You can view the list of my publications on Google Scholar and ResearchGate. The following list is not exhaustive, but includes in particular publications that are no longer available or author versions of publications that are difficult to obtain.
von Bülow, Friedrich; Meisen, Tobias
A Review on Methods for State of Health Forecasting of Lithium-Ion Batteries Applicable in Real-World Operational Conditions Journal Article
In: Journal of Energy Storage, vol. 57, pp. 105978, 2023, ISSN: 2352-152X.
The ageing of Lithium-ion batteries can be described as change of state of health (∆SOH). It depends on the battery's operation during charging, discharging, and rest phases. Mapping the operation conditions during these phases for long time windows to a ∆SOH enables forecasting the battery's SOH. With SOH forecasting fleet managers of battery electric vehicle (BEV) fleets can plan vehicle replacement and optimize the fleet's operational strategy. Inspired by the applicability from a user's perspective of fleet managers and battery designers, this work motivates and defines key criteria for SOH forecasting models. The key criteria concern the encoding of information in the model inputs, model transferability to other batteries, and the applicability to 2nd life battery applications. Based on these key criteria we review SOH forecasting models. Currently, only few models satisfy the majority of the defined key criteria, while three others only fail at two key criteria. The majority (71 %) of the methods use machine learning models which can be seen as current research trend due to the complex dependence of battery operational data and battery ageing. We show limitations of the applicability and comparability of existing models due to different data sets, different metrics, different output values, and different forecast horizons. Furthermore, code and data are only rarely shared and publicly available.
Bülow, Friedrich; Wassermann, Markus; Meisen, Tobias
State of Health Forecasting of Lithium-Ion Batteries Operated in a Battery Electric Vehicle Fleet Journal Article
In: Journal of Energy Storage, vol. 72, pp. 108271, 2023, ISSN: 2352-152X.
Most existing methods for battery state of health (SOH) forecasting have been applied to battery cell data from laboratory operation for training and testing. This work goes beyond that by using battery pack data from real-world vehicle operation. Our data source is a fleet of 550 battery electric vehicles (BEVs). We aim to provide different feature sets that are accessible to the user groups of the SOH forecasting model like private BEV owners, BEV fleet managers, and battery designers. To this end, we investigate histogram-based features and accessible features. Our results show that a state-of-the-art SOH forecasting method based on histogram features works not only on battery cell data from laboratory operation, but also on battery system data from real-world BEV fleet operation. The model was able to learn the dependence of the SOH from the battery load, i.e., BEV usage. Switching from accessible features to the histogram-based features showed an improvement in model performance of up to 6.1 %. Two use cases for different operating strategies exemplary illustrate how the SOH forecasting model can be applied.
von Bülow, Friedrich; Meisen, Tobias
State of Health Forecasting of Heterogeneous Lithium-ion Battery Types and Operation Enabled by Transfer Learning Proceedings Article
In: PHM Society European Conference, pp. 490–508, 2022.
Due to the global transition to electromobility and the associated increased use of high-performance batteries, research is increasingly focused on estimating and forecasting the state of health (SOH) of lithium-ion batteries. Several data-intensive and well-performing methods for SOH forecasting have been introduced. However, these approaches are only reliable for new battery types, e.g., with a new cell chemistry, if a sufficient amount of training data is given, which is rarely the case. A promising approach is to transfer an established model of another battery type to the new battery type, using only a small amount of data of the new battery type. Such methods in machine learning are known as transfer learning. The usefulness and applicability of transfer learning and its underlying methods have been very successfully demonstrated in various fields, such as computer vision and natural language processing. Heterogeneity in battery systems, such as differences in rated capacity, cell cathode materials, as well as applied stress from use, necessitate transfer learning concepts for data-based battery SOH forecasting models. Hereby, the general electrochemical behavior of lithium-ion batteries, as a major common characteristic, supposedly provides an excellent starting point for a transfer learning approach for SOH forecasting models. In this paper, we present a transfer learning approach for SOH forecasting models using a multilayer perceptron (MLP). We apply and evaluate it on the method presented by von Bülow, Mentz, and Meisen (2021) using five battery datasets. In this regard, we investigate the optimal conditions and settings for the development of transfer learning with respect to suitable data from the target domain, as well as hyperparameters such as learning rate and frozen layers. We show that for the transfer of a SOH forecasting model to a new battery type it is more beneficial to have data of few old batteries, compared to data of many new batteries, especially in the case of superlinear degradation with knee points. Contrarily to computer vision freezing no layers is preferable in 95% of the experimental scenarios.
Pomp, André; Paulus, Alexander; Burgdorf, Andreas; Meisen, Tobias
A Semantic Data Marketplace for Easy Data Sharing within a Smart City Proceedings Article
In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 4774–4778, Association for Computing Machinery, Virtual Event, Queensland, Australia, 2021, ISBN: 9781450384469.
Today, smart city applications are largely based on data collected from different stakeholders. This presupposes that the required data sources are publicly available. While open data platforms already provide a number of urban data sources, enterprises and citizens have few opportunities to make their data available. To complicate things further, if the data is published, the processing of this data is already extremely time-consuming today, as the data sources are heterogeneous and the corresponding homogenization has to be carried out by the data consumers themselves. In this paper, we present a data marketplace that enables different stakeholders (public institutions, enterprises, citizens) to easily provide data that can especially contribute to the further realization of smart cities. This marketplace is based on the principles of semantic data management, i.e., data providers annotate their added data with semantic models. With the help of these models, the data sources can be found and understood by data consumers and finally homogenized in a way that is suitable for their application.
von Bülow, Friedrich; Heinrich, Felix; Meisen, Tobias
Fleet Management Approach for Manufacturers displayed at the Use Case of Battery Electric Vehicles Proceedings Article
In: 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 3218-3225, 2021, ISBN: 978-1-6654-4207-7.
Currently, fleet management approaches only focus on the perspective of the fleet operating company and the operators, but not on the perspective of the manufacturer of the fleet members. The manufacturer aims at optimizing existing fleets and supporting the development process of future fleet generations. Furthermore, data-driven models have increasing importance in fleet applications. Thus, this paper proposes a concept for a holistic fleet management approach for manufacturers supporting the development process of future fleet generations and services. We build our concept on three layers, one for the manufacturer, the fleet operator, and the machines respectively. We also discuss interactions and information flow in between the layers. Thus, enabling manufacturers to integrate operational data of customers into the development process making the products and services more customer-oriented. Before launching data-driven fleet services extensive training data is required. However, when launching new fleets disadvantageously only little data is available. As solution, we discuss the transfer of machine learning models in between different fleets (inter-fleet transfer learning). This enables quickly launching reliable machine models for new fleets with a lack of data.
von Bülow, Friedrich; Mentz, Joshua; Meisen, Tobias
State of Health Forecasting of Lithium-ion Batteries Applicable in Real-world Operational Conditions Journal Article
In: Journal of Energy Storage, vol. 44, pp. 103439, 2021, ISSN: 2352-152X.
Currently, several methods for battery state of health (SOH) prediction exist which are applicable to battery electric vehicles (BEV). However, only few research has been conducted on SOH forecasting based on features that encode causes for battery ageing applicable in real world applications. This paper proposes a machine learning method for SOH forecasting applicable for BEV fleet managers and battery designers in real world applications. As model inputs, we use the battery's operation time within certain operation ranges defined by combinations of the battery signals current, state of charge (SOC) and temperature. Different variants of this temporal aggregation of the battery operation time and of the operation ranges of the battery signals are examined. Our findings state that combining different cycle window widths ww to one training data set improves the generalization of the model. Also, we find that the fineness of the operational ranges of the signals does not limit the model's performance if ww is larger than 100 cycles or different ww are combined.
Langer, Tristan; Meisen, Tobias
Towards Utilizing Domain Expertise for Exploratory Data Analysis Proceedings Article
In: Proceedings of the 12th International Symposium on Visual Information Communication and Interaction, Association for Computing Machinery, Shanghai, China, 2019, ISBN: 9781450376266.
Kirmse, Andreas; Kraus, Vadim; Langer, Tristan; Pomp, André; Meisen, Tobias
How To RAMI 4.0: Towards An Agent-based Information Management Architecture Proceedings Article
In: 2019 International Conference on High Performance Computing & Simulation (HPCS), pp. 961-968, 2019.
Jungnickel, Robert; Pomp, André; Kirmse, Andreas; Li, Xiang; Samsonov, Vladimir; Meisen, Tobias
Evaluation and Comparison of Cross-lingual Text Processing Pipelines Proceedings Article
In: 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 417-425, 2019.
Ionita, Andrei; Pomp, André; Cochez, Michael; Meisen, Tobias; Decker, Stefan
Where to Park? Predicting Free Parking Spots in Unmonitored City Areas Proceedings Article
In: Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics, Association for Computing Machinery, Novi Sad, Serbia, 2018, ISBN: 9781450354899.
Several smart cities around the world have begun monitoring parking areas in order to estimate free spots and help drivers that are looking for parking. The current results are indeed promising, however, this approach is limited by the high costs of sensors that need to be installed throughout the city in order to achieve an accurate estimation rate. This work investigates the extension of estimating parking information from areas equipped with sensors to areas that are missing them. To this end, similarity values between city neighborhoods are computed based on background data, i.e., from geographic information systems. Using the derived similarity values, we analyze the adaptation of occupancy rates from monitored- to unmonitored parking areas.
Jeschke, Sabina; Brecher, Christian; Meisen, Tobias; Özdemir, Denis; Eschert, Tim
Industrial Internet of Things and Cyber Manufacturing Systems Book Chapter
In: Jeschke, Sabina; Brecher, Christian; Song, Houbing; Rawat, Danda B (Ed.): Industrial Internet of Things: Cybermanufacturing Systems, pp. 3–19, Springer International Publishing, 2017, ISBN: 978-3-319-42559-7.
Kuschicke, Felix; Thiele, Thomas; Meisen, Tobias; Jeschke, Sabina
A Data-Based Method for Industrial Big Data Project Prioritization Proceedings Article
In: Proceedings of the International Conference on Big Data and Internet of Thing, pp. 6–10, Association for Computing Machinery, London, United Kingdom, 2017, ISBN: 9781450354301.
The application of Big Data Techniques (BDT) in discrete manufacturing appears to be very promising, considering lighthouse projects in this area. In general, the goal is to collect all data from manufacturing systems comprehensively, in order to enable new findings and decision support by means of appropriate Industrial Big Data (IBD) analysis procedures. However, due to limited human and economic resources, potential IBD projects need to get prioritized -- in the best case according to their cost-benefit ratio. Available methods for this purpose are insufficient, due to their limited ability to be operationalized, error-proneness, and lack of scientific evidence. In this paper, we discuss how cost-benefit-analysis frameworks can be applied to the preliminary selection of production use cases for the implementation of BDT in larger production systems. It supports the use case selection process from information about production needs, available BDT, and given condition(s) per use case. This concept paper attempts to consolidate the hitherto fragmented discourse on how to prioritize IBD projects, evaluates the challenges of prioritization in this field, and presents a prioritization concept to overcome these challenges.
Tercan, Hasan; Khawli, Toufik Al; Eppelt, Urs; Büscher, Christian; Meisen, Tobias; Jeschke, Sabina
Improving the Laser Cutting Process Design by Machine Learning Techniques Journal Article
In: Production Engineering, vol. 11, no. 2, pp. 195–203, 2017, ISSN: 1863-7353.
In the field of manufacturing engineering, process designers conduct numerical simulation experiments to observe the impact of varying input parameters on certain outputs of the production process. The disadvantage of these simulations is that they are very time consuming and their results do not help to fully understand the underlying process. For instance, a common problem in planning processes is the choice of an appropriate machine parameter set that results in desirable process outputs. One way to overcome this problem is to use data mining techniques that extract previously unknown but valuable knowledge from simulation results. This paper presents a hybrid machine learning approach for applying clustering and classification techniques in a laser cutting planning process. In a first step, a clustering algorithm is used to divide large parts of the simulation data into groups of similar performance values and select those groups that are of major interest (e.g. high cut quality results). Next, classification trees are used to identify regions in the multidimensional parameter space that are related to the found groups. The evaluation shows that the models accurately identify multidimensional relationships between the input parameters and the output values of the process. In addition to that, a combination of appropriate visualization techniques for clustering with interpretable classification trees allows designers to gain valuable insights into the laser cutting process with the aim of optimizing it through visual exploration.
Antkowiak, Daniela; Luetticke, Daniel; Langer, Tristan; Thiele, Thomas; Meisen, Tobias; Jeschke, Sabina
Cyber-Physical Production Systems: A Teaching Concept in Engineering Education Proceedings Article
In: 2017 6th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), pp. 681-686, 2017.
Wang, You; Tercan, Hasan; Thiele, Thomas; Meisen, Tobias; Jeschke, Sabina; Schulz, Wolfgang
Advanced Data Enrichment and Data Analysis in Manufacturing Industry by an Example of Laser Drilling Process Proceedings Article
In: 2017 ITU Kaleidoscope: Challenges for a Data-Driven Society (ITU K), pp. 1-5, 2017.
Hoffmann, Max; Thomas, Philipp; Schütz, Daniel; Vogel-Heuser, Birgit; Meisen, Tobias; Jeschke, Sabina
Semantic Integration of Multi-Agent Systems using an OPC UA Information Modeling Approach Proceedings Article
In: 2016 IEEE 14th International Conference on Industrial Informatics (INDIN), pp. 744-747, 2016.
Meisen, Philipp; Keng, Diane; Meisen, Tobias; Recchioni, Marco; Jeschke, Sabina
Querying Time Interval Data Proceedings Article
In: Hammoudi, Slimane; Maciaszek, Leszek; Teniente, Ernest; Camp, Olivier; Cordeiro, José (Ed.): Enterprise Information Systems, pp. 45–68, Springer International Publishing, Cham, 2015, ISBN: 978-3-319-29133-8.
Analyzing huge amounts of time interval data is a task arising more and more frequently in different domains like resource utilization and scheduling, real time disposition, as well as health care. Analyzing this type of data using established, reliable, and proven technologies is desirable and required. However, utilizing commonly used tools and multidimensional models is not sufficient, because of modeling, querying, and processing limitations. In this paper, we address the problem of querying large data sets of time interval data, by introducing a query language capable to retrieve aggregated and analytical results from such a database. The introduced query language enables analysis of time interval data in an on-line analytical manner. It is based on requirements stated by business analysts from different domains. In addition, we introduce our query processing, established using a bitmap-based implementation. Finally, we present and critically discuss a performance analysis.
Meisen, Tobias; Reinhard, Rudolf; Schilberg, Daniel; Jeschke, Sabina
A Framework For Adaptive Data Integration In Digital Production Book Chapter
In: Jeschke, Sabina; Isenhardt, Ingrid; Hees, Frank; Henning, Klaus (Ed.): Automation, Communication and Cybernetics in Science and Engineering 2011/2012, pp. 1053–1066, Springer Berlin Heidelberg, Berlin, Heidelberg, 2013, ISBN: 978-3-642-33389-7.
Hoffmann, Max; Meisen, Tobias; Schilberg, Daniel; Jeschke, Sabina
Multi-Dimensional Production Planning Using a Vertical Data Integration Approach: A Contribution to Modular Factory Design Proceedings Article
In: 2013 10th International Conference and Expo on Emerging Technologies for a Smarter World (CEWIT), pp. 1-6, 2013.
Meisen, Tobias; Meisen, Philipp; Schilberg, Daniel; Jeschke, Sabina
Application Integration of Simulation Tools Considering Domain Specific Knowledge Book Chapter
In: Jeschke, Sabina; Isenhardt, Ingrid; Hees, Frank; Henning, Klaus (Ed.): Äutomation, Communication and Cybernetics in Science and Engineering 2011/2012", pp. 1067–1089, Springer Berlin Heidelberg, Berlin, Heidelberg, 2013, ISBN: 978-3-642-33389-7.
Because of the increasing complexity of modern production processes, it is necessary to plan these processes virtually before realizing them in a real environment. On the one hand there are specialized simulation tools simulating a specific production technique with exactness close to the real object of the simulation. On the other hand there are simulations which simulate whole production processes, but often do not achieve prediction accuracy comparable to the specialized tools. The simulation of a production process as a whole achieving the needed accuracy is hard to realize. Incompatible file formats, different semantics used to describe the simulated objects and missing data consistency are the main causes of this integration problem. In this paper, a framework is presented that enables the interconnection of simulation tools of production engineering considering the specific knowledge of a certain domain (e.g. material processing). Therefore, an ontology-based integration approach using domain specific knowledge to identify necessary semantic transformations has been realized. The framework provides generic functionality which, if concretized for a domain, enables the system to integrate any domain specific simulation tool in the process.
Schilberg, Daniel; Meisen, Tobias; Cerfontaine, Philippe; Jeschke, Sabina
Enterprise Application Integration for Virtual Production Book Chapter
In: Jeschke, Sabina; Isenhardt, Ingrid; Hees, Frank; Henning, Klaus (Ed.): Äutomation, Communication and Cybernetics in Science and Engineering 2011/2012", pp. 1141–1151, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, ISBN: 978-3-642-33389-7.
The focus of this work is to promote the adoption of Enterprise Application Integration (EAI) as a framework for virtual production. The product planning phase in real and virtual production usually requires a huge range of various applications that are used by different departments of a company. To increase productivity on the one hand and reduce complexity of application integration on the other hand, it is essential to be able to interconnect the differing syntax, structure and semantics of the distributed applications. The presented EAI framework will be used in the production planning process of a Line-Pipe as a use case. The successful application interconnection in this use case is used to validate the framework.
Reinhard, Rudolf; Büscher, Christian; Meisen, Tobias; Schilberg, Daniel; Jeschke, Sabina
Virtual Production Intelligence - A Contribution to the Digital Factory Proceedings Article
In: Su, Chun-Yi; Rakheja, Subhash; Liu, Honghai (Ed.): Intelligent Robotics and Applications, pp. 706–715, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, ISBN: 978-3-642-33509-9.
Meisen, Tobias; Meisen, Philipp; Schilberg, Daniel; Jeschke, Sabina
Adaptive Information Integration: Bridging the Semantic Gap between Numerical Simulations Proceedings Article
In: Zhang, Runtong; Zhang, Juliang; Zhang, Zhenji; Filipe, Joaquim; Cordeiro, José (Ed.): Enterprise Information Systems, pp. 51–65, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, ISBN: 978-3-642-29958-2.
The increasing complexity and costs of modern production processes makes it necessary to plan processes virtually before they are tested and realized in real environments. Therefore, several tools facilitating the simulation of different production techniques and design domains have been developed. On the one hand there are specialized tools simulating specific production techniques with exactness close to the real object of the simulation. On the other hand there are simulations which simulate whole production processes, but in general do not achieve prediction accuracy comparable to such specialized tools. Hence, the interconnection of tools is the only way, because otherwise the achievable prediction accuracy would be insufficient. In this chapter, a framework is presented that helps to interconnect heterogeneous simulation tools, considering their incompatible file formats, different semantics of data and missing data consistency.
Meisen, Tobias; Meisen, Philipp; Schilberg, Daniel; Jeschke, Sabina
Digitale Produktion via Enterprise Application Integration Proceedings Article
In: Jeschke, Sabina; Isenhardt, Ingrid; Henning, Klaus (Ed.): Automation, Communication and Cybernetics in Science and Engineering 2009/2010, pp. 609–622, Springer Berlin Heidelberg, Berlin, Heidelberg, 2011, ISBN: 978-3-642-16208-4.
Schilberg, Daniel; Meisen, Tobias; Reinhard, Rudolf; Jeschke, Sabina
Simulation and Interoperability in the Planning Phase of Production Processes Proceedings
vol. Volume 3: Design and Manufacturing, 2011.
Beer, Thomas; Garbereder, Gerrit; Meisen, Tobias; Reinhard, Rudolf; Kuhlen, Torsten
A Multi Level Time Model for Interactive Multiple Dataset Visualization: The Dataset Sequencer Proceedings Article
In: Bebis, George; Boyle, Richard; Parvin, Bahram; Koracin, Darko; Wang, Song; Kyungnam, Kim; Benes, Bedrich; Moreland, Kenneth; Borst, Christoph; DiVerdi, Stephen; Yi-Jen, Chiang; Ming, Jiang (Ed.): Advances in Visual Computing, pp. 681–690, Springer Berlin Heidelberg, Berlin, Heidelberg, 2011, ISBN: 978-3-642-24031-7.
Integrative simulation methods are used in engineering sciences today for the modeling of complex phenomena that cannot be simulated or modeled using a single tool. For the analysis of result data appropriate multi dataset visualization tools are needed. The inherently strong relations between the single datasets that typically describe different aspects of a simulated process (e.g. phenomena taking place at different scales) demand for special interaction metaphors, allowing for an intuitive exploration of the simulated process. This work focuses on the temporal aspects of data exploration. A multi level time model and an appropriate interaction metaphor (the Dataset Sequencer) for the interactive arrangement of datasets in the time domain of the analysis space is described. It is usable for heterogeneous display systems ranging from standard desktop systems to immersive multi-display VR devices.
Meisen, Tobias; Reinhard, Rudolf; Beer, Thomas; Schilberg, Daniel; Jeschke, Sabina
IT-Infrastructure for an Integrated Visual Analysis of Distributed Heterogeneous Simulations Proceedings Article
In: Mechatronics and Materials Processing I, pp. 1940–1946, Trans Tech Publications Ltd, 2011.
Computational simulations are used for the optimization of production processes in order to significantly reduce the need for costly experimental optimization approaches. Yet individual simulations can rarely describe more than a single production step. Hence, a set of simulations has to be used to simulate a contiguous representation of a complete production process. Besides, simulated results have to be analyzed by domain experts to gather insight from the performed computations. In this paper, an IT-infrastructure is proposed that aims at a rather non-intrusive way of interconnecting simulations and domain expert’s knowledge to facilitate the collaborative setup, execution and analysis of distributed simulation chains.
Schilberg, Daniel; Meisen, Tobias
Ontology Based Semantic Interconnection of Distributed Numerical Simulations for Virtual Production Proceedings Article
In: 2009 16th International Conference on Industrial Engineering and Engineering Management, pp. 1789-1793, 2009.
Schilberg, Daniel; Meisen, Tobias; Henning, Klaus
Semantic Data Integration for Virtual Production Proceedings Article
In: 2009 Second International Conference on Computer and Electrical Engineering, pp. 184-187, 2009.