English
智能化农业装备学报（中英文）

智能化农业装备学报（中英文） ›› 2025, Vol. 6 ›› Issue (1): 91-98.DOI: 10.12398/j.issn.2096-7217.2025.01.009

• • 上一篇    下一篇

基于MobileNetV3卷积神经网络的农用机械发动机水泵气密性检测方法

王胜1,2(), 杨晨3, 惠向晖4()   

  1. 1.郑州信息科技职业学院，河南 郑州，450000
    2.河南省气密性能检测工程研究中心，河南 郑州，450000
    3.吉林大学生物与农业工程学院，吉林 长春，130000
    4.河南农业大学信息与管理科学学院，河南 郑州，450000
  • 收稿日期:2024-05-22 修回日期:2024-09-29 出版日期:2025-02-15 发布日期:2025-02-15
  • 通讯作者: 惠向晖
  • 作者简介:王胜，男，1982年生，河南南阳人，工学博士，副教授；研究方向为智能农业装备设计。E-mail：henanddws@126.com
  • 基金资助:
    河南省2024年科技发展计划(242102220006);2024年度河南省高等学校重点科研项目(24B460009)

New insight for MobileNetV3 convolutional neutral network applied in air tightness detection of agricultural machinery engine pump

WANG Sheng1,2(), YANG Chen3, HUI Xianghui4()   

  1. 1.Zhengzhou Vocational College of Information Technology，Zhengzhou 450000，China
    2.Henan Air-Leakage Test Engineering Research Center，Zhengzhou 450000，China
    3.College of Biological and Agricultural Engineering，Jilin University，Changchun 130000，China
    4.College of Information and Management Science，Henan Agricultural University，Zhengzhou 450000，China
  • Received:2024-05-22 Revised:2024-09-29 Online:2025-02-15 Published:2025-02-15
  • Contact: HUI Xianghui
  • About author:WANG Sheng，E-mail： henanddws@126.com
  • Supported by:
    Henan Technology Research Plan 2024(242102220006);Key Program of Higher University of Henan Province 2024(24B460009)

RichHTML

PDF

摘要：

农业机械装备智能化升级是目前农业机械领域研究的热点。机器视觉技术应用于农作物的修剪、采摘等领域的研究，已取得初步成果，但是在农业机械装备中进行机器视觉的缺陷检测鲜有研究。研究针对农用机械发动机水泵气密性能缺陷，进行基于机器视觉的自动化检测技术进行相关试验研究。采用基于MobileNetV3卷积神经网络的深度学习算法进行气泡识别。在进行气密性检测试验中，首先需要对气泡原始图像进行气泡区域提取算法处理，以降低图像的分辨率，然后将处理后的图像用于MobileNetV3卷积神经网络进行深度学习，训练后的神经网络模型就可以实现气密性检测中对气泡进行识别和定位。将识别结果与人工标注结果进行对比，计算出气泡识别算法的气泡漏检率。试验结果表明，气泡识别算法的漏检率与气泡平均直径存在较大关联，总体上表现为气泡平均直径越小，气泡的漏检率越高，气泡平均直径与发动机水泵壳体上的泄漏孔大小成正比关系。当气泡平均直径大于0.2mm时，气泡漏检率均在2%以下；平均直径小于0.2 mm的气泡，漏检情况相对较多，漏检率在5%~10%波动。研究提出的气泡识别算法能够对图像中的气泡进行识别和标记，从而检测出发动机水泵壳体的气密性能。算法对于小尺寸气泡的识别能力有待进一步提高，以增强对微小气泡特征的捕捉能力。

关键词: 发动机水泵, 卷积神经网络, 气密性检测, 漏检率

Abstract:

The intelligent advancement of agricultural machinery is a key focus in current agricultural engineering research. While machine vision technology has made preliminary progress in applications such as harvesting， breeding， and other crop-related fields， its use in defect detection for agricultural machinery remains limited. This study focused the airtightness defect detection of the agricultural machine pump， and presented a novel approach for automated detection based on machine vision. A deep learning algorithm based on MobileNetV3 convolutional neural network （CNN） was employed for the bubble recognition. In the airtightness detection experiment， the original bubble images were first processed by a bubble region extraction algorithm to reduce the image resolution. The post-processed images were then used for deep learning by MobileNetV3 CNN. The trained neural network model could recognize the bubble and its location in the airtightness detection. For performance evaluation， the recognition results could be compared with manually marked results to calculate the missing bubble recognition rate of the algorithm. The experiment results indicated that the missing recognition rate of the bubble algorithm is closely related with average diameter of the bubbles. The smaller of the average bubble diameter， the higher of the missing recognition rate， and the average bubble diameter was proportional to the leakage hole size on the pump. When the average bubble diameter was larger than 0.2 mm， the missing bubble recognition rate was below 2%， and when the average bubble diameter was smaller than 0.2 mm， the missing bubble recognition rate fluctuated between 5% and 10%. In this paper， the proposed bubble recognition algorithm effectively identifies and marks bubbles in images， enabling the detection of airtightness in agricultural pumps. However， further optimization is required to improve the algorithm's ability to recognize smaller bubbles and enhance its sensitivity to minute features in future work.

Key words: engine water pump, convolutional neural networks, air tightness testing, missed detection rate

中图分类号: