基于生成式数据增强与Faster-RCNN改进的发动机打刻面缺陷检测

doi:10.11896/jsjkx.241200025

摘要/Abstract

摘要： 汽车发动机的打刻面具有承载发动机信息、丢失查找以及防止私自拆改发动机等作用,打刻面的质量将直接决定车辆是否能正常上牌行驶。但是在汽车制造领域,现阶段对打刻面的缺陷检测主要采用人工目视检测的方法,存在漏检的风险。虽然业界已有一些针对表面缺陷检测的研究,但它们无法完全适应发动机打刻面缺陷检测的特点,容易出现错检、漏检情况。为了革新发动机打刻面缺陷检测的方式,提出了一种基于生成式数据增强与Faster-RCNN改进的缺陷检测方法。首先,针对发动机打刻面缺陷样本少的小样本问题,提出了一种基于stable diffusion的打刻面缺陷图片生成方法。该方法通过两个掩膜图分别控制缺陷生成的位置以及恢复图像的字符特征,从而完成打刻面缺陷样本图像的生成,实现数据集的增强。其次,提出了一种同步双向融合特征金字塔网络替换原模型所使用的特征金字塔网络,增强多尺度特征融合能力,解决打刻面缺陷目标尺度范围广的问题。实验结果表明,所提出的方法在检测发动机打刻面缺陷时,均值平均精度(mAP)达到了97.52%,相比原始的Faster-RCNN模型提高了34.73%,可以满足发动机打刻面缺陷的检测需求。

关键词: 缺陷检测, 图像生成, 数据增强, Faster-RCNN, 多尺度特征融合

Abstract: The engraved surface of automotive engine has the functions of carrying engine information,searching for lost,and preventing unauthorized disassembly and modification of the engine.The quality of the engraved surface will directly determine whether the vehicle can be registered and driven normally.However,in the field of automobile manufacturing,manual visual inspection is mainly used for defect detection of engraved surfaces at present,which poses a risk of missed detection.Although there have been some studies on surface defect detection in the industry,they cannot fully adapt to the defect detection of engine engraved surface,which can easily lead to false positives and false negatives.In order to innovate the method of detecting engine engraved surface defects,this paper proposes a defect detection method based on generative data augmentation and improved Faster-RCNN.Firstly,a method for generating engraved surface defect images based on stable diffusion model is proposed to address the problem of limited samples of engine engraved surface defects.This method controls the location of defect generation and restores the character features of the image through a dual mask image,thereby completing the generation of engraved surface defect images and achieving data augmentation of the dataset.Secondly,a synchronous bidirectional fusion feature pyramid network(SBFFPN) is proposed to replace the feature pyramid network(FPN) used in the original algorithm,enhancing the multi-scale feature fusion capability and solving the problem of wide target scale range of engraved surface defects.The experimental results show that the proposed method achieves mAP of 97.52% in detecting engine engraved surface defects,which is 34.73% higher than the original Faster RCNN model and can meet the detection requirements of engine engraved surface defects.

Key words: Defect detection, Image generation, Data augmentation, Faster-RCNN, Multi-scale feature fusion

中图分类号:

TP391

谭建辉, 张峰. 基于生成式数据增强与Faster-RCNN改进的发动机打刻面缺陷检测[J]. 计算机科学, 2025, 52(11A): 241200025-7. https://doi.org/10.11896/jsjkx.241200025

TAN Jianhui, ZHANG Feng. Defect Detection of Engine Engraved Surface Based on Generative Data Augmentation andImproved Faster-RCNN[J]. Computer Science, 2025, 52(11A): 241200025-7. https://doi.org/10.11896/jsjkx.241200025

参考文献

[1]YUN J P,CHOI S H,KIM J W,et al.Automatic detection of cracks in raw steel block using Gabor filter optimized by univariate dynamic encoding algorithm for searches(uDEAS)[J].NDT &E International,2009,42(5):389-397.
[2]LIU Y,XU K,XU J.An Improved MB-LBP Defect Recognition Approach for the Surface of Steel Plates[J].Applied Sciences,2019,9(20):4222.
[3]WANG J,FU P,GAO R X.Machine vision intelligence for pro-duct defect inspection based on deep learning and Hough transform[J].Journal of Manufacturing Systems,2019,51:52-60.
[4]WEI L,DRAGOMIR A,DUMITRU E,et al.SSD:Single Shot MultiBox Detector[J].arXiv:1512.02325,2015.
[5]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]//2016 IEEE/Conference on Computer Vision and Pattern Recognition(CVPR).2016:779-788.
[6]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,39(6):1137-1149.
[7]CHEN J W,LIU Z G,WANG H R,et al.Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network[J].IEEE Transactions on Instrumentation & Measurement,2017,67(2):257-269.
[8]LIU X Y,GAO J.Surface Defect Detection Method of Hot Rol-ling Strip Based on Improved SSD Model[C]//International Conference on Database Systems for Advanced Applications.2021.
[9]LI J,SU Z,GENG J,et al.Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network Science Direct[J].IFAC-Papers OnLine,2018,51(21):76-81.
[10]WANG K,TENG Z,ZOU T.Metal Defect Detection Based on Yolov5[J].Journal of Physics:Conference Series,2022,2218(1):012050.
[11]DING R,DAI L,LI G,et al.TDD-Net:A Tiny Defect Detection Network for Printed Circuit Boards[J].CAAI Transactions on Intelligence Technology,2019,4(2):7.
[12]LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature Pyramid Networks for Object Detection[C]//2017 IEEE/Conference on Computer Vision and Pattern Recognition(CVPR).2017:936-944.
[13]YIN T P,YANG J.Detection of Steel Surface Defect Based onFaster R-CNN and FPN[C]//ICCAI’21.2021.
[14]ROMBACH R,BLATTMANN A,LORENZ D,et al.High-Re-solution Image Synthesis with Latent Diffusion Models[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2022:10674-10685.
[15]LIU S,QI L,QIN H,et al.Path Aggregation Network for Instance Segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.2018:8759-8768.
[16]TAN M,PANG R,LE Q V.EfficientDet:Scalable and Efficient Object Detection[C]//2020 IEEE/CVF Conference on ComputerVision and Pattern Recognition(CVPR).2020:10778-10787.
[17]QIAO S,CHEN L C,YUILLE A.DetectoRS:Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution[C]//2021 IEEE/Computer Vision and Pattern Recognition.2021.
[18]WANG J,CHEN K,XU R,et al.CARAFE:Content-Aware ReAssembly of Features[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV).2019:3007-3016.
[19]PANG J,CHEN K,SHI J,et al.Libra R-CNN:Towards Ba-lanced Learning for Object Detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2019:821-830.
[20]ZHU M J,HAN K,YU C B,et al.Dynamic Feature PyramidNetworks for Object Detection[C]//Fifteenth International Conference on Signal Processing Systems(ICSPS 2023).2024:504-511.
[21]CHEN K,CAO Y,LOY C C,et al.Feature Pyramid Grids[J].arXiv:2004.03580,2020.
[22]REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[J].arXiv:1804.02767,2018.
[23]GE Z,LIU S,WANG F,et al.YOLOX:Exceeding YOLO Series in 2021[J].arXiv:2107.08430,2021.
[24]WANG A,CHEN H,LIU L,et al.YOLOv10:Real-Time End-to-End Object Detection[C]//NIPS’24.2025:107984-108011.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed