Search for: All records

Abstract Model‐based systems engineering (MBSE) is rapidly gaining popularity among U.S. industries. Though industry practitioners and academic researchers have identified several advantages in transitioning to MBSE, several adoption challenges of MBSE in industries, such as insufficient tool knowledge, lack of skilled personnel, and resistance in organizations toward a shift to MBSE, are observed. Attesting to the challenges in industry adoption of MBSE, a previous research study by the authors characterized the adoption challenges as tools‐based, knowledge‐based, cultural, political, and cost‐related, and customer understanding and acceptance of MBSE practices. This study is motivated to explore further and address the challenge of low MBSE tool knowledge and lack of skilled personnel with MBSE knowledge for industry adoption. This paper presents a two‐phased research approach framed by an overarching question of the extent to which the MBSE academic curriculum is aligned with industry workforce requirements. In Phase 1 of the study, we survey industry professionals from Defense, Aerospace, Automotive, and other industry clusters to identify MBSE tools, languages, and concepts preferred by industry professionals in a candidate for hire. This is followed by Phase 2 of the survey targeted at academic institutions with Systems and MBSE programs to analyze the extent to which MBSE curricula reflect industry workforce hiring requirements. Further, we also identify the challenges reported in academic institutions in training the Workforce on MBSE. The contributions of this paper are two‐fold: providing a pathway for academic institutions to align their curricula to MBSE industry workforce requirements and triggering discussion in the broader MBSE community to identify strategies for addressing MBSE adoption challenges and training future model‐based systems engineers. 

Model-based systems engineering (MBSE) is being rapidly adopted in U.S. industries across various sectors. While practitioners and academics recognize many benefits of adopting MBSE, industries also report challenges such as limited tool expertise and a shortage of skilled personnel. Highlighting the difficulties in industry adoption of MBSE, prior research by the authors identified challenges such as tool limitations, knowledge gaps, cultural and political barriers, costs, and the level of customer understanding and acceptance of MBSE practices. Additionally, another study by the authors points out a gap between industry demands for MBSE skills in new hires and the current academic training programs. To further assess the MBSE industry’s workforce needs, this paper introduces a two-phase method for the Structured Extraction of MBSE competencies using large language models based on current workforce demands from LinkedIn job postings. Phase 1 involved extracting 1960 job descriptions from LinkedIn using the term “model-based systems engineer.” In phase 2, large language models (LLMs) employing deep transformer architectures were used to transform unstructured text into structured data. An AI agent was used as an autonomous software layer to manage every interaction between the raw dataset from Phase 1 and the LLM. Supported by the analyzed data, a competency framework is proposed that summarizes the tools, technical skills, and soft skills expected of a model-based systems engineer by the industry. The framework is designed to include core competencies shared across all MBSE roles, with specific competencies tailored for aerospace & defense, manufacturing and automotive, and software and IT sectors. 

System modeling language (SysML) diagrams generated manually by system modelers can sometimes be prone to errors, which are time-consuming and introduce subjectivity. Natural language processing (NLP) techniques and tools to create SysML diagrams can aid in improving software and systems design processes. Though NLP effectively extracts and analyzes raw text data, such as text-based requirement documents, to assist in design specification, natural language, inherent complexity, and variability pose challenges in accurately interpreting the data. In this paper, we explore the integration of NLP with SysML to automate the generation of system models from input textual requirements. We propose a model generation framework leveraging Python and the spaCy NLP library to process text input and generate class/block definition diagrams using PlantUML for visual representation. The intent of this framework is to aid in reducing the manual effort in creating SysML v1.6 diagrams—class/block definition diagrams in this case. We evaluate the effectiveness of the framework using precision and recall measures. The contribution of this paper to the systems modeling domain is two-fold. First, a review and analysis of natural language processing techniques for the automated generation of SysML diagrams are provided. Second, a framework to automatically extract textual relationships tailored for generating a class diagram/block diagram that contains the classes/blocks, their relationships, methods, and attributes is presented.