中国科技论文
中國科技論文
중국과기논문
Sciencepaper Online
2012年
1期
58-63
,共6页
烟雾检测%图像分析%K均值聚类%熔炼过程
煙霧檢測%圖像分析%K均值聚類%鎔煉過程
연무검측%도상분석%K균치취류%용련과정
smoke detection%image analysis%K-means clustering%smelting process
针对熔炼过程中产生的烟雾浓度难以检测的问题，提出了一种利用图像分析的方法量化其烟雾浓度，并通过K均值聚类分析不同烟雾浓度下图像特征的聚类特性，从而对熔炼过程的烟雾进行检测。通过工频熔炼过程的实际图像测试和现场实际应用，验证了该算法的有效性和实用性。
針對鎔煉過程中產生的煙霧濃度難以檢測的問題，提齣瞭一種利用圖像分析的方法量化其煙霧濃度，併通過K均值聚類分析不同煙霧濃度下圖像特徵的聚類特性，從而對鎔煉過程的煙霧進行檢測。通過工頻鎔煉過程的實際圖像測試和現場實際應用，驗證瞭該算法的有效性和實用性。
침대용련과정중산생적연무농도난이검측적문제，제출료일충이용도상분석적방법양화기연무농도，병통과K균치취류분석불동연무농도하도상특정적취류특성，종이대용련과정적연무진행검측。통과공빈용련과정적실제도상측시화현장실제응용，험증료해산법적유효성화실용성。
To solve the question that available technology was difficult to detection smoke concentration in the smelting process, this paper presented investigations into the smoke detection using image analysis and K-means clustering. First, image features related to smoke concentration property was extracted from the smoke image. Then the k-means clustering was used to classify the image features based on the unique clustering property of different smelting stage. The correlations between the image features selected and smoke concentration were also identified and analyzed. The industrial application image analysis results show that the proposed method can detect the smoke concentration effectively.
