基于树莓派的井下水仓水位智能测控系统

陈海舰; 王唯一; 范锦鸽; 潘逸冬; 闫子骥; 吴保磊

doi:10.13272/j.issn.1671-251x.2022110072

基于树莓派的井下水仓水位智能测控系统

doi: 10.13272/j.issn.1671-251x.2022110072

陈海舰^{1, 2,},
王唯一³,
范锦鸽³,
潘逸冬³,
闫子骥³,
吴保磊^3, ,

1.
中煤科工集团常州研究院有限公司, 江苏常州　213015
2.
天地(常州)自动化股份有限公司, 江苏常州　213015
3.
中国矿业大学计算机科学与技术学院, 江苏徐州　221116

基金项目: 中国矿业大学实验室开放项目（2020SYKF06）。

详细信息

作者简介:
陈海舰（1983—），男，江苏宿迁人，高级工程师，现从事矿山智能化、防爆电气、科研管理方面的工作，E-mail：chj120606@163.com

通讯作者:
吴保磊（1979—），男，江苏邳州人，副教授，主要研究方向为图像处理、智能控制，E-mail:4092@cumt.edu.cn

中图分类号: TD745
计量
- 文章访问数: 224
- HTML全文浏览量: 69
- PDF下载量: 29
- 被引次数: 0
出版历程
- 收稿日期: 2022-11-17
- 修回日期: 2023-08-04
- 网络出版日期: 2023-09-04

Intelligent measurement and control system of mine water level based on Raspberry Pi

CHEN Haijian^{1, 2
,},
WANG Weiyi³,
FAN Jinge³,
PAN Yidong³,
YAN Ziji³,
WU Baolei^{3
, ,}

1.
CCTEG Changzhou Research Institute, Changzhou 213015, China
2.
Tiandi(Changzhou) Automation Co., Ltd., Changzhou 213015, China
3.
School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China

摘要

摘要: 针对目前井下水仓水位监测方法精度较低、易受环境影响、实时性不强、对机器算力的要求较高、硬件成本较高等问题，提出了一种基于树莓派的井下水仓水位智能测控系统。该系统通过防爆监控摄像机采集水仓标尺周围水位图像，采用树莓派作为图像处理平台。首先，将采集的彩色图像转换为灰度图像，利用Otsu法对图像进行阈值分割，通过形态学运算去除噪声并增强图像边缘信息，进而将标尺轮廓从背景中分离出来；其次，利用Canny算子检测标尺边缘，并利用Hough变换方法提取水位线与标尺竖边的交线，得到水位线在图像空间中的坐标；然后，对水位线附近区域一定范围内的标尺数字图像进行阈值分割和滤波增强处理，再通过模板匹配法实现标尺数字识别，从而得到水位线数值；最后，将水仓水位线数值转换为电流模拟量，利用树莓派发送给水泵控制器，根据电流大小控制水泵开停，实现水仓水位智能控制。该系统具有成本较低、部署便捷、精度高、实时性好等优点，能够实现水仓水位快速精准识别与控制。
- 井下水仓 /
- 水位测控 /
- 树莓派 /
- 边缘检测 /
- Hough变换 /
- 数字识别
Abstract: The current water level monitoring methods have the problems of low precision, susceptibility to environmental impact, weak real-time performance, high requirements for machine computing power, and high hardware costs. In order to solve the above problems, a Raspberry Pi-based intelligent water level measurement and control system for underground water storage is proposed. The system collects water level images around the water tank scale through explosion-proof monitoring cameras, and uses raspberry pie as the image processing platform. Firstly, the method converts the collected color images into grayscale images, and uses the Otsu method to perform threshold segmentation on the images. The method removes noise and enhances image edge information through morphological operations, and then separates the ruler contour from the background. Secondly, the Canny operator is used to detect the edge of the scale, and the Hough transform method is used to extract the intersection line between the water level line and the vertical edge of the scale, obtaining the coordinates of the water level line in the image space. Thirdly, threshold segmentation and filtering enhancement processing are performed on the digital image of the scale within a certain range of the area near the water level line. Then, the template matching method is used to achieve the recognition of the scale number, thereby obtaining the water level line value. Finally, the method converts the numerical value of the water level line in the water tank into a current analog quantity, and uses Raspberry Pi to send the water pump controller to control the start and stop of the water pump based on the current magnitude. The method achieves intelligent control of the mine water level. This system has the advantages of low cost, convenient deployment, high precision, and good real-time performance. It can achieve rapid and accurate recognition and control of mine water level.
- mine water tank /
- water level measurement and control /
- Raspberry Pi /
- edge detection /
- Hough transform /
- number recognition

HTML全文

图 1 基于树莓派的井下水仓水位智能测控系统组成

Figure 1. Composition of intelligent measurement and control system of mine water level based on Raspberry Pi

下载: 全尺寸图片幻灯片

图 2 基于树莓派的井下水仓水位智能测控系统流程

Figure 2. Flow of intelligent measurement and control system of mine water level based on Raspberry Pi

下载: 全尺寸图片幻灯片

图 3 水位图像

Figure 3. Water level image

下载: 全尺寸图片幻灯片

图 4 形态学处理结果

Figure 4. Morphological processing result

下载: 全尺寸图片幻灯片

图 5 Canny边缘检测结果

Figure 5. Canny edge detection result

下载: 全尺寸图片幻灯片

图 6 Hough变换空间映射关系

Figure 6. Hough transform space mapping relationship

下载: 全尺寸图片幻灯片

图 7 Hough变换直线检测结果

Figure 7. Hough transform line detection result

下载: 全尺寸图片幻灯片

图 8 标尺数字区域图像预处理结果

Figure 8. Image preprocessing results of digital area of ruler

下载: 全尺寸图片幻灯片

图 9 轮廓检测与数字提取结果

Figure 9. Results of contour detection and digital extraction

下载: 全尺寸图片幻灯片

表 1 不同极坐标参数下水位线识别准确率

Table 1. Recognition accuracy of water level under different polar coordinate parameters

$\left\|{\theta }_{i}-{\theta }_{j}\right\|$	不同$ \left\|{\rho }_{i}-{\rho }_{j}\right\| $下的准确率/%
$\left\|{\theta }_{i}-{\theta }_{j}\right\|$	6.0	6.5	7.0	7.5	8.0	8.5	9.0	9.5
0.07	72.50	71.67	71.67	71.67	71.67	73.33	73.33	57.50
0.10	80.83	88.33	88.33	88.33	88.33	81.67	81.67	65.83
0.13	89.17	90.83	90.83	82.50	82.50	74.17	74.17	68.33
0.16	89.17	90.83	90.83	90.83	90.83	82.50	82.50	76.67
0.19	89.17	90.83	90.83	82.50	82.50	74.17	74.17	68.33

下载: 导出CSV

参考文献(21)

[1]	石军杰. 煤矿井下水仓智能清理机的设计及关键技术研究[D]. 太原: 太原理工大学, 2022. SHI Junjie. Design and key technology research of intelligent waster silo cleaning machine in coal mine[D]. Taiyuan: Taiyuan University of Technology, 2022.
[2]	李文俊. 煤矿与非煤矿山安全评价指导手册[M]. 徐州: 中国矿业大学出版社, 2006. LI Wenjun. Guidelines for safety assessment of coal and non coal mines[M]. Xuzhou: China University of Mining and Technology Press, 2006.
[3]	MT/T 674—1997 矿井生产时期排水技术规范[S]. MT/T 674-1997 Technical specification for drain of mine water during the period of production[S].
[4]	林王峰. 基于视频图像的船舶水尺自动测量系统的设计与实现[D]. 厦门: 集美大学, 2017. LIN Wangfeng. The design and implementation of a ship's draft automatica measurement system base on the video image recognition technology[D]. Xiamen: Jimei University, 2017.
[5]	郭秀艳. 船舶水尺吃水值检测方法研究[D]. 大连: 大连海事大学, 2014. GUO Xiuyan. Research on detection method of ship draft[D]. Dalian: Dalian Maritime University, 2014.
[6]	张亚,宗军,蒋东进,等. 气泡压力式水位计现场检测装置设计与实现[J]. 水文,2021,41(6):60-65. ZHANG Ya,ZONG Jun,JIANG Dongjin,et al. Design and implementation of field detection device for bubble pressure-type stage recorder[J]. Journal of China Hydrology,2021,41(6):60-65.
[7]	王磊,陈明恩,孟凯凯,等. 基于深度学习算法的水位识别方法研究[J]. 水利信息化,2020(3):39-43,56. WANG Lei,CHEN Ming'en,MENG Kaikai,et al. Research on water level recognition method based on deep learning algorithms[J]. Water Resources Informatization,2020(3):39-43,56.
[8]	WANG Xing, CHEN Hu, WU Qinge, et al. On research of video stream detection algorithm for ship waterline[C]. International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, Fuzhou, 2020: 204-208.
[9]	石则斌,罗雪峰,王隐,等. 基于卷积神经网络的智能垃圾分拣车[J]. 实验室研究与探索,2022,41(12):123-126. SHI Zebin,LUO Xuefeng,WANG Yin,et al. Intelligent garbage sorting vehicle based on convolutional neural network[J]. Research and Exploration in Laboratory,2022,41(12):123-126.
[10]	张琪. 结合边缘检测的图像二值化算法[D]. 长春: 吉林大学, 2011. ZHANG Qi. Image binarization algorithm combined with edge detection[D]. Changchun: Jilin University, 2011.
[11]	林爱萍. 智能平仓机器人的视觉导航系统设计[D]. 成都: 电子科技大学, 2021. LIN Aiping. Research on the vision navigation system of intelligent grain leveling robot[D]. Chengdu: University of Electronic Science and Technology of China, 2021.
[12]	范九伦,赵凤. 灰度图像的二维Otsu曲线阈值分割法[J]. 电子学报,2007(4):751-755. FAN Jiulun,ZHAO Feng. Two-dimensional Otsu's curve thresholding segmentation method for gray-level images[J]. Acta Electronica Sinica,2007(4):751-755.
[13]	戴青云,余英林. 数学形态学在图象处理中的应用进展[J]. 控制理论与应用,2001(4):478-482. DAI Qingyun,YU Yinglin. The advances of mathematical morphology in image processing[J]. Control Theory & Applications,2001(4):478-482.
[14]	王家晨,王新房. 基于ButterWorth滤波的X射线钢管焊缝缺陷检测方法[J]. 微型机与应用,2017,36(23):21-24. WANG Jiachen,WANG Xinfang. Automatic detection of weld defects in X-ray based on ButterWorth filtering[J]. Microcomputer & Its Applications,2017,36(23):21-24.
[15]	段瑞玲,李庆祥,李玉和. 图像边缘检测方法研究综述[J]. 光学技术,2005(3):415-419. DUAN Ruiling,LI Qingxiang,LI Yuhe. Summary of image edge detection[J]. Optical Technique,2005(3):415-419.
[16]	陈若珠,薛彪. 基于MATLAB的改进Canny算子的图像边缘检测研究[J]. 工业仪表与自动化装置,2014(4):113-116. CHEN Ruozhu,XUE Biao. The research of image edge detection based on improved Canny operator of MATLAB[J]. Industrial Instrumentation and Automation,2014(4):113-116.
[17]	王植,贺赛先. 一种基于Canny理论的自适应边缘检测方法[J]. 中国图象图形学报,2004(8):65-70. WANG Zhi,HE Saixian. An adaptive edge-detection method based on Canny algorithm[J]. Journal of Image and Graphics,2004(8):65-70.
[18]	李静,陈桂芬,丁小奇. 基于改进Canny算法的图像边缘检测方法研究[J]. 计算机仿真,2021,38(4):371-375. LI Jing,CHEN Guifen,DING Xiaoqi. Research on image edge detection method based on improved Canny algorithm[J]. Computer Simulation,2021,38(4):371-375.
[19]	李小兰. 基于霍夫变换的海面小目标检测方法研究[D]. 西安: 西安电子科技大学, 2022. LI Xiaolan. Detection methods based on Hough transforms of sea-surface small targets[D]. Xi'an: Xidian University, 2022.
[20]	张志强,冯伟,赵小虎,等. 面向边缘计算的选煤厂刮板检测方法[J]. 工矿自动化,2021,47(4):92-97. ZHANG Zhiqiang,FENG Wei,ZHAO Xiaohu,et al. Edge computing-oriented scraper detection method for coal preparation plants[J]. Industry and Mine Automation,2021,47(4):92-97.
[21]	王健. 基于PHOW特征的人脸姿态识别算法研究[D]. 济南: 山东财经大学, 2016. WANG Jian. PHOW based feature detection for head pose estimation[D]. Jinan: Shandong University of Finance and Economics, 2016.