Nonlinear Autoregressive Approach Research Articles

Machine learning approach for prediction of ionospheric irregularities on ROTI index over the Northern anomaly crest in Egypt during solar cycle 24

This paper reports the prediction results of the ionospheric irregularities represented by the ROTI index close to the equatorial ionization anomaly's Northern peak. A feedforward backpropagation Neural Network (NN) approach is implemented using a time series Nonlinear Autoregressive approach with Exogenous inputs (NARX). We used the data from a dual frequency GPS-SCINDA station located at Helwan (geographic coordinates of 29.86°N, 31.32°E, and MLAT of 29.94°N) in Egypt. To allow the model to be independently tested during varying levels of solar activities, we collected a 5-minute resolution of ROTI data for the solar cycle 24 from 2009 to 2017. The factors that influence the development of ionospheric irregularities are involved in the established model representing the diurnal and seasonal variations as well as solar and geomagnetic activity parameters. To support learning, we included IRI-foF2 and IRI-hmF2 parameters in the input layer neurons to improve the model learning about the behavior of the ionospheric F layer. The results show that the NN-ROTI values precisely match the GPS-ROTI values with an RMSE of 0.106 TECU/min and a prediction efficiency of 95%. The predicted values are highly correlated with the originals, with a regression of 0.89. Furthermore, the irregularities were more prevalent during the equinox months than during the solstice months. It is also observed that predicted NN-ROTI values in all seasons have RMSEs less than 0.03 and 0.05 TECU/min for the low and high solar activity, respectively. The results also showed a clear correlation between solar activity and the occurrence percentage of ionospheric irregularities indicating a solar cycle dependency. The prediction values of the NN-ROTI occurrence % demonstrated a remarkable correlation with the observed GPS-ROTI occurrence % across SC24.

Three-factor mean reverting Ornstein-Uhlenbeck process with stochastic drift term innovations: Nonlinear autoregressive approach with dependent error

This paper introduces a novel approach, withen the context of energy market, by employing a three-factor mean reverting Ornstein-Uhlenbeck process with a stochastic nonlinear autoregressive drift term having a dependent error. Initially the unique solvability for the given nonlinear system is investigated. Then, to estimate the nonlinear regression function, a semiparametric method, based on the conditional least square estimator for the parametric approach, and the nonparametric kernel method for autoregressive modification estimation have been presented . A maximum likelihood estimator has been used for parameter estimation of the Ornstein-Uhlenbeck process. Finally, some numerical simulations and real data studies have been provided to support the main conclusions of the study.

Prediction of remaining useful life for lithium-ion battery with multiple health indicators

Lithium-ion (Li-ion) battery has become a primary energy form for a variety of engineering equipments. To ensure the equipments’ reliability, it is crucial to accurately predict Liion battery’s remaining capacity as well as its remaining useful life (RUL). In this study, we propose a novel method for Li-ion battery’s online RUL prediction, which is based on multiple health indicators (HIs) and can be derived from the battery’s historical operation data. Firstly, four types of indirect HIs are built according to the battery’s operation current, voltage and temperature data respectively. On this basis, a generalized regression neural network (GRNN) is presented to estimate the battery’s remaining capacity, and the nonlinear autoregressive approach (NAR) is applied to predict the battery’s RUL based on the estimated capacity value. Furthermore, to reduce the interference, twice wavelet denoising are performed with different thresholds. A case study is conducted with a NASA battery dataset to demonstrate the effectiveness of the method. The result shows that the proposed method can obtain Li-ion batteries’ RUL effectively.

Gas turbine monitoring using neural network dynamic nonlinear autoregressive with external exogenous input modelling

The main purpose of the present work is to propose an effective tool which allows to ensure the protection and the safety measures against the instability phenomena in a gas turbine based on the modelling of its dynamic behaviour. In order to provide an efficient diagnostic strategy for this type of rotating machine, a supervision system based on the development of artificial neural network tools is proposed in this paper. Where, the dynamic nonlinear autoregressive approach with external exogenous input NARX is used for the identification of the studied system dynamics, to monitor the vibrational dynamics of the operating turbine. This leads to establishing a solution for the different ranges of rotational speed and ensuring dynamic stability through the vibration indicators, determined by the proposed neural network approach. Also, offer a normalized mean square error on the order of 3.8414e−3 for the high-pressure turbine, 1.29152e−1 for the gas control valve and 2.12090 e-4 for the air control valve. Furthermore, it permits the vibration monitoring and efficiently extracts the essentials of dynamic model behaviour, to effectively size the operating gas turbine system.The obtained results of the application of the proposed approach on the gas turbine system presented in this paper proves its ability for the detection and the management on real-time of the eventual failures caused mainly by intrinsic vibrations. On the other side, these results prove clearly the effectiveness of the use of the artificial neural networks as a very powerful calculation tools in the modelling of complex dynamic systems.

A GNSS-based weather forecasting approach using Nonlinear Auto Regressive Approach with Exogenous Input (NARX)

The rapid variation of precipitation that occurs in the troposphere potentially affects weather conditions. Using GNSS-derived precipitable water vapour (PWV) and external input of rainfall data is useful and beneficial for the prediction of rapid changes of PWV which eventually leads to rainfall prediction in near real time. A nonlinear autoregressive approach with exogenous input (NARX) is an effective approach to statistical forecasting which is used in weather forecasting studies. Furthermore, choosing the most effective algorithm between the Levenberg Marquardt regularization and Bayesian Regularization may be ideal for predicting rainfall. Ten GNSS stations from the Malaysia real-time kinematic network (MyRTKnet) were selected. The selected GNSS stations cover Perak states in Malaysia from 1 January to 31 December 2013. While Obtained results from linear regression model show only 1% correlation between rainfall data and GNSS-derived PWV, comparing the predicted values by NARX networks and actual data show a significant improvement. Addition of GNSS-derived PWV along with daily rainfall data collected from meteorological stations significantly improves the prediction results between 30% and 59% correlation for Bayesian and Levenberg Marquardt regularization, respectively. Furthermore, the Levenberg Marquardt training algorithm may be the most accurate model among the forms of ANN used. Such a significant improvement is favourable to use NARX networks for near real time prediction.

A Nonlinear Autoregressive Approach to Statistical Prediction of Disturbance Storm Time Geomagnetic Fluctuations Using Solar Data

A nonlinear autoregressive approach with exogenous input is used as a novel method for statistical forecasting of the disturbance storm time index, a measure of space weather related to the ring current which surrounds the Earth, and fluctuations in disturbance storm time field strength as a result of incoming solar particles. This ring current produces a magnetic field which opposes the planetary geomagnetic field. Given the occurrence of solar activity hours or days before subsequent geomagnetic fluctuations and the potential effects that geomagnetic storms have on terrestrial systems, it would be useful to be able to predict geophysical parameters in advance using both historical disturbance storm time indices and external input of solar winds and the interplanetary magnetic field. By assessing various statistical techniques it is determined that artificial neural networks may be ideal for the prediction of disturbance storm time index values which may in turn be used to forecast geomagnetic storms. Furthermore, it is found that a Bayesian regularization neural network algorithm may be the most accurate model compared to both other forms of artificial neural network used and the linear models employing regression analyses.