电站锅炉炉管腐蚀产物拉曼光谱智能识别  

Intelligent Identification of Raman Spectroscopy for Corrosion Products of Boiler Tube in Power Plant

作　　者：齐建涛[1] 刘永豪 朱永强 孙治谦[1] QI Jiantao;LIU Yonghao;ZHU Yongqiang;SUN Zhiqian(College of New Energy,China University of Petroleum(East China),Qingdao 266580,Shandong,China)

机构地区：[1]中国石油大学(华东)新能源学院,山东青岛266580

出　　处：《实验室研究与探索》2025年第3期6-11,56,共7页Research and Exploration In Laboratory

基　　金：国家自然科学基金项目(51701239);教育部产学研协同育人项目(BINTECH-KJZX-20220831-35);中国石油大学(华东)教学改革项目(CM2022057);中国石油大学(华东)大学生创新创业项目(S202310425101)。

摘　　要：生物质燃料电站锅炉存在腐蚀产物组分复杂、炉管腐蚀失效难以快速检测等问题,为此提出一种基于拉曼光谱的腐蚀产物智能识别方法。针对电站锅炉省煤器和水冷壁顶部、中部、内壁腐蚀产物,采用扫描电镜和拉曼光谱技术,明确腐蚀产物种类,并基于基线校正、宇宙射线消除、平滑处理等预处理过程,获得腐蚀产物的拉曼光谱数据集。通过主成分分析(PCA)结合线性判别分析(LDA)、支持向量机(SVM)以及偏最小二乘法判别分析(PLS-DA)模型进行腐蚀产物分类性能评估,并将性能最佳的分析模型进行应用验证。结果表明,PCA-SVM线性核模型在腐蚀产物分类上效果最佳,现场应用的整体准确率达到90.00%。In view of the complex composition of corrosion products in biomass fuel power plant boilers and the difficulty in quickly detecting boiler tube corrosion failures,an intelligent identification method based on Raman spectroscopy is proposed.Corrosion products on the top,middle,and inner walls of the economizer and water-cooled wall in power plant boilers are obtained by scanning electron microscopy(SEM)and Raman spectroscopy techniques to identify the types of corrosion products.A Raman spectroscopy dataset of these products is constructed through preprocessing operations,including baseline calibration,cosmic ray elimination,and smoothing.The classification performance of corrosion products is evaluated using principal component analysis(PCA)combined with linear discriminant analysis(LDA),support vector machine(SVM),and partial least squares-discriminant analysis(PLS-DA)models.The best performing model is then validated in practical application.The results show that the PCA-SVM linear kernel model performs best in classifying corrosion products.It achieves an overall accuracy of 90.00%in field applications.This provides experimental and theoretical support for developing a rapid and accurate intelligent identification method for boiler corrosion products.

关 键 词：锅炉腐蚀 腐蚀检测 拉曼光谱 机器学习 生物质燃料 

分 类 号：TB37[一般工业技术—材料科学与工程]