首页> 外文期刊>Journal of information and computational science >Train Basic Resistance Identification and Its Online Update Algorithm
【24h】

Train Basic Resistance Identification and Its Online Update Algorithm

机译:列车基本阻力识别及其在线更新算法

获取原文
获取原文并翻译 | 示例
           

摘要

Basic resistance parameters are important for the energy-consumption of a train control system. Different from the traditional Least Square Error (LSE) algorithm, we employed the Genetic Algorithm (GA) to identify the train basic resistance parameters using the actual measured data obtained in the coasting stage. First, we divided the speed data into some sections by different intervals (2 km/h, 1 km/h and 0.5 km/h) to ensure the computational stability. The results showed that minimal error was obtained when the speed interval was 1 km/h. Furthermore, we found that GA not only can avoid the irrational results by the LSE algorithm, but also improved the identification accuracy. The online update algorithm based on LMS (Least mean square) is proposed to update the resistance parameter to overcome the disturbance during the running process of a train. Computational results show that the online update algorithm can change parameters dynamically and make the error less.
机译:基本电阻参数对于列车控制系统的能耗很重要。与传统的最小二乘误差(LSE)算法不同,我们使用遗传算法(GA)使用滑行阶段获得的实际测量数据来识别列车基本阻力参数。首先,我们将速度数据按不同的间隔(2 km / h,1 km / h和0.5 km / h)分成几个部分,以确保计算的稳定性。结果表明,当速度间隔为1 km / h时,获得的误差最小。此外,我们发现遗传算法不仅可以避免LSE算法的不合理结果,而且可以提高识别精度。提出了一种基于LMS(最小均方)的在线更新算法,以更新阻力参数,克服列车运行过程中的干扰。计算结果表明,在线更新算法可以动态改变参数,减少误差。

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