Robust Kalman Filter for Linear System With Convex Polytopic Uncertainties

Yu, Xiaohui; Xin, Dong-Jin; Li, Jianxun

doi:10.1109/tcsii.2022.3170911

Cited by 5 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This poses a challenge in control and signal processing communities. 9,10 Generally speaking, to address the above challenge, various robust filters/estimators are developed based on different criteria and methods. 4,11,12 Among them the most representative ones are finite/moving horizon filters, 13,14 adaptive filter, 1,15 (unbiased) finite impulse response ((U)FIR) filter, 16 energy-to-peak filter, 17 peak-to-peak filter, 18 H 2 filter, 19 H ∞ filter, 20 and their extensions.…”

Section: Introductionmentioning

confidence: 99%

“…4,27 As it is well known, the multiplicative-noise system depicts a broader situation, which also is more sensitive to accurate modeling and model uncertainty. 10,28 Besides, multiplicative noise has a more drastic influence on model uncertainty than additive noise does. 29 In addition, the considered perturbations in existing works are usually stable but not violent.…”

Section: Introductionmentioning

confidence: 99%

“…3. Compared with multiplicative-noise-based robust filters, 10,28 this article employs an ambiguity set to model uncertainty, which outperforms them in both accuracy and efficiency.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, the desired robust version 8 of standard KF against noise disturbances and model perturbations is an urgent need. This poses a challenge in control and signal processing communities 9,10 …”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust Kalman filters under epistemic uncertainty for non‐Gaussian systems with multiplicative noise

Yu,

Wu,

Xin

et al. 2024

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

This article proposes two robust Kalman filters to solve the issue of inaccurate modeling in multiplicative noise systems due to epistemic limitations. First, we construct all conceivable state/measurement transition probability densities as an ambiguity set. This ambiguity set chooses the Wasserstein distance or the moment‐based metric as the distance metric. Besides, this set is an inequality set with a chosen tolerance, which can be seen as a non‐negative radius ball. Then, by combining the robust solution of the least favorable model in that ball with the alternating direction method of multipliers or an efficient direct solution method, we propose two robust Kalman filters based on the minimum mean square error criterion. A classical example is provided to verify the effectiveness of the proposed robust filters in comparison to existing state‐of‐the‐art filters.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…3. Compared with multiplicative-noise-based robust filters, 10,28 this article employs an ambiguity set to model uncertainty, which outperforms them in both accuracy and efficiency.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Kalman filters under epistemic uncertainty for non‐Gaussian systems with multiplicative noise

Yu,

Wu,

Xin

et al. 2024

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

show abstract

“…Model-based methods include sliding mode observer 6 and Kalman filter (KF). 7,8 Due to the nonlinearity of the model, improved algorithms of the KF, such as unscented Kalman filter (UKF), H-infinity filter (HIF), cubature Kalman filter, etc. [9][10][11] are extensively applied in SOC estimation.…”

mentioning

confidence: 99%

Multi-Measurement Kalman-Filtering-Based Neural Network Estimator for SOC of Lithium Batteries

Qin,

Hao,

Ding

2023

J. Electrochem. Soc.

View full text Add to dashboard Cite

State of charge (SOC) refers to the remaining capacity of the battery, which cannot be measured directly. A multi-measurement Kalman filter which is composed of two sub Kalman filters is constructed to improve the estimation accuracy of SOC. The two sub filters share the same state function but have different measurements, namely the terminal voltage and the SOC estimation from neural network, respectively. Based on minimizing the trace of error covariance, an optimal weighted matrix is computed to fuse the estimates of the two sub filters. The training dataset of neural network is collected from mixed discharging cycles experiment and corresponding charging process. By comparing the results with model-based methods, such as H-infinity filter, unscented Kalman filter, data-driven methods, like neural networks and hybrid method, the multi-measurement Kalman filter is verified by both the root mean square error and mean absolute error that are less than 2% in different drive cycles.

show abstract

Distributed Robust Kalman Filters under Model Uncertainty and Multiplicative Disturbance

2022

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

Robust Kalman Filter for Linear System With Convex Polytopic Uncertainties

Cited by 5 publications

References 23 publications

Robust Kalman filters under epistemic uncertainty for non‐Gaussian systems with multiplicative noise

Robust Kalman filters under epistemic uncertainty for non‐Gaussian systems with multiplicative noise

Multi-Measurement Kalman-Filtering-Based Neural Network Estimator for SOC of Lithium Batteries

Distributed Robust Kalman Filters under Model Uncertainty and Multiplicative Disturbance

Contact Info

Product

Resources

About