Efficient Bayesian sensor placement algorithm for structural identification: a general approach for multi‐type sensory systems

Yuen, Ka‐Veng; Kuok, Sin‐Chi

doi:10.1002/eqe.2486

Cited by 108 publications

(112 citation statements)

References 39 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…It can be seen that the expected relative information or expected K-L divergence has a direct connection to the robust information entropy proposed by Papadimitriou et al [13] and extended by Yuen and Kuok [24] for non-uniform distributions.…”

Section: Expected Utility Functionmentioning

confidence: 65%

“…The contribution from the prior is the result of the application of the Bayesian optimal experimental design proposed herein based on optimizing the expected K-L divergence. Alternatively, Yuen and Kuok [24] have also proposed a non-uniform prior on the information entropy measure in order to solve this unidentifiability problem. For uniform prior and unidentifiable case, Papadimitriou and Lombaert [16] proposed the sum of the log of the nonzero eigenvalues in the FIM to be maximized instead of the sum of the log of all eigenvalues.…”

Section: Formulation For Modal Identificationmentioning

confidence: 99%

“…This is due to the fact that the FIM becomes singular. Yuen and Kuok [24] noted that introducing non-uniform priors in the Bayesian posterior used in the information entropy measures resolves the problem. For uniform priors, Papadimitriou and Lombaert [16] obtained reasonable sensor placement design by excluding the zero eigenvalues from the product of the eigenvalues of the FIM used for computing the determinant of the FIM that is required in information entropy formulations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent Concrete with Self-x Capabilities for Smart Cities

Wang

Han

et al. 2017

J Smart Cities

View full text Add to dashboard Cite

A Bayesian optimal experimental design (OED) method is proposed in this work for estimating the best locations of sensors in structures so that the measured data are most informative for estimating reliably the structural modes. The information contained in the data is measured by the Kullback-Leibler (K-L) divergence between the prior and posterior distribution of the model parameters taken in modal identification to be the modal coordinates. The optimal sensor placement that maximizes the expected K-L divergence is shown also to minimize the information entropy of the posterior distribution. Unidentifiability issues observed in existing formulations when the number of sensors is less than the number of identified modes, are resolved using a non-uniform prior in the Bayesian OED. An insightful analysis is presented that demonstrates the effect of the variances of Bayesian priors on the optimal design. For dense mesh finite element models, sensor clustering phenomena are avoided by integrating in the methodology spatially correlated prediction error models. A heuristic forward sequential sensor placement algorithm and a stochastic optimization algorithm are used to solve the optimization problem in the continuous physical domain of variation of the sensor locations. The theoretical developments and algorithms are applied for the optimal sensor placement design along the deck of a 537 m concrete bridge.

show abstract

Section: Expected Utility Functionmentioning

confidence: 65%

Section: Formulation For Modal Identificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Concrete with Self-x Capabilities for Smart Cities

Wang

Han

et al. 2017

J Smart Cities

View full text Add to dashboard Cite

show abstract

“…A flourishing direction to address this issue is by the use of Bayesian inference. It provides a rigorous solution for system identification using probabilistic logic (Beck, ; Box & Tiao, ; Yuen & Kuok, ) and it has demonstrated profound impact to engineering applications (Ching, Beck et al., ; Huang, Beck, Wu, & Li, ; Jiang, Mahadevan, & Adeli, ; Katafygiotis, Papadimitriou, & Lam, ; Kuok & Yuen, ; Lam, Hu, & Yang, ; Mu & Yuen, ; Papadimitriou et al., ; Yan & Ren, ; Yin, Lam, & Chow, ; Yuen, ; Yuen & Kuok, ). Taking the advantage of Bayesian inference, Bayesian model class selection offers a rational basis for assessing the relative performance of the model classes.…”

Section: Introductionmentioning

confidence: 99%

Self‐calibrating Bayesian real‐time system identification

Yuen

Kuok

Dong

2019

Computer aided Civil Eng

View full text Add to dashboard Cite

In this article, a novel Bayesian framework is proposed for real‐time system identification with calibratable model classes. This self‐calibrating scheme adaptively reconfigures the model classes to achieve reliable real‐time estimation for the system state and model parameters. At each time step, the plausibilities of the model classes are computed and they serve as the cue for calibration. Once calibration is triggered, all model classes will be reconfigured. Thereafter, identification will continue to propagate with the calibrated model classes until the next recalibration. Consequently, the model classes will evolve and their deficiencies can be corrected adaptively. This remarkable feature of the proposed framework stimulates the accessibility of reliable real‐time system identification. Examples are presented to demonstrate the efficacy of the proposed approach using noisy response measurement of linear and nonlinear time‐varying dynamical systems under stationary condition.

show abstract

“…Structural health monitoring also requires sensor placement strategies that have been studied by Yi et al, Li et al, and Debnath et al [26][27][28][29]. Bayesian probabilistic approaches have been shown to be effective in determining the optimal sensor configuration based on model estimations by Beck and Katafygiotis, Beck and Yuen, Katafygiotis et al, Papadimitriou et al, and Yuen and Kuok [30][31][32][33][34]. These 2 Journal of Sensors researchers and many others have made significant contributions in the field and there are several more methods for sensor location identification.…”

Section: Introductionmentioning

confidence: 99%

The Reduction of Modal Sensor Channels through a Pareto Chart Methodology

Lemler¹,

Semke

2015

Journal of Sensors

View full text Add to dashboard Cite

Presented herein is a new experimental sensor placement procedure developed to assist in placing sensors in key locations in an efficient method to reduce the number of channels for a full modal analysis. It is a fast, noncontact method that uses a laser vibrometer to gather a candidate set of sensor locations. These locations are then evaluated using a Pareto chart to obtain a reduced set of sensor locations that still captures the motion of the structure. The Pareto chart is employed to identify the points on a structure that have the largest reaction to an input excitation and thus reduce the number of channels while capturing the most significant data. This method enhances the correct and efficient placement of sensors which is crucial in modal testing. Previously this required the development and/or use of a complicated model or set of equations. This new technique is applied in a case study on a small unmanned aerial system. The test procedure is presented and the results are discussed.

show abstract

Efficient Bayesian sensor placement algorithm for structural identification: a general approach for multi‐type sensory systems

Cited by 108 publications

References 39 publications

Intelligent Concrete with Self-x Capabilities for Smart Cities

Intelligent Concrete with Self-x Capabilities for Smart Cities

Self‐calibrating Bayesian real‐time system identification

The Reduction of Modal Sensor Channels through a Pareto Chart Methodology

Contact Info

Product

Resources

About