{"title":"一种慢动辐射源单机智能无源定位处理算法","authors":"Siqiang Ma, X. Yang, Chao Peng, Zheyu Zhang","doi":"10.1109/EEI59236.2023.10212967","DOIUrl":null,"url":null,"abstract":"When the traditional airborne passive reconnaissance and positioning system locates the slow-moving emitter in a single aircraft, many factors such as direction-finding time window and positioning angle will affect the positioning accuracy and convergence time of the system. It is difficult to select the optimal parameter combination for different emitter targets quickly. In order to solve this problem, a method for solving the optimal location parameters based on machine learning and intelligent optimization algorithm is studied. First of all, the model of typical slow moving target location on the sea surface is established based on the least square and sliding window processing methods, and the prediction model of location accuracy and convergence time is established using different machine learning algorithms such as support vector regression, random forest, and multi-layer perceptron; then, an optimization problem with the weighted positioning result evaluation function as the objective function and six direction-finding parameters as the decision variables is constructed and solved by using differential evolution algorithm; finally, the optimized parameters are used for positioning, and the positioning results are compared with the results before optimization. The verification results show that the proposed algorithm is better than the traditional algorithm for different targets and scenes.","PeriodicalId":363603,"journal":{"name":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Single Aircraft Intelligent Passive Location Processing Algorithm for Slow Moving Emitter\",\"authors\":\"Siqiang Ma, X. Yang, Chao Peng, Zheyu Zhang\",\"doi\":\"10.1109/EEI59236.2023.10212967\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"When the traditional airborne passive reconnaissance and positioning system locates the slow-moving emitter in a single aircraft, many factors such as direction-finding time window and positioning angle will affect the positioning accuracy and convergence time of the system. It is difficult to select the optimal parameter combination for different emitter targets quickly. In order to solve this problem, a method for solving the optimal location parameters based on machine learning and intelligent optimization algorithm is studied. First of all, the model of typical slow moving target location on the sea surface is established based on the least square and sliding window processing methods, and the prediction model of location accuracy and convergence time is established using different machine learning algorithms such as support vector regression, random forest, and multi-layer perceptron; then, an optimization problem with the weighted positioning result evaluation function as the objective function and six direction-finding parameters as the decision variables is constructed and solved by using differential evolution algorithm; finally, the optimized parameters are used for positioning, and the positioning results are compared with the results before optimization. The verification results show that the proposed algorithm is better than the traditional algorithm for different targets and scenes.\",\"PeriodicalId\":363603,\"journal\":{\"name\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/EEI59236.2023.10212967\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EEI59236.2023.10212967","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Single Aircraft Intelligent Passive Location Processing Algorithm for Slow Moving Emitter
When the traditional airborne passive reconnaissance and positioning system locates the slow-moving emitter in a single aircraft, many factors such as direction-finding time window and positioning angle will affect the positioning accuracy and convergence time of the system. It is difficult to select the optimal parameter combination for different emitter targets quickly. In order to solve this problem, a method for solving the optimal location parameters based on machine learning and intelligent optimization algorithm is studied. First of all, the model of typical slow moving target location on the sea surface is established based on the least square and sliding window processing methods, and the prediction model of location accuracy and convergence time is established using different machine learning algorithms such as support vector regression, random forest, and multi-layer perceptron; then, an optimization problem with the weighted positioning result evaluation function as the objective function and six direction-finding parameters as the decision variables is constructed and solved by using differential evolution algorithm; finally, the optimized parameters are used for positioning, and the positioning results are compared with the results before optimization. The verification results show that the proposed algorithm is better than the traditional algorithm for different targets and scenes.