.Gray bootstrap method for estimating frequency-varying random vibration signal with small samples[J].Chinese Journal of Aeronautics,2013,24(2):383-389.
[25]CHEN S,LI Y X.Constructing confidence intervals of extreme rainfall quantiles using Bayesian,bootstrap,and profile likelihood approaches[J].Science China,2016,34(4):573-585.
[26]ZHANG W,HU C H.Bootstrap-adaptive chaotic clone network and gyroscopic drift prediction[J].Acta Electronica Sinica,2009,37(9):2035-2040.