Application of natural language processing for systematic requirement management in model‐based systems engineering

INCOSE International Symposium, vol. 31, pp. 806–815

Abstract

Abstract Today, manufacturing companies are confronted with an enormous number of product requirements, which increasingly demand an interaction of the different engineering disciplines mechanics, electric/electronic (E/E) and software. At the same time, companies must realize a shorter time to market, lower costs and higher quality. As a result, development methods are required, which support the fast, flexible and structured transfer of numerous requirements into products despite this increased complexity in processes and products. In this context, Model‐Based Systems Engineering (MBSE) takes advantage of the increasing digitalization of products and development processes. It provides structures and processes for the efficient processing of requirements by fostering the collaboration between different engineering disciplines and enabling early validation of the product. In this context, it is often challenging that requirements are not structured, but rather unstructured and heterogeneous. For the processing within MBSE, text‐based requirements today usually still have to be prepared with high manual effort. This paper presents a methodology that supports the transformation of unstructured and heterogeneous text‐based requirements using Natural Language Processing in order to prepare them for further processing within MBSE.

Authors 6

1. Michael Riesener corresponding Aachen Laboratory for Machine Tools and Production Engineering (WZL) Laboratory for Machine Tools and Production (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering of RWTH Aachen University

   Laboratory for Machine Tools and Production, Engineering of RWTH Aachen University

2. Christian Dölle Aachen Laboratory for Machine Tools and Production Engineering (WZL) Laboratory for Machine Tools and Production (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering of RWTH Aachen University

   Laboratory for Machine Tools and Production, Engineering of RWTH Aachen University

3. Annika Becker Aachen Laboratory for Machine Tools and Production Engineering (WZL) Laboratory for Machine Tools and Production (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering of RWTH Aachen University

   Laboratory for Machine Tools and Production, Engineering of RWTH Aachen University

4. Sofia Gorbatcheva Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

5. Eric Rebentisch

   Massachusetts Institute of Technology

   Affiliation as printed

   MIT Center for Sociotechnical Systems Research

6. Günther Schuh Aachen Laboratory for Machine Tools and Production Engineering (WZL) Laboratory for Machine Tools and Production (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering of RWTH Aachen University

   Laboratory for Machine Tools and Production, Engineering of RWTH Aachen University