A novel unscented Kalman filter for recursive state-input-system identification of nonlinear systems

Lei, Ying; Xia, Dandan; Erazo, Kalil; Nagarajaiah, Satish

doi:10.1016/j.ymssp.2019.03.013

Cited by 129 publications

(47 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In theory, EKF-LS is based on the sequential application of EKF for the structural parameters and LS algorithm for the unmeasured excitation. Although it simplifies the complexity of the identification process through a use of first-order Taylor expansion, an error is produced during the local linearization of the extended state vector (Lei et al, 2019). Therefore, it is crucial to introduce a more effective algorithm to reduce the linearization errors caused by EKF-LS.…”

Section: The Ekf-ls Methodsmentioning

confidence: 99%

A new physical parameter identification method for shear frame structures under limited inputs and outputs

Liu

Chang

et al. 2020

Advances in Structural Engineering

View full text Add to dashboard Cite

A new physical parameter identification method with a name of EKPF-LS is proposed for shear frame structures under limited inputs and outputs by a combination of extended Kalman particle filter (EKPF) and least square (LS) algorithm. The basic principle of EKPF-LS is to establish the proposed distribution function of the particle filter through EKF-LS. In this method, EKPF is introduced to get rid of the restriction of Gaussian white noise model and reduce the linearization error caused by EKF. Meanwhile, LS is utilized to address the problem of unmeasured excitation estimations. The effectiveness and accuracy of the proposed EKPF-LS method is verified by a numerical example of a four-story hysteretic shear frame under an earthquake excitation and an experimental test of a four-story shear type frame using Gaussian white noise and sine sweep signal as excitations, respectively. Gaussian colored noises are then added to the solved and measured response signals in the numerical example and experimental test, respectively. The results demonstrate that the proposed method can identify the stiffness of shear frame structures effectively and is superior to the existed EKF-LS approach when the structural system is nonlinear structural system or Colored noise model.

show abstract

Section: The Ekf-ls Methodsmentioning

confidence: 99%

A new physical parameter identification method for shear frame structures under limited inputs and outputs

Liu

Chang

et al. 2020

Advances in Structural Engineering

View full text Add to dashboard Cite

show abstract

“…By substituting L k from Equations (37) in Equation (35) and rearranging them, the updated covariance matrix P Z kjk can be expressed as follows: 35…”

Section: Sigma Points Approach For Cmvu Algorithmmentioning

confidence: 99%

“…The numerical study presented by Wu and Smyth 24 showed that UKF was efficient for real‐time parameter estimation of highly non‐linear systems with degradation and pinching, where the input was known. Recently, Lei et al 37 have presented a UKF‐based algorithm for simultaneous identification of non‐linear structural parameters and input excitation.…”

Section: Introductionmentioning

confidence: 99%

Experimental verification of constrained minimum variance unbiased estimator for simultaneous input and state estimation of Bounded Input and Bounded Output (BIBO) type Bouc–Wen hysteretic structural system

Tamuly

Chakraborty

Das

2020

Struct Control Health Monit

View full text Add to dashboard Cite

Constraint minimum variance unbiased estimator is improvised for simultaneous input and parameter estimation of the Bouc-Wen hysteretic system of a full-scale bridge pier. The essential structural properties in this case (i.e., bounded input and bounded output) are incorporated in the form of constraint conditions along with degradation and pinching effects. To demonstrate the efficiency of this algorithm, two different types of sigma points generation schemes (viz., unscented transformed points and cubature quadrature points) are presented here. First, the algorithm is validated using simulated response obtained from a single-bay single-storey reinforced concrete frame, whose hysteretic parameters are obtained by minimizing the error between the model and experimentally observed load-deformation characteristics. The rationale behind the use of experimentally observed hysteresis in simulation is to replicate the actual structure so that the realistic material behaviour is maintained. Once the algorithm is validated, its performance is further demonstrated using experimental results of a full-scale bridge pier, which is the main objective of this study. The numerical results presented in this paper clearly show the robustness of the proposed algorithm using unscented sigma points, which can identify both hysteretic properties and input excitation with sufficient level of accuracy.

show abstract

“…In this paper, the Kalman filtering algorithm, which is an optimal filtering algorithm for linear systems and is also applicable to nonlinear systems [28], [29], especially those suitable for computer recursive processing, is used for data preprocessing. It has three functional features: first, it can smooth historical data; second, the current data can be filtered; third, it can predict future data.…”

Section: Data Preprocessing 1) Outlier Detection and Missing Valuementioning

confidence: 99%

Prediction of Natural Gas Consumption for City-Level DHS Based on Attention GRU: A Case Study for a Northern Chinese City

et al. 2019

View full text Add to dashboard Cite

With the increasing energy demand and environmental protection requirements of heating systems, natural gas (NG), as an efficient and clean alternative energy source for coal, plays an increasingly important role in district heating systems (DHSs). The accurate prediction of the DHS consumption of NG in the whole city is helpful in formulating an efficient energy scheduling plan. However, because the DHS is a complex non-linear system with time-space delay effect and multi-factors, the traditional algorithms have deficiencies in the prediction accuracy of the natural gas consumption for city-level DHS. To achieve accurate prediction, a gas consumption prediction algorithm based on the attention gated recurrent unit (AGRU) model is proposed, which can obtain high-level features of historical data that affect gas consumption prediction. In addition, the attention mechanism can help to select more critical feature inputs and improve the prediction accuracy of gas consumption. Detailed comparative experiments were performed between the proposed AGRU and state-of-art NG consumption prediction algorithms, such as the recurrent neural network (RNN), long short-term memory (LSTM), GRU, attention RNN (ARNN), attention LSTM (ALSTM), support vector regression (SVR), random forest regression (RFR), gradient boosting regression (GBR) and decision tree regression (DTR). An analysis of the experimental results shows that the proposed AGRU algorithm has a prediction accuracy of 95.3%, which is significantly better than other algorithms. In addition, the hyperparameters of the AGRU algorithm are also tested in detail to optimize the selection. INDEX TERMS Natural gas consumption prediction, district heating system, attention mechanism, gated recurrent unit.

show abstract

A novel unscented Kalman filter for recursive state-input-system identification of nonlinear systems

Cited by 129 publications

References 43 publications

A new physical parameter identification method for shear frame structures under limited inputs and outputs

A new physical parameter identification method for shear frame structures under limited inputs and outputs

Experimental verification of constrained minimum variance unbiased estimator for simultaneous input and state estimation of Bounded Input and Bounded Output (BIBO) type Bouc–Wen hysteretic structural system

Prediction of Natural Gas Consumption for City-Level DHS Based on Attention GRU: A Case Study for a Northern Chinese City

Contact Info

Product

Resources

About