General Regression Neural Network GRNN Research Articles

Novel MPPT techniques for photovoltaic systems under uniform irradiance and Partial shading

In PV systems, the non-uniform irradiance and diversified unpredictable weather conditions fall into the category of Partial Shading (PS). Under PS, it is challenging for PV systems to obtain the maximum output through Maximum Power Point Tracking (MPPT), i.e., the parameters of the controller are adjusted online to yield the maximum power. In the literature, various techniques have been proposed to track the MPP (Maximum Power Point) under the uniform irradiance. On the contrary, few techniques have been proposed to efficiently track MPP under PS. In this paper, a few novel MPPT techniques have been proposed, which include Adaptive Cuckoo Search Optimization Algorithm (ACOA), General Regression Neural Network GRNN) with Fruit fly Optimization algorithm (FFOA), and Dragonfly Optimization Algorithm (DFO) to track the MPP under various weather condition. The proposed techniques enhance the performance of the PV system, save the computational time and greatly reduce the oscillation around the global maximum power point. For the validation of the proposed techniques, comparative analysis of their results with the Bio-inspired Particle Swarm Optimization (PSO), Cuckoo Search Optimization (CS), Artificial Bee Colony Algorithm (ABC) and PSO Gravitational search Optimization (PSOGS) is presented. The comparison shows that the proposed techniques are better in term of quick power tracking, stability, and high efficiency under various weather conditions. The comparison also demonstrates that the proposed techniques can efficiently locate the GM (global maxima) under the PS and Dynamic Partial Shading (DPS) conditions. Furthermore, statistical analysis is presented to check the stability, sensitivity and robustness of the proposed techniques.

A Committee Machine with Intelligent Systems for Estimating Monthly Mean Reference Evapotranspiration in an Arid Region

The aim of this research is to estimate the reference evapotranspiration ETo as given by FAO-56 PM equation in Basrah city, southern Iraq by using several climatic inputs data including maximum monthly mean air temperature, minimum monthly mean air temperature, monthly mean relative humidity and monthly mean wind speed. Three artificial intelligent systems (generalized regression neural network GRNN, multi-layer perceptron MLP and adaptive neuro-fuzzy inference systems ANFIS) were used for predicting reference evapotranspiration. Root mean squared error and coefficient of determination were used as comparison criteria for evaluation of performance of all the developed models. The results shown that the models performances of multi-layer perceptron models are better than adaptive neuro-fuzzy inference systems models and slightly better than generalized regression neural network models with different inputs combination. A Committee Machine with Intelligent Systems (CMIS) was constructed for estimation of ETo by integrating the results of predicting ETo from GRNN, MLP and ANFIS, each of them has a weight factor representing its contribution in overall estimation. The results illustrated that the performance of committee machine with intelligent systems is better than any one of the individual artificial intelligent systems for predicting ETo.

Signal and Noise Modeling of Microwave Transistors Using Characteristic Support Vector-based Sparse Regression

In this work, an accurate and reliable S- and Noise (N) - parameter black-box models for a microwave transistor are constructed based on the sparse regression using the Support Vector Regression Machine (SVRM) as a nonlinear extrapolator trained by the data measured at the typical bias currents belonging to only a single bias voltage in the middle region of the device operation do- main of (VDS/VCE, IDS/IC, f). SVRMs are novel learning machines combining the convex optimization theory with the generalization and therefore they guarantee the global minimum and the sparse solution which can be expressed as a continuous function of the input variables using a subset of the training data so called Support Vector (SV)s. Thus magnitude and phase of each S- or N- param- eter are expressed analytically valid in the wide range of device operation domain in terms of the Characteristic SVs obtained from the substantially reduced measured data. The proposed method is implemented successfully to modeling of the two LNA transistors ATF-551M4 and VMMK 1225 with their large operation domains and the comparative error-metric analysis is given in details with the counterpart method Generalized Regression Neural Network GRNN. It can be concluded that the Characteristic Support Vector based-sparse regression is an accurate and reliable method for the black-box signal and noise modeling of microwave transistors that extrapolates a reduced amount of training data consisting of the S- and N-data measured at the typical bias currents belonging to only a middle bias voltage in the form of continuous functions into the wide operation range.

Optimal intelligent control for a variable-speed wind turbine using general regression neural network and adaptive PSO algorithm

In this paper, a robust optimal general regression neural network sliding mode GRNNSM controller is designed for a variable speed wind turbine VSWT. The main objective of the controller is to optimise the energy captured from the wind. Sliding mode control SMC approach emerges as an especially suitable option to deal with a VSWT. However, for large uncertain systems, the SMC produces chattering problems due to the higher needed switching gain. In order to guarantee the wind power capture optimisation without any chattering problems, this study propose to combine the SMC with the general regression neural network GRNN based on adaptive particle swarm optimisation APSO algorithm. The GRNN is used for the prediction of uncertain model part and hence enable a lower switching gain to be used for compensating only the prediction errors. The APSO algorithm with efficient global search is used to train the weights of GRNN in order to improve the network performance in terms of the speed of convergence and error level. The stability is shown by the Lyapunov theory and the control action used did not exhibit any chattering behaviour. The effectiveness of the designed method is illustrated in simulations by the comparison with traditional SMC.

Hybrid classification and regression models via particle swarm optimization auto associative neural network based nonlinear PCA

For solving classification and regression problems, we propose a hybrid system consisting of two phases which work in tandem. In the first phase, particle swarm optimization is employed to train a 3-layered auto associative neural network henceforth called PSOAANN. In this phase, dimensionality reduction takes place in hidden layer, where the hidden nodes should be less than the input nodes. The outputs from the hidden nodes are then treated as nonlinear principal components NLPC. They are fed to the second phase where several classifiers and regression methods are invoked. The second phase includes techniques viz., threshold accepting logistic regression TALR, probabilistic neural network PNN, group method of data handling GMDH, support vector machine SVM and genetic programming GP for classification problems. For regression problems, general regression neural network GRNN is used in place of PNN. In addition, support vector machine SVM, Genetic Programming GP, GMDH are also employed, as they are versatile. The efficiency of the hybrid is analyzed on five banking datasets namely Spanish banks, Turkish banks, US banks and UK banks and UK credit dataset and five regression datasets viz., Bodyfat, Forestfires, AutoMPG, Boston Housing and Pollution. All the datasets are analyzed using 10 fold cross validation 10 FCV. It turns out that the proposed hybrid yielded higher accuracies across classification and regression problems.

Color space conversion algorithm of generalized regression neural network based on digital proof

Color conversion algorithm of CMYK and CIE L a b is the key technique in output device characterization and color management module.In this paper the forward and reverse color space conversion models between CMYK and CIE L a b based on Generalized Regression Neural Network GRNN were built using the color data of the digital proof.Then the accuracy of the models were tested.Finally The result shows that it is an efficient method to build the color space conversion between CIE L a b and CMYK using GRNN which gains an advantage over BP network not only in training convenience speed but also precision.network not only in training convenience speed but also precision.

Optimisation of effective factors in geometrical specifications of laser percussion drilled holes

Abstract Nowadays, laser percussion drilling is finding increasingly widespread application in industry. Precise modeling has not yet been achieved due to the complexity of this process. The neural network has been used in this study for process modeling. Approximate experimental models of the process have been developed by the neural network (Generalized Regression Neural Network—GRNN) according to the results of the experiments. Then the optimum input parameters (peak power, pulse time, pulse frequency, number of pulses, gas pressure and focal plane position) were specified using the genetic algorithm (GA) method, the results of which are optimum output parameters. The output parameters include the hole entrance diameter, circularity of entrance and exit holes, hole exit diameter and taper angle of the hole. The tests were carried out on stainless steel 304 sheets with a thickness of 2.5 mm. A Nd:YAG laser machine was employed with a wavelength of 1.06 μm. Oxygen was used as an assist gas. Diameter of the central nucleus of laser beam was 600 μm. Considering the precision of the optimum numerical results and the high speed of the neural network in modeling, this method is reliable and economical and also confirms the qualitative results of the previous studies. Therefore, one can use this method to optimally adjust input parameters of the process in multipurpose and single purpose optimisation modes, which indicates substitute application of the method for optimising the laser percussion drilling process.

Modeling the functional performance of plasma polymerized thin films

Plasma polymerized thin films are of increasing importance in the field of transparent packaging. In particular, hydrocarbon coatings prepared by the reactive magnetron sputtering method combined with plasma-stimulated gas-phase polymerization have proved to have excellent diffusion barrier properties for gases and water vapor. However, the non-linear relationship between stretch failure and permeation properties poses a challenge when it comes to modeling the functional coatings to meet the required product specifications. An improvement in the functionality of these films has been achieved using the general regression neural network GRNN. The method employs the input parameters of the coating such as gas flow, pressure and process time. To improve the prediction performance the training input and output vectors were linearily transformed into the space defined by the principal components of the given training data. The degree of the polymer-like phase in the carbon network and its effect on the functional performance has been studied using a combination of spectroscopic methodology and functional testing. In conclusion, it can be stated that modeling of plasma processes according to the film characteristics makes possible a more controlled and systematic production of thin films.