基于机器学习的甲烷预混火焰当量比测量  

Measurement of Methane Premixed Flame Equivalence Ratio Based on Machine Learning

作　　者：张燕[1] 杨健晟 ZHANG Yan;YANG Jiansheng(The Electrical Engineering College,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学电气工程学院,贵州贵阳550025

出　　处：《软件工程》2025年第4期11-15,共5页Software Engineering

摘　　要：为了克服传统当量比测量模型存在的局限性,提出了一种基于机器学习的多特征输入方法。该方法摒弃了以往单一依赖CH*与C_(2)*比值的方式,而是综合利用C_(2)*swan band的多个化学发光波段。为了验证这种多输入方法的有效性,采用支持向量机(SVM)和多层感知机(MLP)两种不同的机器学习模型进行实验验证。实验结果表明,多特征输入在这两种模型上展现出优异的回归预测性能,回归系数均达到了0.99,证明了所提方法在精确测量当量比方面的可靠性和有效性。In order to overcome the limitations of the traditional equivalence ratio measurement model,a multi-feature input method based on machine learning is proposed.Instead of relying on a single CH to C_(2)ratio,this method integrates multiple chemiluminescence bands of the C_(2)swan band.To validate the effectiveness of this multi-feature method,two distinct machine learning models,Support Vector Machine(SVM)and Multilayer Perceptron(MLP),are employed for experimental verification.The experimental results demonstrate that the multi-feature input exhibits excellent regression prediction performance on both models,with regression coefficients reaching 0.99,thereby proving the reliability and effectiveness of the proposed method in accurately measuring the equivalence ratio.

关 键 词：当量比 多特征输入 支持向量机 多层感知机 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]