期刊文献+

钻井现场指针式仪表读数自动识别方法研究 被引量:1

Study on Automatic Identification Method of Pointer Instrument Reading in Drilling Field
下载PDF
导出
摘要 钻井数据采集过程中,由于现场安装、拉线等限制,传输稳定性不高,采集效果并不理想。引入了SSD+MoblieNet目标检测算法快速检测表盘位置并将表盘从复杂环境分离。使用Retinex特征增强算法并改进自适应Gamma增强使得复杂光在仪表上表现得更加自然,并在原有的图像去模糊技术上加入了模板匹配技术对表盘图像进行去抖动恢复,稳定有效地获取圆盘信息,进一步获取表盘指针角度信息。实验表明,改进后的方案能够在光照不均以及小幅度抖动下将误差控制在3%内,基本满足钻井现场指针仪表的测量要求,相对于传统方案,有着更强的实用性。 In the process of drilling data acquisition,the transmission stability is not high,and the acquisition effect is not ideal due to the limitations of field installation and wire drawing.The SSD+MoblieNet target detection algorithm is introduced to quickly detect the dial position and separate the dial from the complex environment.Retinex feature enhancement algorithm and adaptive Gamma enhancement are used to make the complex light more natural on the instrument.The template matching technology is added to the original image deblurring technology to restore the on-site dial image,so as to obtain the disc information stably and effectively,the dial pointer angle information is obtained for the next step.The experimental results show that the scheme can control the error within 3%under the condition of uneven illumination and small amplitude jtter,and basically meet the measurement requirements of oil drilling field pointer instrument.Compared with the traditional scheme,the scheme has stronger practicability.
作者 刘海龙 马波 张奇志 LIU Hailong;MA Bo;ZHANG Qizhi(College of Electronic Engineering,Xi'an Shiyou University,Xian 710065,China;Key Laboratory of Shanxi Province for Gas and Oil Well Logging Technology,Xi'an Shiyou University,Xian 710065,China)
出处 《控制工程》 CSCD 北大核心 2023年第9期1665-1672,共8页 Control Engineering of China
基金 陕西省教育厅科研计划资助项目(20JS123)。
关键词 仪表识别 目标检测 RETINEX算法 图像去抖 HOUGH变换 Instrument identification target detection Retinex algorithm image deburring Hough transform
  • 相关文献

参考文献10

二级参考文献89

共引文献169

同被引文献4

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部