Recycling is becoming increasingly important, due to growing resource shortages and the need of a reduction in CO2 emission. Automated disassembly is essential for accelerating recycling processes and optimizing the extraction of valuable materials. To achieve an automated disassembly, it is crucial for an automated disassembly system to know the type of connections between components in an assembly. We present a method for extracting connections from 3D CAD models of assemblies. Our approach identifies connections through collision detection and populates a knowledge graph with the acquired data. This knowledge graph serves as foundation for software systems to assess product recyclability or to optimize recycling processes.

Large language models (LLMs) have shown effectiveness in various natural language understanding (NLU) tasks. However, they face notable limitations like hallucinations, a lack of contextual knowledge, and outdated or incomplete knowledge when applied across knowledge-intensive domains such as scientific research, biomedical sciences, finance, law, and others. These challenges commonly arise from the scarcity and under-representation of domain-specific data during the training and model alignment phases. Furthermore, Large Language Models (LLMs) struggle to provide nuanced expertise, as their internal knowledge remains static and generalized, hindering their ability to reason accurately or deliver context-aware results in specialized tasks. This survey investigates the integration of external knowledge into LLMs to address these limitations. The focus is on decoder-based LLMs, that is, autoregressive models that generate text sequentially. By investigating parametric and non-parametric approaches, this work discusses methods to enhance model reasoning capabilities, factual accuracy, and adaptability for domain-specific and knowledge-intensive tasks. Additionally, it highlights the potential of integrating external knowledge to improve explainability and ensure more trustworthy outputs. This survey supports software developers and natural language processing (NLP) researchers in designing NLU systems for specialized domains by leveraging pre-trained LLMs. Additionally, the work provides a foundation for advancing LLM-based NLU systems with insights into future research areas.

Early phases of space missions rely on diverse engineering tools that often share similar data structures and domains but lack interoperability. As a result, data exchange between tools typically requires manual effort or custom-built converters, limiting efficient collaboration and reuse of design data. This paper proposes the concept of a Semantic Adapter to enable flexible and automated data exchange between heterogeneous engineering tools without tool-specific adaptions. The approach combines OpenAPI, as a standardized way to access and exchange tool data, with a mapping and model transformation algorithm that aligns and converts data between different tool-specific models. The concept was demonstrated and evaluated in a case study involving two concurrent engineering centers collaborating on a joint space mission study. The evaluation shows that the Semantic Adapter enables automated data retrieval and transformation, demonstrating the general feasibility of combining API specifications and model transformations for engineering data exchange. However, results also indicate that automatically writing transformed data to target tools via OpenAPI remains a challenge, especially when dealing with complex, dynamically typed models. The paper concludes by discussing limitations and directions for future work.

In times of global crises, the resilience of production chains is becoming increasingly important. If a supply chain is interrupted, a cost-effective solution must be established quickly. In the context of Industry 4.0, the concept of smart manufacturing offers a solution for fast and automated decision-making in production planning. The core idea of smart manufacturing is the digitalization of the product life cycle and the linking of individual phases of this cycle. Computer Aided Process Planning (CAPP) plays an important role as the connecting element between design and manufacturing. An important prerequisite for CAPP is the automated analysis of 3D models of components. The aim of this work is the development of an automatic feature recognition (AFR) -method to recognize geometric manufacturing features and their properties from 3D-models and then store them in a knowledge base. In that way, the result of the design can be automatically analysed and compared with manufacturing information afterwards in order to achieve an automated process planning. Geometric and topological information of a 3D model (STEP-AP242 format) generated by CAD systems is extracted by a Python-script developed and stored in an ontology-based knowledge base. The extracted product data is analysed using a Python-script to identify manufacturing features. To provide a comprehensive extensibility of the model, geometric features are defined according to a layered and hierarchical structure.

The reliability of well-performing production processes not only depends on internal but also on external factors in the upstream supply chain. Therefore, companies require fast and reliable information exchange with cooperating organizations. We aim to support the industry in improving their communication methods and, therefore, have conducted a survey to capture the current state and needs in this area — addressing inter- instead of the usually surveyed intra-organizational degree of digitalization. In this paper, we outline the main outcomes of our survey. We received 135 evaluable questionnaires from manufacturing companies based in Germany, predominantly from small and medium-sized companies. Based on the responses, we detected that the use of modern methods correlates with the company size. Furthermore, we showed that only a few companies are completely satisfied with their current methods for inter-organizational information exchange. The greatest potential for improvement is seen in standardization and the increase of required resources.

By estimating manufacturing costs and times at an early design stage, design of a part and production planning can be improved to significantly reduce product costs. Therefore, a concept for automated estimation of costs and times based on similarity analysis is introduced. This concept is based on a semantic and machine-interpretable representation of part geometries, manufacturing processes and machine capabilities stored in a knowledge graph and uses a semantic distance combined with a numerical distance to compare a new part design with already produced parts. With combined similarity measures and information on manufacturing process steps stored in the knowledge graph, it is possible to estimate the expected manufacturing costs and times.

Abstract The reliability of well‐performing production processes not only depends on internal but also on external factors in the upstream supply chain. Therefore, companies require fast and reliable information exchange with cooperating organisations. Since existing researches usually put focus on reviewing intra‐organisational solutions, the authors have conducted a survey to capture the current state and needs regarding the inter‐organisational information exchange between German companies. The main outcomes of the authors’ survey are outlined. In a first step, the current status of digitalisation in the companies is analysed. The authors have found that the use and implementation of modern methods correlates positively with the company size. Taking a look on the current methods for inter‐organisational information exchange in a second step, it is seen that only a few companies are completely satisfied with their current methods. Companies see the greatest potential for the improvement of information exchange in standardisation and the increase of required resources. This indicates that companies would be best supported by the development of solutions that can be implemented easily and help to form the heterogeneous landscape of data exchange strategies towards a structured, standardised way.

The continuing drive towards digitization in manufacturing leads to an increasing number of digital twins for monitoring and controlling all kinds of processes. While these capture crucial data of all individual steps and allow for analysis and optimization, more often than not the underlying models are confined to individual systems or organizations. This hinders data exchange, especially across institutional borders and thus represents an important barrier for economic success. Similar challenges in the scientific community led to the emergence of the FAIR principles (Findable, Accessible, Interoperable, and Reusable) as guidelines towards a sustainable data landscape. Despite the growing presence within academia, their transfer to industry has not yet received similar attention. We argue that the existing efforts and experiences in science can be exploited to address current data management challenges in industry as well. An improved data exchange within organizations and beyond can not just lower costs, but also opens up new opportunities ranging from discovering new suppliers or partners to improving existing value chains.

This paper presents OntoHuman, a toolchain for involving humans in a process of automatic information extraction and ontology enhancement. Document Semantic Annotation Tool (DSAT) [13], a user interface of OntoHuman, offers an automatic function to extract information in the form of key-value-unit tuples from PDF documents based on ontologies. Additionally, it allows users to provide feedback to improve the ontologies used. Although the information extraction can be improved with the ontology, our use cases were previously limited to an area of space engineering. OntoHuman now tackles this shortcoming by allowing users to upload their customized ontologies. This entends usages to various domains and enables this shareable knowledge to be used cooperatively. Then we display the ontologies in a node-link representation so they are easier to understand. Another major improvement in OntoHuman is the graph data points extraction, which is still missing in the existing information extraction tools. The application of OntoHuman can be used for documents related to any engineering domain and makes the work with ontologies intuitive and collaborative for users.

The success of a concurrent engineering study hinges on the ability of the design team to develop a concept conforming to the predefined mission requirements and constraints. A key facilitator of this is the usage of a shared baseline for defining and modifying the design components and parameters. At DLR’s Concurrent Engineering Facility (CEF) this has been achieved through the use of the in-house software package Virtual Satellite since 2011. The progression of the design over the study period can be visualised by tracking and plotting the updates and commits of changes to the model made by the study team. In this paper we present a visualisation of the total launch mass and the mass breakdown by subsystem for one space mission design study as well as a comparative statistic of a subset of Concurrent Engineering studies from the CEF archive.

The demand for efficient and digital systems for supporting the decision making during the design of a product is a key issue in manufacturing companies. Decisions made during the development and design of a product have a strong impact on the costs and delivery times of a product. Hence, a digital system which supports the engineer during and after the development process with information about the manufacturability of the product can reduce the production costs and times. In order to be able to evaluate the manufacturing capabilities at manufacturing process and machine level, there is a need to represent them in a digital way. Digital knowledge bases like taxonomies and ontologies provide the possibility for a representation of manufacturing resources. The state of the art shows different approaches for the use of ontologies in the domain of subtractive manufacturing processes as well as additive manufacturing (AM) processes. The goal of this work is the semantical representation of manufacturing technology capabilities with focus on AMmachines and processes. In this paper we introduce taxonomies of Manufacturing Features and Manufacturing Restrictions which were developed in accordance with current standards. To enrich the taxonomies with information, it was enhanced by relations between different manufacturing related entities in a knowledge graph. If manufacturing processes and machines can be digitally mapped, described and linked to the geometric information of a product together with information on the current performance of the company/network, bottlenecks and delivery delays during the manufacturing of parts can be avoided.

To describe modeling objects in Model-Based Systems Engineering (MBSE) tools, physical properties of these objects are often provided only in data sheets, which are not truly machine-readable. Previously, we proposed a product data hub to exchange spacecraft product information between manufacturers and various MBSE tools. However, issues with heterogeneous structures and semantics of information, such as differences in data format and vocabularies, persist. Using ontologies to maintain product descriptions can mitigate the heterogeneity problem by providing semantic descriptions and supporting different vocabularies for a single concept. To automatically and semantically obtain information from documents that contain tables, lists, and text, we developed an ontology-based information extraction tool. We present how to use the Data Sheets Annotation Tool (DSAT) for, either manually or automatically, extracting information from data sheets, and populating a database with the obtained data. Particularly, we emphasize on the usage of DSAT as a user interface for improving ontologies, which, in turn, are used for a (better) information extraction from the data sheets. Although DSAT is initially created for supporting collaborative systems engineering, it is not limited to the domain of spacecraft design. It can also be applied to other domains, where information needs to be extracted from a multitude of heterogeneous sources.

In engineering projects involving various parts from global suppliers, one common task is to determine which parts are best suited for the project requirements. Information about specific parts' characteristics is published in so called data sheets. However, these data sheets are oftentimes only published in textual form, e.g., as a PDF. Hence, they have to be transformed into a machine-interpretable format. This transformation process still requires a lot of manual intervention and is prone to errors. Automated approaches make use of ontologies to capture the given domain and thus improve automated information extraction from the data sheets. However, ontologies rely solely on experiences and perspectives of their creators at the time of creation and cannot accumulate knowledge over time on their own. This paper presents ConTrOn -- Continuously Trained Ontology -- a system that automatically augments ontologies. ConTrOn tackles terminology problems by combining the knowledge extracted from data sheets with an ontology created by domain experts and external knowledge bases such as WordNet and Wikidata. To demonstrate how the enriched ontology can improve the information extraction process, we selected data sheets from spacecraft development as a use case. The evaluation results show that the amount of information extracted from data sheets based on ontologies is significantly increased after the ontology enrichment.

In this paper, we introduce a system to collect product information from manufacturers and make it available in tools that are used for concurrent design of spacecraft. The planning of a spacecraft needs experts from different disciplines, like propulsion, power, and thermal. Since these different disciplines rely on each other there is a high need for communication between them, which is often realized by a Model-Based Systems Engineering (MBSE) process and corresponding tools. We show by comparison that the product information provided by manufacturers often does not match the information needed by MBSE tools on a syntactic or semantic level. The information from manufacturers is also currently not available in machine-readable formats. Afterwards, we present a prototype of a system that makes product information from manufacturers directly available in MBSE tools, in a machine-readable way.

A lot of different parties have to communicate and exchange data with each other during the lifecycle of a spacecraft. One example we are looking into is the usage of information from manufacturers in CE studies during the planning phase of a spacecraft. Currently, information from manufacturers is usually offered as a PDF file that describes the technical features of a component. This information must then be entered manually in an MBSE tool by an engineer. That, and finding a fitting component for the mission requirements in the first place, costs time. It also is error prone due to typing mistakes for example. How about a system where an engineer can place a request and get a list of fitting components from different manufacturers - maybe even directly connected to the MBSE tool? To realize such a system, it is necessary that all manufacturers describe their products in a uniform and comparable way. Electronic Data Sheets (EDS) can be a way to realize such a uniform description - not only for the described use case but for many more. A uniform automatic exchange of information about spacecraft components is also relevant in other (also depends on?) phases of the lifecycle of a spacecraft, for example when testing manufactured components. For testing, a different view on the component is relevant. While during planning mass budgets are calculated and compared, for testing it is relevant to have detailed information about interfaces, protocols, and commands. Not only are different views relevant for different phases of the lifecycle but different categories of components have also different sets of relevant parameters. Frequencies for example are interesting for antennas but rather not for batteries. So, there will be neither one EDS that contains the information for one component in every phase of the lifecycle of a spacecraft nor one EDS format that fits all components categories at the same time. Still, for automated communication it is necessary to develop standards for the description of components - it just might not be one standard but a set of standards with a common vocabulary. To ensure the semantic compatibility between different EDS formats we think that ontologies can help. For example, one ontology can describe the semantics of a mechanical Interface Control Document (ICD) and another ontology can describe the semantics of an electrical ICD. But both ontologies can share common parts, in this example the description of the pins of an interface. In software engineering it became common to develop rather small applications that are linked together instead of a huge one that covers all use cases. We think that a similar approach also makes sense for documents and information exchange - to have small documents but a common language that enables different parties to talk with each other without having to understand each other’s domains fully. This concept also encourages the knowledge sharing and reusing the existing ontology.

Professionals of many disciplines are involved in a spacecraft mission. They all use different software tools that are tailored to their tasks and they share data in various ways among themselves. These data sharing activities form a network, which, given modern software engineering practices, offers a lot of opportunities for improvement: simplify data source discoverability, automate previously manual data sharing activities, and better make use available data sources. To simplify data source discoverability, we propose a digital platform with a serviceoriented architecture. Such an architecture also helps to better make use of available data sources. Additionally, we present our projects that automate previously manual data sharing activities and that make better use of available data sources. With the development of the digital platform we aim at providing a significant reduction in resource expenditure, especially time expenditure, for spacecraft missions.