@inproceedings{63193,
  abstract     = {{The integration of data-driven models and specifically machine learning for conditon monitoring and predictive maintenance into companies, especially small and medium-sized enterprises, offers significant opportunities in reducing costs, operating more sustainably, and maintaining long-term competitiveness. However, many small and medium-sized enterprises lack the necessary resources and expertise to derive knowledge from data and integrate their own machine learning based solutions. To address this challenge, a framework is presented that enables the automated generation of data-driven models with a particular focus on condition monitoring and predictive maintenance, but applicable to other use cases as well. Using a dataset from the 2022 data challenge of the prognostics and health management society, it is demonstrated that the framework can generate high-performing models, achieving F1-scores up to 0.998, exemplarily for a classification task.}},
  author       = {{Löwen, Alexander and Quirin, Dennis and Hesse, Marc and Aimiyekagbon, Osarenren Kennedy and Sextro, Walter}},
  booktitle    = {{2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}},
  location     = {{Porto}},
  publisher    = {{IEEE}},
  title        = {{{Facilitating the Automated Generation of Data-Driven Models for the Diagnostics and Prognostics of Technical Systems}}},
  doi          = {{10.1109/etfa65518.2025.11205799}},
  year         = {{2025}},
}

@article{58556,
  abstract     = {{To predict and prevent uneven tire wear in addition to a reduction of overall tire wear, it is essential to estimate not only the total amount of wear but also how the wear is distributed across the tire width. This requires knowledge of the frictional power distribution in the tire contact patch, which is the basis for calculating tire wear using a wear law. Usually, only 3D structural tire models can generate such distributed contact results. However, they involve high computational costs and cannot be used for comprehensive optimization of a vehicle’s suspension system with respect to tire wear characteristics. Hence, this contribution presents a methodology on how to accelerate the prediction of the frictional power distribution using two components: The structural tire model is replaced by an empirical tire model that on its own is not able to generate distributed contact results. Therefore, an artificial neural network is trained to predict the desired contact results from the kinematic quantities calculated by the empirical tire model. In the initial training phase, both components are fitted to data generated by the original complex tire model. After training, the empirical tire model can replace the structural tire model in vehicle simulations, resulting in significantly shorter calculation times. The simulation results are fed into the artificial neural network, which predicts the frictional power distributions over the tire width with negligible additional effort. Overall, the methodology reduces calculation time for the prediction of tire wear based on virtual test drives to approximately 25% of the time needed when using structural tire models.}},
  author       = {{Muth, Lars and Zharia, Raphael and Sahin, Hürkan and Sextro, Walter}},
  journal      = {{Tire Science and Technology}},
  publisher    = {{The Tire Society}},
  title        = {{{Prediction of the Frictional Power Distribution in the Tire Contact Patch Based on an Empirical Tire Model and an Artificial Neural Network}}},
  doi          = {{https://doi.org/10.2346/TST-24-009}},
  year         = {{2025}},
}

@unpublished{60881,
  abstract     = {{<jats:p>Hybrid modeling aims to combine physical and data-driven models to increase simulation accuracy without losing physical interpretability. In the context of dynamic mechanical systems, this enables the compensation of modeling inaccuracies that arise from simplifications, missing effects, or uncertain parameters. In this work, a hybrid model is used as a starting point, in which the discrepancy between simulation and measurement is learned and compensated by a data-driven correction element. To integrate such models into commercial multibody system (MBS) software like MSC Adams and Simpack, the formulation is adapted to operate directly on the force level. This allows implementation via standard co-simulation interfaces without modifying the system’s differential equations or solvers. The method is demonstrated using a single-mass oscillator with synthetic measurement data. Results show that the coupled simulation works reliably and that the hybrid model significantly improves accuracy while remaining compatible with established industrial simulation workflows.</jats:p>}},
  author       = {{Wohlleben, Meike Claudia and Linneweber, Jill Mercedes and Schütte, Jan and Sextro, Walter}},
  publisher    = {{MDPI AG}},
  title        = {{{Enabling Hybrid Modeling in Commercial MBS Software: A Force-Level Approach}}},
  year         = {{2025}},
}

@article{51518,
  abstract     = {{In applications of piezoelectric actuators and sensors, the dependability and particularly the reliability throughout their lifetime are vital to manufacturers and end-users and are enabled through condition-monitoring approaches. Existing approaches often utilize impedance measurements over a range of frequencies or velocity measurements and require additional equipment or sensors, such as a laser Doppler vibrometer. Furthermore, the non-negligible effects of varying operating conditions are often unconsidered. To minimize the need for additional sensors while maintaining the dependability of piezoelectric bending actuators irrespective of varying operating conditions, an online diagnostics approach is proposed. To this end, time- and frequency-domain features are extracted from monitored current signals to reflect hairline crack development in bending actuators. For validation of applicability, the presented analysis method was evaluated on piezoelectric bending actuators subjected to accelerated lifetime tests at varying voltage amplitudes and under external damping conditions. In the presence of a crack and due to a diminished stiffness, the resonance frequency decreases and the root-mean-square amplitude of the current signal simultaneously abruptly drops during the lifetime tests. Furthermore, the piezoelectric crack surfaces clapping is reflected in higher harmonics of the current signal. Thus, time-domain features and harmonics of the current signals are sufficient to diagnose hairline cracks in the actuators.}},
  author       = {{Aimiyekagbon, Osarenren Kennedy and Bender, Amelie and Hemsel, Tobias and Sextro, Walter}},
  issn         = {{2079-9292}},
  journal      = {{Electronics}},
  keywords     = {{piezoelectric transducer, self-sensing, fault detection, diagnostics, hairline crack, condition monitoring}},
  number       = {{3}},
  publisher    = {{MDPI AG}},
  title        = {{{Diagnostics of Piezoelectric Bending Actuators Subjected to Varying Operating Conditions}}},
  doi          = {{10.3390/electronics13030521}},
  volume       = {{13}},
  year         = {{2024}},
}

@inproceedings{55336,
  abstract     = {{Predicting the remaining useful life of technical 
systems has gained significant attention in recent years due to 
increasing demands for extending the lifespan of degrading system 
components. Therefore, already used systems are retrofitted by 
integrating sensors to monitor their performance and 
functionality, enabling accurate diagnosis of their condition and 
prediction of their remaining useful life. One of the main 
challenges in this field is identified in the missing data from the 
time where the retrofitted system has already run but without 
being monitored by sensors. In this paper, a novel approach for 
the combined diagnostics and prognostics of retrofitted systems is 
proposed. The methodology aims to provide an accurate diagnosis 
of the system’s health state and estimation of the remaining useful 
life by a combination of a machine learning and expert knowledge. 
To evaluate the effectiveness of the proposed methodology, a case 
study involving a retrofitted system in an industrial setting is 
selected and applied. It is demonstrated that the approach 
effectively diagnose the current system’s health state and 
accurately predict its remaining useful life, thereby enabling 
predictive maintenance and decision-making. Overall, our 
research contributes to advancing the field of condition 
monitoring for retrofitted systems by providing a comprehensive 
methodology that addresses the challenge of missing data.}},
  author       = {{Bender, Amelie and Aimiyekagbon, Osarenren Kennedy and Sextro, Walter}},
  booktitle    = {{Proceedings of the 2024 Prognostics and System Health Management Conference (PHM)}},
  isbn         = {{979-8-3503-6058-5}},
  keywords     = {{retrofit, diagnosis, prognostics, RUL prediction, missing data, ball bearings}},
  location     = {{Stockholm, Schweden}},
  publisher    = {{IEEE Computer Society}},
  title        = {{{Diagnostics and Prognostics for Retrofitted Systems: A Comprehensive Approach for Enhanced System Health Assessment}}},
  doi          = {{10.1109/PHM61473.2024.00038}},
  year         = {{2024}},
}

@inproceedings{56862,
  author       = {{Redeker, Magnus and Quirin, Dennis and Schroeder, Rafael and Klausmann, Tobias and Löwen, Alexander and Wollbrink, Alexander and Stichweh, Heiko and Althoff, Simon and Bender, Amelie and Sextro, Walter and Hesse, Marc}},
  booktitle    = {{2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)}},
  publisher    = {{IEEE}},
  title        = {{{Towards a One-Stop-Shop Solution for the Application of Data-Driven Value-Adding Services in Production}}},
  doi          = {{10.1109/etfa61755.2024.10711095}},
  volume       = {{13}},
  year         = {{2024}},
}

@article{55568,
  abstract     = {{<jats:p>Historical condition monitoring data from technical systems can be utilized to develop data-driven models for predicting the remaining useful life (RUL) of similar systems, whereas the Health Index (HI) often is a crucial component. The development of robust and accurate models requires meaningful features that reflect the system’s degradation process, enabling an accurate prediction of the system's HI. Traditionally, the identification of those is supported by one of various feature ranking methods. In literature, feature interdependencies and their transferability across various similar systems are not sufficiently considered in feature selection, exacerbating the challenge of HI prediction posed by the scarcity of data and system diversity in real-world applications. This work addresses this gaps by demonstrating how filter-based feature selection, incorporating failure thresholds and cross correlations, enhances feature selection leading to improved HI prediction. The proposed methodology is applied to a novel dataset* obtained from run-to-failure experiments on geared motors conducted as part of this study, which presents the aforementioned challenges. It is revealed that classical feature selection, consisting of feature ranking only, leaves potential untapped, which is utilized by the proposed selection methodology. It is shown that the proposed feature selection methodology leads to the best result with a RMSE of 0.14 in predicting the HI of a constructive different gearbox, while the features, determined by classical feature selection, lead to a RMSE of 0.19 at best.</jats:p>}},
  author       = {{Löwen, Alexander and Wissbrock, Peter and Bender, Amelie and Sextro, Walter}},
  isbn         = {{978-1-936263-40-0}},
  journal      = {{PHM Society European Conference}},
  location     = {{Prague}},
  number       = {{1}},
  pages        = {{955--964}},
  publisher    = {{PHM Society}},
  title        = {{{Filter-based feature selection for prognostics incorporating cross correlations and failure thresholds}}},
  doi          = {{10.36001/phme.2024.v8i1.4075}},
  volume       = {{8}},
  year         = {{2024}},
}

@inproceedings{55631,
  abstract     = {{This paper investigates the remaining useful lifetime (RUL) estimation of bearings under dynamic, i.e., time-varying, operating conditions (OC). Unlike conventional studies that assume constant OC in bearing accelerated life tests, we introduce a dataset with time-varying OC during run-to-failure experiments, simulating real-world scenarios. We explore data-driven approaches to identify the transition point from a healthy to an unhealthy state and estimate the RUL. Additionally, we examine strategies for integrating OC information to enhance RUL estimations. These methodologies are evaluated through numerical experiments using various machine learning algorithms.}},
  author       = {{Javanmardi, Alireza and Aimiyekagbon, Osarenren Kennedy and Bender, Amelie and Kimotho, James Kuria and Sextro, Walter and Hüllermeier, Eyke}},
  booktitle    = {{PHM Society European Conference}},
  isbn         = {{978-1-936263-40-0}},
  location     = {{Prague, Czech Republic}},
  number       = {{1}},
  publisher    = {{PHM Society}},
  title        = {{{Remaining Useful Lifetime Estimation of Bearings Operating under Time-Varying Conditions}}},
  doi          = {{10.36001/phme.2024.v8i1.4101}},
  volume       = {{8}},
  year         = {{2024}},
}

@article{56113,
  abstract     = {{Abstract This study focuses on hybrid modeling approaches that combine physical and data-driven methods to create more effective dynamical system models. In particular, it examines discrepancy models, a type of hybrid model that integrates a physical system model with data-driven compensation for inaccuracies. The study applies two discrepancy modeling methods to a multibody system using discrepancies in the state vector and its time derivative, respectively. As an application example, a four-bar linkage with nonlinear damping is investigated, using a simplified conservative system as a physical model. The comparative analysis of the two methods shows that the continuous approach generally outperforms the discrete method in terms of accuracy and computational efficiency, especially for velocity prediction and prediction horizon. However, scenarios, where input signals for training and testing differ, present nuanced findings. When the continuous method is trained on complex signals (sine) and tested on simpler ones (stair), it struggles to deliver satisfactory results, exhibiting notably higher root mean square error (RMSE) values, particularly in angular velocity prediction. Conversely, training on simple signals (stair) and testing on complex ones (sine) surprisingly yields low RMSE values, indicating the continuous method’s adaptability. While the discrete method aligns more closely with expectations and performs better in certain scenarios, its results are consistently moderate, neither exceptional nor particularly poor. The study also introduces a selection framework for choosing the most suitable algorithm based on the specific characteristics of the modeling task. This framework provides guidance for researchers and practitioners in leveraging hybrid modeling effectively. Finally, the study concludes with an outlook on future research directions.}},
  author       = {{Wohlleben, Meike Claudia and Röder, Benedict and Ebel, Henrik and Muth, Lars and Sextro, Walter and Eberhard, Peter}},
  journal      = {{PAMM}},
  pages        = {{e202400027}},
  title        = {{{Hybrid modeling of multibody systems: Comparison of two discrepancy models for trajectory prediction}}},
  doi          = {{https://doi.org/10.1002/pamm.202400027}},
  year         = {{2024}},
}

@inproceedings{61756,
  author       = {{Scheidemann, Claus and Hemsel, Tobias and Sextro, Walter}},
  location     = {{Hannover, Germany}},
  title        = {{{Characteristic behavior of lead-free and lead-containing piezo ring ceramics in ultrasonic transducers}}},
  year         = {{2024}},
}

@inproceedings{51119,
  author       = {{Scheidemann, Claus and Hagedorn, Oliver Ernst Caspar and Hemsel, Tobias and Sextro, Walter}},
  location     = {{Jeju, Korea}},
  title        = {{{Experimental Investigation of Bond Formation and Wire Deformation in the Ultrasonic Wire Bonding Process}}},
  year         = {{2023}},
}

@inproceedings{51338,
  author       = {{Schütte, Jan and Sextro, Walter}},
  booktitle    = {{20. VDI-Fachtagung Reifen - Fahrwerk - Fahrbahn}},
  location     = {{Karlsruhe}},
  pages        = {{165--180}},
  publisher    = {{VDI Verlag GmbH}},
  title        = {{{Einfluss der Radhubkinematik auf den Reifenverschleiß}}},
  volume       = {{2425}},
  year         = {{2023}},
}

@inproceedings{47116,
  abstract     = {{This paper presents a comprehensive study on diagnosing a spacecraft propulsion system utilizing data provided by the Prognostics and Health Management (PHM) society, specifically obtained as part of the Asia-Pacific PHM conference’s data challenge 2023. The objective of the challenge is to identify and diagnose known faults as well as unknown anomalies in the spacecraft’s propulsion system, which is critical for ensuring the spacecraft’s proper functionality and safety. To address this challenge, the proposed method follows a systematic approach of feature extraction, feature selection, and model development. The models employed in this study are kMeans clustering and decision trees combined to ensembles, enriched with expert knowledge. With the method presented, our team was capable of reaching high accuracy in identifying anomalies as well as diagnosing faults, resulting in attaining the seventh place with a score of 93.08 %.}},
  author       = {{Aimiyekagbon, Osarenren Kennedy and Löwen, Alexander and Bender, Amelie and Muth, Lars and Sextro, Walter}},
  booktitle    = {{Proceedings of the Asia Pacific Conference of the PHM Society 2023 }},
  keywords     = {{PHM, Fault Diagnostics, Multiple Fault Modes, Expert-Informed Diagnostics, Anomaly Detection}},
  number       = {{1}},
  title        = {{{Expert-Informed Hierarchical Diagnostics of Multiple Fault Modes of a Spacecraft Propulsion System}}},
  doi          = {{10.36001/phmap.2023.v4i1.3596}},
  volume       = {{4}},
  year         = {{2023}},
}

@inproceedings{46813,
  abstract     = {{Modelling of dynamic systems plays an important role in many engineering disciplines. Two different approaches are physical modelling and data‐driven modelling, both of which have their respective advantages and disadvantages. By combining these two approaches, hybrid models can be created in which the respective disadvantages are mitigated, with discrepancy models being a particular subclass. Here, the basic system behaviour is described physically, that is, in the form of differential equations. Inaccuracies resulting from insufficient modelling or numerics lead to a discrepancy between the measurements and the model, which can be compensated by a data‐driven error correction term. Since discrepancy methods still require a large amount of measurement data, this paper investigates the extent to which a single discrepancy model can be trained for a physical model with additional parameter dependencies without the need for retraining. As an example, a damped electromagnetic oscillating circuit is used. The physical model is realised by a differential equation describing the electric current, considering only inductance and capacitance; dissipation due to resistance is neglected. This creates a discrepancy between measurement and model, which is corrected by a data‐driven model. In the experiments, the inductance and the capacity are varied. It is found that the same data‐driven model can only be used if additional parametric dependencies in the data‐driven term are considered as well.}},
  author       = {{Wohlleben, Meike Claudia and Muth, Lars and Peitz, Sebastian and Sextro, Walter}},
  booktitle    = {{Proceedings in Applied Mathematics and Mechanics}},
  issn         = {{1617-7061}},
  keywords     = {{Electrical and Electronic Engineering, Atomic and Molecular Physics, and Optics}},
  publisher    = {{Wiley}},
  title        = {{{Transferability of a discrepancy model for the dynamics of electromagnetic oscillating circuits}}},
  doi          = {{10.1002/pamm.202300039}},
  year         = {{2023}},
}

@inproceedings{51117,
  author       = {{Scheidemann, Claus and Hemsel, Tobias and Friesen, Olga and Claes, Leander and Sextro, Walter}},
  location     = {{Jeju, Korea}},
  title        = {{{Influence of Temperature and Pre-Stress on the Piezoelectric Material Behavior of Ring-Shaped Ceramics}}},
  year         = {{2023}},
}

@inproceedings{29934,
  abstract     = {{Tire and road wear are a major source of emissions of nonexhaust particulate matter (PM) and make up the largest share of microplastics in the environment. To reduce tire wear through numerical optimization of a vehicle's suspension system, fast simulations of the representative usage of a vehicle are needed. Therefore, this contribution evaluates if instead of a full simulation of a representative test drive, only specific driving maneuvers resulting from a clustering of the driving data can be used to predict tire wear. As a measure for tire wear, the friction work between tire and road is calculated. It is shown that enough clusters result in negligible deviations between the total friction work of the full simulation and the cluster simulations as well as between the distributions of the friction work over the tire width. The calculation time can be reduced to about 1% of the full simulation.}},
  author       = {{Muth, Lars and Noll, Christian and Sextro, Walter}},
  booktitle    = {{Advances in Dynamics of Vehicles on Roads and Tracks II - Proceedings of the 27th Symposium of the International Association of Vehicle System Dynamics, IAVSD 2021}},
  editor       = {{Orlova, Anna and Cole, David}},
  isbn         = {{978-3-031-07304-5}},
  keywords     = {{Tire Wear, Vehicle Dynamics, Clustering, Virtual Test}},
  location     = {{Saint Petersburg, Russia}},
  publisher    = {{Springer}},
  title        = {{{Generation of a Reduced, Representative, Virtual Test Drive for Fast Evaluation of Tire Wear by Clustering of Driving Data}}},
  doi          = {{10.1007/978-3-031-07305-2_92}},
  year         = {{2022}},
}

@techreport{52045,
  author       = {{Scheidemann, Claus and Hemsel, Tobias and Sextro, Walter}},
  publisher    = {{LibreCat University}},
  title        = {{{Modellbasierte Ermittlung optimaler Prozessparameter für neuartige Ultraschallbondverbindungen}}},
  doi          = {{10.2314/KXP:1879655276}},
  year         = {{2022}},
}

@inbook{29727,
  author       = {{Wohlleben, Meike Claudia and Bender, Amelie and Peitz, Sebastian and Sextro, Walter}},
  booktitle    = {{Machine Learning, Optimization, and Data Science}},
  isbn         = {{9783030954697}},
  issn         = {{0302-9743}},
  publisher    = {{Springer International Publishing}},
  title        = {{{Development of a Hybrid Modeling Methodology for Oscillating Systems with Friction}}},
  doi          = {{10.1007/978-3-030-95470-3_8}},
  year         = {{2022}},
}

@inproceedings{30371,
  abstract     = {{To achieve optimum bond results at ultrasonic bonding thick copper wire on sensitive components is quite challenging.
Bearing in mind that high normal force and ultrasonic power are needed for bond quality but as well increase stress and finally failure risk of the substrate, methods should be found to achieve high bond quality even at lower bond parameters. Therefore, bond experiments with different bond tool grove geometries have been conducted for copper and aluminum wire on direct copper bonded (DCB) substrates to investigate the impact of geometric parameters on bond formation and bond quality. The wire material depending impact of geometry changes on the bond formation and deformation was quantified. Additionally, a bonding parameter design of experiments (DOE) has been conducted for the reference and the most promising groove geometry. Higher shear values were achieved at reduced vertical tool displacement for most bonding parameter combinations, compared to the reference tool. This behavior allows for reducing ultrasonic power to obtain equal shear values; consequently, mechanical stresses in the interface decrease. This could potentially reduce the risk of chip damage and thus yield loss.}},
  author       = {{Hagedorn, Oliver Ernst Caspar and Broll, Marian and Kirsch, Olaf and Hemsel, Tobias and Sextro, Walter}},
  booktitle    = {{CIPS 2022 - 12th International Conference on Integrated Power Electronics Systems}},
  isbn         = {{ISBN 978-3-8007-5757-2 }},
  location     = {{Berlin}},
  pages        = {{138--143}},
  publisher    = {{VDE VERLAG GMBH}},
  title        = {{{Experimental Investigation of the Influence of different Bond Tool Grooves on the Bond Quality for Ultrasonic Thick Wire Bonding}}},
  year         = {{2022}},
}

@misc{47159,
  author       = {{Aimiyekagbon, Osarenren Kennedy and Bender, Amelie and Sextro, Walter}},
  booktitle    = {{ Condition Monitor}},
  issn         = {{0268-8050}},
  number       = {{425}},
  pages        = {{5 -- 10}},
  title        = {{{On the applicability of time series features as health indicators for technical systems operating under varying conditions}}},
  year         = {{2022}},
}