The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
To properly manage the variability of wind generation, this paper presents an adaptive procedure for short-term forecasting of wind speed based on recursive least squares. Firstly, hourly wind speed data are transformed to make their distribution approximately Gaussian and standardized to remove the diurnal nonstationarity. Then, the procedure fits an AR model to the standardized transformed hourly...
Based on wind speed sequences, three-layer neural network model of wind speed prediction is analyzed to obtain the selecting method of neural network input, output and hidden layers' node parameters, and to predict wind speed through rolling wind speed data. In accord with the nonlinear of wind speed sequences, a BP neural network model is established to forecast wind speed. The feasibility and validity...
Daily solar radiation prediction is a nonlinear and non-stationary process. It's hard to model with a single method. A Genetic Algorithm Optimization of Wavelet Neural Network (GAO-WNN) model was set in this paper. The nonlinear process of daily solar radiation was forecasted by neural network and the non-stationary process of daily solar radiation was decomposed into quasi-stationary at different...
Classical statistic detection theory regards chaotic noise as random signal, which weakens the performance of signal detection. Based on chaotic dynamic mechanism, detecting weak signal embedded in chaos is discussed in this paper. This method uses the Adaptive Neuro-Fuzzy Inference System (ANFIS) to establish a prediction model of chaotic background for the ANFIS's powerful ability of learning and...
Yearly natural streamflow data of five hydrologic stations over the upper of Weihe basin for 1945–2000 were utilized to analyze the drought characteristics by using Run-theory and Grey system. Based on the theory of run and intercept method, the hydrologic drought duration, drought severity and the value of conditional probability were calculated to evaluate the regional hydrological drought characteristics...
The photovoltaic (PV) system design of a balance of system includes design of a solar module, a battery, an inverter and a charge controller. The study of electrical response of a solar module is important, since it decides the key design parameters. This paper presents an overview and comparative study of electrical response of few existing PV models. A more reliable and accurate model for predicting...
Aming at the problem of Hybrid Electric Vehicle(HEV) control strategy being sensitive to the road situation, a model predictive control strategy was designed with length information of the drive mission from a global positioning system(GPS) to improve the Robustness against the road situation based on a Matlab/Simulink vehicle dynamic model for series-parallel plug-in HEV. In this paper, a blended...
This paper introduces optimized polymerization kettle of PVC production temperature control scheme. Because polymerization kettle has many features, such as large-scale, many variables and special complex temperature control, we use programmable controller CPU222, apply program control of the polymerization kettle temperature and use double model predictive function control strategy in the algorithm...
The research of artificial neuron network has been maturated both in theory and practical application, so it is also employed into nonlinear time series forecasting. However, concerning with the problem of time series forecasting based on traditional neural network, such as black box, poor accuracy, and facing the shortage of post knowledge, the dynamic intelligent neural network is proposed in the...
There are a huge number of network attacks on the Internet, and are increasing each year. The condition of internet attacks is developing toward a distributed, collaborative direction. Internet attacks exhaust a lot of resources, take up a lot of bandwidth, making the victim host can not accept normal network requests, resulting in substantial economic losses. This paper is based on the analysis of...
Support vector machines (SVM), which are based on statistical learning theory and structural risk minimization principle, according to limited sample information, search the best compromise between the model complexity and the learning ability, and have good prediction effect. However, in the methods of load forecasting which are based on SVM, the choices of penalty coefficient c, insensitive coefficient...
In order to improve the accuracy of traffic forecasts, it's important to apply the supporting vector regression in prediction of network traffic. This paper introduced key factors in supporting vector-machine regression modeling, and this model is applied to calculate the actual network traffic prediction, which compared with the BP neural network model. The results showed that supporting vector-machine...
This paper describes the classification of 74 atmospheric circulation parameters firstly. Secondly through the monthly data of different periods of 31 years, 21 years and 11 years, the author calculates the correlation of parameter couples. At last, the article describes strong correlation parameter couples in different periods, different months and different types. Correlation is the basis consideration...
In order to find out the quantitative relationship between the change of land use and ecosystem service in the future, an Ecosystem Service Value-Markov model (ESV-Markov model) is developed and evaluated. Based on the model, the values of ecosystem services of the land use in Wuhan from 2009 to 2019 are predicted. In summary, the model can finely reflect the change of quantitative relationship between...
In order to accurately analyze the trend of health state variation of aero-generator, a grey prediction model based on genetic algorithm is presented in this paper. Then use the original grey model and the optimized grey model respectively to carry out health state trend analysis of the aero-generator. On this basis, the two models were used to study aero-generator health trends, and compared with...
The support vector machine(SVM) based on structural risk minimization is more and more widely used to solve the problems of small sample, nonlinear, high dimensional and local minimization attributes because of its good generalization. But the performance of SVM is influenced by the model parameters very much. At present there is not a unified method of model selection, which makes it troublesome...
A Model Predictive Control (MPC) based fault tolerant control application has been described. The controller was applied to control the concentration and level of a solid crystal dissolution tank. The system was frequently suffering process upset due to difficulty in solid discharge. The controller used an error calculated from an intermittent signal as a feedforward to the controller. The intermittent...
As for the textile printing and dyeing industry being difficulty to be realized on-line real-time monitoring wastewater treatment, a kind of adjustable linear combination of combined kernel function support vector machine modeling way was put forward. The "acid fuchsine decolorization rate" modeling simulation research, which made in the process of printing and dyeing wastewater treatment,...
In order to further improve the accuracy and the mechanism of predicting winter wheat quality using remote sensing method, The quantitative relationships between remote sensing variables and agronomy parameters of winter wheat were analyzed. The results of the study showed that: the relationships between sedimentation value (SV) and remote sensing variables were more significant at booting stage than...
In the accelerated modernization, China confronts with the serious challenges including population explosion, water pollution, though the Chinese water resource is ample. The scientific and reasonable prediction of water resource requirement is essential for the environment protection and continually development. After analysis the use of a serial of artificial neural networks for the water resource...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.