多维注意力机制驱动的航天器柔性热控镀膜表面缺陷检测方法

doi:10.13385/j.cnki.vacuum.2025.05.07

摘要/Abstract

摘要： 柔性热控薄膜作为多层隔热组件包覆于航天器外表面,基于自身热物理特性实现对航天器表面热平衡的控制。在其磁控溅射制备过程中,工艺不稳定性、张力控制等问题常导致各种镀膜缺陷的出现,进而影响镀膜质量。传统磁控溅射镀膜缺陷需要停机检测,检测效率低、反应不及时。针对此问题,提出一种多维注意力机制驱动的图像检测深度学习算法,构建了基于监测数据-检测图像敏感特征-镀膜缺陷的关联映射模型,以实现缺陷的高效、高准确率智能辨识。经实验验证,模型对破裂、电火花、漏镀三种缺陷的识别精度达到96%以上,为实现航天器柔性热控镀膜在线检测奠定了坚实基础。

关键词: 热控薄膜, 磁控溅射, 多维注意力机制, 智能辨识

Abstract: Flexible thermal control coatings are applied to the outer surface of spacecraft to control the thermal balance of the spacecraft surface based on their own thermo-physical properties. During the magnetron sputtering process, process instability often leads to various defects in the coating, which in turn affects the coating quality. Traditional magnetron sputtering coating defect detection requires shutdown for inspection, which is inefficient and does not respond in a timely manner. This paper proposes a deep learning algorithm for image detection driven by a multi-dimensional attention mechanism, constructing a correlation mapping model between monitoring data, detection image sensitive features, and coating defects, to achieve efficient and high-accuracy intelligent identification. The experimental verification shows that the model recognition accuracy for cracks, electric sparks, and underplating defects is above 96%, laying a solid foundation for the online detection of flexible thermal control coatings on spacecrafts.

Key words: thermal control coating, magnetron sputtering, multi-dimensional attention mechanism, intelligent identification

中图分类号: TB43

倪俊, 郭腾, 李灿伦, 何恒扬, 李荣义. 多维注意力机制驱动的航天器柔性热控镀膜表面缺陷检测方法[J]. 真空, 2025, 62(5): 44-52.

NI Jun, GUO Teng, LI Canlun, HE Hengyang, LI Rongyi. Surface Defect Detection Method of Spacecraft Flexible Thermal Control Coating Driven by Multidimensional Attention Mechanism[J]. VACUUM, 2025, 62(5): 44-52.

参考文献

[1] 张东,张有玮,张家强,等. 低吸收高发射热控涂层及填料发展展望[J]. 新技术新工艺,2021,401(5):1-6.
[2] HOŁYŃSKA M, TIGHE A, SEMPRIMOSCHNIG C. Coatings and thin films for spacecraft thermos-optical and related functional applications[J]. Advanced Materials Interfaces, 2018, 5(11): 1701644.
[3] DUNN B D.Materials and processes: for spacecraft and high reliability applications[M]. Switzerland: Springer, 2016:667.
[4] WANG X J, LIU S H, ZHANG H, et al.Defects detection of lithium-ion battery electrode coatings based on background reconstruction and improved canny algorithm[J]. Coatings, 2024, 14(4): 392.
[5] ZHANG H, GAO B, TIAN G Y, et al.Metal defects sizing and detection under thick coating using microwave NDT[J]. NDT & E International, 2013, 60: 52-61.
[6] PATIL S S, SHALIGRAM A D.On-line defect detection of aluminum coating using fiber optic sensor[J]. Photonic Sensors, 2015, 5:72-78.
[7] WIN M, BUSHROA A R, HASSAN M A, et al.A contrast adjustment thresholding method for surface defect detection based on mesoscopy[J]. IEEE Transactions on Industrial Informatics, 2017, 11(3):642-649.
[8] LUO M T, ZHONG S C, HUANG Y, et al.Combined terahertz pulsed imaging and optical coherence tomography detection method for multiple defects in thermal barrier coatings[J]. Coatings, 2024, 14(4): 380.
[9] LIN E, WANG H D, DONG L H, et al.Surface crack detection of the abradable seal coating by laser bidirectional scanning thermography[J]. Infrared Physics & Technology, 2023, 128: 104498.
[10] LEE I G, YOON Y J, CHOI K S, et al.Design of an optical transparent absorber and defect diagnostics analysis based on near-field measurement[J]. Sensors, 2021, 21(9): 3076.
[11] HE D, KUSANO M, WATANABE M.Detecting the defects of warm-sprayed Ti-6Al-4V coating using Eddy current testing method[J]. NDT & E International, 2022, 125:102565.
[12] WANG H, HSIEH S J, ZHOU X, et al.Using active thermography to inspect pin-hole defects in anti-reflective coating with k-mean clustering[J]. Ndt & E International, 2015, 76: 66-72.
[13] TANG Q J, DAI J M, BU C W, et al.Experimental study on debonding defects detection in thermal barrier coating structure using infrared lock-in thermographic technique[J]. Applied Thermal Engineering, 2016, 107:463-468.
[14] ZHANG Z H, SHI T T, HUANG Y, et al.Defect detection method for self-lubricating sliding bearing coating using terahertz total variation image fusion[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 74: 4500115.
[15] XIA D H, SONG Y, SONG S Z, et al.Identifying defect levels in organic coatings with electrochemical noise (EN) measured in single cell (SC) mode[J]. Progress in Organic Coatings, 2019, 126: 53-61.
[16] 雷震霆,朱兴龙,孙进,等. 融合坐标注意力和自适应特征的YOLOv5陶瓷膜缺陷检测方法[J]. 电子测量技术,2023,46(7):133-137.
[17] TANG K, ZI B, XU F, et al.Coating defect detection method based on data augmentation and network optimization design[J]. IEEE Sensors Journal, 2023, 23(13): 14522-14533.
[18] TAO X R, GAO H J, WU Q, et al.Detection of Defects in Adhesive Coating Based on Machine Vision[J]. IEEE Sensors Journal, 2023, 24(4): 5172-5185.
[19] XIAO D, XIE F T, GAO Y, et al.A detection method of spangle defects on zinc-coated steel surfaces based on improved YOLO-v5[J]. The International Journal of Advanced Manufacturing Technology, 2023, 128(1-2): 937-951.
[20] YU Y, HOSHYAR A N, SAMALI B, et al.Corrosion and coating defect assessment of coal handling and preparation plants (CHPP) using an ensemble of deep convolutional neural networks and decision-level data fusion[J]. Neural Computing and Applications, 2023, 35(25): 18697-18718.
[21] CHANG F, LIU M, DONG M Y, et al.A mobile vision inspection system for tiny defect detection on smooth car-body surfaces based on deep ensemble learning[J]. Measurement Science and Technology, 2019, 30(12): 125905.
[22] ZHOU W J, WANG Z J, WANG L W, et al.Wind turbine actual defects detection based on visible and infrared image fusion[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-8.
[23] ZUBAYER M H, ZHANG C Q, LIU W, et al.Automatic defect detection of jet engine turbine and compressor blade surface coatings using a deep learning-based algorithm[J]. Coatings, 2024, 14(4):501.
[24] TAO X R, GAO H J, YANG K, et al.Expanding the defect image dataset of composite material coating with enhanced image-to-image translation[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108590.
[25] YAN A, RUPNOWSKI P, GUBA N, et al.Towards deep computer vision for in-line defect detection in polymer electrolyte membrane fuel cell materials[J]. International Journal of Hydrogen Energy, 2023, 48(50): 18978-18995.
[26] MARTÍNEZ S S, VÁZQUEZ C O, GARCÍA J G, et al. Quality inspection of machined metal parts using an image fusion technique[J]. Measurement, 2017, 111: 374-383.
[27] LEE Y, YUN J, LEE S, et al.Image data-centric visual feature selection on roll-to-roll slot-die coating systems for edge wave coating defect detection[J]. Polymers, 2024, 16(8): 1156.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed