HUANG Jingde
（Zhuhai College of Science and Technology, Zhuhai 519041， China）
Abstract： Glass fibrereinforced (GFR) structure is extensively used in radome, spoiler and some other equipment. In engineering practice, due to the influence of wear, aging, impact, chemical corrosion of surface structure and other factors, the internal structure of this kind of structure gradually evolves into a defect state and expands to form defects such as bubbles, scratches, shorts, cracks, cavitation erosion, stains and other defects. These defects have posed a serious threat to the quality and performance of GFR structure. From the propagation process of GFR structure defects, its duration is random and may be very short. Therefore, designing a scientific micro defect intelligent detection system for GFR structure to enhance the maintainability of GFR structure will not only help to reduce emergencies, but also have positive theoretical significance and application value to ensure safe production and operation. Firstly, the defect detection mechanism of GFR structure is discussed, and the defect detection principle and defect area identification method are analyzed. Secondly, the processing process of defect edge signal is discussed, a classifier based on MLP is established, and the algorithm of the classifier is designed. Finally, the effectiveness of this method is proved by realtime monitoring and defect diagnosis of a typical GFR structure. The experimental results show that this method improves the efficiency of defect detection and has high defect feature recognition accuracy, which provides a new idea for the online detection of GFR structure defects.
Key words： glass fibrereinforced (GFR) structure； multilayer perceptron (MLP)； machine vision； defect detection
References
［1］ZHANG L. Research ononline detection method of glass defects based on machine vision. Xi’an： Xi’an University of Technology, 2020.
［2］KNOPF G K, GUPTA M M. A multipurpose neural processor for machine vision systems. IEEE Transactions on Neural Networks, 1993, 4(5)： 762777.
［3］REN Z H, FANG F Z, YAN N, et al. State of the art in defect detection based on machine vision. International Journal of Precision Engineering and ManufacturingGreen Technology, 2021, 8(3)： 131.
［4］XUE Y. Research onclassification and recognition of glass defect based on machine vision. Hefei： Hefei University of Technology, 2018.
［5］MASCI J, MEIER U, CIRESAN D, et al. Steel defect classification with maxpooling convolutional neural networks//International Joint Conference on Neural Networks, Jun. 1015, 2012, Brisane, Australi. New York： IEEE, 2012： 1015.
［6］SERGIO R T, FELIPE A T, ALEXANDRA C G B, et al. Osteopathic manual therapy in heart failure patients： a randomized clinical trial. Journal of Bodywork & Movement Therapies, 2018, 22(2)： 293299.
［7］WANG Y, LIN S B, MIU X R. Application of machine vision in detection of glass defect based on lab view. Industrial Control Computer, 2011, 24(4)： 7577.
［8］DAI J Z, DAI S G. Glass defect detection based on lab view programming platform. Measurement & Control Technology, 2017, 36(7)： 912.
［9］ALEKSENDRIC D, BELLINI C, CARLONE P, et al. Neuralfuzzy optimization of thick composites curing process. Materials and Manufacturing Processes, 2019, 33(3)： 262273.
［10］SHARIFI S, TIVAY A, REZAEI S M, et al. Leakage fault detection in electrohydraulic servo systems using a nonlinear representation learning approach. ISA Transactions, 2018, 73： 154164.
［11］WANG X, HILL T L, NEILD S A, et al. Model updating strategy for structures with localised nonlinearities using frequency response measurements. Mechanical Systems and Signal Processing, 2018, 100： 940961.
［12］SPRECO A, ERIKSSON O, DAHLSTRM , et al. Influenza detection and prediction algorithms： comparative accuracy trial in stergtland county, Sweden. Epidemiology and Infection, 2017, 145(10)： 21662175.
［13］ELIAS G S. Detection and characterization of intermittent shorts and opens in ermanent magnet AC machines//The 7th International Conference on Reliability of Electrical Products & Electrical Contacts, Nov. 46, 2019, Suzhou, China. Beijing: CEI, 2019： 1317.
［14］LU N Y, JIANG G B, MENG X F, et al. Diagnosis, diagnostic ability analysis,and test point design for multiple faults based on multisignal modeling and blind source separation. IEEE Transactions on Systems, Man, and Cybernetics： Systems, 2020, 50(1)： 137148.
［15］ZHU T. Design of automatic fault repair system for variable speed generator bearing based on machine vision. Automation & Instrumentation, 2020, 31(12)： 153.
基于视觉图像分析的纤维增强玻璃结构缺陷特征识别方法
黄景德
（珠海科技学院， 广东 珠海 519041)
摘要:雷达罩、 扰流板等装备中广泛采用了纤维增强玻璃结构。 在工程实践中， 此类结构由于受到表面结构磨损、 老化、 冲击、 化学腐蚀等因素的影响， 其内部结构逐渐演变成缺陷状态， 扩展形成诸如气泡、 划痕、 缺胶、 裂纹、 空蚀、 污点等缺陷， 这些缺陷对设备质量性能已构成严重威胁。 从纤维增强玻璃结构缺陷的传播过程来看， 其持续时间随机， 且可能很短。 因此， 设计一套科学的纤维增强玻璃结构微缺陷智能检测系统， 增强纤维增强玻璃结构的维护性， 不仅有助于减少突发事件， 而且对确保安全生产运行具有积极的理论意义和应用价值。 首先， 讨论了纤维增强玻璃结构的缺陷检测机制， 分析了缺陷检测原理和缺陷区域的识别方法。 其次， 讨论了缺陷边缘信号的处理过程， 建立了基于MLP的分类器， 并设计了分类器的算法。 最后， 通过对典型纤维增强玻璃结构的实时监测和缺陷诊断， 证明了该方法的有效性。 实验结果表明， 该方法提高了缺陷检测的效率， 具有较高的缺陷特征识别精度， 为纤维增强玻璃结构缺陷的在线检测提供了新思路。
关键词:纤维增强玻璃结构； 多层感知机； 机器视觉； 缺陷检测
引用格式：HUANG Jingde． Defect feature recognition method of glass fibrereinforced structure based on visual image analysis． Journal of Measurement Science and Instrumentation， 2022， 13（1）： 6167. DOI： 10．3969／j．issn．16748042．2022．01．007
[full text view]
