Free Form Surface Reconstruction Method Based on LS-SVM

2011 ◽  
Vol 308-310 ◽  
pp. 280-283
Author(s):  
Fu Zhong Wu

A free form surface reconstruction method based on least square support vector regression is presented. Firstly in order to eliminate noise points, some sample points are chosen from the measured data to construct LS-SVM model. Thus a LS-SVM model to approximate the measured points is obtained. And the distribution probability of the approximation error is figured out. In result, the noise points are eliminated when their error probability is less than the specified threshold value. Then the boundary points are extracted. Lastly the surface model is reconstructed by use of the measured points from which noise points have been eliminated. The results indicate that the reconstruction precision can satisfy the demands of engineering application.

2011 ◽  
Vol 308-310 ◽  
pp. 962-966 ◽  
Author(s):  
Zhong Liang Lu ◽  
Di Chen Li

A free form surface reconstruction method based on least square support vector regression is presented. Firstly in order to eliminate noise points, some sample points are chosen from the measured data to construct LS-SVM model. Thus a LS-SVM model to approximate the measured points is obtained. And the distribution probability of the approximation error is figured out. In result, the noise points are eliminated when their error probability is less than the specified threshold value. Then the boundary points are extracted. Lastly the surface model is reconstructed by use of the measured points from which noise points have been eliminated. The results indicate that the reconstruction precision can satisfy the demands of engineering application.


Author(s):  
P. A. van Elsas ◽  
J. S. M. Vergeest

Abstract Surface feature design is not well supported by contemporary free form surface modelers. For one type of surface feature, the displacement feature, it is shown that intuitive controls can be defined for its design. A method is described that, given a surface model, allows a designer to create and manipulate displacement features. The method uses numerically stable calculations, and feedback can be obtained within tenths of a second, allowing the designer to employ the different controls with unprecedented flexibility. The algorithm does not use refinement techniques, that generally lead to data explosion. The transition geometry, connecting a base surface to a displaced region, is found explicitly. Cross-boundary smoothness is dealt with automatically, leaving the designer to concentrate on the design, instead of having to deal with mathematical boundary conditions. Early test results indicate that interactive support is possible, thus making this a useful tool for conceptual shape design.


2017 ◽  
Vol 21 (1) ◽  
pp. 37 ◽  
Author(s):  
Hua Deng ◽  
Yan Li ◽  
Yingchao Zhang ◽  
Hou Zhou ◽  
Peipei Cheng ◽  
...  

The forecast of wind energy is closely linked to the prediction of the variation of winds over very short time intervals. Four wind towers located in the Inner Mongolia were selected to understand wind power resources in the compound plateau region. The mesoscale weather research and forecasting combining Yonsei University scheme and Noah land surface model (WRF/YSU/Noah) with 1-km horizontal resolution and 10-min time resolution were used to be as the wind numerical weather prediction (NWP) model. Three statistical techniques, persistence, back-propagation artificial neural network (BP-ANN), and least square support vector machine (LS-SVM) were used to improve the wind speed forecasts at a typical wind turbine hub height (70 m) along with the WRF/YSU/Noah output. The current physical-statistical forecasting techniques exhibit good skill in three different time scales: (1) short-term (day-ahead); (2) immediate-short-term (6-h ahead); and (3) nowcasting (1-h ahead). The forecast method, which combined WRF/YSU/Noah outputs, persistence, and LS-SVM methods, increases the forecast skill by 26.3-49.4% compared to the direct outputs of numerical WRF/YSU/Noah model. Also, this approach captures well the diurnal cycle and seasonal variability of wind speeds, as well as wind direction. Predicción de vientos en una altiplanicie a la altura del eje con el esquema de la Universidad Yonsei/Modelo Superficie Terrestre Noah y la predicción estadísticaResumenLa estimación de la energía eólica está relacionada con la predicción en la variación de los vientos en pequeños intervalos de tiempo. Se seleccionaron cuatro torres eólicas ubicadas al interior de Mongolia para estudiar los recursos eólicos en la complejidad de un altiplano. Se utilizó la investigación climática a mesoscala y la combinación del esquema de la Universidad Yonsei con el Modelo de Superficie Terrestre Noah (WRF/YSU/Noah), con resolución de 1km horizontal y 10 minutos, como el modelo numérico de predicción meteorológica (NWP, del inglés Numerical Weather Prediction). Se utilizaron tres técnicas estadísticas, persistencia, propagación hacia atrás en redes neuronales artificiales y máquina de vectores de soporte-mínimos cuadrados (LS-SVM, del inglés Least Square Support Vector Machine), para mejorar la predicción de la velocidad del viento en una turbina con la altura del eje a 70 metros y se complementó con los resultados del WRF/YSU/Noah. Las técnicas de predicción físico-estadísticas actuales tienen un buen desempeo en tres escalas de tiempo: (1) corto plazo, un día en adelante; (2) mediano plazo, de seis días en adelante; (3) cercano, una hora en adelante. Este método de predicción, que combina los resultados WRF/YSU/Noah con los métodos de persistencia y LS-SVM incrementa la precisión de predicción entre 26,3 y 49,4 por ciento, comparado con los resultados directos del modelo numérico WRF/YSU/Noah. Además, este método diferencia la variabilidad de las estaciones y el ciclo diurno en la velocidad y la dirección del viento.


Author(s):  
J. M. Zheng ◽  
K. W. Chan ◽  
I. Gibson

Abstract There is an increasing demand in the conceptual design for more intuitive methods for creating and modifying free-form curves and surfaces in CAD modeling systems. The methods should be based not only on the change of the mathematical parameters but also on the user’s specified constraints and shapes. This paper presents a new surface representation model for free-form surface deformation representation. The model is a combination of two functions: a displacement function and a function for representing an existing NURBS surface called parent surface. Based on the surface model, the authors develop two deformation methods which are named SingleDef (Single-point constraint based deformation method), and MultiDef (Multiple-points constraints based deformation method). The techniques for free-form surface deformation allow conceptual designer to modify a parent surface by directly applying point constraints to the parent surface. The deformation methods are implemented and taken in an experimental CAD system. The results show that the designer can easily and intuitively control the surface shape.


2009 ◽  
Vol 27 (6) ◽  
pp. 725-747 ◽  
Author(s):  
Hong Zhou ◽  
Yonghuai Liu ◽  
Longzhuang Li ◽  
Baogang Wei

2010 ◽  
Vol 102-104 ◽  
pp. 544-549 ◽  
Author(s):  
Chun Jiang Zhou ◽  
Hong Chun Chen

The development of surface high-speed machining has put forward higher demands for uniform cutting load and smooth cutting tool path. Most current tool-path planning methods are based on constant scallop height, but they have the disadvantage of path point redundancy during the path discretization process. To overcome the problem, a tool path generation method of equal approximation error in each step for free-form surface is presented based on geodesic principle and curvature judgment. In this method, the NURBS curve is employed to realize smooth transition for adjacent two tool paths in high-speed machining. A certain angle of inclination of flat-end milling cutter during multi-axis machining improves the machining efficiency. Because of the advantage of this machining condition, the cutter location point generation algorithm during the machining condition is given by the method. The method is verified and simulated by C++. Experiment results proved that it can obtain uniform cutting load and continuous smooth cutting tool path during surface high-speed machining by the proposed method.


Author(s):  
Yiqing Fan ◽  
Zhihui Sun

In order to effectively improve the accuracy of Consumer Price Index (CPI) prediction so as to more truly reflect the overall level of the country’s macroeconomic situation, a CPI big data prediction method based on wavelet twin support vector machine (SVM) is proposed. First, the historical CPI data are decomposed into high-frequency part and low-frequency part by wavelet transform. Then a more advanced twin SVM is used to build a prediction model to obtain two kinds of prediction results. Finally, the wavelet reconstruction method is used to fuse the two kinds of prediction results to obtain the final CPI prediction results. The wavelet twin SVM model is used to fit and predict CPI index. Experimental results show that compared with the similar prediction methods, the proposed prediction method has higher fitting accuracy and smaller root mean square error.


2000 ◽  
Vol 2000.3 (0) ◽  
pp. 541-542
Author(s):  
Yasuhiro TAKAYA ◽  
Seojoon LEE ◽  
Satoru TAKAHASHI ◽  
Takashi MIYOSHI

Sign in / Sign up

Export Citation Format

Share Document