Stream Data Association Analysis Based On Missing Data

Radar is an important means to monitor aerial target,which can obtain the running trajectory of aerial target and obtain the real-time location information of target.However,the target information obtained by radar is limited and the target feature portrait cannot be fully established by radar signal.As a general aviation communication signal,the Monitoring Signal of Civil Aviation Control(MSCAC)contains detailed information such as target position,speed,course and aircraft identification number.By fusing the radar track and the position information of the MSCAC with the correlated characteristics,the target feature can be expanded,the sharpness of the target feature image is improved,and the precision of the target recognition is improved.When the target passes the radar reconnaissance range,the radar can obtain the track information of the target,and can obtain the more detailed trajectory and identification number of the target through the MSCAC signal.To realize the fusion between radar and MSCAC signal and to improve the number of target features,the following problems need to be solved: Fist,Missing data processing.The information that gets from the target may be missing because of various factors,and the missing data will interfere with the result of the association fusion.Second,Track correlation.It is also a problem that how to search for the fusion of target trajectory with correlation relation if we get multiple target aviation trajectory through radar and MSCAC information.Third,Delayed track correlation.Air traffic control information is abrupt and intermittent,and it is also a problem to be solved when the information obtained by radar is correlated with the intermittent position information of MSCAC Therefore.Based on the above problems,the main research work is as follows:A method of missing data processing based on sliding window is proposed.To deal with the stream data with missing data,this method uses dynamic sliding window technology to limit the amount of data in the window and to fill the missing data and other operations.Study on multidimensional information feature correlation technology.The method of TOPSIS is used to improve the gray correlation algorithm.The TOPSIS method is used to find the set of ideal solution,and the optimal result is judged by calculating the distance between each factor and the ideal solution.By using the improved algorithm to simulate and analyze the multi-target track,the results show that the method can improve the correlation accuracy of the gray correlation algorithm and the nearest neighbor algorithm.To study the lag correlation analysis of data stream based on window.In this paper,the correlation algorithms based on Euclidean distance and random distance is proposed.By using the Euclidean distance in three-dimensional space,the relationship between targets is measured by the real distance,and the influence of the track trend on the correlation result is reduced by the random distance.The simulation results show that the proposed algorithm has an effect on the correctness of track correlation,and the result shows that the algorithm has better correlation accuracy than the simple weighting method.In this paper,some basic problems in the correlation of MSCAC and radar signal are studied,and some methods to solve the problems are proposed.The experimental simulation analysis of each method and the improved algorithm shows that the proposed method has better results and can basically solve some problems in the association,and this can also provide the basis for information fusion and target recognition.