Automated measuring of engineering progress based on ML algorithms

Automated measuring of engineering progress based on ML algorithms
复制标题

基于机器学习算法的工程进度自动测量

DOI:
10.1016/j.procir.2021.03.114
复制
发表时间:
2020
期刊:
Procedia CIRP
影响因子:
--
通讯作者:
Tsigkros
Tsigkros
中科院分区:
--
文献类型:
--
作者:
Tsigkros

文献摘要

参考文献

相似文献

管理成功的工程项目的一个重大挑战是随时了解它们的状态。本文介绍了工程项目进展的背景,并提出了一种基于机器学习(ML)算法(如KNN、随机森林和决策树)的自动化方法。测量工程活动的进度所需的信息是从工程工件中提取出来的,然后对项目的进度进行分析和解释。该方法通过考虑使用ML算法的历史数据和实际未完成的工件来确定完成程度,从而集成了以前项目的信息。
A significant challenge of managing successful engineering projects is to know their status at any time. This paper describes the background of engineering projects’ progress and presents an automated approach based on machine learning (ML) algorithms (e.g., KNN, random forest, and decision tree). The information required to measure engineering activities’ progress is extracted from engineering artifacts and subsequently analyzed and interpreted concerning the project’s progress. The approach integrates information from previous projects by considering historical data using ML algorithms and actual unfinished artifacts to determine the degree of completion.
DOI: --
发表时间: 2014
期刊: Product Lifecycle Management
影响因子: --
作者:
R. Stark;T. Damerau;H. Hayka;Sebastian Neumeyer;R. Woll
通讯作者: R. Woll
DOI: --
发表时间: 2019
影响因子: 5.8
作者:
C. Snider;J. Gopsill;Simon Jones;Lia Emanuel;B. Hicks
通讯作者: B. Hicks
DOI: --
发表时间: 2017
影响因子: 2.9
作者:
José Alejandro Lugo García;Anié Bermudez Peña;P. P. Pérez;Rafael Bello
通讯作者: Rafael Bello
DOI: --
发表时间: 2018
期刊: Zeitschrift für wirtschaftlichen Fabrikbetrieb
影响因子: --
作者:
Alexandra Klauke;K. Fleischer;R. Schmitt;T. Vollmer;Eike Permin
通讯作者: Eike Permin