基于稀疏数据规约的CMAC大气腐蚀数据补偿方法-计算机应用研究.PDFVIP

优先出版 计 算 机 应 用 研 究 第33 卷 基于稀疏数据规约的CMAC大气腐蚀数据补偿方法* 李志平，付冬梅，穆志纯 (北京科技大学 自动化学院，北京 100083) 摘 要：如何准确的补偿缺失的大气腐蚀等级数据成为函待解决的问题。分别针对大气腐蚀等级的两个关键因素氯离子 浓度、二氧化硫浓度单独缺失的情况进行数据建模补偿。针对中国地区腐蚀等级以及相关环境参数数据稀疏分布的特性， 提出了一种基于稀疏数据规约的 CMAC 大气腐蚀数据补偿方法。同时，针对二氧化硫浓度缺失的情况，根据现有的有 效数据，提出了二氧化硫浓度的经验公式。结果表明，氯离子浓度单独缺失时预测准确率为86.5%，二氧化硫浓度缺失 单独缺失时预测准确率为82.6%。该算法提高了大气腐蚀等级数据补偿准确率，为材料选择提供了重要依据。 关键词：缺失数据；大气腐蚀等级；小脑模型；稀疏数据规约；二氧化硫浓度经验公式 中图分类号：TP391.1 Missing data compensation method in atmospheric corrosion data with CMAC based on sparse data regular Li Zhiping, Fu Dongmei, Mu Zhichun (School of Automation Electrical Engineering, University of Science Technology Beijing, Beijing 100083) Abstract: How to compensate accurately for atmospheric corrosion data is a problem which needs to be solved. Two key factors which determine the atmospheric corrosion level. chlorine ion concentration and sulfur dioxide concentration. usually do not have data. This paper solved the problem by imputing missing data. Atmospheric corrosion level data and relevant environmental parameters data in China are both sparse distribution. According to the characteristic. this paper put forward a missing data compensation method in atmospheric corrosion data with CMAC based on sparse data regular. For the situation of imputing sulfur dioxide concentration data. this paper put an empirical formula of sulfur dioxide concentration. The results showed that the prediction accuracy was 86.5% when the chloride ion concentration was absent. and the prediction accuracy was 82.6% when the sulfur dioxide con