摘要
为提高着舰指挥决策的准确度,本文以预测的着舰航迹为决指挥策依据,提出了基于航迹预测的着舰指挥决策算法。该算法分为航迹预测和指挥决策两个模型,两个模型以历史着舰数据为训练样本,分别基于径向基函数RBF网络和属性相关贝叶斯算法建立,并针对着舰航迹的阶段特性,提出了基于RBF网络集成的着舰航迹预测模型。与常规算法的对比仿真实验表明:基于RBF网络集成的着舰航迹预测模型具有更高的预测精度,基于航迹预测的着舰指挥决策算法的决策结论与着舰指挥官的决策结论基本一致,能够有效提高着舰成功率。
To improve the accuracy of the carrier landing command decision-making,we propose a related algorithm based on trajectory prediction algorithm( TPCLCD),which takes the predicted landing trajectory as the basis of command decision-making. TPCLCD includes the trajectory prediction model and the command decision-making model,which are derived based on radial basis function( RBF) network and attribute-related Bayesian algorithm,respectively. Aiming at the stage characteristics of carrier landing trajectory,we establish the trajectory prediction model based on RBF network ensemble to improve the accuracy of the model. Compared with the conventional algorithm,the simulation results show that the carrier landing trajectory prediction model based on the RBF network ensemble has higher prediction accuracy. The decision result of TPCLCD is basically consistent with the landing signal commander. Hence,the proposed model can effectively improve the success rate of carrier landing.
引文
[1]NATOPS landing signal officer manual[S]. Naval Air Systems Command,2007.
[2]MAZZA C J,JOHNS F R. Preliminary study of optimal wave-off control:a parametric approach[R]. Naval Air Development Center,1973.
[3]朱齐丹,李晖,夏桂华,等.舰载机着舰风险动态多属性决策[J].哈尔滨工程大学学报,2013,34(5):615-622.ZHU Qidan,LI Hui,XIA Guihua,et al. Dynamic multiattribute decision making of carrier-based aircraft landing risk[J]. Journal of Harbin Engineering University,2013,34(5):615-622.
[4]MARZOUK M,ABUBAKR A. Decision support for tower crane selection with building information models and genetic algorithms[J]. Automation in construction, 2016, 61:1-15.
[5]CARMINATI M,CARON R,MAGGI F. BankSealer:a decision support system for online banking fraud analysis and investigation[J]. Computers&security,2015,53:175-186.
[6]GYO Z X,NGAI E W T,YANG C,et al. An RFID-based intelligent decision support system architecture for production monitoring and scheduling in a distributed manufacturing environment[J]. International journal of production economics,2015,159:16-28.
[7]HEIDI W,THUMFART S,LUGHOFER E,et al. Machine learning based analysis of gender differences in visual inspection decision making[J]. Information sciences,2013,224:62-76.
[8]GOEL S,SINGH J,OJHA N. Intelligent Aircraft landing decision support system using artificial bee Colony[C]//2016 3rd International Conference on Computing for Sustainable Global Development(INDIACom). New Delhi,India:IEEE,2016:2412-2416.
[9]JIA Lintong,TONG Zhongxiang,WANG Chaozhe,Aircraft combat survivability calculation based on combination weighting and multiattribute intelligent grey target decision model[J]. Mathematical problems in engineering,2016,2016:8934749.
[10]LU Keke,LI Qing,CHENG Nong. An autonomous carrier landing system design and simulation for unmanned aerial vehicle[C]//Proceedings of 2014 IEEE Chinese Guidance,Navigation and Control Conference. Yantai,China:IEEE,2015:1352-1356.
[11]LPEZ-RUIZ A,BERGILLOS R J,ORTEGA-SNCHEZ M. The importance of wave climate forecasting on the decision-making process for nearshore wave energy exploitation[J]. Applied energy,2016,182:191-203.
[12]SCHEPEN A,ZHAO T,WANG Q J,et al. Optimising seasonal streamflow forecast lead time for operational decision making in Australia[J]. Hydrology and earth system sciences,2016,20(10):4117-4128.