Veröffent­lichungen

@article{Gabrek.2025,

title = {How the correlation between electricity prices and emission intensity affects the economic and ecological potential of industrial demand-side flexibility measures},

author = {Nadine Gabrek and Stefan Seifermann},

doi = {10.1016/j.jclepro.2025.145863},

issn = {09596526},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Journal of Cleaner Production},

volume = {518},

pages = {145863},

abstract = {In the scope of the energy transition, many studies proclaim the high potential of industrial demand-side 

 

management for providing flexibility to support the integration of volatile renewable energies into the energy 

 

system. By shifting loads from times with high emission intensity of the electricity mix to times with lower 

 

emissions, demand-side flexibility further contributes to an indirect reduction in greenhouse gas emissions. 

 

Although contributions to climate neutrality are welcome for marketing purposes, corporate decision-making 

 

processes are mainly driven by cost-based factors. Consequently, flexibility measures are primarily managed 

 

with a view to maximizing cost savings. 

 

In order to investigate the relationship between cost savings and the emissions reduction potential of flexibility 

 

measures, this study analyses the correlation between price signals of the day-ahead market and the emission 

 

intensity of the German electricity mix. In addition, the deviations in the cost and emissions savings of flexibility 

 

measures are evaluated by optimizing them with regard to the highest possible cost savings and the maximum 

 

reduction in emissions. 

 

While there is a strong correlation between the day-ahead price and emission intensity, the two optimization 

 

approaches show considerable differences in cost and emissions savings. The results indicate that a purely 

 

electricity price-driven management of flexibility measures does not exploit a large part of the potential emis1sions reduction. This gap can be closed by providing suitable incentives to prioritize emissions reduction more 

 

strongly in the management of flexibility measures or by taking better account of the current emission intensity 

 

of the electricity mix in electricity pricing.},

keywords = {Flexibilit{ä}tsvermarktung},

pubstate = {published},

tppubtype = {article}

}

@article{Ruan.2025,

title = {Fine-tuning large language models with contrastive margin ranking loss for selective entity matching in product data integration},

author = {Qian Ruan and Dachuan Shi and Thomas Bauernhansl},

doi = {10.1016/j.aei.2025.103538},

issn = {14740346},

year  = {2025},

date = {2025-01-01},

journal = {Advanced Engineering Informatics},

volume = {67},

pages = {103538},

abstract = {Entity Matching (EM) concerns identifying entities from different data sources that correspond to the same real-world object. It is widely used for product data integration in e-commerce, product classification, and inventory management, enabling the matching of duplicate product records with heterogeneous descriptions across various platforms and software systems. The standard EM solution consists of two steps: a blocking step to retrieve a subset of candidates and a pairwise matching step to classify whether the query entity matches each candidate. However, a significant challenge arises when pairwise matching fails to account for similar distractors within the candidate subset, often leading to false positive matches. This issue has been largely overlooked in prior work and existing benchmark datasets. In this study, we address this gap through three key aspects. First, we revisit the standard pairwise EM setting by recompiling existing benchmark datasets to include more hard negative (HN) candidates, which are semantically similar to corresponding query entities. We then evaluate state-of-the-art (SOTA) pairwise matchers on these recompiled datasets, revealing the limitations of the conventional pairwise EM approach under more challenging and realistic conditions. Second, we propose a selective EM approach that formulates EM as a listwise selection task, where the query entity is compared directly with the entire candidate set rather than evaluated through independent pairwise classifications. Accordingly, a new evaluation framework is introduced, including recompiled benchmark datasets and a new evaluation metric. Third, we propose a selective EM method Mistral4SelectEM, which fine-tunes a large language model for selective EM by structuring it into a Siamese network and fine-tuning it with a novel contrastive margin ranking loss (CMRL). It aims to enhance the model's ability to distinguish true positives from semantically similar HNs. Extensive experiments demonstrate that our method outperforms SOTA pairwise EM approaches in both efficiency and performance across multiple benchmark datasets.},

keywords = {Flexibilit{ä}tsautomatisierung},

pubstate = {published},

tppubtype = {article}

}

@article{Shi.2025,

title = {Dual data mapping with fine-tuned large language models and asset administration shells toward interoperable knowledge representation},

author = {Dachuan Shi and Olga Meyer and Michael Oberle and Thomas Bauernhansl},

doi = {10.1016/j.rcim.2024.102837},

issn = {07365845},

year  = {2025},

date = {2025-01-01},

journal = {Robotics and Computer-Integrated Manufacturing},

volume = {91},

pages = {102837},

keywords = {Flexibilit{ä}tsautomatisierung},

pubstate = {published},

tppubtype = {article}

}

@article{Zink.2025,

title = {Continual learning for very short-term load forecasting: A case study on parts cleaning},

author = {Robin Zink and Jonathan Magin and Oliver Griess and Matthias Weigold},

doi = {10.1016/j.apenergy.2025.126905},

issn = {03062619},

year  = {2025},

date = {2025-01-01},

journal = {Applied Energy},

volume = {402},

pages = {126905},

abstract = {The transition to climate-neutral energy systems demands increased flexibility in electricity consumption by in1dustrial entities. Accurate very short-term load forecasting enables adapting energy use in response to supply 

 

fluctuations. However, real-world production systems are dynamic and subject to concept drift, which causes 

 

model performance to degrade over time due to new data patterns. Consequently, the models must incrementally 

 

acquire and consolidate knowledge which is referred to as continual learning (CL). In CL, catastrophic forgetting 

 

(CF) poses major challenges by causing performance on earlier tasks to degrade after learning new ones. In our 

 

study, we developed a novel framework based on concept drift detection (CDD) and CL for adaptive modeling 

 

that proves to effectively mitigate CF and offers high knowledge retention. The validation was conducted using 

 

data from a throughput parts cleaning machine (TPCM) which is part of a representative production chain of the 

 

metalworking industry. Five regularization-based CL methods were compared providing insights into the relative 

 

strengths and weaknesses of the algorithms under identical conditions. The experimental results show that synap2tic intelligence (SI) and memory aware synapses (MAS) improve forecasting performance by 21 % compared to 

 

traditional offline learning approaches. While learning without forgetting (LWF) and online elastic weight consol3idation (OEWC) provide increased robustness, LWF is additionally characterized by its ease of use. Furthermore, 

 

these methods introduce minimal computational and memory overhead. The findings confirm that the proposed 

 

CDD-CL framework enables efficient and robust load forecasting in dynamic industrial environments.},

keywords = {Flexibilit{ä}tsumsetzung},

pubstate = {published},

tppubtype = {article}

}

@article{Gabrek.2025b,

title = {How the correlation between electricity prices and emission intensity affects the economic and ecological potential of industrial demand-side flexibility measures},

author = {Nadine Gabrek and Stefan Seifermann},

doi = {10.1016/j.jclepro.2025.145863},

issn = {09596526},

year  = {2025},

date = {2025-01-01},

journal = {Journal of Cleaner Production},

volume = {518},

pages = {145863},

abstract = {In the scope of the energy transition, many studies proclaim the high potential of industrial demand-side 

 

management for providing flexibility to support the integration of volatile renewable energies into the energy 

 

system. By shifting loads from times with high emission intensity of the electricity mix to times with lower 

 

emissions, demand-side flexibility further contributes to an indirect reduction in greenhouse gas emissions. 

 

Although contributions to climate neutrality are welcome for marketing purposes, corporate decision-making 

 

processes are mainly driven by cost-based factors. Consequently, flexibility measures are primarily managed 

 

with a view to maximizing cost savings. 

 

In order to investigate the relationship between cost savings and the emissions reduction potential of flexibility 

 

measures, this study analyses the correlation between price signals of the day-ahead market and the emission 

 

intensity of the German electricity mix. In addition, the deviations in the cost and emissions savings of flexibility 

 

measures are evaluated by optimizing them with regard to the highest possible cost savings and the maximum 

 

reduction in emissions. 

 

While there is a strong correlation between the day-ahead price and emission intensity, the two optimization 

 

approaches show considerable differences in cost and emissions savings. The results indicate that a purely 

 

electricity price-driven management of flexibility measures does not exploit a large part of the potential emis1sions reduction. This gap can be closed by providing suitable incentives to prioritize emissions reduction more 

 

strongly in the management of flexibility measures or by taking better account of the current emission intensity 

 

of the electricity mix in electricity pricing.},

keywords = {Flexibilit{ä}tsvermarktung},

pubstate = {published},

tppubtype = {article}

}

@article{Ruan.2025b,

title = {Fine-tuning large language models with contrastive margin ranking loss for selective entity matching in product data integration},

author = {Qian Ruan and Dachuan Shi and Thomas Bauernhansl},

doi = {10.1016/j.aei.2025.103538},

issn = {14740346},

year  = {2025},

date = {2025-01-01},

journal = {Advanced Engineering Informatics},

volume = {67},

pages = {103538},

abstract = {Entity Matching (EM) concerns identifying entities from different data sources that correspond to the same real-world object. It is widely used for product data integration in e-commerce, product classification, and inventory management, enabling the matching of duplicate product records with heterogeneous descriptions across various platforms and software systems. The standard EM solution consists of two steps: a blocking step to retrieve a subset of candidates and a pairwise matching step to classify whether the query entity matches each candidate. However, a significant challenge arises when pairwise matching fails to account for similar distractors within the candidate subset, often leading to false positive matches. This issue has been largely overlooked in prior work and existing benchmark datasets. In this study, we address this gap through three key aspects. First, we revisit the standard pairwise EM setting by recompiling existing benchmark datasets to include more hard negative (HN) candidates, which are semantically similar to corresponding query entities. We then evaluate state-of-the-art (SOTA) pairwise matchers on these recompiled datasets, revealing the limitations of the conventional pairwise EM approach under more challenging and realistic conditions. Second, we propose a selective EM approach that formulates EM as a listwise selection task, where the query entity is compared directly with the entire candidate set rather than evaluated through independent pairwise classifications. Accordingly, a new evaluation framework is introduced, including recompiled benchmark datasets and a new evaluation metric. Third, we propose a selective EM method Mistral4SelectEM, which fine-tunes a large language model for selective EM by structuring it into a Siamese network and fine-tuning it with a novel contrastive margin ranking loss (CMRL). It aims to enhance the model's ability to distinguish true positives from semantically similar HNs. Extensive experiments demonstrate that our method outperforms SOTA pairwise EM approaches in both efficiency and performance across multiple benchmark datasets.},

keywords = {Flexibilit{ä}tsautomatisierung},

pubstate = {published},

tppubtype = {article}

}