基于ZYNQ图像处理研制便携式水质检测系统

孙冰洋; 杨顺生; 陈鹏; 张大文

doi:10.13205/j.hjgc.202307024

基于ZYNQ图像处理研制便携式水质检测系统

doi: 10.13205/j.hjgc.202307024

西南交通大学土木工程学院, 成都 610031

详细信息

作者简介:
孙冰洋,博士研究生,高级工程师,主要研究方向为水生态、污泥处理与利用技术。

计量
- 文章访问数: 95
- HTML全文浏览量: 7
- PDF下载量: 6
- 被引次数: 0
出版历程
- 收稿日期: 2022-03-04

DEVELOPMENT OF A PORTABLE WATER QUALITY DETECTION SYSTEM BASED ON ZYNQ IMAGE PROCESSING

School of Civil Engineering, Southwest Jiaotong University, Chengdu 610031, China

摘要

摘要: 综合光电检测技术和光谱分析技术中的紫外-可见吸收光谱法，研制多参数便携式地表水水质检测系统，能够现场快速检测出磷酸盐、亚硝酸盐、化学需氧量（COD）和NH₃-N水质参数。对水体中吸收特征波长在可见光部分的物质，使用摄像头采集其可见光谱，并对其可见光谱图像的灰度图进行卷积神经网络建模，吸收特征波长在紫外波段的物质，通过光电检测技术测其浓度值，将建立的卷积神经网络模型移植到ZYNQ中，结合紫外光电传感器，将被检测物质的浓度值通过LCD显示出来，以此实现水质检测仪的便携性。结果表明：所得卷积神经网络预测值为样本溶液在8种浓度值输出类型中的倾向值，准确率最高为100%，最低为40%。COD浓度值的最高误差为10%，证实该检测系统具有很好的实用价值。
- 紫外-可见吸收光谱法 /
- 水质检测 /
- 卷积神经网络 /
- 灰度模型
Abstract: Combined with photoelectric detection technology and UV-Vis absorption spectroscopy in spectral analysis technology, a multi-parameter portable surface water quality detection system was developed, which can quickly detect phosphate, nitrite, and chemical oxygen demand (COD) and ammonia nitrogen on-site. For the substances in the water body that absorb the characteristic wavelengths in the visible range, a camera was used to collect the visible spectrum, and the grayscale image of the visible spectrum image was modelled by a convolutional neural network. The concentration value of substances, whose absorption characteristic wavelength is within the ultraviolet band, was measured by photoelectric detection technology. The established convolutional neural network model was transplanted into ZYNQ, and combined with an ultraviolet photoelectric sensor, the concentration value of the detected substance was displayed on the LCD to realize the portability of the water quality detector. Research indicated that:the prediction value of the convolutional neural network was obtained as the tendency value of sample solution in 8 output types of concentration value, the highest accuracy was 100%, and the lowest was 40%. The highest error of COD concentration value was 10%, proving that the detection system has good practical value.
- UV-Vis absorption spectroscopy /
- water quality testing /
- convolutional neural network /
- grayscale model

HTML全文

参考文献(27)

[1]	刘录三,黄国鲜,王璠,等.长江流域水生态环境安全主要问题、形势与对策[J].环境科学研究,2020,33(5):1081-1090.
[2]	WRIGHT J, GUNDRY S, CONROY R.Household drinking water in developing countries:a systematic review of microbiological contamination between source and point-of-use[J].Trop Med Int Health, 2004,9(1):106-117.
[3]	SAID A, STEVENS D K, SEHLKE G.An innovative index for evaluating water quality in streams[J].Environmental Management, 2004, 34(3):406-414.
[4]	PELETZ R, KISIANGANI J, BONHAM M, et al.Why do water quality monitoring programs succeed or fail? a qualitative comparative analysis of regulated testing systems in sub-Saharan Africa[J].International Journal of Hygiene and Environmental Health,2018, 221(6):907-920.
[5]	WU L H, MA T S,BIAN Y C, et al.Improvement of regional environmental quality:government environmental governance and public participation[J].Science of the Total Environment, 2020, 717:137265.
[6]	王维理.水质检测过程控制及水质检测质量[J].建筑工程技术与设计,2019(5):4134.
[7]	SYU W J, CHANG T K, PAN S Y.Establishment of an automatic real-time monitoring system for irrigation water quality management[J].Int J Environ Res Public Health, 2020,17(3):737.
[8]	CHEN H W, ZHAO L L, YU F B, et al.Detection of phosphorus species in water:technology and strategies[J].Analyst, 2019, 144(24):7130-7148.
[9]	田珍珠.基于紫外光谱法的水质化学需氧量在线检测技术尝试[J].中外交流,2020,27(17):151.
[10]	FIGUEIR, RUSSO M R.Fish farming water quality monitored by optical analysis:the potential application of UV-Vis absorption and fluorescence spectroscopy[J].Aquaculture, 2018(1):484-486.
[11]	AARESTRUP F M, WOOLHOUSE M E.Using sewage for surveillance of antimicrobial resistance[J].Science, 2020,367(6478):630-632.
[12]	KHVOSTENKO O G, KINZYABULATOV R R, KHATYMOVA L Z, et al.The lowest triplet of tetracyanoquinodimethane via UV-vis absorption spectroscopy with Br-containing solvents[J].J Phys Chem A, 2017, 121(39):7349-7355.
[13]	雷惠,潘德炉,陶邦一,等.东海典型水体的黄色物质光谱吸收及分布特征[J].海洋学报,2009,31(2):57-62.
[14]	周琳,马荣华,段洪涛,等.浑浊Ⅱ类水体叶绿素a浓度遥感反演(Ⅰ):模型的选择[J].2011,30(6):531-536.
[15]	汪银龙,冯民权,董向前.汾河下游雨季硝酸盐污染源解析[J].环境科学,2019,40(9):4033-4041.
[16]	BRUN L, TRÉMEAU A.Color quantization[M]//Digital Color Imaging Handbook.CRC Press, 2017:589-637.
[17]	YANG X H, REN T, TAN L H.Size distribution measurement of coal fragments using digital imaging processing[J].Measurement, 2020,160:107867.
[18]	邹雄,刘国栋,曾文平.QR码图像预处理中的滤波研究[J].应用光学,2010,31(3):413-417.
[19]	OSHI A, BOYAT A K, JOSHI B K.Impact of wavelet transform and median filtering on removal of salt and pepper noise in digital images[C]//2014 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT).IEEE, 2014:838-843.
[20]	CHEUNG G, MAGLI E, TANAKA Y, et al.Graph spectral image processing[J].Proceedings of the IEEE, 2018,106(5):907-930.
[21]	MORRIS R.Spectrophotometry[J].Current Protocols Essential Laboratory Techniques, 2015, 11(1):2-1.
[22]	HUANG P J, WANG K, HOU D B, et al.In situ detection of water quality contamination events based on signal complexity analysis using online ultraviolet-visible spectral sensor[J].Applied Optics, 2017, 56(22):6317-6323.
[23]	林峰,王智敏,王一菲.紫外光照下尿嘧啶在磷酸盐水溶液中的新型光化学反应研究[J].高等学校化学学报,2004,25(5):926-929.
[24]	CHEN J, LIU S, QI X, et al.Study and design on chemical oxygen demand measurement based on ultraviolet absorption[J].Sensors and Actuators B:Chemical, 2018, 254:778-784.
[25]	孙平安,祁俊,谭秋月.利用卷积神经网络改进迭代深度学习算法的图像识别方法研究[J].计算机应用研究,2019,36(7):2223-2227.
[26]	SARIGUL M, OZYILDIRIM B M, AVCI M.Differential convolutional neural network[J].Neural Networks, 2019(116):279-287.
[27]	CHEUNG G, MAGLI E, TANAKA Y, et al.Graph spectral image processing[J].Proceedings of the IEEE, 2018,106(5):907-930.