首页> 外文会议>IEEE International Conference on Grey Systems and Intelligent Services >Non-equidistant GM(1,1) model based on GCHM_WBO and its application to corrosion rate prediction
【24h】

Non-equidistant GM(1,1) model based on GCHM_WBO and its application to corrosion rate prediction

机译:基于GCHM_WBO的非等距GM(1,1)模型及其在腐蚀速率预测中的应用

获取原文

摘要

GM(1,1) model is widely used in the field of corrosion rate prediction. In this paper, we present a new model, which combines the non-equidistant GM(1,1) model with GCHM_WBO (GCHM, Generalized Contra-Harmonic Mean; WBO, Weakening Buffer Operator), to solve the deadlock that a large number of non-equidistant corrosion rate is difficult to establish a reasonable prediction model and to improve prediction accuracy. It contains a morphing parameter, so as to effectively control the intensity of the weakening operator. The present paper proposes an algorithm to calculate morphing parameter based on a given sample. Finally, the model is applied to predict the corrosion rate of the same series of 6 steels at Guangzhou Experimental Station, and relative error of prediction is within 8.89% to predict the corrosion rate of the 15th year.
机译:GM(1,1)模型广泛用于腐蚀速率预测领域。在本文中,我们提出了一个新模型,该模型将非等距GM(1,1)模型与GCHM_WBO(GCHM,广义逆谐波均值; WBO,弱化缓冲算子)相结合,以解决大量非等速腐蚀速率难以建立合理的预测模型和提高预测精度。它包含一个变形参数,以便有效地控制弱化算子的强度。本文提出了一种基于给定样本计算变形参数的算法。最后,利用该模型对广州实验站相同系列的6种钢的腐蚀速率进行预测,预测第15年的腐蚀速率的相对预测误差在8.89%以内。

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