高级检索

基于CCBFE-RCNN模型的焊缝X射线图像缺陷识别算法

戴铮, 刘骁佳, 潘泉

戴铮, 刘骁佳, 潘泉. 基于CCBFE-RCNN模型的焊缝X射线图像缺陷识别算法[J]. 焊接学报, 2025, 46(1): 24-33. DOI: 10.12073/j.hjxb.20231104001
引用本文: 戴铮, 刘骁佳, 潘泉. 基于CCBFE-RCNN模型的焊缝X射线图像缺陷识别算法[J]. 焊接学报, 2025, 46(1): 24-33. DOI: 10.12073/j.hjxb.20231104001
DAI Zheng, LIU Xiaojia, PAN Quan. Defect identification algorithm for weld X-ray imagesbased on the CCBFE-RCNN model[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2025, 46(1): 24-33. DOI: 10.12073/j.hjxb.20231104001
Citation: DAI Zheng, LIU Xiaojia, PAN Quan. Defect identification algorithm for weld X-ray imagesbased on the CCBFE-RCNN model[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2025, 46(1): 24-33. DOI: 10.12073/j.hjxb.20231104001

基于CCBFE-RCNN模型的焊缝X射线图像缺陷识别算法

详细信息
    作者简介:

    戴铮,博士;主要研究方向为无损检测、深度学习和图像处理; Email: zdai_800@163.com

    通讯作者:

    潘泉,教授,博士研究生导师;Email: panquan2023@163.com

  • 中图分类号: TG 409

Defect identification algorithm for weld X-ray imagesbased on the CCBFE-RCNN model

  • 摘要:

    针对X射线图像人工评定过程中存在劳动强度大、检测效率低等问题,提出一种基于Cascade-RCNN网络改进的多尺度目标检测网络CCBFE-RCNN模型,采用合并卷积层结构和FPN特征金字塔网络提升模型特征提取的尺度范围,增强了模型对于多尺度特征的提取能力;使用BFE特征批量消除网络,随机消除特征图区域,避免多次训练过程中的过拟合问题并强化了特征区域表达,同时对损失函数进行改进,对模型没有准确识别出含缺陷图像加大惩罚. 通过构建并扩充熔焊焊缝X射线图像数据集,对模型进行测试. 结果表明,CCBFE-RCNN缺陷检测模型全类别召回率均值、全类别精确率均值为93.09%和91.92%,与Cascade-RCNN网络模型相比平均召回率提升5.16%,平均精确率提升5.27%. 并使用工业缺陷检测数据集对CCBFE-RCNN模型进行测试,验证了模型的泛化能力,可为焊缝缺陷智能化识别提供算法支撑.

    Abstract:

    In view of the problems of high labor intensity and low detection efficiency in the manual evaluation process of X-ray images, a multi-scale object detection network CCBFE-RCNN model based on the improved Cascade-RCNN network is proposed. The combined convolutional layer structure and FPN feature pyramid network are used to enhance the scale range of model feature extraction, and the model's ability to extract multi-scale features is enhanced; Use BFE features to batch eliminate networks, randomly eliminate feature map regions, avoid overfitting problems during multiple training processes, and enhance feature region expression. At the same time, improve the loss function to increase penalties for models that do not accurately identify images containing defects. The model was tested by constructing and expanding a dataset of X-ray images of fusion welds The results show that the CCBFE-RCNN defect detection model has an average recall rate of 93.09% and an average precision rate of 91.92% across all categories, which is 5.16% higher than the average recall rate and 5.27% higher than the average precision rate of the Cascade-RCNN network model. The CCBFE-RCNN model is tested using an industrial defect detection dataset to verify its generalization ability, which can provide algorithm support for intelligent recognition of weld defects.

  • 随着电子元器件封装密度的增加,陶瓷球栅阵列(CBGA)和陶瓷柱栅阵列(CCGA)因其高密度的面排布引脚形式,在航空航天等高可靠性领域产品中得到了广泛应用[1-2]. CBGA和CCGA封装器件分别通过陶瓷管壳上的焊球和焊柱实现与PCB基板的组装互连,由于氧化铝陶瓷管壳(热膨胀系数为6.5 × 10−6/℃)和PCB基板(热膨胀系数为18 × 10−6 ~ 21 × 10−6/℃)的热膨胀系数差了近3倍,这种差异会在温度变化过程中产生剪切应变而导致裂纹萌生,进而引发焊点失效,因此温度循环成为了封装器件可靠性评估的关键手段. CCGA封装是在CBGA封装的基础上,用柱栅阵列代替了球栅阵列,增加互连引脚的距离,大大缓解了热膨胀系数不匹配带来的焊点失效问题,提高了焊点的可靠性,成为大尺寸产品封装的更优选择[3-5].

    在温度循环过程中,焊点的界面显微组织会发生变化,包括金属间化合物(IMC)的成分及厚度等[6-8],界面的显微组织会影响焊点的可靠性,焊点的抗剪强度是反映其可靠性最直观的方式,因此分析温度循环过程中焊点的显微组织与抗剪强度的演变关系对揭示CCGA封装焊点的失效机理及建立可靠性评估依据具有重要的参考价值.

    文中以CCGA484封装器件为研究对象,分析温度循环过程中焊点的界面显微组织演变与抗剪强度的对应关系,研究温度循环过程中焊点的失效机理,为CCGA封装的发展及应用提供理论指导.

    试验中选用高温共烧氧化铝陶瓷外壳,型号为CLGA484,镀层为Ni/Au,焊盘直径为ϕ0.8 mm ± 0.05 mm,焊盘间距为1.27 mm,板级封装用PCB板上的焊盘直径为ϕ0.8 mm ± 0.05 mm,焊柱采用ϕ0.51 mm × 2.21 mm的Pb90Sn10普通高铅焊柱,植柱和组装到PCB板上采用的锡膏均采用Sn63Pb37.

    试验样品制备过程为:丝网印刷锡膏→植柱→真空回流焊接→清洗→PCB板喷印锡膏→CCGA器件与PCB焊盘喷印锡膏光学对位→真空回流焊接,完成板级封装后的试验样品如图1所示,将组装到PCB板的试样与未组装的CCGA器件同时进行温度循环试验,前者用于观察不同温度循环次数下焊柱的外观形貌,后者用于焊点的金相分析和剪切力测试.

    图  1  CCGA板级封装试样
    Figure  1.  Specimen of CCGA board-level packages

    对CCGA484试验样品进行温度循环试验,试验条件按照美军标MIL-STD-883. 温度循环曲线如图2所示,温度范围为−65 ~ 150 ℃,循环周期为50 min,高低温保温时间均为15 min,升降温速率相同,试验过程中,每隔100次温度循环取出进行形貌观察、剪切力测试和金相分析,共进行500次温度循环.

    图  2  温度循环曲线
    Figure  2.  Parameter of thermal cycling of CCGA solder joints

    选用抗剪强度作为CCGA焊点的可靠性评估依据,试验设备采用专门的微焊点强度测试仪(DAGE4800),剪切速度均为0.4 mm/s,由于CCGA484器件的焊柱间距较小,试验过程中需要铲去周围的焊柱,保证剪切工具在行进时不会接触其它材料.

    由于陶瓷管壳和PCB板的热膨胀系数差别较大,这种热失配会在温度变化过程中产生剪切应变,宏观表现为焊柱发生塑性变形.

    温度循环过程中焊柱形貌如图3所示. 从图中可以看出,温度循环次数达到400次时,焊柱在反复热冲击作用下开始发生明显的塑性变形,且表面变得更加粗糙,焊点位置伴随有轻微的颈缩现象,500次后焊柱的扭曲程度进一步加剧,但肉眼还未观察到焊点开裂现象.

    图  3  不同温度循环次数下CCGA封装器件的宏观形貌
    Figure  3.  Evolution of solder column morphology at different thermal cycling times. (a) 100 times; (b) 300 times; (c) 400 times; (d) 500 times

    由于焊柱在长时间的高温、恒压力作用下,即使应力小于屈服强度也会慢慢发生蠕变变形[9]. 在温度循环的升温及高温保温阶段,陶瓷的热膨胀系数大于PCB基板,焊柱发生倾斜,在温度循环的降温及低温保温阶段,焊柱恢复至初始状态后向相反方向偏移,在反复的升温降温过程中,焊柱蠕变变形逐渐累积,达到宏观可见的扭曲状态,而焊点钎料的强度要略大于焊柱,因此在焊点处会有颈缩现象产生.

    在焊点形成过程中,钎料与焊盘金属在短时间的高温作用下扩散生成硬脆的IMC层,实现焊柱与基板之间的电气和机械连接,但是在长时间的温度循环过程中,扩散作用导致IMC层厚度逐渐增加,其成分也会发生相应的变化,由于IMC的热膨胀系数与钎料相差较大,因此过厚的IMC会对焊点的可靠性产生不利的影响.

    不同温度循环次数下的CCGA焊点界面显微组织如图4所示,在温度循环前,高铅焊柱与Ni焊盘界面观察不到明显的IMC层,因为Ni相对稳定,其界面反应层与铜相比是相当薄的,所以观察不到,随着循环次数增加,界面出现不同颜色对比度的中间层,且厚度逐渐增加,根据Ni-Sn二元相图可知,Sn-Pb钎料与Ni焊盘扩散反应生成的界面IMC从Ni侧依次包括Ni3Sn,Ni3Sn2和Ni3Sn4,具体的化合物成分取决于Sn与Ni的相对浓度.

    图  4  CCGA封装器件焊点显微组织
    Figure  4.  Microstructure of CCGA solder joints at different thermal cycling times. (a) original; (b) 100 times; (c) 200 times; (d) 300 times

    采用EDS分析界面IMC成分,不同温度循环次数下测试IMC成分的位置如图5 ~ 图7所示,对应不同位置的成分如表1所示. 从图中可以看出,100次温度循环时,界面点1主要为偏析的富锡相,点2处Ni与Sn的原子比接近3∶4,结合Ni-Sn二元相图可知,应为Ni3Sn4化合物,与已有的研究一致[8];在200次温度循环后,界面点1处仍为Ni3Sn4相,靠近Ni焊盘侧的点2处Ni与Sn的原子比接近3∶2,推测为Ni3Sn2相;500次温度循环后,在Ni与Ni3Sn2相之间的点2处,Ni与Sn的原子比接近3∶1,应为Ni3Sn相,因此推测随着温度循环次数增加,从焊柱到Ni焊盘之间依次生成的IMC为富锡相→Ni3Sn4→Ni3Sn2→Ni3Sn. 分析IMC形成过程,认为在温度循环前,富锡相与Ni通过元素相互扩散,反应生成极少量Ni3Sn4化合物层,Ni3Sn4化合物层的生成阻挡了Sn与Ni的扩散反应,Ni与Ni3Sn4化合物层中微量的Sn继续发生扩散反应,生成Ni含量更高的Ni3Sn2化合物相,之后,Ni3Sn2化合物层进一步阻挡Ni3Sn4化合物层中Sn与Ni的扩散反应,生成Ni含量更高的Ni3Sn化合物相. 统计不同温度循环次数下界面IMC厚度,如图8所示,两者基本呈指数为1/2的幂函数增长关系,符合扩散控制机制.

    图  5  温度循环100次焊点界面IMC成分
    Figure  5.  IMC component of CCGA solder joints at thermal cycling of 100 times
    图  7  温度循环500次焊点界面IMC成分
    Figure  7.  IMC component of CCGA solder joints at thermal cycling of 500 times
    图  6  温度循环200次焊点界面IMC成分
    Figure  6.  IMC component of CCGA solder joints at thermal cycling of 200 times

    界面IMC层存在离子键或共价键,所以往往具有硬脆特性,与基板和焊柱的线膨胀系数差别较大,随着温度循环次数增加,硬脆的IMC层厚度会逐渐增加,因此焊点界面处会产生较大的应力集中,在反复热应力作用下会萌生不同方向的细微裂纹,如图7所示,推测随着温度循环次数继续增加,应力集中导致微裂纹沿着剪切应变方向逐渐扩展,直到覆盖整个焊点,导致基板与焊柱之间发生断裂失效.

    表  1  不同温度循环次数下焊点界面的成分分析
    Table  1.  Component of CCGA solder joints at different thermal cycling times
    循环次数界面点质量分数w(%)原子分数a(%)
    PbSnNiPbSnNi
    100点113.4376.3910.187.3572.9919.66
    点24.9769.3725.662.355.941.8
    200点1964.8326.174.252.7543.05
    点24.9151.9943.11.9335.6362.44
    500点18.7745.4445.793.5131.7764.72
    点28.2428.1663.62.9217.4479.64
    下载: 导出CSV 
    | 显示表格
    图  8  温度循环次数与界面IMC厚度的关系
    Figure  8.  Variations of IMC thickness of CCGA solder joint with different thermal cycling times

    焊点的力学性能是评估其可靠性的最直观方法之一,采用DAGE4800微焊点强度测试仪测试不同循环次数下焊点的抗剪强度,如图9所示. 随着温度循环次数的增加,CCGA封装焊点的抗剪强度呈现下降趋势,到500次温度循环结束,抗剪强度相对下降了15.6%,且下降的速率逐渐增大. 结合上文界面显微组织分析可知,长时间高温会促进界面元素相互扩散,依次生成Ni3Sn4,Ni3Sn2和Ni3Sn多种IMC化合物层,且IMC层厚度逐渐增加,这些化合物与Sn,Pb的晶格常数和晶格结构存在较大差异,具有较高的熔点,呈现硬脆特性,因此在反复塑性变形过程中会产生应力集中,容易萌生裂纹而导致焊点失效,所以焊点的力学性能随着IMC厚度增加而逐渐下降,与已有的研究结果一致[10]. 对抗剪强度Rτ与温度循环次数n之间的关系做曲线拟合,得到下式,即

    图  9  不同循环次数下焊点剪切力变化
    Figure  9.  Variations of shear strength of CCGA solder joints with different thermal cycling times
    $${R_\tau } = 682.25 - 0.06\;n - 2.77 \times {10^{ - 4}}{n^2}$$ (1)

    根据技术指标要求,焊柱的最小剪切力为5.6 N,由式(1)推算可得,当温度循环次数大于550次时,焊点的抗剪强度将不满足要求.

    (1) 温度循环超过400次时,CCGA器件焊柱开始发生明显的塑性变形.

    (2) CCGA封装器件的焊点随着温度循环次数增加,从Ni焊盘侧依次生成的IMC层成分为Ni3Sn→Ni3Sn2→Ni3Sn4,且IMC层厚度逐渐增加.

    (3) CCGA封装器件焊点的抗剪强度随着温度循环次数增加呈下降趋势,且下降的速率逐渐增大,到500次温度循环结束,抗剪强度相对下降了15.6%,这是由于硬脆的IMC层厚度增加,在变形过程中导致应力集中而引发焊点失效.

  • 图  1   Faster-RCNN网络

    Figure  1.   Faster-RCNN network

    图  2   级联网络

    Figure  2.   Cascade-RCNN network

    图  3   CCBFE-RCNN网络

    Figure  3.   CCBFE-RCNN network

    图  4   合并卷积层

    Figure  4.   Concatnate convolutional layer

    图  5   FPN网络

    Figure  5.   FPN network

    图  6   BFE模块

    Figure  6.   Batch feature erasing module

    图  7   数据集样本

    Figure  7.   Dataset samples. (a) porosity; (b) slag inclusion; (c) lack of penetration; (d) no defects

    图  8   损失值变化

    Figure  8.   Loss value

    图  9   不同网络模型识别结果

    Figure  9.   Identification results of different network models

    表  1   Resnet101网络

    Table  1   Resnet101 network

    卷积层Resnet101
    conv1conv,7 × 7,64,stride 2
    max pool,3 × 3, stride 2
    conv2$ \left[ {\begin{array}{*{20}{l}} {{\text{conv}},1 \times 1,64} \\ {{\text{conv}},3 \times 3,64} \\ {{\text{conv}},1 \times 1,256} \end{array}} \right] \times 3 $
    conv3$ \left[ {\begin{array}{*{20}{l}} {{\text{conv}},1 \times 1,128} \\ {{\text{conv}},3 \times 3,128} \\ {{\text{conv}},1 \times 1,512} \end{array}} \right] \times 4 $
    conv4$ \left[ {\begin{array}{*{20}{l}} {{\text{conv}},1 \times 1,256} \\ {{\text{conv}},3 \times 3,256} \\ {{\text{conv}},1 \times 1,1024} \end{array}} \right] \times 23 $
    conv5$ \left[ {\begin{array}{*{20}{l}} {{\text{conv}},1 \times 1,512} \\ {{\text{conv}},3 \times 3,512} \\ {{\text{conv}},1 \times 1,2048} \end{array}} \right] \times 3 $
    下载: 导出CSV

    表  2   指标计算公式

    Table  2   Calculation formula

    评价指标公式
    召回率R$ \dfrac{{TP}}{{TP + FN}} $
    精确率P$ \dfrac{{TP}}{{TP + FP}} $
    全类别召回率均值RmAR@0.5$\dfrac{ {\displaystyle\sum\limits_{j = 1}^c {\sum\limits_{i = 1}^x {R_i} } } }{ {cx} }$
    全类别精确率均值PmAP@0.5$\dfrac{ {\displaystyle\sum\limits_{j = 1}^c {\displaystyle\sum\limits_{i = 1}^x {P_i} } } }{ {cx} }$
    下载: 导出CSV

    表  3   不同模型测试结果

    Table  3   Results of different models

    模型夹渣未焊透气孔全类别召回率
    均值
    RmAR@0.5(%)
    全类别精确率
    均值
    PmAP@0.5(%)
    频率
    f/(帧·s−1)
    召回率R(%)精确率P(%)召回率R(%)精确率P(%)召回率R(%)精确率P(%)
    YOLOV5-Tiny90.2389.6083.6888.7189.6586.3287.8588.2161
    SSD85.9886.3380.2485.1385.0786.6883.7686.0556
    Cascade-RCNN89.2087.1185.2687.9289.3384.9287.9386.6527
    SRYOLOV388.2786.9984.4787.8288.6786.8187.1487.2151
    TLMDDNet92.1390.4588.1190.1892.6790.7390.9790.4519
    Swin-Cascade-RCNN93.1588.4286.7988.4890.2688.9890.0788.9929
    CCBFE-RCNN93.6990.6390.4093.0195.2092.1393.0991.9222
    下载: 导出CSV

    表  4   不同数据集测试结果

    Table  4   Test results for different datasets

    数据集全类别召回率均值
    RmAR@0.5(%)
    全类别精确率均值
    PmAP@0.5(%)
    DAGM92.5691.84
    NEU95.6893.58
    AITEX89.3487.59
    下载: 导出CSV
  • [1]

    Li Y W. Research progress of aluminum alloy welding technology[J]. The International Journal of Advanced Manufacturing Technology, 2020, 109(1): 1207 − 1218.

    [2]

    Chen S B. On intelligentized welding manufacturing. In: Robotic welding[C]//Intelligence and Automation: RWIA’2014. Springer International Publishing, 2015: 3 − 34.

    [3]

    Ahmed, Mohamed M Z. Friction stir welding of aluminum in the aerospace industry: the current progress and state-of-the-art review[J]. Materials, 2023, 16(8): 2971. doi: 10.3390/ma16082971

    [4]

    Mohandas T. Welding technologies in aerospace applications[J]. Aerospace Materials and Material Technologies, 2017, 2(1): 65 − 83.

    [5]

    Wang G, Liao T W. Automatic identification of different types of welding defects in radiographic images[J]. Ndt & E International, 2002, 35(8): 519 − 528.

    [6]

    Madhvacharyula, Anirudh Sampath, Pavan, et al. In situ detection of welding defects: a review[J]. Welding in the World, 2022, 66(4): 611 − 628. doi: 10.1007/s40194-021-01229-6

    [7]

    Andrew G, Vignesh S, Sooyoung L, et al. Applications of deep learning for fault detection in industrial cold forging[J]. International Journal of Production Reseach, 2021, 59(16): 4826 − 4835.

    [8]

    Lenka L, Jan S, Renata W. The learning path to neural network industrial application in distributed envisonment[J]. Processes, 2021, 9(12): 2247. doi: 10.3390/pr9122247

    [9]

    Dutta, Sourav. An overview on the evolution and adoption of deep learning applications used in the industry[J]. Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery, 2018, 8(4): 1257. doi: 10.1002/widm.1257

    [10] 王睿, 胡云雷, 刘卫朋, 等. 基于边缘AI的焊缝X射线图像缺陷检测[J]. 焊接学报, 2022, 43(1): 79 − 84.

    Wang Rui, Hu Yunlei, Liu Weipeng, et al. Defect detection of weld X-ray image based on edge AI[J]. Transactions of the China Welding Institution, 2022, 43(1): 79 − 84.

    [11] 刘欢, 刘骁佳, 王宇斐, 等. 基于复合卷积层神经网络结构的焊缝缺陷分类技术[J]. 航空学报, 2022, 43(S1): 165 − 172.

    Liu Huan, Liu Xiaojia, Wang Yufei, et al. Weld defect classification technology based on compound convolution neural network structure[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(S1): 165 − 172.

    [12] 任文坚, 王永红, 李春凯, 等. 液体火箭发动机推力室熔焊缝数字化胶片图像缺陷识别方法研究[J]. 电焊机, 2023, 53(1): 9 − 14.

    Ren Wenjian, Wang Yonghong, Li Chunkai, et al. Research on automatic detection method of DR digital imaging for brazing seam defects of thrust chamber body[J]. Electric Welding Machine, 2023, 53(1): 9 − 14.

    [13] 程松, 杨洪刚, 徐学谦, 等. 基于YOLOv5的改进轻量型X射线铝合金焊缝缺陷检测算法[J]. 中国激光, 2022, 49(21): 136 − 144.

    Cheng Song, Yang Honggang, Xu Xueqian, et al. Improved lightweight X-ray aluminum alloy weld defects detection algorithm basedon YOLOv5[J]. Chinese Journal of Lasers, 2022, 49(21): 136 − 144.

    [14] 杨会敏, 李春棚, 袁新安, 等. 基于SSD的交流电磁场缺陷智能识别方法[J]. 无损检测, 2022, 44(8): 25 − 30.

    Yang Huimin, Li Chunpeng, Yuan Xin’an, et al. Defects intelligent recognition method of ACFM based on SSD[J]. Nondestructive Testing, 2022, 44(8): 25 − 30.

    [15]

    Zhang Z, Zhang Y, Wen Y, et al. Intelligent defect detection method for additive manufactured lattice structures based on a modified YOLOv3 model[J]. Journal of Nondestructive Evaluation, 2022, 41(1): 1 − 14. doi: 10.1007/s10921-021-00836-z

    [16]

    Wei X, Wei D, Suo D, et al. Multi-target defect identification for railway track line based on image processing and improved YOLOv3 model[J]. IEEE Access, 2020, 8(1): 973 − 988.

    [17]

    Dong C, Zhang K, Xie Z, et al. An improved cascade RCNN detection method for key components and defects of transmission lines[J]. IET Generation, Transmission Distribution, 2023, 17(19): 4277 − 4292. doi: 10.1049/gtd2.12948

    [18]

    Redmon J, Divvala S, Girshick R, et al. You only look once: unified, realtime object detection[J]. Computer Vision and Pattern Recognition, 2016, 91(1): 779 − 788.

    [19]

    Bhavya Sree B, Yashwanth Bharadwaj V, Neelima N. An inter-comparative survey on state-of-the-art detectors—R-CNN, YOLO and SSD[C]//Intelligent Manufacturing and Energy Sustainability: Proceedings of ICIMES 2020. Springer Singapore, 2021: 475 − 483.

    [20]

    Cao C Q. An improved faster R-CNN for small object detection[J]. Ieee Access, 2019, 7(1): 106838 − 106846.

    [21]

    Bharati P, Pramanik A. Deep learning techniques—R-CNN to mask R-CNN: a survey[J]. Computational Intelligence in Pattern Recognition:Proceedings of CIPR 2019, 2020(1): 657 − 668.

    [22]

    Cai Z W, Vasconcelos N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recongnition, 2018: 6165 − 6162.

    [23]

    Sun C Y, Hong X J, Shi S, et al. Cascade faster R-CNN detection for vulnerable plaques in OCT images[J]. IEEE Access, 2021(9): 24697 − 24704.

    [24]

    Cai Z W, Vasconcelos Nuno. Cascade R-CNN: high quality object detection and instance segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(5): 1483 − 1498.

    [25]

    Feng T, Liu J G, Xia F, et al. A double-branch surface detection system for armatures in vibration motors with miniature volume based on ResNet-101 and FPN[J]. Sensors, 2020, 20(8): 1 − 16. doi: 10.1109/JSEN.2020.2978309

    [26]

    Alshammari A, Chabaan R C. Sppn-Rn101: spatial pyramid pooling network with resnet 101-Based foreign object debris detection in airports[J]. Mathematics, 2023, 11(4): 841. doi: 10.3390/math11040841

    [27]

    Ren K, Huang L, Fan C Q, et al. Real-time traffic sign detection network using DS-DetNet and lite fusion FPN[J]. Journal of Real-Time Image Processing, 2021, 18(6): 1 − 11.

    [28]

    Li Y C, Zhou S L, Chen H, et al. Attention-based fusion factor in FPN for object detection[J]. Applied Intelligence, 2022, 1(1): 1 − 10.

    [29]

    Chen J Y, Liu S P, Zhao L. Small object detection combining attention mechanism and a novel FPN[J]. Journal of Intelligent Fuzzy Systems, 2022, 42(4): 3691 − 3703.

    [30]

    Dai Z Z, Chen M Q, Gu X D, et al. Batch drop block network for person re-identification and beyond [C]// Proceedings of the IEEE Conference on Computer Vision, 2019: 3690 − 3700.

    [31]

    Ye J. Single valued neutrosophic cross-entropy for multicriteria decision making problems[J]. Applied Mathematical Modelling, 2014, 38(3): 1170 − 1175. doi: 10.1016/j.apm.2013.07.020

    [32]

    Chen Y P, Xu K, Zhou P, et al. Improved cross entropy loss for noisy labels in vision leaf disease classification[J]. IET Image Processing, 2022, 16(6): 1511 − 1519. doi: 10.1049/ipr2.12402

    [33] 程松, 戴金涛, 杨洪刚, 等. 基于改进型YOLOv4的焊缝图像检测与识别[J]. 激光与光电子学进展, 2022, 59(16): 105 − 111.

    Cheng Song, Dai Jintao, Yang Honggang, et al. Weld Image detection and recognition based on improved YOLOv4[J]. Laser & Optoelectronics Progress, 2022, 59(16): 105 − 111.

  • 期刊类型引用(10)

    1. 陈澄,尹红波,王成,倪大海,谢璐,曾超林. 钼铜载体与铝合金外壳的无压纳米银胶低温烧结强度. 半导体技术. 2025(01): 95-100 . 百度学术
    2. 黄玺,张亮,王曦,陈晨,卢晓. 电子封装用纳米级无铅钎料的研究进展. 材料导报. 2024(23): 136-148 . 百度学术
    3. 黄天,甘贵生,刘聪,马鹏,江兆琪,许乾柱,陈仕琦,程大勇,吴懿平. 电子封装低温互连技术研究进展. 中国有色金属学报. 2023(04): 1144-1178 . 百度学术
    4. 官紫妍,吴丰顺,周龙早,李可为,丁立国,李学敏. 功率模块纳米银烧结技术研究进展. 电子工艺技术. 2023(04): 1-6 . 百度学术
    5. 傅必成,方毅,张乐,李道会,齐放,宋利军,祝温泊. Fluxless bonding with silver nanowires aerogel in die-attached interconnection. China Welding. 2023(02): 32-41 . 百度学术
    6. 杜伟,强军锋,余竹焕,高炜,阎亚雯,王晓慧,刘旭亮. 电子封装用纳米复合焊膏的研究进展. 材料导报. 2023(19): 162-172 . 百度学术
    7. 龙旭,种凯楠,苏昱太. 烧结银细观孔隙结构对宏观力学性能的影响. 焊接学报. 2023(12): 15-20+27+137-138 . 本站查看
    8. 齐苗苗,贺晓斌,刘双宝,杨婉春,祝温泊. Ag-Cu固溶体颗粒制备及低温烧结互连接头性能. 焊接学报. 2022(07): 97-101+119 . 本站查看
    9. 杨婉春,胡少伟,祝温泊,李明雨. 低温烧结纳米银膏研究进展. 焊接学报. 2022(11): 137-146+169-170 . 本站查看
    10. 王刘珏,瞿昀昊,吉勇. 颗粒形貌对银焊膏无压烧结行为的影响. 材料导报. 2022(S2): 347-351 . 百度学术

    其他类型引用(10)

图(9)  /  表(4)
计量
  • 文章访问数:  119
  • HTML全文浏览量:  20
  • PDF下载量:  36
  • 被引次数: 20
出版历程
  • 收稿日期:  2023-11-03
  • 网络出版日期:  2024-03-18
  • 刊出日期:  2025-01-24

目录

/

返回文章
返回