Papers by Keyword: Grey Model

Abstract: Arch bridges will produce horizontal internal force at arch springing under vertical load. The horizontal internal forces and displacement of abutments have significant influences on structural behavior of arch bridge, which was located at soft soil foundation. One of the effective methods to solve the problem is applied the pre-pushing technique behind abutment by two horizontal anti-slide slab. However, there is soil creep deformation at the arch springing under the long-term vertical load. Therefore, an unequal interval multivariable grey model was established to predict the soil creep deformation. This grey model was extended by a single point and equal interval model. The modeling steps are also proposed in this paper. And then the calculated results by the proposed model will compared with the measured results and the results of Burgers model. The compared results showed that it can precisely and effectively predict the amplitude of the creep deformations.

Abstract: In this paper, based on the basic theory of GM(1,1), we present a new method based on cosine function transform the discrete data sequence disposed through the standardization processing to improve the smoothness, first we theoretically proved that this transformation can improve smoothness of the original data sequence after a certain standardization, and more effective than some former method, an example is used to demonstrate the effectiveness of this method in the last of this paper.

Abstract: In the development of socialist modernization today, the social gap between rich and poor is still very large. Poor university students account for a quite large proportion in university students' whole groups. How to ensure poor university students' rights and interests is very important. From the analysis of poor university students’ all aspects of rights, this paper compared the difference of two countries’ protecting the rights of poor university students by analysis of grey theory and anonymous questionnaire survey. It analyzes the reasons of difference and explores the basic methods of educating poor students, establishing and perfecting contemporary university students' education system, so as to help poor students gain legal safeguard of rights and interests and lay a solid foundation for the construction of a harmonious campus and a harmonious society.

Abstract: To detect the moving vehicles correctly, we proposed a vehicle tracking method based on background model, fuzzy C-Means clustering and Grey model. In this paper, the background image is updated adaptively to accommodate vehicle detection in variable outer environment. The Grey model is employed to predict the center and number of C-Means clustering, solving the dependency of fuzzy C-Means upon clustering center of initial frame. The result of clustering provides updated data of Grey model for the position of target in the next frame. The experimental results show that, the method proposed improves both of the speed and accuracy of C-Means clustering, and promote the robustness and real-time of vehicle tracking system.

Abstract: Due to the short investment time of the new equipment, the materiel consumption and maintenance data is not much. As a result, its demand prediction belongs to the prediction of small sample data. Since general demand prediction methods are difficult to predict the materiel demand of new equipment, an applicable and efficient prediction method should be explored to solve the problem. Therefore, combining grey prediction theory and least square support vector machine and operating accumulative generation on the original data sequence to extract its deep law characteristic, the new equipment materiel demand prediction model based on Grey Least Square Support Vector Machine (GLSSVM) was established, and the model's parameters was optimized by SIWPSO. Finally an example was set using Neural Network, traditional LSVSM and GLSSVM to predict the materiel demand of new equipment X to verify the accuracy and effectiveness of GLSSVM. The result shows that the prediction precision of GLSSVM is superior to the other two methods.

Abstract: Short-term traffic flow forecasting is a core problem in Intelligent Transportation System .Considering linear and nonlinear, this paper proposes a short-term traffic flow intelligent combination approach. The weight of four forecasting model is given by the correlation coefficient and standard deviation method. The experimental results show that the new approach of real-time traffic flow prediction is higher precision than single method.

Abstract: This paper presents an improved grey model used in power load forecasting. In order to overcome the limitation of the traditional grey model GM(1,1), vector θ is introduced to modify the calculating formula for background sequence value in grey model and build a more adaptable model. Using artificial fish school algorithm can solve the value of vector θ . It reflects that the improved model has higher accuracy of load forecasting and has wider application by cases analysis.

Abstract: Based on the traditional differential hydrological grey-model, this paper applied the annual/seasonal index to data pre-processing of precipitation and runoff and established the Differential Hydrological Grey Self-memory Model with the self-memory theory. The model was used to simulate and predict the runoff in different time scales. The results showed that:1The model performed much better in year time scale with achieving precision requirement of hydrological model;2the relative deviation was decreased to 0.6%, the correlation coefficient and Nash-Sutcliffe were raised to 0.744 and 0.704 respectively with the pre-processing data of precipitation and runoff;3the model was applicable to predicting the runoff especially in the year time scale. The structure model was simple and easy to be calculated, nevertheless, the factors of evaporation, land-use and human activity should be taken into consideration so that the model can be more perfect. Keywords: Grey model; self-memory theory; annual/seasonal index; runoff

Abstract: Scientific research funds task indicator is one of the most important management which is becoming highly valued in research institutions. The key issue of scientific research management is how to define stimulating and scientific annual task indicator. Based on sustainable development theory, the paper comparing quadratic and Grey model GM (1, 1) based on actual data of one research institution, the result suggest that Grey model GM (1, 1) reach high forecast accuracy and can be use to forecast Scientific research funds. The conclusions as follows were reached,first, the next funds is highly correlated with historical funds, and Grey model GM (1, 1) is worth applying to define and forecast annual target of scientific research funds.

Abstract: Wind speed forecasting is an effective method to improve power stability of wind farm. Grey system theory have certain advantages in the study of poor information and uncertainty problems, it is suitable for the system with limited computing power and data storage capacity, such as wind turbine control system. In order to further improve the prediction accuracy of grey model, we combined GM (1, 1) model and BP neural network prediction model in this paper, and improved the combined model by background value optimizing and introducing genetic algorithm. Through analyzing the simulation results and comparing the forecasting results with the actual wind speed, it is clear that the improved combined prediction model is superior to pure grey forecasting model and it meets the needs of the wind power control.