一种平台惯导系统综合性能实用组合预测评判方法

发布时间：2018-05-20 14:41

本文选题：PINS + 导航误差LS-SVR　；参考：《中国惯性技术学报》2014年01期

【摘要】：平台惯导系统(PINS)长期重复性参数是评价PINS综合性能是否满足导航精度的重要因素。在PINS动态飞行条件下,采用PINS导航误差模型能够根据PINS各单项性能参数对其综合性能进行精确计算,但该方法计算时间长,在PINS应用决策阶段不能满足快速评判的时效要求。对此提出了基于PINS导航误差模型和最小二乘支持向量机回归(LS-SVR)相结合的PINS综合性能预测方法。在PINS贮存准备阶段采用导航误差模型与LS-SVR组合方法构建PINS综合性能预测模型,在应用决策阶段采用实时预测的PINS各单项性能指标参数,运用PINS综合性能预测模型对每套PINS进行足够次数综合性能预测,使用PINS综合性能评判指标对每套PINS综合性能进行评判,可以快速得到PINS综合性能评判结果。经过计算验证,表明该组合预测方法不仅具有很高的PINS综合性能预测精度,而且有效提高了PINS综合性能预测效率和评判效果,具有很好的实际应用及评判决策价值。
[Abstract]:The long-term repeatability of platform inertial navigation system (sins) is an important factor to evaluate whether the integrated performance of PINS meets the navigation accuracy. Under the condition of PINS dynamic flight, the PINS navigation error model can accurately calculate its comprehensive performance according to the individual performance parameters of PINS, but the calculation time of this method is long, so it can not meet the time requirement of fast evaluation in the PINS application decision stage. Based on the PINS navigation error model and the least squares support vector machine regression algorithm (LS-SVR), a comprehensive performance prediction method for PINS is proposed. The integrated performance prediction model of PINS is constructed by the combination of navigation error model and LS-SVR in the stage of PINS storage and preparation. In the stage of decision making, the parameters of each single item performance index of PINS are predicted in real time. The comprehensive performance prediction model of PINS is used to predict the comprehensive performance of each set of PINS, and the comprehensive performance of each set of PINS is evaluated by PINS comprehensive performance evaluation index. The comprehensive performance evaluation results of PINS can be obtained quickly. The results of calculation and verification show that the combined prediction method not only has high prediction accuracy of PINS comprehensive performance, but also effectively improves the efficiency and evaluation effect of PINS comprehensive performance prediction, and has a good practical application and decision value.
【作者单位】：哈尔滨工业大学空间控制与惯性技术研究中心;解放军96117部队;北京自动化控制设备研究所;
【基金】：国防重点项目(61388010404)
【分类号】：TN966

【参考文献】