Virtual sensing in an onshore wind turbine tower using a Gaussian process latent force model

Bilbao, Joaquin A.; Lourens, Eliz-Mari; Schulze, Andreas; Ziegler, Lisa

doi:10.1017/dce.2022.38

Cited by 7 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bilbao et al [122] explored the application of GPLFM for the monitoring of fatigue loads on wind turbine towers through virtual sensing, by employing acceleration measurements to forecast the dynamic strain. This model facilitates the estimation of both the dynamic loading applied and the resultant strain responses, with its validity is confirmed by comparison with actual strain gauge measurements.…”

Section: Pigp-based Methodsmentioning

confidence: 99%

On the Use of Indirect Measurements in Virtual Sensors for Renewable Energies: A Review

Benabdesselam,

Dollon,

Zemouri

et al. 2024

Electronics

View full text Add to dashboard Cite

In the dynamic landscape of renewable energy, the primary goal continues to be the enhancement of competitiveness through the implementation of cutting-edge technologies. This requires a strategic focus on reducing energy costs and maximizing system performance. Within this framework, the continuous online monitoring of assets is essential for efficient operations, by conducting measurements that describe the condition of various components. However, the execution of these measurements can present technical and economic obstacles. To overcome these challenges, the implementation of indirect measurement techniques emerges as a viable solution. By leveraging measurements obtained in easily accessible areas, these methods enable the estimation of quantities in regions that would otherwise be inaccessible. This approach improves the monitoring process’s efficiency and provides previously unattainable information. Adopting indirect measurement techniques is also cost-effective, allowing the replacement of expensive sensors with existing infrastructure, which cuts down on installation costs and labor. This paper offers a detailed state-of-the-art review by providing an in-depth examination and classification of indirect measurement techniques and virtual sensing methods applied in the field of renewable energies. It also identifies and discusses the existing challenges and limitations within this topic and explores potential future developments.

show abstract

Section: Pigp-based Methodsmentioning

confidence: 99%

On the Use of Indirect Measurements in Virtual Sensors for Renewable Energies: A Review

Benabdesselam,

Dollon,

Zemouri

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Differently, if more typologies of sensors are used, the main diagonal of will include the variances of each measurement noise, while the off-diagonal elements will represent the measurement noise covariances and will be equal to zero if noise sources are uncorrelated. The elements of the matrix can either be inferred along with the GP hyperparameters or estimated by using different techniques (see, e.g., Bilbao et al (2022)). The first approach will used in this paper.…”

Section: Mathematical Formulation Of the Switching Gaussian Process L...mentioning

confidence: 99%

“…For this reason, different approaches have been proposed over the years. Zou et al (2022) and Bilbao et al (2022) determine the optimal hyperparameters by minimizing the Hellinger distance between the empirical distribution of the measurements and the modelled Gaussian prior on the observed states; nonetheless, this approach can only be used when the response distribution is well-approximated by a Gaussian. Finally, Rogers at al.…”

Section: Mathematical Formulation Of the Switching Gaussian Process L...mentioning

confidence: 99%

“…In Rogers et al (2018Rogers et al ( , 2020, the GPLFM is also used to infer the uncertain physical parameters of the system. Further applications of the GPLFM to joint input-state identification can be found in recent experimental studies (Bilbao et al, 2022;Petersen et al, 2022;Zou et al, 2023Zou et al, , 2022b. Finally, in Rogers and Friis (2022), the GPLFM is applied to the nonlinear identification of mechanical systems with a known driving force.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A switching Gaussian process latent force model for the identification of mechanical systems with a discontinuous nonlinearity

Marino

Cicirello

2023

DCE

View full text Add to dashboard Cite

An approach for the identification of discontinuous and nonsmooth nonlinear forces, as those generated by frictional contacts, in mechanical systems that can be approximated by a single-degree-of-freedom model is presented. To handle the sharp variations and multiple motion regimes introduced by these nonlinearities in the dynamic response, the partially known physics-based model and noisy measurements of the system’s response to a known input force are combined within a switching Gaussian process latent force model (GPLFM). In this grey-box framework, multiple Gaussian processes are used to model the unknown nonlinear force across different motion regimes and a resetting model enables the generation of discontinuities. The states of the system, nonlinear force, and regime transitions are inferred by using filtering and smoothing techniques for switching linear dynamical systems. The proposed switching GPLFM is applied to a simulated dry friction oscillator and an experimental setup consisting of a single-storey frame with a brass-to-steel contact. Excellent results are obtained in terms of the identified nonlinear and discontinuous friction force for varying: (i) normal load amplitudes in the contact; (ii) measurement noise levels, and (iii) number of samples in the datasets. Moreover, the identified states, friction force, and sequence of motion regimes are used for evaluating: (1) uncertain system parameters; (2) the friction force–velocity relationship, and (3) the static friction force. The correct identification of the discontinuous nonlinear force and the quantification of any remaining uncertainty in its prediction enable the implementation of an accurate forward model able to predict the system’s response to different input forces.

show abstract

“…The approach used a mix between an augmented Kalman filter approach (Lourens et al, 2012), where the loads are estimated with the states of the system, and a physics-based aerodynamic estimator for aerodynamic thrust. Bilbao et al (2022) used a Gaussian process latent force model to estimate the forcing of the system and thereby obtain the section loads along the tower. Drivetrains are another component for which a digital twin has been applied, with physics-based approaches presented in Mehlan et al (2022Mehlan et al ( , 2023 and data-driven models presented in Kamel et al (2023).…”

Section: Introductionmentioning

confidence: 99%

A digital twin solution for floating offshore wind turbines validated using a full-scale prototype

Branlard,

Jonkman,

Brown

et al. 2024

Wind Energ. Sci.

View full text Add to dashboard Cite

Abstract. In this work, we implement, verify, and validate a physics-based digital twin solution applied to a floating offshore wind turbine. The digital twin is validated using measurement data from the full-scale TetraSpar prototype. We focus on the estimation of the aerodynamic loads, wind speed, and section loads along the tower, with the aim of estimating the fatigue lifetime of the tower. Our digital twin solution integrates (1) a Kalman filter to estimate the structural states based on a linear model of the structure and measurements from the turbine, (2) an aerodynamic estimator, and (3) a physics-based virtual sensing procedure to obtain the loads along the tower. The digital twin relies on a set of measurements that are expected to be available on any existing wind turbine (power, pitch, rotor speed, and tower acceleration) and motion sensors that are likely to be standard measurements for a floating platform (inclinometers and GPS sensors). We explore two different pathways to obtain physics-based models: a suite of dedicated Python tools implemented as part of this work and the OpenFAST linearization feature. In our final version of the digital twin, we use components from both approaches. We perform different numerical experiments to verify the individual models of the digital twin. In this simulation realm, we obtain estimated damage equivalent loads of the tower fore–aft bending moment with an accuracy of approximately 5 % to 10 %. When comparing the digital twin estimations with the measurements from the TetraSpar prototype, the errors increased to 10 %–15 % on average. Overall, the accuracy of the results is promising and demonstrates the possibility of using digital twin solutions to estimate fatigue loads on floating offshore wind turbines. A natural continuation of this work would be to implement the monitoring and diagnostics aspect of the digital twin to inform operation and maintenance decisions. The digital twin solution is provided with examples as part of an open-source repository.

show abstract

Virtual sensing in an onshore wind turbine tower using a Gaussian process latent force model

Cited by 7 publications

References 33 publications

On the Use of Indirect Measurements in Virtual Sensors for Renewable Energies: A Review

On the Use of Indirect Measurements in Virtual Sensors for Renewable Energies: A Review

A switching Gaussian process latent force model for the identification of mechanical systems with a discontinuous nonlinearity

A digital twin solution for floating offshore wind turbines validated using a full-scale prototype

Contact Info

Product

Resources

About