This paper presents a novel design of multi-agent system framework that applies large language model (LLM) to automate the parametrization process simulations in digital twins. We propose includes four types agents: observation, reasoning, decision and summarization. By enabling dynamic interaction between LLM agents simulation model, developed can automatically explore use heuristic reasoning determine set parameters control achieve an objective. The proposed approach enhances by infusing...

The domain of industrial automation faces challenges such as shortened product life cycles, a shortage skilled labor, and increasing complexity. Addressing these issues necessitates innovative solutions, one which is the Digital Twin — virtual counterpart physical asset. Central to quality data it harnesses. While current Twins draw primarily from their corresponding assets, future interconnected production environments promise an influx additional external devices. However, remains...

Behavior models in the Digital Twin are relevant to many use cases such as digital product development, virtual system optimization or commissioning. However, behavior structured literature according different criteria and levels, which complicates selection of correct properties for specific cases. One criterion discussed very differently is modeling depth models. This paper presents approaches structure from introduces a new concept with focus on depth. These levels depths, well...

Die Produktion von Wasserstoff und Folgeprodukten unter Nutzung erneuerbarer Energien gilt als großer Hoffnungsträger für das Erreichen einer Klimaneutralität. Im Rahmen des Leitprojekts H2Mare soll der Betrieb Offshore-Plattform Power-to-X-Produktionsprozesse erforscht erprobt werden. vorliegenden Beitrag wird zunächst Projektkonzept modularen skizziert. Anschließend werden mit dem Digitalen Zwilling System zur optimalen Betriebsführung zwei Forschungsansätze präsentiert, die...

Industrial automation is driven by trends such as autonomy, intelligence and networking. Increasing energy demands, scarce resources shorter product lifecycles pose challenges to production systems interoperability, flexibility extensibility. The concept of the Digital Twin, acting a virtual representation system, can address these challenges. This paper presents that realizes dynamic scheduling partial function Twin using Asset Administration Shell service-oriented architecture. authors...

Industrial automation is becoming increasingly networked, intelligent and autonomous. Digital Twins, which serve as virtual representations, are a key technology in this context. The Twin of modular production system contains many different models that mostly created for specific applications fulfil requirements. In particular, simulation the development phase can be used operational such prediction or operation-parallel simulation. Due to high heterogeneity model landscape context system,...

Behavior models are central components of Digital Twins that enable the simulation assets. Two typical requirements for running behavior time and accuracy, which influenced by solver used step size at run. In this paper, existing system solvers with different sizes investigated their impact on accuracy. For purpose, a vacuum gripping compared measured values. The results show use case specific selection may be necessary.

The trend in industrial automation is towards networking, intelligence and autonomy. Digital Twins, which serve as virtual representations, are becoming increasingly important this context. Twin of a modular production system contains many different models that mostly created for specific applications fulfil requirements. Especially simulation models, the development phase, can be used during operational phase such prognosis or operation-parallel simulation. Due to high heterogeneity model...

Many decision-making approaches rely on the exploration of solution spaces with regards to specified criteria. However, in complex environments, brute-force strategies are usually not feasible. As an alternative, we propose combination task's vertical sub-division into layers representing different sequentially interdependent sub-problems paramount problem and a horizontal self-sustained sub-spaces. In this paper, present universal methodology for intelligent derive use-case specific example...

The concept of the Digital Twin, which in context this paper is virtual representation a production system or its components, can be used as "digital playground" to master increasing complexity these assets. One central subcomponents Twin are behavior models that enable benefits over entire machine life cycle. However, creation, adaption and use throughout cycle very time-consuming, why approaches improve cost-benefit ratio needed. Furthermore, there lack specific cases illustrate...

The ongoing digitization of the industrial sector has reached a pivotal juncture with emergence Digital Twins, offering digital representation physical assets and processes. One key aspect those representations are simulation models, enabling deeper insight in current state its characteristics. This paper asserts that next evolutionary step this journey involves integration intelligent linkages between diverse models within Twin framework. Crucially, for to be scalable cost-effective...

Wireless communication between road users is essential for environmental perception, reasoning, and mission planning to enable fully autonomous vehicles, thus improve safety transport efficiency. To collaborative driving, the concept of vehicle-to-Everything (V2X) has long been introduced industry. Within last two decades, several standards have developed based on IEEE 802.11p cellular standards, namely Dedicated Short-Range Communication (DSRC), Intelligent Transportation System G5...