Short-term prediction of UT1-UTC by combination of the grey model and neural networks

Yu, Lei; Guo, Min; Hu, Dandan; Cai, Haiyuan; Zhao, Di; Hu, Zhaopeng; Gao, Yuping

doi:10.1016/j.asr.2016.10.030

Cited by 23 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the performance of the proposed model, this paper used grey neural network architecture [16][17][18][19]. Fig.…”

Section: Health Index and Proposed Neural Network Architecturementioning

confidence: 99%

On-line prediction remaining useful life for ball bearings via grey NARX

Niu¹,

Tong²,

Cao³

et al. 2019

J. vibroeng.

View full text Add to dashboard Cite

The Huge vibration data are generated continuously by many sensors in daily high-speed rotating machinery operations. Accurate online prediction based on big vibration data streaming can reduce the risks related to failures and avoid service disruptions. This paper presents a hybrid nonlinear autoregressive network with exogenous inputs (NARX) model to forecast the remaining useful life of ball bearings through health index based on big vibration data streaming. This approach is validated by a real data from PRONOSTIA experimentation platform and industrial test rig compared with backpropagation neural network (BP), Elman and general regression neural network (GRNN) prediction model. Root mean square error, mean absolute error and correlation coefficient were used as performance indexes to evaluate the prediction accuracy of these models. The mean absolute error, the root mean square error and the correlation coefficient of hybrid NARX model evaluation index are 2.04, 2.85 and 0.98 respectively. It shows that the model presented in this paper has higher prediction accuracy. It can meet the needs of actual ball bearing remaining useful life prediction and also provide reference in other fields.

show abstract

“…To verify the performance of the proposed model, this paper used grey neural network architecture [16][17][18][19]. Fig.…”

Section: Health Index and Proposed Neural Network Architecturementioning

confidence: 99%

On-line prediction remaining useful life for ball bearings via grey NARX

Niu¹,

Tong²,

Cao³

et al. 2019

J. vibroeng.

View full text Add to dashboard Cite

show abstract

“…The original series of the eigenvalues of the uncertain system is x is exponential growth law after one accumulation, so the data can be fitted and predicted by a continuous function or differential equation. 21 x ð1Þ t is yðtÞ, and N parameters of the gray neural network model of differential equations for the expression are given as…”

Section: Gbp (Gray Neural Network) Theorymentioning

confidence: 99%

Prediction of long-term gas load based on particle swarm optimization and gray neural network model

Zhang

Liu

2017

Advances in Mechanical Engineering

View full text Add to dashboard Cite

With the continuous consumption of fossil energy and environmental pollution, natural gas as a clean energy has received more and more attention. How to accurately predict the future of natural gas load has a vital significance. A long-term natural gas load forecasting model based on GBP is established to solve the problem of natural gas load forecasting. First, the method of correlation index is used to optimize the 20 indicators and then the optimized index number is 16; second, combining the advantages of gray neural network (BP) in fitting time series and particle swarm optimization in optimization parameters, a long-term load forecasting model of natural gas based on PSO-BP is established; finally, in order to verify the validity of the model, taking the natural gas load sample from 2005 to 2015 in Anhui Province as an example, the BP and GBP alone prediction models are compared with this model. The results show that compared with BP and GBP alone, the PSO-GBP prediction model improved the mean absolute deviation and mean absolute percentage error values by 0.065 and 0.03485 and 6.67944 and 3.62817, respectively, and increased the calculation time by 0.00726 and 0.00378 s.

show abstract

“…Several techniques have been developed to improve the accuracy of LOD prediction. These algorithms could be classified into two groups: first, the methods that use the information within the LOD time series, e.g., auto-covariance (AC) (Kosek et al 1998;Kosek 2002), wavelet decomposition (Akyilmaz et al 2011), or neural network (Schuh et al 2002;Liao et al 2012;Lei et al 2015Lei et al , 2017. Besides, this group includes the hybrid methods using the combination of least squares (LS) and auto-regressive (AR), auto-regressive moving average (ARMA), auto-covariance, and neural network (Kosek et al 2005;Xu and Zhou 2015;Wu et al 2019).…”

Section: Introductionmentioning

confidence: 99%

A new hybrid method to improve the ultra-short-term prediction of LOD

Modiri

Belda

Hoseini

et al. 2020

J Geod

View full text Add to dashboard Cite

Accurate, short-term predictions of Earth orientation parameters (EOP) are needed for many real-time applications including precise tracking and navigation of interplanetary spacecraft, climate forecasting, and disaster prevention. Out of the EOP, the LOD (length of day), which represents the changes in the Earth's rotation rate, is the most challenging to predict since it is largely affected by the torques associated with changes in atmospheric circulation. In this study, the combination of Copula-based analysis and singular spectrum analysis (SSA) method is introduced to improve the accuracy of the forecasted LOD. The procedure operates as follows: First, we derive the dependence structure between LOD and the Z component of the effective angular momentum (EAM) arising from atmospheric, hydrologic, and oceanic origins (AAM + HAM + OAM). Based on the fitted theoretical Copula, we then simulate LOD from the Z component of EAM data. Next, the difference between LOD time series and its Copula-based estimation is modeled using SSA. Multiple sets of short-term LOD prediction have been done based on the IERS 05 C04 time series to assess the capability of our hybrid model. The results illustrate that the proposed method can efficiently predict LOD.

show abstract

Short-term prediction of UT1-UTC by combination of the grey model and neural networks

Cited by 23 publications

References 13 publications

On-line prediction remaining useful life for ball bearings via grey NARX

On-line prediction remaining useful life for ball bearings via grey NARX

Prediction of long-term gas load based on particle swarm optimization and gray neural network model

A new hybrid method to improve the ultra-short-term prediction of LOD

Contact Info

Product

Resources

About