GenAI-Enhanced Systematic Review: Data-Driven Decision Support Systems in Production Ramp-Up Management

Institute

Institut für Werkzeugmaschinen und Betriebswissenschaften

Type

Bachelor's Thesis / Semester Thesis /

Content

theoretical /  

Description

Motivation

In today’s competitive and innovation-driven markets, companies face increasingly shorter product life cycles (PLCs). Products are being developed, launched, and replaced at a faster pace than ever before. This trend poses new challenges for production ramp-up management, where organizations must quickly and efficiently scale up manufacturing processes while maintaining quality and cost-effectiveness. To address these challenges, data-driven decision support systems (DDSS) are gaining importance as tools to enable better, faster, and evidence-based decisions during ramp-up.

However, while the relevance of DDSS in production management is widely recognized, a comprehensive overview of the current state of science and practice in this field is still lacking. Furthermore, the role of grey literature and practice-driven insights (e.g., from consulting firms or international organizations) is underexplored, despite their practical relevance.

Objective

The aim of this thesis is to provide a systematic literature review on the state of science and practice regarding data-driven decision support systems in production ramp-up management, conducted according to the PRISMA framework.

The work will consist of three key parts:

• Exploratory research and market analysis on how product life cycles have changed over time, with a focus on shorter innovation cycles and their implications for production.
• Systematic literature review, combining academic sources (Scopus, Web of Science, etc.) and grey literature (reports from consultant firms, international organizations, …), supported by the ASReview tool for screening.
• Integration of generative AI tools (e.g., Deep Research, ChatGPT-based approaches) into the literature search process, to expand coverage beyond traditional databases and include relevant grey literature.

The outcome will be a structured and critical overview of existing research and practice, highlighting current gaps, challenges, and opportunities for the application of DDSS in production ramp-up management.

Requirements

ualifications

• Some exposure or a strong interest in production engineering or similar fields
• Interest in the application of Active Learning and GenAI for systematic literature reviews
• Familiar with Latex or willingness to learn it.
• Solid English communication and writing skills. German is beneficial.

Why iwb?

• Personal and thematic supervision
• Professional perspective at an excellent institute of the TUM

Contact

M.Sc. Julian Stang
Department Production Management and Logistics
Mail: julian.stang@iwb.tum.de
Tel.: +49 89 - 289 15549

Tags

iwbStang

Possible start

sofort

Contact

Julian Stang
Phone: +49 (89) 289 - 155 49
julian.stangiwb.tum.de

Announcement