Hybrid Radial Basis Function Network Research Articles

Generating high-resolution climate maps from sparse and irregular observations using a novel hybrid RBF network

ABSTRACT Sparse and irregular climate observations in many developing countries are not enough to satisfy the need of assessing climate change risks and planning suitable mitigation strategies. The wide-used statistical downscaling model (SDSM) software tools use multi-linear regression to extract linear relations between large-scale and local climate variables and then produce high-resolution climate maps from sparse climate observations. The latest machine learning techniques (e.g. SRCNN, SRGAN) can extract nonlinear links, but they are only suitable for downscaling low-resolution grid data and cannot utilize the link to other climate variables to improve the downscaling performance. In this study, we proposed a novel hybrid RBF (Radial Basis Function) network by embedding several RBF networks into new RBF networks. Our model can well incorporate climate and topographical variables with different resolutions and extract their nonlinear relations for spatial downscaling. To test the performance of our model, we generated high-resolution precipitation, air temperature and humidity maps from 34 meteorological stations in Bangladesh. In terms of three statistical indicators, the accuracy of high-resolution climate maps generated by our hybrid RBF network clearly outperformed those using a multi-linear regression (MLR), Kriging interpolation or a pure RBF network.

State of health estimation of lithium-ion battery based on an adaptive tunable hybrid radial basis function network

Accurate state of health (SOH) estimation is critical for the durability and safety of Lithium-ion batteries (LIBs). It is challenging to predict the SOH of LIBs due to the complex aging mechanism. In this paper, a novel adaptive tunable hybrid radial basis function network is proposed for accurate and robust SOH estimation. Firstly, two Kullback-Leibler distances are exploited to extract the dynamic and static characteristics of LIBs during the aging process. Secondly, the hybrid network is combined with the radial basis function network and the autoregressive model. A novel hybrid network state-space model is built to simulate the aging mechanism of LIBs. To increase the adaptive ability of the hybrid network, the structural parameters of the proposed hybrid network are adaptively modulated by Brownian motion modeling and particle filter. The Brownian motion with drift and scale coefficients is introduced in the state-space model to simulate the dynamic aging behavior of LIBs. The particle filter is used to update the structural parameters of the hybrid network in real-time. Furthermore, experiments are conducted on two datasets. The experimental results demonstrate that the proposed model has a high prediction accuracy. Moreover, the batteries with Gaussian white noise and dynamic discharging profiles are adopted to prove the reliability and robustness of the proposed model.

An Adaptive-Tunable-Based Hybrid RBF Network for EGTM Prediction

Aero-engine exhaust gas temperature margin (EGTM) is one of the main indexes of engine replacement; however, the application of existing methods in EGTM forecasting is restricted because of the limited prediction accuracy and many non-linearities. In this study, an adaptive-tunable-based hybrid radial basis function (RBF) network is proposed to improve the prediction accuracy of aero-engine EGTM. Firstly, a hybrid RBF network consisting of a RBF network and a linear regression model is built as a fundamental EGTM predictive algorithm. Secondly, to increase the network’s adaptation capabilities, the structural parameters of the proposed network are adaptively modulated by Brownian motion modeling and particle filter without physics-based models. Finally, multiple sets of EGTM data from a certain type aero-engines in an airline company is selected for engine removal time prediction. Experiment results demonstrate that the proposed adaptive-tunable-based hybrid RBF network with a high prediction accuracy, and can reflect the characteristics of EGTM well and truly, which can capture the dynamic nature of EGTM in time during the forecasting process.

Characterization of the displacement response in chromatic confocal microscopy with a hybrid radial basis function network.

Characterization of the displacement response is critical for accurate chromatic confocal measurement. Current characterization methods usually provide a linear or polynomial relationship between the extracted peak wavelengths of the spectral signal and displacement. However, these methods are susceptible to errors in the peak extraction algorithms and errors in the selected model. In this paper, we propose a hybrid radial basis function network method to characterise the displacement response. With this method, the peak wavelength of the spectral signal is firstly extracted with a state-of-art peak extraction algorithm, following which, a higher-accuracy chromatic dispersion model is applied to determine the displacement-wavelength relationship. Lastly, a radial basis function network is optimized to provide a mapping between the spectral signals and the residual fitting errors of the chromatic dispersion model. Using experimental tests, we show that the hybrid radial basis function network method significantly improves the measurement accuracy, when compared to the existing characterizing methods.

Hybrid multilayered perceptron networks

This paper introduces a modified multilayered perception network (MLP) called the Hybrid Multilayered Perceptron (HMLP) network to improve the performance of a MLP network. The convergence rate of the proposed network is further improved by proposing a modified version of the recursive prediction error algorithm as the training algorithm. The capability of the proposed network architecture trained using the modified recursive prediction error algorithm was demonstrated using simulated and real data sets. The results indicated that the proposed network provides a significant improvement over a standard MLP network. These additional linear input connections do not significantly increase the complexity of the MLP network since the connections are linear. In fact, by using the linear input connections, the number of hidden nodes required by the standard MLP network model can be reduced, which will also reduce computational load. The performance of the HMLP network was also compared with Radial Basis Function (RBF) and Hybrid Radial Basis Function (HRBF) networks. It was found that the proposed HMLP network was much more efficient than both RBF and HRBF networks.