An intelligent magnetic particle testing method for forgings based on the improved EfficientNet

被引：0
|
作者：
Wang C. [1 ,2 ]
Tang Y. [1 ]
Zhang X. [1 ]
Liu C. [1 ]
Li D. [3 ]
机构：
[1] College of Mechanical Engineering, Hubei University of Automotive Technology, Shiyan
[2] Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, Shanghai University, Shanghai
[3] Shiyan Branch of Hubei Special Equipment Inspection and Testing Institute, Shiyan
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2021年 / 42卷 / 09期
关键词：
Cylinder head; EfficientNet-F; Feature pyramid network; Flange; Magnetic particle testing;
D O I：
10.19650/j.cnki.cjsi.J2107796
中图分类号：
学科分类号：
摘要：
Aiming at the problems of low efficiency and low detection accuracy of parts defects in forging manufacturers, an improved EfficientNet model (EfficientNet-F) is proposed to detect the fluorescent magnetic particle flaw detection images of two kinds of forgings. A deep learning model with EfficientNet as the backbone feature extraction network is formulated, and the feature pyramid network is introduced as the feature fusion layer to improve the multi-scale feature fusion ability of the model. Complete intersection over union and attention mechanism are utilized to improve the robustness and detection efficiency of the model. Meanwhile, the fluorescent magnetic particle flaw detection image acquisition platform and the defective sample data set are both established. Experimental results show that the mean average precision precision of the optimal model of EfficientNet-F on the test set reaches 95.03%. The F1 score is 0.96 and the floating point operations is 1.86 B. Compared with other deep learning models, the proposed method improvec the detection accuracy and efficiency. It can meet the needs of relevant production enterprises. © 2021, Science Press. All right reserved.
引用
收藏
页码：89 / 96
页数：7
相关论文
共 22 条
  • [1] ZHANG F, GUO SH SH, CHENG S B., Realization of detection system based on eddy for surface crack of steel material, Journal of Test and Measurement Technology, 20, 5, pp. 467-470, (2006)
  • [2] LIANG H B, ZHU AN Q, ZHAO L., The newly research and application of ultrasonic testing technique, Nondestructive Testing, 30, 3, pp. 45-48, (2008)
  • [3] PENG D., Research on crack automatic detection for fluorescent magnetic image, (2017)
  • [4] SU H, ZHANG J B, ZHANG B H, Et al., Review of research on the inspection of surface defect based on visual perception, Computer Integrated Manufacturing Systems, pp. 1-31
  • [5] ZHOU F Y, JIN L P, DONG J., Review of convolutional neural network, Chinese Journal of Computers, 40, 6, pp. 1229-1251, (2017)
  • [6] XIANG K, LI S S, LUAN M H, Et al., Aluminum product surface defect detection method based on improved faster RCNN, Chinese Journal of Scientific Instrument, 42, 1, pp. 191-198, (2021)
  • [7] XIANG W, SHI J F, LIU G H, Et al., Application of improved alexnet model in fluorescent magnetic particle testing, Manufacturing Automation, 42, 7, pp. 40-45, (2020)
  • [8] CAI B, SHEN K, FU J L, Et al., Research on defect detection of X-ray DR images of casting based on mask R-CNN, Chinese Journal of Scientific Instrument, 41, 3, pp. 61-69, (2020)
  • [9] HAN H D, XU Y R, SUN B, Et al., Using active thermography for defect detection of aerospace electronic solder joint based on the improved Tiny-YOLOv3 network, Chinese Journal of Scientific Instrument, 41, 11, pp. 42-49, (2020)
  • [10] GAO SH Q., Research on fluorescent image processing technology of magnetic particle flaw detection, (2011)
123