Nonlinear Optimal Estimation for Neural Networks Data Fusion

Ma, Ye; Wang, Xiao Tong; Li, Bo; Fu, Jianguo

doi:10.1007/978-3-540-28648-6_112

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, UKF-NN has attracted more attention and has been applied in various fields. For instance, Ma et al proposed a global information fusion model based on UKF-NN for ship navigation system, and the test results show that this method is effective and feasible 22 .…”

Section: Introductionmentioning

confidence: 99%

Artificial neural network based on strong track and square root UKF for INS/GNSS intelligence integrated system during GPS outage

Yang,

Wang,

Zhang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

When INS/GNSS (inertial navigation system/global navigation satellite system) integrated system is applied, it will be affected by the insufficient number of visible satellites, and even the satellite signal will be lost completely. At this time, the positioning error of INS accumulates with time, and the navigation accuracy decreases rapidly. Therefore, in order to improve the performance of INS/GNSS integration during the satellite signals interruption, a novel learning algorithm for neural network has been presented and used for intelligence integrated system in this article. First of all, determine the input and output of neural network for intelligent integrated system and a nonlinear model for weighs updating during neural network learning has been established. Then, the neural network learning based on strong tracking and square root UKF (unscented Kalman filter) is proposed for iterations of the nonlinear model. In this algorithm, the square root of the state covariance matrix is used to replace the covariance matrix in the classical UKF to avoid the filter divergence caused by the negative definite state covariance matrix. Meanwhile, the strong tracking coefficient is introduced to adjust the filter gain in real-time and improve the tracking capability to mutation state. Finally, an improved calculation method of strong tracking coefficient is presented to reduce the computational complexity in this algorithm. The results of the simulation test and the field-positioning data show that the proposed learning algorithm could improve the calculation stability and robustness of neural network. Therefore, the error accumulation of INS/GNSS integration is effectively compensated, and then the positioning accuracy of INS/GNSS intelligence integrated system has been improved.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial neural network based on strong track and square root UKF for INS/GNSS intelligence integrated system during GPS outage

Yang,

Wang,

Zhang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Combining general regression neural network model (GRNN) with fuzzy ART (FA) model, Lee built a GRNNFA model for structural local damage detection, which can not only take fast and stable network training but also facilitate the removal of the noise embedded in training samples [5]. Taking the unscented Kalman filter method to calculate network weights instantly, Ma et al [6] built an adaptive ANN model that can simplify the calculation of nonlinear systems to achieve a global optimization on data information through adjusting network weights according to system inputs. El-Sheimy took structural damage identification by combining wavelet multi-resolu-tion analysis with ANN, which is able to separate different frequent components and filter out noise to identify original structural response signals [7].…”

Section: Introductionmentioning

confidence: 99%

Singular value diagnosis in dam safety monitoring effect values

Zhao

Jin

et al. 2011

Sci. China Technol. Sci.

View full text Add to dashboard Cite

Based on the principal component analysis, principal components that have major influence on data variance are determined by the energy percentage method according to the correlation between monitoring effects. Then principal components are extracted through reconstructing multi effects. Moreover, combining with the optimal estimation theory, the method of singular value diagnosis in dam safety monitoring effect values is proposed. After dam monitoring information matrix is obtained, single effect state estimation matrix and multi effect fusion estimation matrix are constructed to make diagnosis on singular values to reduce false alarm rate. And the diagnosis index is calculated by PCA. These methods have already been applied to an actual project and the result shows the ability of the monitoring effect reflecting dam evolution behavior is improved as dam safety monitoring effect fusion estimation can take accurate identification on singular values and achieve data reduction, filter out noise and lower false alarm rate effectively. dam safety monitoring, effect, singular value diagnosis, principal component analysis, optimal estimation Citation: Gu C S, Zhao E F, Jin Y, et al. Singular value diagnosis in dam safety monitoring effect values.

show abstract

Nonlinear Optimal Estimation for Neural Networks Data Fusion

Cited by 2 publications

References 5 publications

Artificial neural network based on strong track and square root UKF for INS/GNSS intelligence integrated system during GPS outage

Artificial neural network based on strong track and square root UKF for INS/GNSS intelligence integrated system during GPS outage

Singular value diagnosis in dam safety monitoring effect values

Contact Info

Product

Resources

About