Credibility Assessment for Digital Twins in Vehicle-in-the-Loop Test Based on Information Entropy

基于信息熵的车环测试中数字孪生可信度评估

阅读:1

Abstract

Digital twins in vehicle-in-the-loop (VIL) test has great practical significance for the functional development, testing and evaluation of intelligent vehicle. The study about the credibility assessment of dynamically evolving models still lacks effective approaches. In addition, it has rarely been studied in automotive tests. In this paper, a closed loop test of dynamic virtual and real-world interaction was built, and its characteristics are also analyzed. According to its characteristics and assessment methods, a credibility assessment methodology based on information entropy is proposed to reveal the degree of its own information confusion and structural relevance of different information, which involves ApEn and cross-ApEn. The algorithm has been successfully verified in experiments and it has been found that the inconsistent weight of the real and digital vehicle is an important factor on digital twins VIL tests. Furthermore, the effect of the length of series on the credibility assessment has been emphatically studied, and the results show that it has no more than 2% effect on the credibility assessment.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。