A significant challenge of managing successful engineering projects is to know their status at any time. This paper describes a concept of automated project progress measurement based on data flow models, digital twins, and machine learning (ML) algorithms. The approach integrates information from previous projects by considering historical data using ML algorithms and current unfinished artifacts to determine the degree of completion. The information required to measure the progress of engineering activities is extracted from engineering artifacts and subsequently analyzed and interpreted according to the project’s progress. Data flow models of the engineering process help understand the context of the analyzed artifacts. The use of digital twins makes it possible to connect plan data with actual data during the completion of the engineering project.

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。本文介绍了基于数据流模型、数字孪生和机器学习 (ML) 算法的自动化项目进度测量概念。该方法通过考虑使用 ML 算法和当前未完成工件的历史数据来确定完成程度，从而整合来自先前项目的信息。衡量工程活动进度所需的信息是从工程工件中提取的，随后根据项目进度进行分析和解释。工程过程的数据流模型有助于理解所分析工件的上下文。