基于BP神经网络和最小二乘支持向量机的灰熔点预测和对比  

Prediction and Comparison of Ash Fusion Temperatures Based on BP Neural Network and Least Squares Support Vector Machine

作　　者：时浩 肖海平[1] 刘彦鹏 SHI Hao;XIAO Haiping;LIU Yanpeng(School of Energy,Power and Mechanical Engineering,North China University of Electric Power,Changping District,Beijing 102206,China;Thermal Power Technology Research Institute,China Datang Corporation Science and Technology General Research Institute Ltd.,Shijingshan District,Beijing 100040,China)

机构地区：[1]华北电力大学能源动力与机械工程学院,北京市昌平区102206 [2]中国大唐集团科学技术研究院有限公司火力发电技术研究院,北京市石景山区100040

出　　处：《发电技术》2022年第1期139-146,共8页Power Generation Technology

基　　金：国家自然科学基金项目(51206047)。

摘　　要：为了预测燃煤锅炉受热面的结渣情况,以灰成分金属氧化物、煤灰SO_(3)含量以及结渣评判指标为自变量,灰熔点变形温度(deformation temperature,DT)和软化温度(softening temperature,ST)为因变量,建立了BP神经网络(BP neural network,BPNN)和最小二乘支持向量机(least squares support vector machine,LSSVM)的灰熔点预测模型。回归分析和误差分析结果表明:针对样本量多的DT预测过程,2种模型精度接近,预测结果置信度均达到95%,相关系数均约为0.92,平均相对误差均约为3.4%;针对样本量较少的ST预测过程,LSSVM模型预测效果较优,相关系数为0.95052,高于BPNN模型的0.90426,平均相对误差为4.98%,并且大误差点个数少于BPNN模型。因此,LSSVM模型能够更准确预测飞灰的DT和ST。To predict the slagging on heating surface of coal-fired boilers,BP neural network(BPNN)and least squares support vector machine(LSSVM)prediction models were established to predict ash fusion temperature,deformation temperature(DT)and softening temperature(ST).The models take ash metal oxide,SO_(3) content of ash and slagging evaluation indexes as independent variables,and take DT and ST as dependent variables.Regression analysis and error analysis show that when predicting DT with a large number of samples,the prediction accuracy of the two models is similar,and the confidence of prediction is over 95%.The correlation coefficients are both about 0.92,and the average relative errors are about 3.4%.When predicting ST with less samples,LSSVM model is better with a correlation coefficient of 0.95052,which is higher than 0.90426 of BPNN model.The average relative error is 4.98%,and the number of large error points is less than the BPNN model.Therefore,LSSVM model can predict DT and ST of fly ash more accurately.

关 键 词：BP神经网络(BPNN) 最小二乘支持向量机(LSSVM) 灰熔点 灰成分 结渣评判指标 

分 类 号：TK223[动力工程及工程热物理—动力机械及工程]