Volume 70, Issue 9 - Special Issue: AI Systems Engineering / Jürgen Beyerer, Julius Pfrommer, Thomas Usländer

KI-Engineering – translated as AI Systems Engineering – aims at the development of a new engineering practice in the intersection of Systems Engineering and Artificial Intelligence. Its goal is to professionalize the use of AI methods in a systems engineering context. The article defines KI-Engineering and compares it with historical examples of research disciplines that founded engineering disciplines. It furthermore discusses the long-term challenges where further development is needed and which results were already achieved in the context of the Competence Center for KI-Engineering (CC-KING).

The enormous potential of artificial intelligence, especially artificial neural networks, when used for edge computing applications in cars, traffic lights or smart watches, has not yet been fully exploited today. The reasons for this are the computing, energy and memory requirements of modern neural networks, which typically cannot be met by embedded devices. This article provides a detailed summary of today’s challenges and gives a deeper insight into existing solutions that enable neural network performance with modern HW/SW co-design techniques.

The application of artificial-intelligence-(AI)-based methods within the context of complex systems poses new challenges within the product life cycle. The process model for AI systems engineering, PAISE ® , addresses these challenges by combining approaches from the disciplines of systems engineering, software development and data science. The general approach builds on a component-wise development of the overall system including an AI component. This allows domain specific development processes to be parallelized. At the same time, component dependencies are tested within interdisciplinary checkpoints, thus resulting in a refinement of component specifications.

Machine learning (ML) rapidly gains increasing interest due to the continuous improvements in performance. ML is used in many different applications to support human users. The representational power of ML models allows solving difficult tasks, while making them impossible to be understood by humans. This provides room for possible errors and limits the full potential of ML, as it cannot be applied in critical environments. In this paper, we propose employing Explainable AI (xAI) for both model and data set refinement, in order to introduce trust and comprehensibility. Model refinement utilizes xAI for providing insights to inner workings of an ML model, for identifying limitations and for deriving potential improvements. Similarly, xAI is used in data set refinement to detect and resolve problems of the training data.

Artificial intelligence is increasingly penetrating industrial applications as well as areas that affect our daily lives. As a consequence, there is a need for criteria to validate whether the quality of AI applications is sufficient for their intended use. Both in the academic community and societal debate, an agreement has emerged under the term “trustworthiness” as the set of essential quality requirements that should be placed on an AI application. At the same time, the question of how these quality requirements can be operationalized is to a large extent still open. In this paper, we consider trustworthy AI from two perspectives: the product and organizational perspective. For the former, we present an AI-specific risk analysis and outline how verifiable arguments for the trustworthiness of an AI application can be developed. For the second perspective, we explore how an AI management system can be employed to assure the trustworthiness of an organization with respect to its handling of AI. Finally, we argue that in order to achieve AI trustworthiness, coordinated measures from both product and organizational perspectives are required.

Integration of Artificial Intelligence (AI) methods into industrial systems engineering processes is challenging. Despite an increasing body of knowledge on AI techniques and impressive state-of-the-art reports, the application of AI in industrial contexts is only at an early stage. This paper summarizes challenges for AI Systems Engineering. Two examples of AI systems engineering are provided: the TRUMPF Sorting Guide and ABB BatchInsight. Summaries of the projects give insights into the project executions and related challenges. The learnings from these projects also show that increased maturity of AI systems engineering can be expected from increased method competence and adjusted project setups. Here guidelines and best practices for AI systems engineering can support.

Dieffenbacher has developed a completely new software platform for the digitalization of wood-based panel production plants. The name of the Platform is EVORIS. This article explains how smart data processing in production, with the help of artificial intelligence and machine learning, delivers transparency to production processes and helps operators and technologists to produce smarter. Furthermore, experiences in working methods, the development process, AI engineering and, above all, lessons learnt from theory vs. practice are illustrated.