1 Machinery Industry Shanghai Lanya Petrochemical Equipment Testing Institute Co., Ltd., Shanghai 201614, China
2 PetroChina Yunnan Petrochemical Co., Ltd., Kunming 650300, China
3 School of Mechanical Engineering, Hebei University of Technology, Tianjin 300401, China
Show less
文章历史+
Received
Published
Revised
2025-05-26
2026-06-08
2026-01-07
Online Date
2026-08-07
PDF (6885K)
摘要
石化储罐在长期使用过程中易受内外环境的侵蚀,导致泄漏事故发生,对生态环境、国民经济及居民安全造成重大隐患。目前,深度学习和传统图像处理方法等机器视觉技术在锈蚀的检测与识别上仍存在一定局限,其识别结果通常缺乏客观定量标准。针对上述问题,提出一种基于超像素分割的石化储罐锈蚀检测方法。通过搭建轻型卷积神经网络模型(lightweight convolutional neural networks,LCNN),使用简单线性迭代聚类算法(simple linear iterative clustering,SLIC)对图像初步分割并生成超像素,随后采用融合纹理核的全连接条件随机场算法(conditional random field,CRF)对锈蚀进行准确分割,并利用RGB(red-green-blue)颜色空间判断锈蚀程度。实验表明,相比于深度学习和传统图像处理等检测方法,运用基于超像素分割的石化储罐锈蚀检测方法,可在一定程度上提高对石化储罐锈蚀的检测效率和精准性。
Abstract
Petrochemical storage tanks are susceptible to long-term erosion from internal and external environments during service, which poses significant risks to ecological safety, national economy, and residential security. Current machine vision technologies including deep learning and traditional image processing show limitations in corrosion detection and identification, with recognition results generally lacking objective quantitative standards. Aiming at the above problems, a rust detection method for petrochemical storage tanks based on super-pixel segmentation was proposed. By building a lightweight convolutional neural networks (LCNN) model, the image was initially segmented and super-pixels were generated using simple linear iterative clustering (SLIC) algorithm, and then the fusion of fully connected conditional random field (CRF) algorithm with texture kernel was used to accurately segment the rust and determine the degree of rust using red-green-blue (RGB) color space. The experiments show that compared with the detection methods such as deep learning and traditional image processing, the petrochemical storage tank rust detection method based on super-pixel segmentation can improve the detection efficiency and accuracy of petrochemical storage tank corrosion to a certain extent.
TIAN Li, HAN Jin-ze, XU Ke, LIU Cheng-yan, SUN Ling-yu.
Petrochemical Storage Tank Corrosion Detection Method Based on Super-pixel Segmentation[J].
Science Technology and Engineering, 2026, 26(16): 6861-6866 DOI:10.12404/j.issn.1671-1815.2503910
目前,深度学习和传统图像处理方法等机器视觉技术已在锈蚀检测领域广泛应用,但现有方法的识别结果通常缺乏客观定量标准[9]。为此,提出一种基于超像素分割的石化储罐锈蚀检测方法。通过搭建轻型卷积神经网络模型,使用简单线性迭代聚类算法(simple linear iterative clustering,SLIC)对图像进行初步分割并生成超像素,随后采用融合纹理核的全连接条件随机场算法(conditional random field,CRF)对锈蚀进行准确分割,并利用RGB颜色空间判断锈蚀程度,实现了基于超像素分割的石化储罐锈蚀视觉检测。
WuYang, LiuYuefang, WangXianjun, et al. Maintenance process for external anti-corrosion coating of storage tank[J]. Science Technology and Engineering, 2023, 23(18): 7753-7757.
ChengWei, ChenWei, YuanWenbin, et al. Research on prediction method of corrosion rate of floor of large crude oil storage tank[J]. Pressure Vessel Technology, 2025, 42(2): 80-86.
[7]
HuangX B, ZhangX L, ZhangY, et al. A method of identifying rust status of dampers based on image processing[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 68(8): 5407-5417.
[8]
PanR B, ZhongC M, QianJ B. Balanced fair K-Means clustering[J]. IEEE Transactions on Industrial Informatics, 2023, 20(4): 5914-5923.
[9]
XuJ Z, YuanM K, YanD M, et al. Illumination guided attentive wavelet network for low-light image enhancement[J]. IEEE Transactions on Multimedia, 2022, 25: 6258-6271.
[10]
BembenekM, MandziyT, IvasenkoI, et al. Multiclass level-set segmentation of rust and coating damages in images of metal structures[J]. Sensors, 2022, 22(19): 7600.
[11]
TrivediV K, ShuklaP K, PandeyA. Automatic segmentation of plant leaves disease using min-max hue histogram and k-mean clustering[J]. Multimedia Tools and Applications, 2022, 81(14): 20201-20228.
SongZitao, ZhaoQuanming, ZhangDongmei. Multi-scale residual convolution-vision Transformer and GAN for hyperspectral image classification[J]. Journal of Hebei University of Technology, 2025, 54(2): 42-51.
[14]
WangB, CaiB D, ShengJ F, et al. AAGCN: a graph convolutional neural network with adaptive feature and topology learning[J]. Scientific Reports, 2024, 14(1): 10134.
[15]
LimW X, ChenZ Y. Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G[J]. Medical & Biological Engineering & Computing, 2024, 62(8): 2571-2583.
LiKewen, JiangHengjie, LiGuoqing, et al. Diffusion model based change detection method for remote sensing images[J]. Computer Engineering and Design, 2025, 46(2): 337-344.
[18]
WangH J, LiG H, WangZ K. Fast SVM classifier for large-scale classification problems[J]. Information Sciences, 2023, 642: 119136.
[19]
ZhouW J, DongS H, LeiJ S, et al. MTANet: Multitask-aware network with hierarchical multimodal fusion for RGB-T urban scene understanding[J]. IEEE Transactions on Intelligent Vehicles, 2022, 8(1): 48-58.
WuGuibing, DingBijun, ChengXiaodi, et al. Color difference evaluation method of RGB color space based on digital images of packaging materials[J]. Packaging Engineering, 2024, 45(15): 169-179.