Progress and Prospect of Intelligent Detection Technology for Metal Component Forming Defects of High-end Equipment

doi:10.3981/j.issn.2097-0781.2025.01.011

Science and Technology Foresight ›› 2025, Vol. 4 ›› Issue (1): 108-117.DOI: 10.3981/j.issn.2097-0781.2025.01.011

• Review and Commentary • Previous Articles Next Articles

Progress and Prospect of Intelligent Detection Technology for Metal Component Forming Defects of High-end Equipment

ZHOU Jianxin(), JI Xiaoyuan, HOU Mingjun, DONG Hao, DUAN Haozhe, YIN Yajun, SHEN Xu, LI Wen

State Key Laboratory of Materials Processing and Die & Mould Technology, Huazhong University of Science and Technology, Wuhan 430074, China

Received:2024-12-23 Revised:2025-02-28 Online:2025-03-20 Published:2025-03-27

高端装备金属构件成形缺陷智能检测技术进展与展望

周建新(), 计效园, 侯明君, 董淏, 段浩哲, 殷亚军, 沈旭, 李文

华中科技大学材料成形与模具技术全国重点实验室，武汉 430074

作者简介:周建新，教授，博士研究生导师。国家重点研发计划项目首席科学家、中国铸造学会常务理事、中国铸造协会模具分会常务副理事长兼秘书长、湖北省机械工程学会理事/铸造专业委员会理事长、材料成形与模具技术全国重点实验室首席教授、华铸软件中心负责人。主要从事数字化智能化铸造技术的研发及应用。主持开发的“华铸CAE”、“华铸ERP”等华铸系列软件现已在国内外800多家单位应用。“庆祝中华人民共和国成立70周年”纪念章获得者，荣获“荆楚楷模”“武汉市最美科技工作者”“武汉楷模”称号，入选教育部“新世纪优秀人才支持计划”、国家重大人才工程。获国家科技进步奖二等奖2项（1项第2，1项第4）、省部级科技一等奖5项（均排名第1）；发表学术论文200余篇，以第一作者出版著作4部。电子信箱：zhoujianxin@hust.edu.cn。
基金资助:
国家自然科学基金(52275337);国家自然科学基金(52090042);国家重点研发计划(2020YFB1710100)

Abstract

Abstract:

Material forming, as a key metal processing technology, encompasses various forms such as casting, welding, forging, additive manufacturing, and powder metallurgy, and it is widely applied in important defence fields such as aerospace. Porosity, inclusions, and voids are the main internal defects, which seriously affect the performance and reliability of high-end equipment. In recent years, with the continuous development of software and hardware, defect detection technology has made significant progress. Based on a brief review of the current status of defect detection technology, this article analyzed the major technical breakthroughs and scientific advancements achieved by various detection methods such as radiography, ultrasound, and fluorescence, discussed the future development trends and research directions of intelligent detection for metal components, and provided policy recommendations from four dimensions: standard system construction, core technology breakthroughs, process flow reengineering, and system platform construction, with the aim of providing theoretical and technical support for high-reliability detection of metal components in high-end equipment.

Key words: metal component, defect, detection, radiography, ultrasound, fluorescence

摘要：

材料成形作为一种关键的金属加工工艺，涵盖了铸造、焊接、锻造、增材、粉末冶金等多种形式，广泛应用于航空航天等国防重要领域。气孔、夹杂物、孔隙等是其主要内部缺陷，严重影响高端装备的性能和可靠性。近年来，随着软硬件不断发展，缺陷检测技术也取得了显著进展。文章在简要梳理当前缺陷检测技术现状基础上，分析了射线、超声、荧光等各种检测方法取得的主要技术突破与科学进展，探讨了未来金属构件智能检测的发展趋势与研究方向，并从标准体系构建、核心技术攻关、工艺流程再造、系统平台建设4个维度给出政策建议，以期为高端装备金属构件高可靠检测提供理论与技术支撑。

关键词: 金属构件, 缺陷, 检测, 射线, 超声, 荧光

ZHOU Jianxin, JI Xiaoyuan, HOU Mingjun, DONG Hao, DUAN Haozhe, YIN Yajun, SHEN Xu, LI Wen. Progress and Prospect of Intelligent Detection Technology for Metal Component Forming Defects of High-end Equipment[J]. Science and Technology Foresight, 2025, 4(1): 108-117.

周建新, 计效园, 侯明君, 董淏, 段浩哲, 殷亚军, 沈旭, 李文. 高端装备金属构件成形缺陷智能检测技术进展与展望[J]. 前瞻科技, 2025, 4(1): 108-117.

Figures/Tables 9

Fig. 1 Detected main defects of typical titanium alloy components

Table 1 Different forming methods and common defects

成形方式	常见缺陷
铸造	气孔、缩孔、夹杂、冷隔、粘砂等
焊接	未焊透、咬边、飞溅物残留等
锻造	折叠、过热、氧化皮残留、凹坑、划痕等
增材制造	孔隙、未熔合、阶梯效应、球化效应等
粉末冶金	孔隙、夹杂、成分偏析、烧结不均匀等

Fig. 2 Key components of X-ray detect detection equipment

Fig. 3 Examples of ultrasonic defect detectors

Fig. 4 X-ray inspection equipment in China

Fig. 5 Existing internal defect localization and repair methods

Fig. 6 Automatic X-ray image rating system and its application

Fig. 7 Digital image processing flow for X-ray film

Fig. 8 CTS-PA322T phased array full-focus real-time 3D ultrasonic imaging system

References 29

[1]	李毅, 赵永庆, 曾卫东. 航空钛合金的应用及发展趋势[J]. 材料导报, 2020, 34(增刊1): 280-282.
	Li Y, Zhao Y Q, Zeng W D. Application and development of aerial titanium alloys[J]. Materials Reports, 2020, 34(Suppl 1): 280-282. (in Chinese)
[2]	柳建国, 赵刚, 王东生, 等. “十四五” 规划期间我国铸造行业发展浅析[J]. 铸造, 2023, 72(8): 947-955.
	Liu J G, Zhao G, Wang D S, et al. Analysis on development of China’s foundry industry in the“14th Five-Year Plan period”[J]. Foundry, 2023, 72(8): 947-955. (in Chinese)
[3]	李红, 闫维嘉, 张禹, 等. 先进航空材料焊接过程热裂纹研究进展[J]. 材料工程, 2022, 50(2): 50-61. DOI
	Li H, Yan W J, Zhang Y, et al. Research progress of hot crack in fusion welding of advanced aeronautical materials[J]. Journal of Materials Engineering, 2022, 50(2): 50-61. (in Chinese) DOI
[4]	赵明杰, 黄亮, 李昌民, 等. 300M钢的热变形行为及热锻成形工艺研究现状[J]. 精密成形工程, 2020, 12(6): 16-27.
	Zhao M J, Huang L, Li C M, et al. Research status of the hot deformation behaviors and hot forging process of 300M steel[J]. Journal of Netshape Forming Engineering, 2020, 12(6): 16-27. (in Chinese)
[5]	宋波, 张磊, 王晓波, 等. 面向航空航天的增材制造超材料的研究现状及发展趋势[J]. 航空制造技术, 2022, 65(14): 22-33.
	Song B, Zhang L, Wang X B, et al. Research status and development trend of additive manufacturing metamaterials toward aerospace[J]. Aeronautical Manufacturing Technology, 2022, 65(14): 22-33. (in Chinese)
[6]	陈玉勇, 叶园, 张宇, 等. 粉末冶金制备TiAl合金研究进展[J]. 稀有金属材料与工程, 2023, 52(11): 4002-4012.
	Chen Y Y, Ye Y, Zhang Y, et al. Research progress on TiAl alloy prepared by powder metallurgy[J]. Rare Metal Materials and Engineering, 2023, 52(11): 4002-4012. (in Chinese)
[7]	Shultzman A, Segal O, Kurman Y, et al. Enhanced imaging using inverse design of nanophotonic scintillators[J]. Advanced Optical Materials, 2023, 11(8): 2202318, doi: 10.1002/adom.202202318.
[8]	Zhao X Y, Liang J J, He Z X, et al. Blowhole detection based on bidirectional enhancement and omnidirectional analysis for X-ray inspection of castings[J]. Mathematical Problems in Engineering, 2019, 2019(1): 2468505, doi: 10.1155/2019/2468505.
[9]	Gonzalez R C, Woods R E, Masters B R. Digital image processing[M]. Hoboken: Prentice Hall, 2007.
[10]	Bishop C M. Pattern recognition and machine learning[M]. New York: Springer, 2006.
[11]	Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[12]	Mery D, Hahn D, Hitschfeld N. Simulation of defects in aluminium castings using CAD models of flaws and real X-ray images[J]. Insight-Non-Destructive Testing and Condition Monitoring, 2005, 47(10): 618-624.
[13]	马明辉. 基于分层模板的铸造枝状缩松仿真[D]. 广州: 华南理工大学, 2012.
	Ma M H. Simulation of dendritic shrinkage in casting based on layered template[D]. Guangzhou: South China University of Technology, 2012. (in Chinese)
[14]	周洲. 轮芯缺陷检测及缺陷样本生成技术[D]. 广州: 华南理工大学, 2019.
	Zhou Z. Technology of wheel core defect detection and defect sample generation[D]. Guangzhou: South China University of Technology, 2019. (in Chinese)
[15]	Strecker H. A local feature method for the detection of flaws in automated X-ray inspection of castings[J]. Signal Processing, 1983, 5(5): 423-431.
[16]	李高亮. 基于X射线图像的汽车轮毂缺陷自动检测与识别技术研究[D]. 太原: 中北大学, 2013.
	Li G L. Research on automatic detection and identification technology of automobile wheel hub defects based on X-ray images[D]. Taiyuan: North University of China, 2013. (in Chinese)
[17]	Cha Y J, Choi W, Büyüköztürk O. Deep learning-based crack damage detection using convolutional neural networks[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5): 361-378.
[18]	Yu H, Li X J, Song K C, et al. Adaptive depth and receptive field selection network for defect semantic segmentation on castings X-rays[J]. NDT & E International, 2020, 116: 102345, doi: 10.1016/j.ndteint.2020.102345.
[19]	Hernández S, Sáez D, Mery D. Neuro-fuzzy method for automated defect detection in aluminium castings[M]//Image Analysis and Recognition. Berlin, Heidelberg: Springer, 2004: 826-833.
[20]	Li W, Li K S, Huang Y, et al. A new trend peak algorithm with X-ray image for wheel hubs detection and recognition[M]// Computational Intelligence and Intelligent Systems. Singapore: Springer Singapore, 2016: 23-31.
[21]	刘浩. 基于X射线的铸件缺陷检测的深度学习方法研究及实现[D]. 太原: 太原科技大学, 2018.
	Liu H. Research and implementation of deep learning method for casting defect detection based on X-ray[D]. Taiyuan: Taiyuan University of Science and Technology, 2018. (in Chinese)
[22]	张辉, 张邹铨, 陈煜嵘, 等. 工业铸件缺陷无损检测技术的应用进展与展望[J]. 自动化学报, 2022, 48(4): 935-956.
	Zhang H, Zhang Z Q, Chen Y R, et al. Application advance and prospect of nondestructive testing technology for industrial casting defects[J]. Acta Automatica Sinica, 2022, 48(4): 935-956. (in Chinese)
[23]	Hou M J, Dong H, Ji X Y, et al. I-DCGAN and TOPSIS-IFP: A simulation generation model for radiographic flaw detection images in light alloy castings and an algorithm for quality evaluation of generated images[J]. China Foundry, 2024, 21(3): 239-247.
[24]	Ji X Y, Yan Q Y, Huang D, et al. Filtered selective search and evenly distributed convolutional neural networks for casting defects recognition[J]. Journal of Materials Processing Technology, 2021, 292: 117064, doi: 10.1016/j.jmatprotec.2021.117064.
[25]	Wu B, Zhou J X, Ji X Y, et al. An ameliorated teaching-learning-based optimization algorithm based study of image segmentation for multilevel thresholding using Kapur’s entropy and Otsu’s between class variance[J]. Information Sciences, 2020, 533: 72-107.
[26]	Jiang H Q, Yang D Y, Zhi Z L, et al. A normal weld recognition method for time-of-flight diffraction detection based on generative adversarial network[J]. Journal of Intelligent Manufacturing, 2024, 35(1): 217-233.
[27]	Zhi Z L, Jiang H Q, Yang D Y, et al. An end-to-end welding defect detection approach based on titanium alloy time-of-flight diffraction images[J]. Journal of Intelligent Manufacturing, 2023, 34(4): 1895-1909.
[28]	班瑞, 张日丰, 陶智勇, 等. 金属内部微小缺陷的多通道光纤干涉激光超声无损检测[J]. 中国激光, 2024, 51(14): 144-152.
	Ban R, Zhang R F, Tao Z Y, et al. Laser ultrasonic non-destructive testing of small defects in metals using multi-channel fiber interferometer[J]. Chinese Journal of Lasers, 2024, 51(14): 144-152. (in Chinese)
[29]	罗立群, 朱佳震, 陈均, 等. 稳压器波动管接管与底封头焊缝相控阵超声检测技术研究[J]. 核动力工程, 2024, 45(5): 232-242.
	Luo L Q, Zhu J Z, Chen J, et al. Research on phased array ultrasonic inspection technology for the pressurizer surge nozzle to vessel weld[J]. Nuclear Power Engineering, 2024, 45(5): 232-242. (in Chinese)

Progress and Prospect of Intelligent Detection Technology for Metal Component Forming Defects of High-end Equipment

高端装备金属构件成形缺陷智能检测技术进展与展望

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 29

Related Articles 5

Recommended Articles

Metrics

Access Statistics

Links

Contact Us

WeChat

[1]	YANG Zhan, CHEN Qinkai, WU Zhengnan, FAN Xinjian, SUN Lining. Current Status and Trends in Micro-nano Robots Science and Technology [J]. Science and Technology Foresight, 2024, 3(3): 32-44.
[2]	ZHENG Chong, DENG Qingyun, YE Mao, LI Fei. Research Status and Development Direction of Lunar Lava Tube Exploration [J]. Science and Technology Foresight, 2024, 3(1): 100-108.
[3]	CUI Dedong, FENG Tao, BAI Kun, YANG Ting, MA Long, SHANG Yi. Overview of Target Detection and Recognition Technology in Complex Background [J]. Science and Technology Foresight, 2022, 1(4): 69-80.
[4]	WU Yousheng, SIMA Can, ZHU Zhong, LI Long, NI Tian. Key Development Directions of Marine Science and Technology [J]. Science and Technology Foresight, 2022, 1(2): 20-35.
[5]	WANG Yongjun, ZHAO Chengxuan, LI Detian, WANG Yi, ZHANG Haiyan, LI Cunhui, ZHUANG Jianhong, ZHANG Huzhong. Progress and Development Proposals of Space Dust Detection [J]. Science and Technology Foresight, 2022, 1(1): 38-50.