为精准掌握涡轮机叶片的运行状态，判断其是否需要进行更换，提出船舶涡轮机叶片细小裂痕视觉显著性检测方法。利用改进同态滤波算法平滑叶片CCD图像，增强图像的对比度以及均衡度，基于谱残差视觉注意模型提取显著图，通过线性迭代聚类算法分割获取的显著图，设定判断阈值，确定最终的船舶涡轮机叶片微小裂痕区域，完成船舶涡轮机叶片细小裂痕检测。测试结果显示，该方法具备较好的应用效果，可显著提升图像整体均匀度；显著图的提取效果较好，平均绝对误差至均在0.021以下，可靠确定船舶涡轮机叶片微小裂痕区域。
To accurately grasp the operating status of turbine blades and determine whether they need to be replaced, a visual significance detection method for small cracks in ship turbine blades is proposed. Using an improved homomorphic filtering algorithm to smooth the blade CCD image, enhance the contrast and balance of the image, extract saliency maps based on spectral residual visual attention model, segment the saliency maps obtained through linear iterative clustering algorithm, set the judgment threshold, determine the final small crack area of the ship turbine blade, and complete the detection of small cracks in the ship turbine blade. The test results show that this method has good application effects and can significantly improve the overall uniformity of the image; The extraction effect of saliency maps is good, with an average absolute error below 0.021, which reliably determines the small crack areas of ship turbine blades.
2024,46(18): 167-170 收稿日期：2024-3-1
DOI：10.3404/j.issn.1672-7649.2024.18.030
分类号：TP391
基金项目：山西省科技厅重点研发项目（201903D121171）
作者简介：张麟华(1982-),男,硕士,副教授,研究方向为机器视觉
参考文献：
[1] 周渝航, 林枫, 侯隆安, 等. 单晶涡轮叶片强度分析与结构优化设计[J]. 热能动力工程, 2023, 38(11): 56–62.
ZHOU Yuhang, LIN Feng, HOU Longan, et al. Strength analysis and structural optimization design of single crystal turbine blade[J]. Journal of Engineering for Thermal Energy and Power, 2023, 38(11): 56–62.
[2] 刘仲任, 彭力. 多尺度视觉感知融合的显著性目标检测[J]. 计算机工程, 2023, 49(12): 186-193+204.
LIU Zhongren, PENG Li. Salient object detection with multi-scale visual perception and fusion[J]. Computer Engineering, 2023, 49(12): 186-193+204.
[3] 袁梦, 苏工兵, 王晶, 等. 基于BCGS-YOLOv7 tiny的零件表面微小缺陷检测[J]. 制造技术与机床, 2023(10): 137-144.
YUAN Meng, SU Gongbing, WANG Jing, et al. Part surface micro defect detection based on BCGS-YOLOv7 tiny[J]. Manufacturing Technology & Machine Tool, 2023(10): 137-144.
[4] 余文勇, 张阳, 姚海明, 等. 基于轻量化重构网络的表面缺陷视觉检测[J]. 自动化学报, 2022, 48(9): 2175-2186.
YU WenYong, ZHANG Yang, YAO Haiming, et al. Visual Inspection of Surface Defects Based on Lightweight Reconstruction Network[J]. Acta Automatica Sinica, 2022, 48(9): 2175-2186.
[5] 谷典典, 石屹宁, 刘譞哲, 等. 基于元算子的深度学习框架缺陷检测方法[J]. 计算机学报, 2022, 45(2): 240-255.
GU Diandian, SHi Yining, LIU Xuanzhe, et al. Defect detection for deep learning frameworks based on meta operators[J]. Chinese Journal of Computers, 2022, 45(2): 240-255.
[6] 陈世琼. 基于非线性抗噪声估计的视觉显著性弱小目标检测[J]. 红外与激光工程, 2022, 51(9): 435-440.
CHEN Shiqiong. Visual salient dim small target detection based on nonlinear anti noise estimation[J]. Infrared and Laser Engineering, 2022, 51(9): 435-440.
