This paper presents a framework to utilize multivariate time series data to automatically identify reoccurring events, e.g., resembling failure patterns in real-world manufacturing data by combining selected data mining techniques. The use case revolves around the auxiliary polymer manufacturing process of drying and feeding plastic granulate to extrusion or injection molding machines. The overall framework presented in this paper includes a comparison of two different approaches towards the identification of unique patterns in the real-world industrial data set. The first approach uses a subsequent heuristic segmentation and clustering approach, the second branch features a collaborative method with a built-in time dependency structure at its core (TICC). Both alternatives have been facilitated by a standard principle component analysis PCA (feature fusion) and a hyperparameter optimization (TPE) approach. The performance of the corresponding approaches was evaluated through established and commonly accepted metrics in the field of (unsupervised) machine learning. The results suggest the existence of several common failure sources (patterns) for the machine. Insights such as these automatically detected events can be harnessed to develop an advanced monitoring method to predict upcoming failures, ultimately reducing unplanned machine downtime in the future.

Imagine the possibility to save a simulation at any time, modify or analyze it, and restart again with exactly the same state. The conceptualization and its concrete manifestation in the implementation OntologySim is demonstrated in this paper. The presented approach of a fully ontology-based simulation can solve current challenges in modeling and simulation in production science. Due to the individualization and customization of products and the resulting increase in complexity of production, a need for flexibly adaptable simulations arises. This need is exemplified in the trend towards Digital Twins and Digital Shadows. Their application to production systems, against the background of an ever increasing speed of change in such systems, is arduous. Moreover, missing understandability and human interpretability of current approaches hinders successful, goal oriented applications. The OntologySim can help solving this challenge by providing the ability to generate truly cyber physical systems, both interlocked with reality and providing a simulation framework. In a nutshell, this paper presents a discrete-event-based open-source simulation using multi-agency and ontology.

Semiconductor manufacturing systems are highly complex due to intricate processes and material flows. Operating these systems efficiently remains a significant challenge, particularly under the growing demands for operational excellence and cost reduction. Current approaches often rely on extensive manual modeling, which slows down production planning and adaptation. To address these challenges, we propose a data-driven methodology for Automatic Simulation Model Generation (ASMG), enhanced by machine learning techniques. This fully automated pipeline extracts and processes production data (lot tracking information and resource states) to generate simulation models without manual intervention. A machine learning technique called equipment emulation captures complex tool behaviors and mitigates issues with noisy or incomplete data. Validation in two real-world semiconductor production environments, covering over 300 days and showing an accuracy within 5–7% for throughput and uptime, demonstrates the method’s ability to produce precise models. By reducing the time and expertise required for model creation, this ASMG method facilitates agile digital twin implementations and enables faster, more responsive production planning.

Based on the fundamental principle of teaching psychology that retentiveness increases if students actively apply learning topics rather than only attend oral or visual presentations, the concept of learning factories becomes more and more popular. Academic education in the field of production science is imparted by means of real-world manufacturing facilities. By applying the manufacturing process of a real product, students or professionals incorporate the learning contents effectively and gain consciousness about their practical implications.Most learning factories are focused on lean manufacturing, lean administration or resource efficiency. As today manufacturing is not only subject to a single factory, but a network of globally distributed production sites, at the wbk Institute of Production Science,currently, a learning factory dealing with the topic of global production is developed. On the one hand, the curriculum of the Learning Factory Global Production (LGP) involves the specifics of local production sites with different location factors, such as different degrees of automation, cost structures and qualification levels, and their effects on the reconfigurability of the production systems. On the other hand, the interaction of the production sites in a globally distributed production network and the strategic configuration of the network are also subject to the curriculum.The manufacturing processes are exemplified by the assembly of an automotive e-motor with transmission in the learning factory on global production. The learning factory is realized in cooperation with the Robert Bosch GmbH