Method for automated detection of outliers in crash simulations

IF 1.8 4区工程技术 Q3 ENGINEERING, MANUFACTURING

International Journal of Crashworthiness Pub Date : 2023-01-02 DOI:10.1080/13588265.2022.2074634

D. Kracker, Revan Kumar Dhanasekaran, A. Schumacher, J. Garcke

{"title":"Method for automated detection of outliers in crash simulations","authors":"D. Kracker, Revan Kumar Dhanasekaran, A. Schumacher, J. Garcke","doi":"10.1080/13588265.2022.2074634","DOIUrl":null,"url":null,"abstract":"Abstract Stricter legal requirements in crash safety lead to more complex development processes in computer-aided engineering and result in an increasing number of simulations. Both, the construction of the simulation models as well as their evaluation are costly and time-consuming. Therefore, an automated workflow is required that significantly facilitates the analysis of the results by the engineer and increases the quality of the evaluation. In this study an automated evaluation process is proposed that detects anomalous crash behaviour in a bundle of crash simulations. The individual states from the simulation are analysed separately from each other and an outlier score is calculated using a kth-nearest-neighbour approach. Subsequently, these results are averaged into one score for each simulation. With the help of different statistical methods, a threshold value is calculated, from which a simulation can be identified as an outlier. The evaluation is carried out on 5 datasets. On average, the precision and recall of the presented method are 1.0 and 0.91, respectively.","PeriodicalId":13784,"journal":{"name":"International Journal of Crashworthiness","volume":"28 1","pages":"96 - 107"},"PeriodicalIF":1.8000,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Crashworthiness","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/13588265.2022.2074634","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MANUFACTURING","Score":null,"Total":0}

引用次数: 0

Abstract

Abstract Stricter legal requirements in crash safety lead to more complex development processes in computer-aided engineering and result in an increasing number of simulations. Both, the construction of the simulation models as well as their evaluation are costly and time-consuming. Therefore, an automated workflow is required that significantly facilitates the analysis of the results by the engineer and increases the quality of the evaluation. In this study an automated evaluation process is proposed that detects anomalous crash behaviour in a bundle of crash simulations. The individual states from the simulation are analysed separately from each other and an outlier score is calculated using a kth-nearest-neighbour approach. Subsequently, these results are averaged into one score for each simulation. With the help of different statistical methods, a threshold value is calculated, from which a simulation can be identified as an outlier. The evaluation is carried out on 5 datasets. On average, the precision and recall of the presented method are 1.0 and 0.91, respectively.

查看原文本刊更多论文

碰撞模拟中异常值的自动检测方法

碰撞安全方面的法律要求越来越严格，导致计算机辅助工程的开发过程越来越复杂，仿真的数量也越来越多。仿真模型的构建和评估都是昂贵和耗时的。因此，需要一个自动化的工作流程来极大地促进工程师对结果的分析，并提高评估的质量。在这项研究中，提出了一种自动评估过程，用于检测碰撞模拟中的异常碰撞行为。模拟中的各个状态分别进行分析，并使用第k近邻方法计算离群值。随后，将这些结果平均为每个模拟的一个分数。利用不同的统计方法，计算出一个阈值，从这个阈值中可以识别出一个异常值。评估在5个数据集上进行。该方法的平均查准率和查全率分别为1.0和0.91。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Crashworthiness 工程技术-工程：机械

CiteScore

3.70

自引率

10.50%

发文量

审稿时长

2.3 months

期刊介绍： International Journal of Crashworthiness is the only journal covering all matters relating to the crashworthiness of road vehicles (including cars, trucks, buses and motorcycles), rail vehicles, air and spacecraft, ships and submarines, and on- and off-shore installations. The Journal provides a unique forum for the publication of original research and applied studies relevant to an audience of academics, designers and practicing engineers. International Journal of Crashworthiness publishes both original research papers (full papers and short communications) and state-of-the-art reviews. International Journal of Crashworthiness welcomes papers that address the quality of response of materials, body structures and energy-absorbing systems that are subjected to sudden dynamic loading, papers focused on new crashworthy structures, new concepts in restraint systems and realistic accident reconstruction.