Artificial Intelligence

This article outlines the results of ten expert interviews on the use of machine learning to promote corporate sustainability and then compares them with relevant literature. The study shows that economic factors drive the use of machine learning, the introduction of which is initiated by both top management and specialist departments. However, grounded strategies for implementing machine learning are rarely available and use cases are often based on supervised learning. The environmental impact (the reduction of emissions, for example) outweighs the social impact, though quantification is difficult. Additionally, a lack of trust, expertise, and communication hinders the adoption of machine learning, while some technical challenges regarding data requirements also pose problems.

Software development is fundamental to digital transformation. A good foundation of data is required for developers to tailor software to the needs of the commissioning department. Unfortunately, the data models required for this are incomplete, often created unilaterally by the development department and not embedded in the business context. This makes it difficult for both developers and AI to find the right algorithms. The present approach increases understanding and exchange between the specialist and development departments and offers digital assistance with data modeling as a basis for software development. Furthermore, AI approaches can help to increase the quality and completeness of the data.

Digital twins connect physical and digital systems, furthering efficiency, enabling predictive maintenance, and allowing the production of more customized products. Despite these advantages, challenges such as high costs, data synchronization, and security risks hinder widespread adoption. This article explores the potential of digital twins and examines key barriers to integration and implementation, also considering some industrial applications including additive manufacturing as a relevant use case.

Drone technology and the use of artificial intelligence (AI) offer promising advantages in various sectors, including in inspection. The use of innovative inspection technologies can make inspections more efficient overall. This research project examines various legal and economic aspects of AI-based autonomous drone inspections. It also develops a target process that represents the use of an AI-based drone inspection and controls the use of such inspection technology. In particular, this article focuses on a collaborative approach to this new inspection methodology.

The AI-driven, self-learning digital twin continuously adapts to real system behavior, ensuring an optimal representation of the production process. A comprehensive semantic model serves as the foundation for advanced artificial intelligence (AI) approaches. Insights derived from AI methods are integrated into this model, enhancing the interpretability and explainability of AI systems. Techniques from the field of eXplainable AI (XAI) facilitate the automated description of AI models and their findings, as well as the development of self-explanatory models.

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.