Papers by Keyword: Multiple Nonlinear Regression

Abstract: This article establishes analysis model based on Multiple Nonlinear Regression and analyses the model using SPSS. Then eight indexes such as storage of Material sources are selected as independent variable, and make an empirical analysis by survey data of 40 debris flow valleys. Finally, the test results show that both the importance analysis of the impact factors of debris flow and the rank deviation of risk assessment are right. Moreover, using multiple nonlinear Regression model and SPSS to assess the risk of debris flow is proved feasible.

Abstract: Grinding is the mostly leading machining technology for engineering ceramics. The quality of ground surface can be evaluated by various roughness parameters. And a textural analysis method based on Gray Level Co-occurrence Matrix was employed in researching the roughness of ground ceramics. The relationship between texture features and roughness was investigated through a series of surface images of engineering ceramics collected by a digital microscope. The sampling offset and total gray levels of surface images were determined firstly. Then 4 GLCMs were built up to calculate the average of texture features. And 6 parameters were fixed as main texture parameters. Furthermore, the multiple nonlinear regression theory was used to assess the relation between the texture features and roughness Ra. By statistic test and comparison, the deviation of calculated Ra and actual Ra is less than 0.25. It is shown that this relation is much satisfactory and the method may be suitable for quickly measuring the roughness of ground ceramics.

Abstract: The hill-climbing has been improved by using the percentage random step and by changing variable values instantly, which is under the condition of an improvement in the objective function having been made by a step forward of a variable in a certain direction, and the improved hill-climbing has been used to solve nonlinear regression problems , and the specific algorithm steps is given, and it has been validated with satisfactory results by using practical examples.

Abstract: Uniaxial compression tests on semi-solid AZ61 alloy fabricated by stain-induced activation (SIMA) process and the conventional casts were carried out using the Gleedle-1500 dynamic material testing machine. The relationships between stress and stain were analyzed. The numerical relationships among processing parameters (strain rate z ε&
strain z ε
temperature T
liquid volume fraction L f ) and stress were studied. The proposed constitutive equation was established for semi-solid AZ61 magnesium alloy using the multiple nonlinear regression method. A scientific basic provided for both numerical simulation of processing process of semi- solid AZ61 alloy and rational choice and control of processing parameters.