Künstliche Intelligenz

Engineers are often uncertain about the application of machine learning (ML) due to the amount of different machine learning methods and the complexity of modeling. Thus, the use of ML applications in manufacturing companies remains behind the technical possibilities. This paper presents an intuitive ML guideline for engineers to reduce this uncertainty. The guideline comprises a process model with AI-based solutions to common problems of product development and production. An industrial example is used to demonstrate the functionality and the possibilities of the guide.

Industry 4.0 is a political concept intended to help German manufacturing companies to exploit data potential. Today, maintenance activities are not proactive by current approaches. Decision support systems based on artificial intelligence allow a change here by even foresighted machine maintenance. However, AI’s opaque decision-making process represents a barrier for users, which endangers its effectiveness. Therefore, this article sheds light on both: the technological as well as social factor for the adoption of AI in Industry 4.0.

We are currently experiencing rapid transformation in technologies and society. Due to the convergence of various megatrends, these changes have considerable impacts on everyday life. Our study aims to identify relevant strategies for the digital future of a macro-region (Tyrol, South Tyrol and Veneto). The study conducts semi-structured interviews with representatives of companies, universities and local governments, using the approach of a triple helix model. Based on the empirical analysis, we develop an action plan for the digital transformation of the macro-region.

Manufacturing companies must work economically while delivering quality - in some industries with a zero-defect tolerance. Quality control often is carried out manually and with a time delay, thus errors can only be corrected at a late stage. Using artificial intelligence (AI), visual quality control can be automated, carried out in real time and integrated into the production process - making it more accurate, efficient and cost-effective. A case example shows the advantages of tackling AI issues in interdisciplinary teams with partners.

Artificial intelligence (AI) and self-learning systems have immense economic potential and are a driving force for digitalisation. Artificial Intelligence is radically changing value chains, business models, and employment in industry. Data-driven services are added to traditional products in almost all industries. Integrating Artificial Intelligence in products and services as well as using data from the production process provides opportunities for new business models in an increasing competitive international environment.

Due to competitive pressure pharmaceutical companies are also driven to increase the efficiency of their processes. In this paper an approach for the predictive detection of malfunctions of filling systems for powdery pharmaceutical products using machine learning is presented. The focus is on the prediction of filling deviations with recurrent neural networks, with the objective to detect a drift in the process stability to intervene accordingly.

Due to the advancing digitalization of business sectors and increasing competitive pressures, industrial companies are forced to promote their own digital transformation to sustain on the market. Here, the literature regards the CFO as a key corporate function to induct digitization initiatives within organizations. The blockchain technology, due to its features of transparency, immutability and cryptography combined with its ability to coordinate data flows of e. g. the IoT or AI, constitutes a suitable instrument for the CFO to meet the requirements of the Industry 4.0. The results are improvements of business processes in regard to efficiency and automation, a relocation of the CFO’s strategic role, improvements of CFO-relevant KPIs through integrating machines into payment networks as well as the emergence of integrated business ecosystems facilitating new forms of inter-organizational collaboration.

Machine learning is the key technology of almost every instance of modern Artificial Intelligence. Enormous datasets are produced in digitized industrial processes and in the Internet of Things, which can well be exploited by learning in deep artificial neural networks. Standard machine learning algorithms require these datasets to be centralized before learning a model. Several good reasons - ranging from data privacy over latency to economic efficiency - favor learning at the edge so that reasoning is fast and no local data is transferred. The article shows how decentralized learning works and how to evaluate it. Moreover, we point to special resource-efficient learning algorithms and discuss small remaining risks of data reconstruction.