Model Updating for Nonlinear Dynamic Digital Twins Using Data-Based Inverse Mapping Models

Kessels, Bas M.; Fey, Rob H. B.; Abbasi, Mohammad; Wouw, Nathan van de

doi:10.1007/978-3-031-04122-8_1

Cited by 3 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that, since other generic function approximation algorithms may also be used to constitute IMMs, the authors prefer to refer to this methodology as the inverse mapping parameter updating (IMPU) method. For example, in recent work of the authors, Gaussian processes are used as IMMs, with the added benefit of enabling uncertainty quantification for the estimated parameter values [64]. The main qualitative advantage of this method with respect to previously discussed parameter updating methods is that online parameter updating is enabled even for large-scale systems with high sampling frequencies.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, the three main contributions of this work are: In preliminary work of the authors [65], the IMPU method has been applied to update a nonlinear dynamical model. However, this extended abstract only discussed the use of a single, straightforward timedomain-based feature type (samples of measured timeseries data as directly obtained from measurements).…”

Section: Introductionmentioning

confidence: 99%

“…With respect to this extended abstract, one of the impor-tant novelties of this paper lies in the proposal of different transient-based (both time-domain and frequencydomain) feature types that aim at further improving the accuracy of the parameter estimates using engineering knowledge. The current paper expands upon [65] with the following contributions: (1) a full-fledged description of the IMPU method for nonlinear systems, (2) a more complete application and analysis on two simulated multibody systems, one of them including a comparison with the well-known Kalman filtering technique, (3) an elaborate analysis of generalization capabilities of the IMPU method, and (4) the definition, analysis, and comparison of various transient-based feature types.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-time parameter updating for nonlinear digital twins using inverse mapping models and transient-based features

2023

Self Cite

View full text Add to dashboard Cite

In the context of digital twins, it is essential that a model gives an accurate description of the (controlled) dynamic behavior of a physical system during the system’s entire operational life. Therefore, model updating techniques are required that enable real-time updating of physically interpretable parameter values and are applicable to a wide range of (nonlinear) dynamical systems. As traditional, iterative, parameter updating methods may be computationally too expensive for real-time updating, the inverse mapping parameter updating (IMPU) method is proposed as an alternative. For this method, first, an artificial neural network (ANN) is trained offline using novel features of simulated transient response data. Then, in the online phase, this ANN maps, with little computational cost, a set of measured output response features to parameter estimates enabling real-time model updating. In this paper, various types of transient response features are introduced to update parameter values of nonlinear dynamical systems with increased computational efficiency and accuracy. To analyze the efficacy of these features, the IMPU method is applied to a (simulated) nonlinear multibody system. It is shown that a smart selection of features, based on, e.g., the frequency content of the transient response, can improve the accuracy of the estimated parameter values, leading to more accurate updated models. Furthermore, the generalization capabilities of the ANNs are analyzed for these feature types, by varying the number of training samples and assessing the effect of incomplete training data. It is shown that the IMPU method can predict parameter values that are not part of the training data with acceptable accuracy as well.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time parameter updating for nonlinear digital twins using inverse mapping models and transient-based features

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, Zimmerman uses genetic algorithms [51]. Moreover, in recent work of the authors, Gaussian processes are used as IMMs, with the added benefit of enabling uncertainty quantification for the estimated parameter values [52]. To the best of the authors' knowledge, this IMPU methodology has, however, only been applied to linear(ized) dynamical systems.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, the three main contributions of this work are: In preliminary work of the authors [53], the IMPU method has been applied to update a nonlinear dynamical model. However, this work only discussed the use of a single, straightforward transient-based feature type (samples of measured time-series data as directly obtained from measurements).…”

Section: Introductionmentioning

confidence: 99%

Real-time parameter updating for nonlinear digital twins using inverse mapping models and transient-based features

Kessels

Fey

Wouw

2022

Preprint

View full text Add to dashboard Cite

In the context of digital twins, it is essential that a model gives an accurate description of the (controlled) dynamic behavior of a physical system during the system’s entire operational life. Therefore, model updating techniques are required that enable real-time updating of physically interpretable parameter values and are applicable to a wide range of (nonlinear) dynamical systems. As traditional, iterative, parameter updating methods may be computationally too expensive for real-time updating, the Inverse Mapping Parameter Updating (IMPU) method is proposed as an alternative. For this method, first, an Artificial Neural Network (ANN) is trained offline using novel features of simulated transient response data. Then, in the online phase, this ANN maps, with little computational cost, a set of measured output response features to parameter estimates enabling real-time model updating. In this paper, various types of transient response features are introduced to update parameter values of nonlinear dynamical systems with increased computational efficiency and accuracy. To analyze the efficacy of these features, the IMPU method is applied to a (simulated) nonlinear multibody system. It is shown that a smart selection of features, based on, e.g., the frequency content of the transient response, can improve the accuracy of the estimated parameter values, leading to more accurate updated models. Furthermore, the generalization capabilities of the ANNs are analyzed for these feature types, by varying the number of training samples and assessing the effect of incomplete training data. It is shown that the IMPU method can predict parameter values that are not part of the training data with acceptable accuracy as well.

show abstract

Iterative updating of digital twin for equipment: Progress, challenges, and trends

Zhang,

Ding,

Zheng

et al. 2024

Advanced Engineering Informatics

View full text Add to dashboard Cite

Model Updating for Nonlinear Dynamic Digital Twins Using Data-Based Inverse Mapping Models

Cited by 3 publications

References 3 publications

Real-time parameter updating for nonlinear digital twins using inverse mapping models and transient-based features

Real-time parameter updating for nonlinear digital twins using inverse mapping models and transient-based features

Real-time parameter updating for nonlinear digital twins using inverse mapping models and transient-based features

Iterative updating of digital twin for equipment: Progress, challenges, and trends

Contact Info

Product

Resources

About