@article{64916, abstract = {{The joining of dissimilar materials, such as steel and aluminum, entails significant challenges during thermal curing processes due to differing coefficients of thermal expansion. This study addresses the formation of “viscous fingering” instabilities in structural adhesive joints, which are induced by thermally driven relative displacements during the liquid phase of the adhesive. Using a component-like specimen “bridge specimen,” the dependency of this phenomenon on process temperature and structural stiffness (rivet distance) was characterized. Experimental results reveal that while the relative displacement scales cubically with the free buckling length, the resulting adhesive area reduction follows an exponential trend, leading to a loss of effective bond area of up to 79%, which significantly compromises the joint strength in automotive applications. To predict these process-induced defects, a thermo-chemo-viscoelastic-viscoplastic adhesive model implemented in LS-DYNA was applied. The model combines curing kinetics, viscoelastic relaxation, and pressure-dependent plasticity and features a geometric damage parameter (D) that captures the adhesive area reduction caused by viscous fingering as an exponential function of the accumulated normal strain in the liquid phase. This damage parameter, calibrated on base-specimen level, was transferred to the component geometry. The simulation demonstrated high predictive accuracy with a maximum deviation of the adhesive area reduction of 3.1% compared to experimental data. This validates the model’s capability to predict manufacturing-induced damage in complex hybrid structures solely based on thermal boundary conditions.}}, author = {{Al Trjman, Mohamad and Beule, Felix and Teutenberg, Dominik and Meschut, Gerson and Riese, Julia}}, issn = {{0021-8464}}, journal = {{The Journal of Adhesion}}, keywords = {{Adhesive area reduction, CED coating process, delta alpha problem, epoxy structural adhesive, influence of manufacture, multi-material design, numerical simulation (FEM), relative displacements, viscous fingering (saffman-taylor-instability).}}, pages = {{1--24}}, publisher = {{Informa UK Limited}}, title = {{{Experimental characterization and numerical analysis of the influence of the CED coating process on viscous fingering formation in hybrid-jointed mixed structures}}}, doi = {{10.1080/00218464.2026.2644394}}, year = {{2026}}, } @article{55400, abstract = {{This study contributes to the evolving field of robot learning in interaction with humans, examining the impact of diverse input modalities on learning outcomes. It introduces the concept of "meta-modalities" which encapsulate additional forms of feedback beyond the traditional preference and scalar feedback mechanisms. Unlike prior research that focused on individual meta-modalities, this work evaluates their combined effect on learning outcomes. Through a study with human participants, we explore user preferences for these modalities and their impact on robot learning performance. Our findings reveal that while individual modalities are perceived differently, their combination significantly improves learning behavior and usability. This research not only provides valuable insights into the optimization of human-robot interactive task learning but also opens new avenues for enhancing the interactive freedom and scaffolding capabilities provided to users in such settings.}}, author = {{Beierling, Helen and Beierling, Robin and Vollmer, Anna-Lisa}}, journal = {{Frontiers in Robotics and AI}}, keywords = {{human-robot interaction, human-in-the-loop learning, reinforcement learning, interactive robot learning, multi-modal feedback, learning from demonstration, preference-based learning, scaffolding in robot learning}}, publisher = {{Frontiers }}, title = {{{The power of combined modalities in interactive robot learning}}}, volume = {{12}}, year = {{2025}}, } @inproceedings{62066, abstract = {{In the context of high-performance computing (HPC) for distributed workloads, individual field-programmable gate arrays (FPGAs) need efficient ways to exchange data, which requires network infrastructure and software abstractions. Dedicated multi-FPGA clusters provide inter-FPGA networks for direct device to device communication. The oneAPI high-level synthesis toolchain offers I/O pipes to allow user kernels to interact with the networking ports of the FPGA board. In this work, we evaluate using oneAPI I/O pipes for direct FPGA-to-FPGA communication by scaling a SYCL implementation of a Jacobi solver on up to 25 FPGAs in the Noctua 2 cluster. We see good results in weak and strong scaling experiments.}}, author = {{Alt, Christoph and Plessl, Christian and Kenter, Tobias}}, booktitle = {{Proceedings of the 13th International Workshop on OpenCL and SYCL}}, isbn = {{9798400713606}}, keywords = {{Multi-FPGA, High-level Synthesis, oneAPI, FPGA}}, publisher = {{Association for Computing Machinery}}, title = {{{Evaluating oneAPI I/O Pipes in a Case Study of Scaling a SYCL Jacobi Solver to multiple FPGAs}}}, doi = {{10.1145/3731125.3731131}}, year = {{2025}}, } @article{63053, author = {{Hernández, Carlos and Rodriguez-Fernandez, Angel E. and Schäpermeier, Lennart and Cuate, Oliver and Trautmann, Heike and Schütze, Oliver}}, journal = {{IEEE Transactions on Evolutionary Computation}}, keywords = {{Optimization, Evolutionary computation, Hands, Proposals, Convergence, Computational efficiency, Artificial intelligence, Accuracy, Approximation algorithms, Aerospace electronics, Multi-objective optimization, evolutionary algorithms, nearly optimal solutions, multimodal optimization, archiving, continuation}}, pages = {{1--1}}, title = {{{An Evolutionary Approach for the Computation of ∈-Locally Optimal Solutions for Multi-Objective Multimodal Optimization}}}, doi = {{10.1109/TEVC.2025.3637276}}, year = {{2025}}, } @article{56221, author = {{Rodriguez-Fernandez, Angel E. and Schäpermeier, Lennart and Hernández, Carlos and Kerschke, Pascal and Trautmann, Heike and Schütze, Oliver}}, journal = {{IEEE Transactions on Evolutionary Computation}}, keywords = {{Optimization, Evolutionary computation, Approximation algorithms, Benchmark testing, Vectors, Surveys, Pareto optimization, multi-objective optimization, evolutionary computation, multimodal optimization, local solutions}}, pages = {{1--1}}, title = {{{Finding ϵ-Locally Optimal Solutions for Multi-Objective Multimodal Optimization}}}, doi = {{10.1109/TEVC.2024.3458855}}, year = {{2024}}, } @inproceedings{56636, abstract = {{Abstract. Business reputation ecosystems are a widely untapped research field. In these ecosystems, agents can selectively exchange (monetary) ratings to in-form about the experienced quality in a market. We build a model for conducting a multi-agent simulation that can be used to simulate and evaluate business rep-utation ecosystems as a new system class. We explore the factual occurring vol-untary payment to create positive (pay) or negative ratings (no pay), selling rat-ings selectively to alleviate information asymmetry, and the workings of counter-ratings to prevent buyers' dishonest ratings. Thereby, we analyze, among others, agent profitability, the occurrence of dishonest ratings, and reputation bias and sensitivity. The results provide simulation-based empirical evidence that the con-cept of monetary reputation systems provides necessary incentives for participa-tion, and high-quality sellers and honest buyers benefit from such a system. The results indicate that counter-ratings prompt buyers}}, author = {{Ibrahimli, Ulvi and Hemmrich, Simon and Zauke, Simon and Winkelmann, Axel}}, booktitle = {{19. Internationale Tagung Wirtschaftsinformatik (WI24)}}, keywords = {{Reputation System, Payment as Rating, Multi-Agent Simulation, Lemon Markets}}, location = {{Würzburg}}, title = {{{Overcoming Lemon Markets with Business Reputation Ecosystem – A Multi-agent Simulation on Monetary Ratings}}}, year = {{2024}}, } @inproceedings{45812, author = {{Özcan, Leon and Fichtler, Timm and Kasten, Benjamin and Koldewey, Christian and Dumitrescu, Roman}}, keywords = {{Digital Platform, Platform Strategy, Strategic Management, Platform Life Cycle, Interview Study, Business Model, Business-to-Business, Two-sided Market, Multi-sided Market}}, location = {{Ljubljana}}, title = {{{Interview Study on Strategy Options for Platform Operation in B2B Markets}}}, year = {{2023}}, } @inproceedings{33991, abstract = {{In the course of digitalization, digital platforms are unleashing their full disruptive potential and are already dominating the first industries (e.g., hotel industry). As a result of this success, more and more companies want to build their own platforms and participate in the success. However, building and operating a digital platform involves multiple challenges and most of such ambitions fail. Since most digital platforms fail, strategic leadership of digital platforms must consider both success factors and reasons for platform failure. For this purpose, we conducted a systematic literature analysis and identified 24 success as well as failure factors in 9 dimensions. From a scientific perspective, the article provides a structured analysis of success and failure factors of digital platforms, which previously did not exist in literature. Practitioners can use the resulting knowledge base to successfully manage platform activities and avoid pitfalls.}}, author = {{Özcan, Leon and Koldewey, Christian and Duparc, Estelle and van der Valk, Hendrik and Otto, Boris and Dumitrescu, Roman}}, keywords = {{Digital Platform, Multi-sided Market, Two-sided Market, Success Factor, Failure Factor}}, location = {{Minneapolis}}, title = {{{Why do Digital Platforms succeed or fail? - A Literature Review on Success and Failure Factors}}}, year = {{2022}}, } @inbook{34209, abstract = {{Predicting the durability of components subjected to mechanical load under environmental conditions leading to corrosion is one of the most challenging tasks in mechanical engineering. The demand for precise predictions increases with the desire of lightweight design in transportation due to environmental protection. Corrosion with its manifold of mechanisms often occurs together with the production of hydrogen by electrochemical reactions. Hydrogen embrittlement is one of the most feared damage mechanisms for metal constructions often leading to early and unexpected failure. Until now, predictions are mostly based on costly experiments. Hence, a rational predictive model based on the fundamentals of electrochemistry and damage mechanics has to be developed in order to reduce the costs. In this work, a first model approach based on classical continuum damage mechanics is presented to couple both, the damage induced by the mechanical stress and the hydrogen embrittlement. An elaborated two-scale model based on the selfconsistent theory is applied to describe the mechanical damage due to fatigue. The electrochemical kinetics are elucidated through the Langmuir adsorption isotherm and the diffusion equation to consider the impact of hydrogen embrittlement on the fatigue. The modeling of the mechanism of hydrogen embrittlement defines the progress of damage accumulation due to the electrochemistry. The durability results like the S-N diagram show the influence of hydrogen embrittlement by varying, e.g. the fatigue frequency or the stress ratio.}}, author = {{Shi, Yuhao and Harzheim, Sven and Hofmann, Martin and Wallmersperger, Thomas}}, booktitle = {{Material Modeling and Structural Mechanics}}, isbn = {{9783030976743}}, issn = {{1869-8433}}, keywords = {{Hydrogen embrittlement, Fatigue, Continuum damage mechanics, Numerical simulation, Multi-field problem}}, publisher = {{Springer International Publishing}}, title = {{{A Damage Model for Corrosion Fatigue Due to Hydrogen Embrittlement}}}, doi = {{10.1007/978-3-030-97675-0_9}}, year = {{2022}}, } @inproceedings{48882, abstract = {{In multimodal multi-objective optimization (MMMOO), the focus is not solely on convergence in objective space, but rather also on explicitly ensuring diversity in decision space. We illustrate why commonly used diversity measures are not entirely appropriate for this task and propose a sophisticated basin-based evaluation (BBE) method. Also, BBE variants are developed, capturing the anytime behavior of algorithms. The set of BBE measures is tested by means of an algorithm configuration study. We show that these new measures also transfer properties of the well-established hypervolume (HV) indicator to the domain of MMMOO, thus also accounting for objective space convergence. Moreover, we advance MMMOO research by providing insights into the multimodal performance of the considered algorithms. Specifically, algorithms exploiting local structures are shown to outperform classical evolutionary multi-objective optimizers regarding the BBE variants and respective trade-off with HV.}}, author = {{Heins, Jonathan and Rook, Jeroen and Schäpermeier, Lennart and Kerschke, Pascal and Bossek, Jakob and Trautmann, Heike}}, booktitle = {{Parallel Problem Solving from Nature (PPSN XVII)}}, editor = {{Rudolph, Günter and Kononova, Anna V. and Aguirre, Hernán and Kerschke, Pascal and Ochoa, Gabriela and Tusar, Tea}}, isbn = {{978-3-031-14714-2}}, keywords = {{Anytime behavior, Benchmarking, Continuous optimization, Multi-objective optimization, Multimodality, Performance metric}}, pages = {{192–206}}, publisher = {{Springer International Publishing}}, title = {{{BBE: Basin-Based Evaluation of Multimodal Multi-objective Optimization Problems}}}, doi = {{10.1007/978-3-031-14714-2_14}}, year = {{2022}}, } @inproceedings{48896, abstract = {{Hardness of Multi-Objective (MO) continuous optimization problems results from an interplay of various problem characteristics, e. g. the degree of multi-modality. We present a benchmark study of classical and diversity focused optimizers on multi-modal MO problems based on automated algorithm configuration. We show the large effect of the latter and investigate the trade-off between convergence in objective space and diversity in decision space.}}, author = {{Rook, Jeroen and Trautmann, Heike and Bossek, Jakob and Grimme, Christian}}, booktitle = {{Proceedings of the Genetic and Evolutionary Computation Conference Companion}}, isbn = {{978-1-4503-9268-6}}, keywords = {{configuration, multi-modality, multi-objective optimization}}, pages = {{356–359}}, publisher = {{Association for Computing Machinery}}, title = {{{On the Potential of Automated Algorithm Configuration on Multi-Modal Multi-Objective Optimization Problems}}}, doi = {{10.1145/3520304.3528998}}, year = {{2022}}, } @inproceedings{33997, abstract = {{Digital platforms have already led to disruptions in multiple B2C markets and are becoming increasingly dominant in B2B markets. As a result, more and more companies are trying to participate in the platform economy. However, the successful development and operation of a digital platform is associated with significant challenges, which leads to 85% of all platforms failing. A core challenge is the dynamic nature of the platform economy, with varying strategic objectives at different stages in the platform lifecycle. Platform operators must continuously monitor platform progress and adjust their strategy. Utilizing action research in the real-world platform project AI Marketplace, we developed a lifecycle-oriented performance management approach for digital platforms in B2B markets. It enables platform operators to reflect on their position in the platform lifecycle, derive relevant strategic objectives, and monitor them with suitable key performance indicators. Hence, allowing them to secure the long-term success of their platform business.}}, author = {{Özcan, Leon and Kirchberg, Lisa Irene and Koldewey, Christian and Dumitrescu, Roman}}, booktitle = {{The Role of Innovation: Past, Present, Future}}, editor = {{Bitran, Iain and Bitetti, Leandro and Conn, Steffen and Fishburn, Jessica and Huizingh, Eelko and Torkkeli, Marko and Yang, Jialei}}, keywords = {{Digital Platform, Two-Sided Market, Multi-Sided Market, Platform Lifecycle, Platform Monitoring, Performance Management}}, location = {{Athens}}, title = {{{Performance Management Approach for Digital Platforms in B2B Markets}}}, year = {{2022}}, } @inproceedings{31066, abstract = {{While trade-offs between modeling effort and model accuracy remain a major concern with system identification, resorting to data-driven methods often leads to a complete disregard for physical plausibility. To address this issue, we propose a physics-guided hybrid approach for modeling non-autonomous systems under control. Starting from a traditional physics-based model, this is extended by a recurrent neural network and trained using a sophisticated multi-objective strategy yielding physically plausible models. While purely data-driven methods fail to produce satisfying results, experiments conducted on real data reveal substantial accuracy improvements by our approach compared to a physics-based model. }}, author = {{Schön, Oliver and Götte, Ricarda-Samantha and Timmermann, Julia}}, booktitle = {{14th IFAC Workshop on Adaptive and Learning Control Systems (ALCOS 2022)}}, keywords = {{neural networks, physics-guided, data-driven, multi-objective optimization, system identification, machine learning, dynamical systems}}, location = {{Casablanca, Morocco}}, number = {{12}}, pages = {{19--24}}, title = {{{Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems}}}, doi = {{https://doi.org/10.1016/j.ifacol.2022.07.282}}, volume = {{55}}, year = {{2022}}, } @article{21004, abstract = {{Automated machine learning (AutoML) supports the algorithmic construction and data-specific customization of machine learning pipelines, including the selection, combination, and parametrization of machine learning algorithms as main constituents. Generally speaking, AutoML approaches comprise two major components: a search space model and an optimizer for traversing the space. Recent approaches have shown impressive results in the realm of supervised learning, most notably (single-label) classification (SLC). Moreover, first attempts at extending these approaches towards multi-label classification (MLC) have been made. While the space of candidate pipelines is already huge in SLC, the complexity of the search space is raised to an even higher power in MLC. One may wonder, therefore, whether and to what extent optimizers established for SLC can scale to this increased complexity, and how they compare to each other. This paper makes the following contributions: First, we survey existing approaches to AutoML for MLC. Second, we augment these approaches with optimizers not previously tried for MLC. Third, we propose a benchmarking framework that supports a fair and systematic comparison. Fourth, we conduct an extensive experimental study, evaluating the methods on a suite of MLC problems. We find a grammar-based best-first search to compare favorably to other optimizers.}}, author = {{Wever, Marcel Dominik and Tornede, Alexander and Mohr, Felix and Hüllermeier, Eyke}}, issn = {{0162-8828}}, journal = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}}, keywords = {{Automated Machine Learning, Multi Label Classification, Hierarchical Planning, Bayesian Optimization}}, pages = {{1--1}}, title = {{{AutoML for Multi-Label Classification: Overview and Empirical Evaluation}}}, doi = {{10.1109/tpami.2021.3051276}}, year = {{2021}}, } @article{21808, abstract = {{Modern services consist of interconnected components,e.g., microservices in a service mesh or machine learning functions in a pipeline. These services can scale and run across multiple network nodes on demand. To process incoming traffic, service components have to be instantiated and traffic assigned to these instances, taking capacities, changing demands, and Quality of Service (QoS) requirements into account. This challenge is usually solved with custom approaches designed by experts. While this typically works well for the considered scenario, the models often rely on unrealistic assumptions or on knowledge that is not available in practice (e.g., a priori knowledge). We propose DeepCoord, a novel deep reinforcement learning approach that learns how to best coordinate services and is geared towards realistic assumptions. It interacts with the network and relies on available, possibly delayed monitoring information. Rather than defining a complex model or an algorithm on how to achieve an objective, our model-free approach adapts to various objectives and traffic patterns. An agent is trained offline without expert knowledge and then applied online with minimal overhead. Compared to a state-of-the-art heuristic, DeepCoord significantly improves flow throughput (up to 76%) and overall network utility (more than 2x) on realworld network topologies and traffic traces. It also supports optimizing multiple, possibly competing objectives, learns to respect QoS requirements, generalizes to scenarios with unseen, stochastic traffic, and scales to large real-world networks. For reproducibility and reuse, our code is publicly available.}}, author = {{Schneider, Stefan Balthasar and Khalili, Ramin and Manzoor, Adnan and Qarawlus, Haydar and Schellenberg, Rafael and Karl, Holger and Hecker, Artur}}, journal = {{Transactions on Network and Service Management}}, keywords = {{network management, service management, coordination, reinforcement learning, self-learning, self-adaptation, multi-objective}}, publisher = {{IEEE}}, title = {{{Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning}}}, doi = {{10.1109/TNSM.2021.3076503}}, year = {{2021}}, } @techreport{33854, abstract = {{Macrodiversity is a key technique to increase the capacity of mobile networks. It can be realized using coordinated multipoint (CoMP), simultaneously connecting users to multiple overlapping cells. Selecting which users to serve by how many and which cells is NP-hard but needs to happen continuously in real time as users move and channel state changes. Existing approaches often require strict assumptions about or perfect knowledge of the underlying radio system, its resource allocation scheme, or user movements, none of which is readily available in practice. Instead, we propose three novel self-learning and self-adapting approaches using model-free deep reinforcement learning (DRL): DeepCoMP, DD-CoMP, and D3-CoMP. DeepCoMP leverages central observations and control of all users to select cells almost optimally. DD-CoMP and D3-CoMP use multi-agent DRL, which allows distributed, robust, and highly scalable coordination. All three approaches learn from experience and self-adapt to varying scenarios, reaching 2x higher Quality of Experience than other approaches. They have very few built-in assumptions and do not need prior system knowledge, making them more robust to change and better applicable in practice than existing approaches.}}, author = {{Schneider, Stefan Balthasar and Karl, Holger and Khalili, Ramin and Hecker, Artur}}, keywords = {{mobility management, coordinated multipoint, CoMP, cell selection, resource management, reinforcement learning, multi agent, MARL, self-learning, self-adaptation, QoE}}, title = {{{DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning}}}, year = {{2021}}, } @article{25046, abstract = {{While increasing digitalization enables multiple advantages for a reliable operation of technical systems, a remaining challenge in the context of condition monitoring is seen in suitable consideration of uncertainties affecting the monitored system. Therefore, a suitable prognostic approach to predict the remaining useful lifetime of complex technical systems is required. To handle different kinds of uncertainties, a novel Multi-Model-Particle Filtering-based prognostic approach is developed and evaluated by the use case of rubber-metal-elements. These elements are maintained preventively due to the strong influence of uncertainties on their behavior. In this paper, two measurement quantities are compared concerning their ability to establish a prediction of the remaining useful lifetime of the monitored elements and the influence of present uncertainties. Based on three performance indices, the results are evaluated. A comparison with predictions of a classical Particle Filter underlines the superiority of the developed Multi-Model-Particle Filter. Finally, the value of the developed method for enabling condition monitoring of technical systems related to uncertainties is given exemplary by a comparison between the preventive and the predictive maintenance strategy for the use case.}}, author = {{Bender, Amelie}}, issn = {{2075-1702}}, journal = {{Machines}}, keywords = {{prognostics, RUL predictions, particle filter, uncertainty consideration, Multi-Model-Particle Filter, model-based approach, rubber-metal-elements, predictive maintenance}}, number = {{10}}, title = {{{A Multi-Model-Particle Filtering-Based Prognostic Approach to Consider Uncertainties in RUL Predictions}}}, doi = {{10.3390/machines9100210}}, volume = {{9}}, year = {{2021}}, } @article{46318, abstract = {{Multi-objective (MO) optimization, i.e., the simultaneous optimization of multiple conflicting objectives, is gaining more and more attention in various research areas, such as evolutionary computation, machine learning (e.g., (hyper-)parameter optimization), or logistics (e.g., vehicle routing). Many works in this domain mention the structural problem property of multimodality as a challenge from two classical perspectives: (1) finding all globally optimal solution sets, and (2) avoiding to get trapped in local optima. Interestingly, these streams seem to transfer many traditional concepts of single-objective (SO) optimization into claims, assumptions, or even terminology regarding the MO domain, but mostly neglect the understanding of the structural properties as well as the algorithmic search behavior on a problem’s landscape. However, some recent works counteract this trend, by investigating the fundamentals and characteristics of MO problems using new visualization techniques and gaining surprising insights. Using these visual insights, this work proposes a step towards a unified terminology to capture multimodality and locality in a broader way than it is usually done. This enables us to investigate current research activities in multimodal continuous MO optimization and to highlight new implications and promising research directions for the design of benchmark suites, the discovery of MO landscape features, the development of new MO (or even SO) optimization algorithms, and performance indicators. For all these topics, we provide a review of ideas and methods but also an outlook on future challenges, research potential and perspectives that result from recent developments.}}, author = {{Grimme, Christian and Kerschke, Pascal and Aspar, Pelin and Trautmann, Heike and Preuss, Mike and Deutz, André H. and Wang, Hao and Emmerich, Michael}}, issn = {{0305-0548}}, journal = {{Computers & Operations Research}}, keywords = {{Multimodal optimization, Multi-objective continuous optimization, Landscape analysis, Visualization, Benchmarking, Theory, Algorithms}}, pages = {{105489}}, title = {{{Peeking beyond peaks: Challenges and research potentials of continuous multimodal multi-objective optimization}}}, doi = {{https://doi.org/10.1016/j.cor.2021.105489}}, volume = {{136}}, year = {{2021}}, } @article{17860, abstract = {{Purpose The purpose of this paper is to identify strategic options and challenges that arise when an industrial firm moves from providing smart service toward providing a platform. Design/methodology/approach This conceptual study takes on a multidisciplinary research perspective that integrates concepts, theories and insights from service management and marketing, information systems and platform economics. Findings The paper outlines three platform types – smart data platform, smart product platform and matching platform – as strategic options for firms that wish to evolve from smart service providers to platform providers. Research limitations/implications Investigating smart service platforms calls for launching interdisciplinary research initiatives. Promising research avenues are outlined to span boundaries that separate different research disciplines today. Practical implications Managing a successful transition from providing smart service toward providing a platform requires making significant investments in IT, platform-related capabilities and skills, as well as implement new approaches toward relationship management and brand-building. Originality/value The findings described in this paper are valuable to researchers in multiple disciplines seeking to develop and to justify theory related to platforms in industrial scenarios.}}, author = {{Beverungen, Daniel and Kundisch, Dennis and Wünderlich, Nancy}}, issn = {{507-532}}, journal = {{Journal of Service Management}}, keywords = {{Smart service, Platform, Interdisciplinary research, Manufacturing company, Smart service provider, Platform economics, Information systems, Multi-sided markets, Business-to-business (B2B) markets}}, number = {{4}}, pages = {{507--532}}, publisher = {{Emerald Insight}}, title = {{{Transforming into a Platform Provider: Strategic Options for Industrial Smart Service Providers}}}, doi = {{10.1108/JOSM-03-2020-0066}}, volume = {{32}}, year = {{2021}}, } @inproceedings{22724, abstract = {{ Predictive Maintenance as a desirable maintenance strategy in industrial applications relies on suitable condition monitoring solutions to reduce costs and risks of the monitored technical systems. In general, those solutions utilize model-based or data-driven methods to diagnose the current state or predict future states of monitored technical systems. However, both methods have their advantages and drawbacks. Combining both methods can improve uncertainty consideration and accuracy. Different combination approaches of those hybrid methods exist to exploit synergy effects. The choice of an appropriate approach depends on different requirements and the goal behind the selection of a hybrid approach. In this work, the hybrid approach for estimating remaining useful lifetime takes potential uncertainties into account. Therefore, a data-driven estimation of new measurements is integrated within a model-based method. To consider uncertainties within the system, a differentiation between different system behavior is realized throughout diverse states of degradation. The developed hybrid prediction approach bases on a particle filtering method combined with a machine learning method, to estimate the remaining useful lifetime of technical systems. Particle filtering as a Monte Carlo simulation technique is suitable to map and propagate uncertainties. Moreover, it is a state-of-the-art model-based method for predicting remaining useful lifetime of technical systems. To integrate uncertainties a multi-model particle filtering approach is employed. In general, resampling as a part of the particle filtering approach has the potential to lead to an accurate prediction. However, in the case where no future measurements are available, it may increase the uncertainty of the prediction. By estimating new measurements, those uncertainties are reduced within the data-driven part of the approach. Hence, both parts of the hybrid approach strive to account for and reduce uncertainties. Rubber-metal-elements are employed as a use-case to evaluate the developed approach. Rubber-metal-elements, which are used to isolate vibrations in various systems, such as railways, trucks and wind turbines, show various uncertainties in their behavior and their degradation. Those uncertainties are caused by diverse inner and outer factors, such as manufacturing influences and operating conditions. By expert knowledge the influences are described, analyzed and if possible reduced. However, the remaining uncertainties are considered within the hybrid prediction method. Relative temperature is the selected measurand to describe the element’s degradation. In lifetime tests, it is measured as the difference between the element’s temperature and the ambient temperature. Thereby, the influence of the ambient temperature on the element’s temperature is taken into account. Those elements show three typical states of degradation that are identified within the temperature measurements. Depending on the particular state of degradation a new measurement is estimated within the hybrid approach to reduce potential uncertainties. Finally, the performance of the developed hybrid method is compared to a model-based method for estimating the remaining useful lifetime of the same elements. Suitable performance indices are implemented to underline the differences between the results.}}, author = {{Bender, Amelie and Sextro, Walter}}, booktitle = {{Proceedings of the European Conference of the PHM Society 2021}}, editor = {{Do, Phuc and King, Steve and Fink, Olga}}, keywords = {{Hybrid prediction method, Multi-model particle filtering, Uncertainty quantification, RUL estimation}}, number = {{1}}, title = {{{Hybrid Prediction Method for Remaining Useful Lifetime Estimation Considering Uncertainties}}}, doi = {{https://doi.org/10.36001/phme.2021.v6i1.2843 }}, volume = {{6}}, year = {{2021}}, }