2024 Vol.7 Oct.N05

• Title: Computer vision-based identification of machined surface defects in aluminum alloy parts
• Name: Jingtao Xie
• Company: School of machinery and intelligent manufacturing,Fujian Chuanzheng Communications College, fuzhou 350000,China
• Abstract:

   Influenced by the shooting environment, when identifying surface defects of machined aluminum alloy parts, the lack of effective defect compensation usually leads to poor identification accuracy. In this regard, a method based on computer vision is proposed to identify surface defects on machined aluminum alloy parts. The camera is calibrated by Zhang's calibration method, the camera parameters are obtained, the camera's internal and external parameters are combined, the great likelihood estimation is performed to obtain more accurate distortion parameters, and the image distortion is corrected. The light loss exhibited by different luminance materials in the experimental environment is counted, and the light conditions in the image are compensated as well as equalized by introducing luminance compensation bias. ResNet50 is used to extract multi-scale features and adaptively fuse shallow image texture features and deep image semantic information with a multilayer perceptron, and a classifier is introduced to identify and detect defects. Comparative experimental results show that the algorithm has a lower false detection rate and a more ideal detection accuracy when the proposed method is used for defect detection.

  
  

• Keyword: computer vision; aluminum alloy parts; defect detection; convolutional neural network;
• DOI: 10.12250/jpciams2024090120
• Citation form: Jingtao Xie.Computer vision-based identification of machined surface defects in aluminum alloy parts[J]. Computer Informatization and Mechanical System,2024,Vol.7,pp.91-95

[1] Xiao M , Yang B ,Wang S.He Y.Gao Y.Mo F.GRA-Net: Global receptive attention network for surface defect detection[J].Knowledge-based systems, 2023,. 280(Nov.25):1.1-1.11.

[2] Yang Z , Zhang M ,Chen, YingshuHu, NingGao, LingxiaoLiu, LibingPing, EnxuSong, Jung Il.Surface defect detection method for air rudder based on positive samples[J].Journal of Intelligent Manufacturing, 2024, 35(1):95-113.

[3] Longjian L I , Yang L , Hao Z ,et al. Road sub-surface defect detection based on gprMax forward simulation-sample generation and Swin Transformer- YOLOX[J].Frontiers of Structural and Civil Engineering, 2024, 18(3):334-349.

[4] Cai C , Zhou G , Lu C .Citrus surface defect identification based on PCS-2D-Otsu and CGWO-DT-SVM[J].Multimedia Tools and Applications, 2024, 83(15). 43649-43672.

[5] Li M , Zhou G , Lu C .Peach surface defect identification of complex background based on IDCNN and GWOABC-KM[J].Multimedia Tools and Applications, 2022, 81(12):16309-16334.

[6] Jian X , Xia Y , Chatzi E ,et al. Bridge influence surface identification using a deep multilayer perceptron and computer vision techniques:[J]. Structural Health Monitoring, 2024, 23(3):1606-1626.

[7] Ye Q , Dong Y , Zhang X Z D W S .Robustness defect detection: improving the performance of surface defect detection in interference environment[J]. Optics and Lasers in Engineering, 2024, 175(Apr.):1.1-1.11.

[8] Tang B , Chen L , Sun Z K .Review of surface defect detection of steel products based on machine vision[J].IET image processing, 2023, 17(2):303-322.

[9] Tu F M , Wei M H , Liu J L L L . An adaptive weighting multimodal fusion classification system for steel plate surface defect[J].Journal of Intelligent & amp; Fuzzy Systems: applications in Engineering and Technology, 2023, 45(2):3501-3512.

[10] Boudiaf A , Benlahmidi S , Dahane A ,et al. Development of Hybrid Models Based on AlexNet and Machine Learning Approaches for Strip Steel Surface Defect Classification[J].Journal of Failure Analysis and Prevention, 2024, 24(3):1376-1394.

[11] Kotnala R K , Saini S , Shah J ,et al.Significant role of defect-induced surface energy in water splitting to generate electricity by nickel ferrite hydroelectric cell[J].International Journal of Energy Research, 2022, 46(5):6421-6435.

[12] Zaghdoudi R , Bouguettaya A , Boudiaf A .Steel surface defect recognition using classifier combination[J]. Manufacturing Technology, 2024, 132(7-8):3489-3505. ork for computer vision-based health monitoring of a truss structure subjected to unknown excitations[J].Earthquake Engineering and Engineering Vibration, 2023, 22(1):1-17.

[14] Pei H , Zhang C , Ma L Y .Recognizing materials in cultural relic images using computer vision and attention mechanism[J].Expert Systems with Application, 2024, 239(Apr.):122399.1-122399.11.

[15] Wong H Y , Wong L W , Tsang C S .Superhydrophobic Surface Designing for Efficient Atmospheric Water Harvesting Aided by Intelligent Computer Vision[J ].ACS applied materials & interfaces, 2023, 15(21):25849-25859.