logistic模型在裂纹检测概率曲线拟和中的应用  

The Application of Modified Logistic Model in Fitting of the Flaw Testing Probability Curve

作　　者：肖鹏[1] 白存儒[1] 

机构地区：[1]西北工业大学航空学院,陕西西安710072

出　　处：《华东交通大学学报》2005年第5期158-161,共4页Journal of East China Jiaotong University

摘　　要：提出了一种适合于描述无损检测概率曲线的经过修正的logistic回归模型,并运用最小二乘原理,利用非线性回归分析,结合高斯-牛顿迭代法,给出了求解该模型中未知参数的具体思路与方法.同时结合具体算例,对该模型的拟和优良性进行评估分析.计算结果表明,该模型的预测值与实验值吻合良好,有较高的预测精度.The research in this paper presented a new modified logistic model which could satisfy the demand of data processing of nondestructive testing. Used least squares, adopted nonlinear regression, and applied Gauss - Newton iteration, by which introduced the detail estimation method of distribution parameter. The goodness of fit of the model was also evaluated by integrating a group of concrete reliability test data. Computational result indicates that prediction values of the proposed modified logistic model are in good agreement with the experimental results and the model is suitable for matching testing probability curve and has the higher prediction accuracy and better flexibility.

关 键 词：无损检测 逻辑斯谛模型 非线性回归 高斯-牛顿法 预测精度 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]