In this study, an artificial neural-network (ANN)-based space-vector pulse-width modulation (SVPWM) for capacitor voltage balancing of a three-phase three-level neutral-point clamped converter with improved power qual...
详细信息
In this study, an artificial neural-network (ANN)-based space-vector pulse-width modulation (SVPWM) for capacitor voltage balancing of a three-phase three-level neutral-point clamped converter with improved power quality is presented. The neural-network-based controller offers the advantage of very fast implementation of the SVPWM algorithm. This makes it possible to use an application specific integrated circuit chip in place of a digital signal processor. The proposed scheme employs single layer feed-forward neural-networks at different stages along with a control algorithm using modified reference vector for capacitor voltage balancing of an improved power quality three-phase neutral-point clamped converter. In other words, the neural-network receives three-phase voltages and currents as input and generates symmetrical pulse-width modulation waves for three phases of the converter. A simulated digital signal processor (DSP)-based modulator generates the data which are used to train the network by a back-propagation algorithm in the matlab neural network toolbox. The simulation of converter with ANN-based space-vector modulator shows excellent performance when compared with that of conventional DSP-based modulator.
Most of the countries around the world have paid great attention to flood water level prediction system because flood events may damage on people's life and property. However, since flood water level fluctuates hi...
详细信息
ISBN:
(纸本)9781479956869
Most of the countries around the world have paid great attention to flood water level prediction system because flood events may damage on people's life and property. However, since flood water level fluctuates highly nonlinear, it is a very difficult task to predict flood water level accurately. Since Artificial neuralnetwork is an effective technique for handling nonlinear problems, thus, this paper proposed a 7 hours ahead flood water level prediction modelling using neuralnetwork Autoregressive with Exogenous Input (NNARX) for flood prone area located in Kedah, Malaysia as case study. The model was developed using four inputs and one output. Three inputs were upstream stations water level and one input from water level differences at downstream flood location. The output was the predicted water level at downstream station. Simulation was done using matlab neural network toolbox. Results showNNARX modelling was able to predict flood water level ahead of time.
BP neuralnetwork is a typical representative of the artificial neuralnetwork. The matlab provides many functions to achieve the BP network, including the neuralnetwork's design training and simulation functions...
详细信息
BP neuralnetwork is a typical representative of the artificial neuralnetwork. The matlab provides many functions to achieve the BP network, including the neuralnetwork's design training and simulation functions. It also can achieve real-time visualization of simulation results. This paper uses the matlab neural network toolbox to design the BP neuralnetwork, and then gives an instance.
outlook to apply the highly energetic biogas from anaerobic digestion into fuel cells will result in a significantly higher electrical efficiency and can contribute to an increase of renewable energy production. The p...
详细信息
outlook to apply the highly energetic biogas from anaerobic digestion into fuel cells will result in a significantly higher electrical efficiency and can contribute to an increase of renewable energy production. The practical bottleneck is the fuel cell poisoning caused by several gaseous trace compounds like hydrogen sulfide and ammonia. Hence artificial neuralnetworks were developed to predict these trace compounds. The experiments concluded that ammonia in biogas can indeed be present up to 93 ppm. Hydrogen sulfide and ammonia concentrations in biogas were modelled successfully using the matlab neural network toolbox. A script was developed which made it easy to search for the best neuralnetwork models' input/output-parameters, settings and architectures. The models were predicting the trace compounds, even under dynamical conditions. The resulted determination coefficients (R-2) were for hydrogen sulfide 0.91 and ammonia 0.83. Several model predictive control tool strategies were introduced which showed the potential to foresee, control, reduce or even avoid the presence of the trace compounds. (c) 2004 Elsevier Ltd. All rights reserved.
This paper presents a self-consistent model for the estimation of direct solar radiation in the Indian zone. It takes into account the atmospheric transmittance modified in accordance with the climate zone and calcula...
详细信息
This paper presents a self-consistent model for the estimation of direct solar radiation in the Indian zone. It takes into account the atmospheric transmittance modified in accordance with the climate zone and calculates solar radiation at normal incidence using Hottel's clear day model. The regional weather phenomena are taken into account with the help of variables such as relative humidity, mean duration of sunshine per hour and the rainfall, and a composite parameter referred to as sky clearness index (CI) is determined using artificial neuralnetwork analysis. The CI is finally applied to the modified Hottel's clear day model to predict the grey day solar irradiance. The model predictions for the Indian region are found to be in good agreement with the measurements. The variability of sky CI is represented by the contours of constant value in Indian region, which in turn would enable the present model to be used in a self-consistent manner.
暂无评论