Oliver Nelles
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Oliver Nelles has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
Rolf Isermann
Laboratory of Control Systems and Process Automation, Darmstadt University of Technology, Institute of Automatic Control, Landgraf‐Georg‐Str. 4, D‐64283 Darmstadt, Germany
13 shared publicationsBenjamin Hartmann
Automatic Control, Mechatronics, Department of Mechanical Engineering, University of Siegen, D-57068, Germany
12 shared publicationsMartin Fischer
Laboratory of Control Systems and Process Automation, Darmstadt University of Technology, Institute of Automatic Control, Landgraf‐Georg‐Str. 4, D‐64283 Darmstadt, Germany
8 shared publicationsOliver Banfer
Department of Mechanical Engineering , University of Siegen, Germany
5 shared publications- Alexander Fink
Darmstadt University of Technology, Institute of Automatic Control, Laboratory of Control Engineering and Process Automation, Landgraf-Georg-Strasse 4, 64283 Darmstadt, Germany DE
4 shared publications Geritt Kampmann
4 shared publications
Latest Publications
- Open Access
- 1 October 2025
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 73 (10) , 727-739
Incorporation of structural properties of the response surface into oblique model trees
Oblique model trees are nonparametric regression models that partition the input space using axis-oblique splits to define local regions for regression. The Hierarchical Local Model Tree algorithm (HILOMOT) efficiently constructs these trees and produces a continuous output from overlapping local models, making it well suited for industrial applications. We enhance HILOMOT with a novel semi-greedy splitting method to reduce the short-sightedness of its greedy splitting, eliminate an undesirable trade-off during tree construction that can cause underfitting, and improve split interpretability. Our approach first estimates the strongest direction of curvature in a partition that the existing model cannot approximate. Then, a non-greedy method determines the optimal split orthogonal to this direction. We compare our method in experiments on synthetic data against HILOMOT and other established regression techniques. Qualitative results confirm that our method produces more interpretable splits, while quantitative results show it generally constructs more accurate and compact trees. Regardless of the splitting method, HILOMOT consistently outperforms all reference methods in accuracy.
- 1 October 2025
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 73 (10) , 727-739
Open AccessIncorporation of structural properties of the response surface into oblique model trees
Oblique model trees are nonparametric regression models that partition the input space using axis-oblique splits to define local regions for regression. The Hierarchical Local Model Tree algorithm (HILOMOT) efficiently constructs these trees and produces a continuous output from overlapping local models, making it well suited for industrial applications. We enhance HILOMOT with a novel semi-greedy splitting method to reduce the short-sightedness of its greedy splitting, eliminate an undesirable trade-off during tree construction that can cause underfitting, and improve split interpretability. Our approach first estimates the strongest direction of curvature in a partition that the existing model cannot approximate. Then, a non-greedy method determines the optimal split orthogonal to this direction. We compare our method in experiments on synthetic data against HILOMOT and other established regression techniques. Qualitative results confirm that our method produces more interpretable splits, while quantitative results show it generally constructs more accurate and compact trees. Regardless of the splitting method, HILOMOT consistently outperforms all reference methods in accuracy.
- Open Access
Space-Filling Regularization for Robust and Interpretable Nonlinear State Space Models
The state space dynamics representation is the most general approach for nonlinear systems and often chosen for system identification. During training, the state trajectory can deform significantly leading to poor data coverage of the state space. This can cause significant issues for space-oriented training algorithms which e.g. rely on grid structures, tree partitioning, or similar. Besides hindering training, significant state trajectory deformations also deteriorate interpretability and robustness properties. This paper proposes a new type of space-filling regularization that ensures a favorable data distribution in state space via introducing a data-distribution-based penalty. This method is demonstrated in local model network architectures where good interpretability is a major concern. The proposed approach integrates ideas from modeling and design of experiments for state space structures. This is why we present two regularization techniques for the data point distributions of the state trajectories for local affine state space models. Beyond that, we demonstrate the results on a widely known system identification benchmark.
Open AccessSpace-Filling Regularization for Robust and Interpretable Nonlinear State Space Models
The state space dynamics representation is the most general approach for nonlinear systems and often chosen for system identification. During training, the state trajectory can deform significantly leading to poor data coverage of the state space. This can cause significant issues for space-oriented training algorithms which e.g. rely on grid structures, tree partitioning, or similar. Besides hindering training, significant state trajectory deformations also deteriorate interpretability and robustness properties. This paper proposes a new type of space-filling regularization that ensures a favorable data distribution in state space via introducing a data-distribution-based penalty. This method is demonstrated in local model network architectures where good interpretability is a major concern. The proposed approach integrates ideas from modeling and design of experiments for state space structures. This is why we present two regularization techniques for the data point distributions of the state trajectories for local affine state space models. Beyond that, we demonstrate the results on a widely known system identification benchmark.
- Open Access
- 3 July 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 164
Analysis of space-filling excitation signals and dynamic models for nonlinear system identification of dynamic processes of a Diesel engine
- 3 July 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 164
Open AccessAnalysis of space-filling excitation signals and dynamic models for nonlinear system identification of dynamic processes of a Diesel engine
- Open Access
- 2 May 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 162
Adaptive nonlinear system identification of separation unit for raw materials
- 2 May 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 162
Open AccessAdaptive nonlinear system identification of separation unit for raw materials
- 18 March 2025
- Published by ASME International in ASME Letters in Dynamic Systems and Control
- Vol. 5 (4) , 1-8
Nonlinear System Identification With Gaussian Processes Using Laguerre and Kautz Filters
System identification can be used to determine data-driven mathematical models of dynamic processes. For nonlinear processes, model architectures that are as flexible as possible are required. One possibility is to utilize Gaussian processes (GPs) as a universal approximator with an external dynamics realization, leading to highly flexible models. Novel Laguerre and Kautz filter-based dynamics realizations in GP models are proposed. The Laguerre/Kautz pole(s) are treated as hyperparameters with the GPs’ standard hyperparameter for the squared exponential kernel with automatic relevance determination (SE-ARD) kernel. The two novel dynamics realizations in GP models are compared to different state-of-the-art dynamics realizations such as finite impulse response (FIR) or autoregressive with exogenous input (ARX). The big data case is handled via support points. Using Laguerre and Kautz regressor spaces allows both the dimensionality of the regressor space to be kept small and achieve superior performance. This is demonstrated through numerical examples and measured benchmark data of a Wiener–Hammerstein process.
- 18 March 2025
- Published by ASME International in ASME Letters in Dynamic Systems and Control
- Vol. 5 (4) , 1-8
Nonlinear System Identification With Gaussian Processes Using Laguerre and Kautz Filters
System identification can be used to determine data-driven mathematical models of dynamic processes. For nonlinear processes, model architectures that are as flexible as possible are required. One possibility is to utilize Gaussian processes (GPs) as a universal approximator with an external dynamics realization, leading to highly flexible models. Novel Laguerre and Kautz filter-based dynamics realizations in GP models are proposed. The Laguerre/Kautz pole(s) are treated as hyperparameters with the GPs’ standard hyperparameter for the squared exponential kernel with automatic relevance determination (SE-ARD) kernel. The two novel dynamics realizations in GP models are compared to different state-of-the-art dynamics realizations such as finite impulse response (FIR) or autoregressive with exogenous input (ARX). The big data case is handled via support points. Using Laguerre and Kautz regressor spaces allows both the dimensionality of the regressor space to be kept small and achieve superior performance. This is demonstrated through numerical examples and measured benchmark data of a Wiener–Hammerstein process.
- Open Access
- 13 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 112594-112604
Optimization of Fuel Consumption for Rule-Based Energy Management Strategies of Hybrid Electric Vehicles: SOC Compensation Methods
To optimize the fuel consumption of hybrid electric vehicles (HEV) controlled by rule-based energy management strategies (EMS), multiple driving cycles are simulated. These driving cycles are simulated with different EMS calibrations and the optimizer compares the corresponding fuel consumptions. A drive cycle simulation usually ends with a different end state of charge (SOC) compared to the start SOC. Such an unbalanced SOC for the secondary energy source (battery) affects the consumption of the primary energy source (fuel). Therefore, it is crucial to consider the battery SOC difference when comparing fuel consumption in a drive cycle. In this paper, six different methods are presented to compensate the SOC difference or to achieve a balanced SOC, such as Multiple Sequential Drive Cycle Simulation, Variation of Start SOC, Linear Regression, Static Correction Factor, Individual Correction Factor and Linear Interpolation . These methods are compared in their applicability within a numerical optimization and, for a subset, also in their accuracy in SOC compensation using an exemplary hybrid electric vehicle model. It was determined, that Linear Interpolation requires twice as much computing time as either Static or Individual Correction Factor, but it is the most accurate method. In addition, it supports robust EMS behavior without strongly restricting the boundary conditions within the optimization.
- 13 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 112594-112604
Open AccessOptimization of Fuel Consumption for Rule-Based Energy Management Strategies of Hybrid Electric Vehicles: SOC Compensation Methods
To optimize the fuel consumption of hybrid electric vehicles (HEV) controlled by rule-based energy management strategies (EMS), multiple driving cycles are simulated. These driving cycles are simulated with different EMS calibrations and the optimizer compares the corresponding fuel consumptions. A drive cycle simulation usually ends with a different end state of charge (SOC) compared to the start SOC. Such an unbalanced SOC for the secondary energy source (battery) affects the consumption of the primary energy source (fuel). Therefore, it is crucial to consider the battery SOC difference when comparing fuel consumption in a drive cycle. In this paper, six different methods are presented to compensate the SOC difference or to achieve a balanced SOC, such as Multiple Sequential Drive Cycle Simulation, Variation of Start SOC, Linear Regression, Static Correction Factor, Individual Correction Factor and Linear Interpolation . These methods are compared in their applicability within a numerical optimization and, for a subset, also in their accuracy in SOC compensation using an exemplary hybrid electric vehicle model. It was determined, that Linear Interpolation requires twice as much computing time as either Static or Individual Correction Factor, but it is the most accurate method. In addition, it supports robust EMS behavior without strongly restricting the boundary conditions within the optimization.
- 15 November 2023
- Published by Springer Nature
- p. 311-322
Uniform Design of Experiments for Equality Constraints
- 15 November 2023
- Published by Springer Nature
- p. 311-322
Uniform Design of Experiments for Equality Constraints
- Open Access
- 1 October 2023
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 71 (10) , 833-844
Handling of time delays in system identification with regularized FIR models
System identification with finite impulse response (FIR) models has been recently revised by introducing specific forms of regularization in the estimation. By utilizing prior knowledge of the dynamic process under investigation different kernels for regularization can be derived. However, the dynamical processes considered are mainly restricted to time-delay free systems. Therefore, in this paper we propose two novel methods to handle the time-delay case. Both methods incorporate the time-delay estimation in the hyperparameter optimization of the regularized FIR models. The first method is built on a single kernel (SK) and the second utilizes a multiple kernel (MK) approach. Simulations on different dynamical systems show the superior behavior of both methods in comparison to standard regularization methods, whereupon the MK outperforms the SK approach.
- 1 October 2023
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 71 (10) , 833-844
Open AccessHandling of time delays in system identification with regularized FIR models
System identification with finite impulse response (FIR) models has been recently revised by introducing specific forms of regularization in the estimation. By utilizing prior knowledge of the dynamic process under investigation different kernels for regularization can be derived. However, the dynamical processes considered are mainly restricted to time-delay free systems. Therefore, in this paper we propose two novel methods to handle the time-delay case. Both methods incorporate the time-delay estimation in the hyperparameter optimization of the regularized FIR models. The first method is built on a single kernel (SK) and the second utilizes a multiple kernel (MK) approach. Simulations on different dynamical systems show the superior behavior of both methods in comparison to standard regularization methods, whereupon the MK outperforms the SK approach.
- 1 October 2023
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 71 (10) , 820-832
Latin hypercubes for constrained design of experiments for data-driven models
The quality of data used for data-driven modeling affects the model performance significantly. Thus, design of experiments (DoE) is an important part during model development. The design space is constrained in many applications. In this work, the constrained case is investigated. An Latin hypercube based approach is applied and analyzed for strongly constrained design spaces. Contrary to commonly used optimization techniques, an incremental procedure is proposed. In every step, new data are added to the design. Each new point is selected by a distance-based criterion. The performance of the created designs is evaluated by the quality of the trained models. For different constraints, artificial data sets are created with a function generator. The performance of local model networks and Gaussian process regression models trained with those designs is evaluated and compared to models trained on data sets based on Sobol’ sequences.
- 1 October 2023
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 71 (10) , 820-832
Latin hypercubes for constrained design of experiments for data-driven models
The quality of data used for data-driven modeling affects the model performance significantly. Thus, design of experiments (DoE) is an important part during model development. The design space is constrained in many applications. In this work, the constrained case is investigated. An Latin hypercube based approach is applied and analyzed for strongly constrained design spaces. Contrary to commonly used optimization techniques, an incremental procedure is proposed. In every step, new data are added to the design. Each new point is selected by a distance-based criterion. The performance of the created designs is evaluated by the quality of the trained models. For different constraints, artificial data sets are created with a function generator. The performance of local model networks and Gaussian process regression models trained with those designs is evaluated and compared to models trained on data sets based on Sobol’ sequences.
- Open Access
- 1 January 2023
- Published by Springer Nature
- p. C3
Correction to: Local Linear Neuro-Fuzzy Models: Advanced Aspects
- 1 January 2023
- Published by Springer Nature
- p. C3
Open AccessCorrection to: Local Linear Neuro-Fuzzy Models: Advanced Aspects