Publikationen

State estimation using LSTMs trained on synthetic data and validated with real measurements

Geisler, J. . (2025). State estimation using LSTMs trained on synthetic data and validated with real measurements. Namtes: WESC 2025. http://doi.org/10.5281/zenodo.15830516 (Original work published Juni 2025)

Abstract

This study represents a novel contribution by demonstrating that LSTM-based estimators can replace traditional state estimation pipelines in wind turbine applications. By eliminating the need for detailed modeling and manual tuning, this approach opens up new opportunities for data-driven estimation in renewable energy systems.
Unlike conventional estimators based on linear or nonlinear physical models, the proposed method trains LSTM networks to learn the mapping from inputs and outputs to internal state estimates using only simulation data. Such data can be generated in large volumes with complete access to all internal states, leveraging high-fidelity turbine simulation tools. The trained LSTM functions as a complete estimator, replacing both the predictor and corrector stages typically found in Kalman filter structures.
The approach is evaluated across a variety of estimation tasks, from rotor effective wind speed (REWS) to more complex quantities such as blade deflections and wind shear coefficients. Results demonstrate that LSTMs trained entirely on simulation data can generalize well to real-world measurements, achieving estimation quality comparable to that of EKFs. Moreover, the method proves flexible and scalable to different input-output combinations without extensive manual modeling.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
- Forschungsprojekt
  
  Adaptive Betriebsstrategien für bestehende Windenergieanlagen
- Profilbereich
  
  Erneuerbare Energien und nachhaltige Entwicklung
- Forschungsfeld
  
  Wind
- Fachbereich
  
  Fachbereich 2: Energy and Life Science
Filter Tags
Automatically generated state observers – toolchain and validation with real measurements

Geisler, J. . (2024). Automatically generated state observers – toolchain and validation with real measurements. In Torque 2024. Florenz: IOP Publishing. http://doi.org/10.1088/1742-6596/2767/3/032003 (Original work published Juni 2024)

Abstract

State estimation of wind turbines is the basis for many advanced control strategies and analysis applications such as condition monitoring, fault diagnosis, and much more. It depends on the application and its goals, which states of the real turbine are relevant. Therefore, estimators with different levels of detail and sets of states suitable for the problem at hand are needed. This paper describes a toolchain that generates custom-tailored code for an extended Kalman filter. The aim is to create computationally highly efficient estimators for a wide range of applications. Automatic generation of source code allows for agile experimentation and reduces the risk of time-consuming implementation errors. The new contributions are the selection and combination of all parts of the toolchain, the extension of the integration algorithm to include the Jacobian of the transition function, and the adaptation of an efficient covariance auto-tuning algorithm. Four different models are validated in a three-stage process, including measurement data from a real turbine.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
- Profilbereich
  
  Erneuerbare Energien und nachhaltige Entwicklung
- Forschungsfeld
  
  Wind
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 2: Energy and Life Science
Filter Tags
Simplified dynamic inflow for control engineering models

Geisler, J. . (2022). Simplified dynamic inflow for control engineering models. In Torque 2022. Delft: IOP Publishing. http://doi.org/10.1088/1742-6596/2265/3/032101 (Original work published Mai 2022)

Abstract

Simplified turbine models are needed wherever computational resources are limited and the model needs to run in real-time or faster, or when it is used in analytical procedures such as linearization. These use cases are typically given in control engineering applications, especially advanced methods such as nonlinear model predictive control or state estimation. Many such models with varying levels of detail have been proposed, but most of them rely on a quasi-stationary, rotor averaged/effective representation of aerodynamic forces. Unsteady aerodynamic effects such as dynamic inflow (sometimes referred to as dynamic wake) or dynamic stall are usually neglected. But with ever more advanced methods more detailed yet still computationally efficient models are needed. Therefore, this work proposes an approach for adding the effect of dynamic inflow to any rotor effective force or moment that was previously modeled as quasi-stationary. Novel to this work is the suitability for nonlinear as well as linear models and a focus on computational efficiency while still optimally recreating the effect.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
- Fachbereich
  
  Fachbereich 2: Energy and Life Science
Filter Tags
A symbolic framework to obtain mid-fidelity models of flexible multibody systems with application to horizontal-axis wind turbines

Branlard, E. ., & Geisler, J. . (2022). A symbolic framework to obtain mid-fidelity models of flexible multibody systems with application to horizontal-axis wind turbines. Wind Energy Science, 7, 2351–2371. http://doi.org/10.5194/wes-7-2351-2022

Abstract

The article presents a symbolic framework (also called computer algebra program) that is used to obtain, in symbolic mathematical form, the linear and nonlinear equations of motion of a mid-fidelity multibody system including rigid and flexible bodies. Our approach is based on Kane's method and a nonlinear shape function representation for flexible bodies. The shape function approach does not represent the state of the art for flexible multibody dynamics but is an effective trade-off to obtain mid-fidelity models with few degrees of freedom, taking advantage of the separation of space and time. The method yields compact symbolic equations of motion with implicit account of the constraints. The general and automatic framework facilitates the creation and manipulation of models with various levels of complexity by adding or removing degrees of freedom. The symbolic treatment allows for analytical gradients and linearized equations of motion. The linear and nonlinear equations can be exported to Python code or dedicated software. There are multiple applications, such as time domain simulation, stability analyses, frequency domain analyses, advanced controller design, state observers, and digital twins. In this article, we describe the method we used to systematically generate the equations of motion of multibody systems and present the implementation of the framework using the Python package SymPy. We apply the framework to generate illustrative land-based and offshore wind turbine models. We compare our results with OpenFAST simulations and discuss the advantages and limitations of the method. The Python implementation is provided as an open-source project.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
- Profilbereich
  
  Erneuerbare Energien und nachhaltige Entwicklung
- Fachbereich
  
  Fachbereich 2: Energy and Life Science
Filter Tags
A Familie of Simplified Aerodynamic Models for Wind Turbine Controller Design and Analysis

Geisler, J. . (2021). A Familie of Simplified Aerodynamic Models for Wind Turbine Controller Design and Analysis. Hannover / Online: Wind Energy Science Conference. http://doi.org/10.5281/zenodo.5148441 (Original work published Mai 2021)
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
- Fachbereich
  
  Fachbereich 2: Energy and Life Science
Filter Tags
Symbolic Flexible Multibody Models for Wind Turbine Controller Design and Analysis

Geisler, J. ., & Branlard, E. . (2021). Symbolic Flexible Multibody Models for Wind Turbine Controller Design and Analysis. Hannover / Online: Wind Energy Science Conference. http://doi.org/10.5281/zenodo.5148447 (Original work published Mai 2021)
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
- Fachbereich
  
  Fachbereich 2: Energy and Life Science
Filter Tags
Verfahren zum Betreiben einer Windenergieanlage und Steuerung für eine Windenergieanlage DE102017009985

Geisler, J. ., & Frahm, S. . (2019). Verfahren zum Betreiben einer Windenergieanlage und Steuerung für eine Windenergieanlage DE102017009985. Germany: Senvion GmbH. (Original work published Mai 2019)
- Suche auf Google Scholar
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
Filter Tags
- 2019
- Patent
- - Jens Geisler
  - S. Frahm
Steuerungssystem und Verfahren zum Betreiben mehrerer Windenergieanlagen DE102017009838

Geisler, J. ., & Schmuck, J. . (2019). Steuerungssystem und Verfahren zum Betreiben mehrerer Windenergieanlagen DE102017009838. Germany: Senvion GmbH. (Original work published April 2019)
- Suche auf Google Scholar
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
Filter Tags
- 2019
- Patent
- - Jens Geisler
  - J. Schmuck
Steuerungssystem und Verfahren zum Betreiben einer Mehrzahl von Windenergieanlagen DE102017009837

Geisler, J. ., & Schmuck, J. . (2019). Steuerungssystem und Verfahren zum Betreiben einer Mehrzahl von Windenergieanlagen DE102017009837. Germany: Senvion GmbH. (Original work published April 2019)
- Suche auf Google Scholar
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
Filter Tags
- 2019
- Patent
- - Jens Geisler
  - J. Schmuck
Nichtlineare, ökonomische Modellprädiktive Regelung für die prototypische Erprobung auf einer Windkraftanlage

Geisler, J. . (2019). Nichtlineare, ökonomische Modellprädiktive Regelung für die prototypische Erprobung auf einer Windkraftanlage. RWTH Aachen: Vortragsreihe "Beiträge zur Regelungstechnik". (Original work published Februar 2019)
- Suche auf Google Scholar
Exportformate
Weiterführende Links
- Personenseiten
  
  Geisler, Jens
Filter Tags

Publikationen

Abstract

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags