大气环境腐蚀性因素的相关性

通过相关性数据处理和模糊聚类分析，发现影响大气环境腐蚀性的２１种环境因素在相关系数大于０．５４的情况下，可明显地聚为５类．在此基础上，进一步通过对逐个因素的分类能力的特征评价，选取大气环境腐蚀性的主要因素（ＲＨ＞８０％时数，Ｓ０２沉积速度，水溶性尘降，Ｃｌ－沉积速度，ＮＯ２浓度），进而在特征空间中进行镀锌层样本的大气环境腐蚀性预测和考评，为今后实现我国大气环境腐蚀性等级评判提供依据．

土壤腐蚀性关键因素的评价与选取

在２２种土壤腐蚀性因素的聚类分析的基础上，通过对单个因素分类能力的特征评价，从同类中选取关键性因素，进而在特征空间中进行有关样本的土壤腐蚀性预测和考评，为今后土壤腐蚀性研究中主要因素的选取和等级评判提供一定的依据。

大气环境腐蚀性因素的相关性

通过相关性数据处理和模糊聚类分析，发现影响大气环境腐蚀性的２１种环境因素在相关系数大于０．５４的情况下，可明显地聚为５类在此基础上，进一步通过对逐个因素的分类能力的特征评价，选取大气环境腐蚀性的主要因素（ＲＨ＞８０％时数，ＳＯ２沉积速度，水溶性尘降，Ｃｌ－沉积速度，ＮＯ２浓度），进而在特征空间中进行镀锌层样本的大气环境腐蚀性预测和考评，为今后实现我国大气环境腐蚀性等级评判提供依据．

Corrosion depth prediction based on non-linearity method

Pipeline of oil and gas have an increased risk because of pipeline punctures and rupture caused by corrosion. Therefore it is very important to have a reliable way for pipeline corrosion prediction. The corrosion depth prediction models that based on the support vector machines and chaos were introduced in this paper. A real example was given in this paper. The predicted results showed that the prediction models have a more higher precision. The two corrosion depth prediction models are reasonable in corrosion research, which can supply a scientific basis for pipeline safety management, service life prediction and repair.