Inclination angle adjustment system for shale shaker based on Raspberry Pi and visual image

doi:10.3785/j.issn.1006-754X.2024.03.147

Chinese Journal of Engineering Design

2024, Vol. 31

Issue (2): 254-262 DOI: 10.3785/j.issn.1006-754X.2024.03.147

Whole Machine and System Design

Inclination angle adjustment system for shale shaker based on Raspberry Pi and visual image

Yongjun HOU^1,²(

),Wenjun JIA¹,Bowen LIU³,Xianjin WU⁴

^1.School of Mechatronic Engineering, Southwest Petroleum University, Chengdu 610500, China
^2.Oil and Gas Equipment Technology Sharing and Service Platform of Sichuan Province, Chengdu 610500, China
^3.Chengdu Natural Gas Chemical Plant, Southwest Oil & Gasfeild Company of PetroChina Company Limited, Chengdu 610213, China
^4.BOMCO Chengdu Equipment Manufacturing Company, Chengdu 610052, China

Download:

HTML

PDF(3768KB)
Export: BibTeX | EndNote (RIS)

Abstract

At present, the shale shakers in China are operated by manually detecting the solid-liquid separation status and manually adjusting the inclination angle of the screen surface, which can not realize self-adaptive work, and the phenomenon of drilling fluid "running" often occurs. To solve this problem, an inclination angle adjustment system for shale shaker based on Raspberry Pi and visual image was proposed. The system used Raspberry Pi, dedicated camera, motor drive board and two stepper motors as hardware platform, and was equipped with an image recognition software developed based on OpenCV and improved AlexNet model, which could achieve visual detection of screen surface solid-liquid separation status and automatic adjustment of screen surface inclination angle of the shale shaker. Firstly, according to the position characteristics of the liquid phase termination line during the solid-liquid separation process of shale shaker, the collected screen surface images were divided into three categories: normal, low mud and slurry running state, and the screen surface image dataset was constructed. Then, the AlexNet model based on transfer learning was constructed using TensorFlow platform to automatically recognize the screen surface solid-liquid separation status of shale shaker. Finally, based on the recognition results, two stepper motors were controlled synchronously by the GPIO (general purpose input/output) interface of Raspberry Pi to realize the inclination angle adjustment for the shale shaker. The results showed that the accuracy of the designed inclination angle adjustment system for recognizing screen surface solid-liquid separation status reached 97.3%, and the response time was about 1.5 s, which could meet the inclination angle adjustment requirements of the shale shaker. The inclination angle adjustment system equipment has small volume, low cost and is easy to debug and maintain, which can effectively improve the automation level of shale shakers.

Key words： shale shaker Raspberry Pi inclination adjustment system AlexNet model image recognition

Received: 03 April 2023 Published: 26 April 2024

CLC:

TE 928

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yongjun HOU
	Wenjun JIA
	Bowen LIU
	Xianjin WU

Cite this article:

Yongjun HOU,Wenjun JIA,Bowen LIU,Xianjin WU. Inclination angle adjustment system for shale shaker based on Raspberry Pi and visual image. Chinese Journal of Engineering Design, 2024, 31(2): 254-262.

URL:

https://www.zjujournals.com/gcsjxb/10.3785/j.issn.1006-754X.2024.03.147 OR https://www.zjujournals.com/gcsjxb/Y2024/V31/I2/254

基于树莓派和视觉图像的钻井振动筛倾角调节系统

目前，我国的钻井振动筛均采用人工监测筛面固液分离状态和手动调节筛面倾角的方式进行操作，无法实现自适应工作，常常出现钻井液“跑浆”现象。针对这一问题，提出了一种基于树莓派和视觉图像的钻井振动筛倾角调节系统。该系统以树莓派及专用摄像头、电机驱动板和2台步进电机为硬件平台，搭载基于OpenCV和改进AlexNet模型开发的图像识别软件，用于实现钻井振动筛的筛面固液分离状态视觉检测与筛面倾角自动调节。首先，根据钻井振动筛固液分离过程中液相终止线的位置特征，将采集的筛面图像分为正常、少浆和跑浆状态三种类别，并构建筛面图像数据集。然后，使用TensorFlow平台搭建基于迁移学习的AlexNet模型，以实现钻井振动筛的筛面固液分离状态的自动识别。最后，基于识别结果，由树莓派的GPIO（general purpose input/output，通用型输入/输出）接口控制2台步进电机同步工作，以实现钻井振动筛的倾角调节。结果表明，所设计的倾角调节系统对筛面固液分离状态的识别准确率达到97.33%，响应时间约为1.5 s，可满足钻井振动筛的倾角调节要求。该倾角调节系统设备体积小，成本低，且便于调试与维护，可有效提高钻井振动筛的自动化水平。

关键词： 钻井振动筛, 树莓派, 倾角调节系统, AlexNet模型, 图像识别

Fig.1 Overall block diagram of inclination angle adjustment system for shale shaker

Fig.2 Peripheral layout of Raspberry Pi 4B platform

Fig.3 Sony IMX219 sensor expansion board

Fig.4 Circuit diagram of DRV8825 motor drive chip

Fig.5 Program control flow of inclination angle adjustment system for shale shaker

Fig.6 Filter processing results of screen surface image

Fig.7 Preprocessing results of screen surface image

Fig.8 Samples of screen surface image

Fig.9 Screen surface image recognition model based on improved AlexNet

Fig.10 Training and testing results of screen surface image recognition model based on improved AlexNet

Fig.11 Classification results of screen surface image test set

Fig.12 Accuracy curve of screen surface image recognition model based on improved AlexNet

Fig.13 Recall rate curve of screen surface image recognition model based on improved AlexNet

Fig.14 F₁ value curve of screen surface image recognition model based on improved AlexNet

Table 1 Comparison of accuracy evaluation results of different models

Fig.15 Experimental device of inclination angle adjustment system for shale shaker

Table 2 Test results of inclination angle adjustment system for shale shaker


[1]	高向前.钻井新装备、新工具现状及进展［EB/OL］.（2014-05-11）［2023-02-18］.. GAO X Q. Status and progress of new drilling equipment and new tools［EB/OL］. （2014-05-11）［2023-02-18］. .

[2]	王臣，王皓，代炳晓，等.钻井液固相控制系统的信息化与自动化设计及应用［J］.设备管理与维修，2021（3）：112-113. WANG C， WANG H， DAI B X， et al. Informatization and automation design and application of drilling fluid solid phase control system［J］. Plant Maintenance Engneering， 2021（3）： 112-113.

[3]	河北北钻石油钻采设备有限公司.北钻固控设备智能振动筛控制系统现场工作视频［EB/OL］.（2023-02-01）［2023-02-18］.. Hebei BZ Solids Control Co.， Ltd. BZ intelligent shale shaker system working video［EB/OL］. （2023-02-01）［2023-02-18］. .

[4]	SUN Y N， XUE B， ZHANG M J， et al. Evolving deep convolution neural networks for image classification［J］. IEEE Transactions on Evolutionary Computation， 2020， 24（2）： 394-407.

[5]	RABABAAH A R. Deep learning of human posture image classification using convolutional neural networks［J］. International Journal of Computing Science and Mathematics， 2022， 15（3）： 273-288.

[6]	王美玉，田乔.迁移学习用于电磁目标识别［J］.太赫兹科学与电子信息学报，2021，19（4）：556-561. doi：10.11805/TKYDA2021214 WANG M Y， TIAN Q. Transfer learning for electromagnetic target recognition［J］. Journal of Terahertz Science and Electronic Information Technology， 2021， 19（4）： 556-561. doi: 10.11805/TKYDA2021214

[7]	MIAO R， JIANG Z， ZHOU Q Y， et al. Online inspection of narrow overlap weld quality using two-stage convolution neural network image recognition［J］. Machine Vision & Applications， 2021， 32（1）： 1-22.

[8]	KUCHIBHOTLA S， VOONNA C， PENKI R P， et al. Analysis of facial emotion recognition for image and video data using convolution neural networks［C］//6th International Conference on Electronics， Communication and Aerospace Technology. Coimbatore， Dec. 1-3， 2022.

[9]	ZHANG J Q， SUN Y， GUO L， et al. A new bearing fault diagnosis method based on modified convolutional neural networks［J］. Chinese Journal of Aeronautics， 2020， 33（2）： 439-447.

[10]	NOHA E H， AHMED S， WALID E S， et al. Classification of retinal images based on convolutional neural network［J］. Microscopy Research and Technique， 2021， 84（3）： 394-414.

[11]	赵桐，雷保珍，王训伟，等.基于迁移学习和特征重用的MIM齿轮缺陷检测［J］.传感器与微系统，2021，40（10）：129-131，135. ZHAO T， LEI B Z， WANG X W， et al. MIM gear defect detection based on transfer learning and feature reuse［J］. Transducer and Microsystem Technologies， 2021， 40（10）： 129-131， 135.

[12]	李长齐，王菡，罗昊.基于树莓派的齿轮表面缺陷检测系统设计［J］.仪表技术与传感器，2022（3）：109-113. doi：10.3969/j.issn.1002-1841.2022.03.021 LI C Q， WANG H， LUO H. Design of gear surface defect detection system based on Raspberry Pi［J］. Instrument Technique and Sensor， 2022（3）： 109-113. doi: 10.3969/j.issn.1002-1841.2022.03.021

[13]	李民赞，任新建，杨玮，等.基于树莓派的农田表土层土壤容重检测系统研究［J］.农业机械学报，2021，52（）：329-335，376. doi：10.6041/j.issn.1000-1298.2021.S0.042 LI M Z， REN X J， YANG W， et al. Soil bulk density detection system of framland topsoil based on Raspberry Pi［J］. Transactions of the Chinese Society for Agricultural Machinery， 2021， 52（）： 329-335， 376. doi: 10.6041/j.issn.1000-1298.2021.S0.042

[14]	KRIZHEVSKY A， SUTSKEVER I， HINTON G E. ImageNet classification with deep convolutional neural networks［J］. Advances in Neural Information Processing Systems， 2017， 60（6）： 84-90.

[15]	马燚松.钻井液振动筛的维护使用［J］.西部探矿工程，2018，30（5）：79-81，86. doi：10.3969/j.issn.1004-5716.2018.05.027 MA Y S. Maintenance and use of drilling shale shaker［J］. West-China Exploration Engineering， 2018， 30（5）： 79-81， 86. doi: 10.3969/j.issn.1004-5716.2018.05.027

[16]	郭强强.一种开架式水下作业机器人的设计与实现［D］.南京：南京信息工程大学，2019. GUO Q Q. Design and implementation of an open frame underwater operation robot［D］. Nanjing： Nanjing University of Information Science and Technology， 2019.

[17]	王晓.低成本智能数字式显微镜的搭建［D］.南京：南京大学，2021. WANG X. Construction of low cost “smart” microscope［D］. Nanjing： Nanjing University， 2021.

[18]	张杰飞.基于OpenCV的焊缝图像处理研究［D］.哈尔滨：哈尔滨理工大学，2019. ZHANG J F. Research on weld image processing based on OpenCV［D］. Harbin： Harbin University of Science and Technology， 2019.

[19]	龙满生，欧阳春娟，刘欢，等.基于卷积神经网络与迁移学习的油茶病害图像识别［J］.农业工程学报，2018，34（18）：194-201. doi：10.11975/j.issn.1002-6819.2018.18.024 LONG M S， OUYANG C J， LIU H， et al. Image recognition of camellia oleifera diseases based on convolutional neural network and transfer learning［J］. Transactions of the Chinese Society of Agricultural Engineering， 2018， 34（18）： 194-201. doi: 10.11975/j.issn.1002-6819.2018.18.024

[20]	HINTON G E， SRIVASTAVA N， KRIZHEVSKY A， et al. Improving neural networks by preventing co-adaptation of feature detectors［J］. Computer Science， 2012， 3（4）： 212-223.

[21]	KUMAR S P. Identification of wheat tiller based on AlexNet-feature fusion［J］. Multimedia Tools and Applications， 2022， 81（6）： 8309-8316.

[22]	张瑞青，李张威，郝建军，等.基于迁移学习的卷积神经网络花生荚果等级图像识别［J］.农业工程学报，2020，36（23）：171-180. doi：10.11975/j.issn.1002-6819.2020.23.020 ZHANG R Q， LI Z W， HAO J J， et al. Image recognition of peanut pod grades based on transfer learning with convolutional neural network［J］. Transactions of the Chinese Society of Agricultural Engineering， 2020， 36（23）： 171-180. doi: 10.11975/j.issn.1002-6819.2020.23.020

[23]	张安安，黄晋英，冀树伟，等.基于卷积神经网络图像分类的轴承故障模式识别［J］.振动与冲击，2020，39（4）：165-171. doi：10.16652/j.issn.1004-373x.2020.17.016 ZHANG A A， HUANG J Y， JI S W， et al. Bearing fault pattern recognition based on image classification with CNN［J］. Journal of Vibration and Shock， 2020， 39（4）： 165-171. doi: 10.16652/j.issn.1004-373x.2020.17.016

[1]	LI Bao-zhi, NI Hong-qi, LIN Si-yu, MENG Xian-chun. Axial dimension detection method of corrugated compensator based on image recognition[J]. Chinese Journal of Engineering Design, 2022, 29(1): 10-19.

[2]	HOU Yong-jun, LI Fen, WU Xian-jin, LIU You-ping. Numerical simulation study of the performance of gas-liquid ejector in negative pressure drilling fluid shale shaker[J]. Chinese Journal of Engineering Design, 2019, 26(4): 423-432.

Viewed

Full text

Abstract

Cited

Shared

Discussed