Artificial Intelligence

Aiming to Create Green AI

Aiming to Create Green AI

Putting a focus on AI energy efficiency and minimizing the CO2 footprint of AI-based systems
Marcus Grum ORCID Icon, Maximilian Ambros ORCID Icon, Marcel Rojahn ORCID Icon
Reducing CO2 emissions is one of the most urgent tasks of our time. Simultaneously, artificial intelligence is developing rapidly. However, AI often brings about its own significant CO2 impact. Experimental testing of Green AI strategies is therefore crucial for their long-term success. A management tool can support this process so that both users and managers can make optimal use of AI as a tool.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 18-30 | DOI 10.30844/I4SE.24.6.18
Process Reference Model (PRM) for AI Development in Vehicles

Process Reference Model (PRM) for AI Development in Vehicles

Practical guide to the development of AI functionalities in the automotive industry
Sebastian Grundstein ORCID Icon, Bernhard Burger, Andreas Aichele ORCID Icon
Artificial intelligence is increasingly being integrated into vehicles, but conventional product development processes often do not fully capture the specific requirements of AI projects. In order to meet these requirements, a process reference model (PRM) has been developed specifically for the development of AI functionalities in the automotive industry. This model is intended to support companies in adapting their conventional software development processes more easily to the special features of AI projects.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 96-101
Large Language Models (LLM) in Production

Large Language Models (LLM) in Production

An analysis of the potential for transforming production processes in modern factories
Pius Finkel ORCID Icon, Peter Wurster ORCID Icon, Robin Radler
The rapid development of generative artificial intelligence is opening up new avenues for the manufacturing industry amid a shortage of skilled workers. Large language models can potentially make production processes in medium- sized businesses more efficient. But how exactly is this potential measured? Key areas of application such as communication, training and knowledge management show why a lot depends on employee acceptance.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 48-55 | DOI 10.30844/I4SE.24.6.48
Parameter Optimization for a Brine Injector

Parameter Optimization for a Brine Injector

Development of an AI pipeline using an example from the meat industry
Tim Zeiser ORCID Icon, Theo Lutz ORCID Icon, Corinna Köters ORCID Icon, Maik Schürmeyer, Alexander Prange ORCID Icon
The production of cooked ham involves a number of challenges. In production, cuts of meat are put through in a multi-stage curing and cooking process involving brine. This can lead to fluctuations in quality due to structural defects in the meat. The result: the brine is not optimally absorbed. An AI model trained on historical data intends to solve the problem.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 40-46
Intelligent Shopfloor Assistants

Intelligent Shopfloor Assistants

Increasing productivity through the use of generative AI
Eckart Uhlmann ORCID Icon, Julian Polte ORCID Icon, Christopher Mühlich ORCID Icon, Yassin Elsir
In modern production companies, a heterogeneous IT landscape often complicates day-to-day work. A promising antidote is the use of intelligent agents, which use generative AI for routine tasks and can therefore increase efficiency. Whether these intelligent systems can be successfully integrated into existing networks determines whether the flow of information can be improved and manual effort reduced.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 64-71
Real-time Reactions for Automated Guided Vehicles (AGV)

Real-time Reactions for Automated Guided Vehicles (AGV)

Monitoring and controlling with long latencies
Dominik Augenstein, Lea Basler
The constant advance of digitalization confronts companies with new challenges and opportunities. Immediate data processing is now ubiquitous and the advantages are obvious. However, broadband coverage in Germany is insufficient, which makes it difficult to improve processes. Mathematical approaches and machine learning enable timely optimization and smooth production.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 56-62
Improving Social Media Moderation with Generative Language Models

Improving Social Media Moderation with Generative Language Models

Study on the detection and correction of disinformation
Anton Schegolev, Maximilian Ambros ORCID Icon
Fake news are increasingly dominating the digital world. The question arises: Can modern technologies reverse this trend? The article highlights the potential of the GPT-4o language model for identifying fake news in online comments and news articles and for correcting false information. With impressive accuracy, the model shows how language technology can combat misinformation.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 72-79 | DOI 10.30844/I4SE.24.6.72
Digitization of Raster Drawings with Deep Learning

Digitization of Raster Drawings with Deep Learning

Framework outperforms OCR software in extracting data from mechanical drawings
Xiao Zhao, Marko Weber, Jan Schöffmann, Daniela Oelke ORCID Icon
A new look into the depths of technical drawings: A deep learning framework reads CAD drawings more accurately than ever before, recognizing geometrical dimensioning and tolerancing, dimensions, and every other detail. What used to be tedious manual labor is now carried out by an AI that understands the special features of every line and label. This promising technology not only increases accuracy but also speeds up the processing of drawings considerably. The system thus opens up new avenues for precision in production.
Industry 4.0 Science | Volume 40 | 2024 | Edition 6 | Pages 10-17
AI-Assisted Work Planning

AI-Assisted Work Planning

Extracting expert knowledge from historical data for streamlined efficiency and error mitigation
Jochen Deuse ORCID Icon, Mathias Keil, Nils Killich, Ralph Hensel-Unger
Global competitive pressure is forcing companies to use resources efficiently, especially in high-wage countries. This is further intensified by market and legislative pressure for sustainable products and processes. In the face of digital and ecological change, holistic approaches to optimizing manual work processes are essential. An AI-supported assistance system for work plan creation is intended to remedy this and thus enable more efficient process design.
Industry 4.0 Science | Volume 40 | 2024 | Edition 5 | Pages 74-80 | DOI 10.30844/I4SE.24.5.74
Double Transformation as the Key to Sustainability

Double Transformation as the Key to Sustainability

Methodology for evaluating an AI application in manufacturing companies
Jennifer Link ORCID Icon, Markus Harlacher, Olaf Eisele, Sascha Stowasser
EU regulations demand more intensive and transparent sustainable practices from companies. Industry needs to adapt many processes and products to take charge of this responsibility. Artificial Intelligence (AI) in particular offers innovative potential. Firstly, however, this technology needs to be evaluated focusing on weak AI—market-ready systems that perform specific tasks using algorithms and data-supported models efficiently.
Industry 4.0 Science | Volume 40 | 2024 | Edition 5 | Pages 82-89 | DOI 10.30844/I4SE.24.5.82
1 4 5 6 15