自动化学报2017，Vol.43Issue(12)：2115-2126,12.DOI:10.16383/j.aas.2017.c160621
基于分数阶的多向微分算子的高炉料面轮廓自适应检测
Adaptive Detection of Blast Furnace Surface Contour with Fractional Multi-directional Differential Operator
摘要
Abstract
Blast furnace image contains abundant furnace condition information and blast furnace surface contour can directly reflect the bump ups and downs of burden surface, the gas distribution and other information, but the blast furnace burden surface image has the features of low contrast,inconspicuous details and strong bright spots,which make it difficult to detect the blast furnace surface contour. In this connection, a new blast furnace surface contour detection method is proposed. Firstly, the image is preprocessed to enhance its dynamic range and edge information; secondly, multi-directional differential operators based on fractional are deduced to extract a set of blast furnace burden surface contours of feasible region; then, the optimum fractional order is determined by adaptive method to obtain the optimal surface contour curve in the feasible region;lastly,an improved Canny operator is proposed to correct and compensate the optimal surface contour curve. Theoretical research and experimental results show that the new method can accurately obtain a smooth blast furnace burden surface contour, which has great guiding significance for blast furnace foreman to control charging in time and effectively.关键词
高炉料面图像/轮廓检测/图像增强/分数阶微分/Canny算子Key words
Blast furnace surface image/contour detection/image enhancement/fractional differential/Canny operator引用本文复制引用
蒋朝辉,吴巧群,桂卫华,阳春华,谢永芳..基于分数阶的多向微分算子的高炉料面轮廓自适应检测[J].自动化学报,2017,43(12):2115-2126,12.基金项目
国家自然科学基金(61290325,61621062),高性能复杂制造国家重点实验室自主研究课题(ZZYJKT2016?05)资助Supported by National Natural Science Foundation of China(61290325,61621062)and Independent Research Topics of State Key Labratory of High Performance Complex Manufactring(ZZ YJKT2016?05) （61290325,61621062）
