Dirk Helm
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Dirk Helm has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
- Lukas Morand
Fraunhofer IWM, Freiburg, Germany
12 shared publications Peter Haupt
5 shared publicationsAlexander Butz
Fraunhofer Institute for Mechanics of Materials IWM
4 shared publications- Yoav Nahshon
Materials Informatics, Fraunhofer Institute for Mechanics of Materials IWM,Freiburg im Breisgau,Germany
4 shared publications Maria Baiker
Fraunhofer Institute for Mechanics of Materials IWM, 79108 Freiburg, Germany
3 shared publications- Matthias Büschelberger
Materials Informatics, Fraunhofer Institute for Mechanics of Materials IWM,Freiburg im Breisgau,Germany
3 shared publications
Latest Publications
- Open Access
- 5 September 2026
- Published by Elsevier in Mechanics Research Communications
- Vol. 158
An integrated approach for linking materials science and engineering, digitalization, and artificial intelligence enabled by semantic technologies
- 5 September 2026
- Published by Elsevier in Mechanics Research Communications
- Vol. 158
Open AccessAn integrated approach for linking materials science and engineering, digitalization, and artificial intelligence enabled by semantic technologies
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Digital Products Based on Large Language Models for the Exploration of Graph-Databases in Materials Science and Manufacturing
Semantic technologies are gaining traction in materials science and manufacturing. Specifically, the integration of graph databases with ontologies facilitates the harmonization of typically heterogeneous materials and process data, as well as the representation of complex workflows in the field (e.g., processing experimental and simulation data or transferring and tracking data along process chains). This approach enables previously inaccessible data for scientists and engineers to be made available in a FAIR (findable, accessible, interoperable, reusable) manner. On this basis, both science and industry, anticipate a significant boost in materials and process innovation, leading to a more resilient and sustainable production. Nevertheless, one of the main challenges in making semantic technologies usable for engineers is enabling navigation and exploration of the typically complex and flexible graph-based data structures. This work presents two approaches for data exploration in graph-databases using large language models (LLMs), namely LLM-CypherGen and SPARQL-Agent, and their application in two digital products developed within the EU research project DiMAT demonstrated across different use cases in materials science and manufacturing.
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Digital Products Based on Large Language Models for the Exploration of Graph-Databases in Materials Science and Manufacturing
Semantic technologies are gaining traction in materials science and manufacturing. Specifically, the integration of graph databases with ontologies facilitates the harmonization of typically heterogeneous materials and process data, as well as the representation of complex workflows in the field (e.g., processing experimental and simulation data or transferring and tracking data along process chains). This approach enables previously inaccessible data for scientists and engineers to be made available in a FAIR (findable, accessible, interoperable, reusable) manner. On this basis, both science and industry, anticipate a significant boost in materials and process innovation, leading to a more resilient and sustainable production. Nevertheless, one of the main challenges in making semantic technologies usable for engineers is enabling navigation and exploration of the typically complex and flexible graph-based data structures. This work presents two approaches for data exploration in graph-databases using large language models (LLMs), namely LLM-CypherGen and SPARQL-Agent, and their application in two digital products developed within the EU research project DiMAT demonstrated across different use cases in materials science and manufacturing.
- Open Access
- 26 February 2025
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (8)
StahlDigital: Ontology‐Based Workflows for the Steel Industry
The innovative strength of the steel industry is based on the mastery of microstructure–property relationships. Digital workflows can largely contribute to this aim by making the complexity of workflows reproducible and their execution user independent. In this work, the tools and workflows developed in the project StahlDigital as part of the German MaterialDigital initiative are presented and application examples are provided. A steel ontology builds the foundation for data collection and storage as well as for the semantic description of experimental and simulation data processing workflows. A dataspace powered by the Dataspace Management System (DSMS) digitally represents such workflows and manages data along them in a Findable, Accessible, Interoperable, Reusable manner aiming to derive new knowledge. Experimental data processed via DSMS can be further evaluated and used as input for simulation workflows. The simulations included in such workflows are run by the workflow system pyiron, which has been semantically extended in StahlDigital for this purpose.
- 26 February 2025
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (8)
Open AccessStahlDigital: Ontology‐Based Workflows for the Steel Industry
The innovative strength of the steel industry is based on the mastery of microstructure–property relationships. Digital workflows can largely contribute to this aim by making the complexity of workflows reproducible and their execution user independent. In this work, the tools and workflows developed in the project StahlDigital as part of the German MaterialDigital initiative are presented and application examples are provided. A steel ontology builds the foundation for data collection and storage as well as for the semantic description of experimental and simulation data processing workflows. A dataspace powered by the Dataspace Management System (DSMS) digitally represents such workflows and manages data along them in a Findable, Accessible, Interoperable, Reusable manner aiming to derive new knowledge. Experimental data processed via DSMS can be further evaluated and used as input for simulation workflows. The simulations included in such workflows are run by the workflow system pyiron, which has been semantically extended in StahlDigital for this purpose.
- Open Access
- 18 December 2024
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (8)
Semantic Orchestration and Exploitation of Material Data: A Dataspace Solution Demonstrated on Steel and Copper Applications
In materials science and manufacturing, vast amounts of heterogeneous data (e.g., measurement and simulation logs, process data, publications) serve as the bedrock of valuable knowledge for various engineering applications. However, efficiently storing and managing this diverse data pose challenges due to limited standardization and integration across different organizational units. Addressing these challenges is essential to fully unlock the potential of data‐driven approaches. This article introduces a novel, comprehensive semantic methodology tailored to materials engineering and realized as a technology stack named Dataspace Management System (DSMS), which powers dataspace solutions that leverage the knowledge encoded in heterogeneous data sources to support data‐driven insights and to derive new knowledge. At its core, DSMS offers a distinctive knowledge management approach tuned to meet the specific requirements of the materials science and manufacturing domain, all while adhering to the FAIR (findable, accessible, interoperable, reusable) principles. DSMS provides functionalities for data integration, linkage, exploration, visualization, processing, data sharing, and services (e.g., consulting) to support engineers in decision‐making, design, and optimization. An architectural overview is presented, outlining core concepts and their technological implementation. In addition, the applicability of these concepts to common data processing tasks is demonstrated through use cases from the StahlDigital and KupferDigital research projects within Germany's MaterialDigital initiative.
- 18 December 2024
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (8)
Open AccessSemantic Orchestration and Exploitation of Material Data: A Dataspace Solution Demonstrated on Steel and Copper Applications
In materials science and manufacturing, vast amounts of heterogeneous data (e.g., measurement and simulation logs, process data, publications) serve as the bedrock of valuable knowledge for various engineering applications. However, efficiently storing and managing this diverse data pose challenges due to limited standardization and integration across different organizational units. Addressing these challenges is essential to fully unlock the potential of data‐driven approaches. This article introduces a novel, comprehensive semantic methodology tailored to materials engineering and realized as a technology stack named Dataspace Management System (DSMS), which powers dataspace solutions that leverage the knowledge encoded in heterogeneous data sources to support data‐driven insights and to derive new knowledge. At its core, DSMS offers a distinctive knowledge management approach tuned to meet the specific requirements of the materials science and manufacturing domain, all while adhering to the FAIR (findable, accessible, interoperable, reusable) principles. DSMS provides functionalities for data integration, linkage, exploration, visualization, processing, data sharing, and services (e.g., consulting) to support engineers in decision‐making, design, and optimization. An architectural overview is presented, outlining core concepts and their technological implementation. In addition, the applicability of these concepts to common data processing tasks is demonstrated through use cases from the StahlDigital and KupferDigital research projects within Germany's MaterialDigital initiative.
- Open Access
- 12 February 2024
- Published by Springer Nature in Computational Mechanics
- Vol. 74 (2) , 447-466
Optimizing machine learning yield functions using query-by-committee for support vector classification with a dynamic stopping criterion
In the field of materials engineering, the accurate prediction of material behavior under various loading conditions is crucial. Machine Learning (ML) methods have emerged as promising tools for generating constitutive models straight from data, capable of describing complex material behavior in a more flexible way than classical constitutive models. Yield functions, which serve as foundation of constitutive models for plasticity, can be properly described in a data-oriented manner using ML methods. However, the quality of these descriptions heavily relies on the availability of sufficient high-quality and representative training data that needs to be generated by fundamental numerical simulations, experiments, or a combination of both. The present paper addresses the issue of data selection, by introducing an active learning approach for Support Vector Classification (SVC) and its application in training an ML yield function with suitable data. In this regard, the Query-By-Committee (QBC) algorithm was employed, guiding the selection of new training data points in regions of the feature space where a committee of models shows significant disagreement. This approach resulted in a marked reduction in the variance of model predictions throughout the active learning process. It was also shown that the rate of decrease in the variance went along with an increase in the quality of the trained model, quantified by the Matthews Correlation Coefficient (MCC). This demonstrated the effectiveness of the approach and offered us the possibility to define a dynamic stopping criterion based on the variance in the committee results.
- 12 February 2024
- Published by Springer Nature in Computational Mechanics
- Vol. 74 (2) , 447-466
Open AccessOptimizing machine learning yield functions using query-by-committee for support vector classification with a dynamic stopping criterion
In the field of materials engineering, the accurate prediction of material behavior under various loading conditions is crucial. Machine Learning (ML) methods have emerged as promising tools for generating constitutive models straight from data, capable of describing complex material behavior in a more flexible way than classical constitutive models. Yield functions, which serve as foundation of constitutive models for plasticity, can be properly described in a data-oriented manner using ML methods. However, the quality of these descriptions heavily relies on the availability of sufficient high-quality and representative training data that needs to be generated by fundamental numerical simulations, experiments, or a combination of both. The present paper addresses the issue of data selection, by introducing an active learning approach for Support Vector Classification (SVC) and its application in training an ML yield function with suitable data. In this regard, the Query-By-Committee (QBC) algorithm was employed, guiding the selection of new training data points in regions of the feature space where a committee of models shows significant disagreement. This approach resulted in a marked reduction in the variance of model predictions throughout the active learning process. It was also shown that the rate of decrease in the variance went along with an increase in the quality of the trained model, quantified by the Matthews Correlation Coefficient (MCC). This demonstrated the effectiveness of the approach and offered us the possibility to define a dynamic stopping criterion based on the variance in the committee results.
- Top Cited PapersOpen Access
- 17 October 2023
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 31 (2) , 1097-1127
Neural Networks for Constitutive Modeling: From Universal Function Approximators to Advanced Models and the Integration of Physics
Analyzing and modeling the constitutive behavior of materials is a core area in materials sciences and a prerequisite for conducting numerical simulations in which the material behavior plays a central role. Constitutive models have been developed since the beginning of the 19th century and are still under constant development. Besides physics-motivated and phenomenological models, during the last decades, the field of constitutive modeling was enriched by the development of machine learning-based constitutive models, especially by using neural networks. The latter is the focus of the present review paper, which aims to give an overview of neural networks-based constitutive models from a methodical perspective. The review summarizes and compares numerous conceptually different neural networks-based approaches for constitutive modeling including neural networks used as universal function approximators, advanced neural network models and neural network approaches with integrated physical knowledge. The upcoming of these methods is in-turn closely related to advances in the area of computer sciences, what further adds a chronological aspect to this review. We conclude the review paper with important challenges in the field of learning constitutive relations that need to be tackled in the near future.
- 17 October 2023
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 31 (2) , 1097-1127
Top Cited PapersOpen AccessNeural Networks for Constitutive Modeling: From Universal Function Approximators to Advanced Models and the Integration of Physics
Analyzing and modeling the constitutive behavior of materials is a core area in materials sciences and a prerequisite for conducting numerical simulations in which the material behavior plays a central role. Constitutive models have been developed since the beginning of the 19th century and are still under constant development. Besides physics-motivated and phenomenological models, during the last decades, the field of constitutive modeling was enriched by the development of machine learning-based constitutive models, especially by using neural networks. The latter is the focus of the present review paper, which aims to give an overview of neural networks-based constitutive models from a methodical perspective. The review summarizes and compares numerous conceptually different neural networks-based approaches for constitutive modeling including neural networks used as universal function approximators, advanced neural network models and neural network approaches with integrated physical knowledge. The upcoming of these methods is in-turn closely related to advances in the area of computer sciences, what further adds a chronological aspect to this review. We conclude the review paper with important challenges in the field of learning constitutive relations that need to be tackled in the near future.
- Open Access
- 26 May 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (4) , 1887-1903
A multi-task learning-based optimization approach for finding diverse sets of microstructures with desired properties
Optimization along the chain processing-structure-properties-performance is one of the core objectives in data-driven materials science. In this sense, processes are supposed to manufacture workpieces with targeted material microstructures. These microstructures are defined by the material properties of interest and identifying them is a question of materials design. In the present paper, we addresse this issue and introduce a generic multi-task learning-based optimization approach. The approach enables the identification of sets of highly diverse microstructures for given desired properties and corresponding tolerances. Basically, the approach consists of an optimization algorithm that interacts with a machine learning model that combines multi-task learning with siamese neural networks. The resulting model (1) relates microstructures and properties, (2) estimates the likelihood of a microstructure of being producible, and (3) performs a distance preserving microstructure feature extraction in order to generate a lower dimensional latent feature space to enable efficient optimization. The proposed approach is applied on a crystallographic texture optimization problem for rolled steel sheets given desired properties.
- 26 May 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (4) , 1887-1903
Open AccessA multi-task learning-based optimization approach for finding diverse sets of microstructures with desired properties
Optimization along the chain processing-structure-properties-performance is one of the core objectives in data-driven materials science. In this sense, processes are supposed to manufacture workpieces with targeted material microstructures. These microstructures are defined by the material properties of interest and identifying them is a question of materials design. In the present paper, we addresse this issue and introduce a generic multi-task learning-based optimization approach. The approach enables the identification of sets of highly diverse microstructures for given desired properties and corresponding tolerances. Basically, the approach consists of an optimization algorithm that interacts with a machine learning model that combines multi-task learning with siamese neural networks. The resulting model (1) relates microstructures and properties, (2) estimates the likelihood of a microstructure of being producible, and (3) performs a distance preserving microstructure feature extraction in order to generate a lower dimensional latent feature space to enable efficient optimization. The proposed approach is applied on a crystallographic texture optimization problem for rolled steel sheets given desired properties.
- Open Access
A multi-task learning-based optimization approach for finding diverse sets of material microstructures with desired properties and its application to texture optimization
The optimization along the chain processing-structure-properties-performance is one of the core objectives in data-driven materials science. In this sense, processes are supposed to manufacture workpieces with targeted material microstructures. These microstructures are defined by the material properties of interest and identifying them is a question of materials design. In the present paper, we addresse this issue and introduce a generic multi-task learning-based optimization approach. The approach enables the identification of sets of highly diverse microstructures for given desired properties and corresponding tolerances. Basically, the approach consists of an optimization algorithm that interacts with a machine learning model that combines multi-task learning with siamese neural networks. The resulting model (1) relates microstructures and properties, (2) estimates the likelihood of a microstructure of being producible, and (3) performs a distance preserving microstructure feature extraction in order to generate a lower dimensional latent feature space to enable efficient optimization. The proposed approach is applied on a crystallographic texture optimization problem for rolled steel sheets given desired properties.
Open AccessA multi-task learning-based optimization approach for finding diverse sets of material microstructures with desired properties and its application to texture optimization
The optimization along the chain processing-structure-properties-performance is one of the core objectives in data-driven materials science. In this sense, processes are supposed to manufacture workpieces with targeted material microstructures. These microstructures are defined by the material properties of interest and identifying them is a question of materials design. In the present paper, we addresse this issue and introduce a generic multi-task learning-based optimization approach. The approach enables the identification of sets of highly diverse microstructures for given desired properties and corresponding tolerances. Basically, the approach consists of an optimization algorithm that interacts with a machine learning model that combines multi-task learning with siamese neural networks. The resulting model (1) relates microstructures and properties, (2) estimates the likelihood of a microstructure of being producible, and (3) performs a distance preserving microstructure feature extraction in order to generate a lower dimensional latent feature space to enable efficient optimization. The proposed approach is applied on a crystallographic texture optimization problem for rolled steel sheets given desired properties.
- Open Access
CupNet -- Pruning a network for geometric data
Using data from a simulated cup drawing process, we demonstrate how the inherent geometrical structure of cup meshes can be used to effectively prune an artificial neural network in a straightforward way.
Open AccessCupNet -- Pruning a network for geometric data
Using data from a simulated cup drawing process, we demonstrate how the inherent geometrical structure of cup meshes can be used to effectively prune an artificial neural network in a straightforward way.