• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International System Safety Conference >Hard Landing Prediction with Improved PSO Based-BP Neural Network
【24h】

Hard Landing Prediction with Improved PSO Based-BP Neural Network

机译：基于PSO基于BP的神经网络的硬着陆预测

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Hard landing is one of the several seriously dangerous potential events in terms of flight safety. The current process for deciding whether a hard landing has occurred is based on the subjective assessments by the flight crew. However, because of the lack of reliable quantitative data and accurate models, hard landing prediction is insufficient and pilots and aircraft crew are not satisfied with it, although there have been some researches on the landing safety problems. In this paper, we propose a new hard landing prediction model using improved PSO based-BP neural network. Related influence factors of landing safety are explored and the relevant flight data are collected in the research. As there are several influence factors, multicollinearity problem of input factors exists. Before establishing the prediction model, we first conduct principal component analysis. The BP neural network based on improved PSO optimization has higher accuracy than the BP algorithm, which can make the hard landing prediction model more precise. An empirical study is provided to confirm that the new method is effective.
机译：在飞行安全方面是几种严重危险的潜在事件之一。目前决定是否发生了硬着陆的过程是基于飞行机组人员的主观评估。然而，由于缺乏可靠的定量数据和准确的模型，硬着陆预测不足，飞行员和飞机机组人员对其不满意，尽管对着陆安全问题已经有所研究。在本文中，我们用基于改进的PSO基本网络提出了一种新的硬着陆预测模型。探讨了着陆安全的相关影响因素，并在研究中收集了相关的飞行数据。由于有几个影响因素，存在的输入因素的多元性问题存在。在建立预测模型之前，我们首先进行主成分分析。基于改进的PSO优化的BP神经网络具有比BP算法更高的精度，这可以使硬着陆预测模型更精确。提供了实证研究以确认新方法是有效的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号