CAJ | 학술논문

分析了影响燃油炉燃烧效率的因素，提出一种基于火焰彩色图像像素分类的表征燃烧状况的指标评价函数，用于识辨燃烧状况.该函数基于贝叶斯(Bayes)统计概率分类器原型，在取得先验概率和条件概论的密度函数后，算出后验概率，最终以后验概率为判断依据，建立判断模型.从实际炉膛拍摄火焰图象选取学习样本，得到分类决策函数，并应用检验样本分析图象分类精度进而估计类别选取的合理程度.实际试验结果表明，该方法不仅能够得到与目视判别一致的结果，而且判断的可靠性更高.
분석료영향연유로연소효솔적인소，제출일충기우화염채색도상상소분류적표정연소상황적지표평개함수，용우식변연소상황.해함수기우패협사(Bayes)통계개솔분류기원형，재취득선험개솔화조건개론적밀도함수후，산출후험개솔，최종이후험개솔위판단의거，건립판단모형.종실제로당박섭화염도상선취학습양본，득도분류결책함수，병응용검험양본분석도상분류정도진이고계유별선취적합리정도.실제시험결과표명，해방법불부능구득도여목시판별일치적결과，이차판단적가고성경고.
Presents the fuel combustion status evaluation function established by analyzing the factors having effect on the efficiency of industrial furnaces and based on the flame color image classification by Gauss classification theory and the Bayes classification fule, from which, the density function of prior probability and conditional probability of the flame image classification can be obtained, and the posterior probability can be used to establish the judge model, and the learning speciment selected from the practical furnace flame image to establish the classification decision function specimen are then used to analyse the classification precision to account the reasonable degree of the image category, and concludes from test results that the method can not noly coincide with human judgement but also eliminate the man-made interference.