基于智能视觉的流动水体污染监控方法及应用

曾祥吉; 鄢锋; 李勇刚; 潘岩; 杨静雅; 谭翔天

doi:10.13205/j.hjgc.202311014

基于智能视觉的流动水体污染监控方法及应用

doi: 10.13205/j.hjgc.202311014

1. 长沙有色冶金设计研究院有限公司, 长沙 410019;
2. 中南大学自动化学院, 长沙 410083

基金项目:

国家重点研发计划资助项目"盐湖化工产业集聚区域网络协同制造集成技术研究与应用示范"（2020YFB1713800）；湖南省科技创新计划资助"湖南省科技创新领军人才项目"（2021RC4047）

详细信息

作者简介:
曾祥吉(1986-),男,工程师,研究方向为有色金属行业智能制造、图像处理、工业视觉、模式识别和流程仿真等研究。cinf_zxj@163.com

通讯作者:
鄢锋(1981-),正高级工程师,研究方向为智能矿山、重有色金属冶炼领域智能工厂关键技术研究。cinf_yf@163.com

计量
- 文章访问数: 106
- HTML全文浏览量: 12
- PDF下载量: 7
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-05
- 网络出版日期: 2023-12-25

MONITORING METHODS AND THEIR APPLICATION OF FLOWING WATER POLLUTION BASED ON INTELLIGENT VISION

1. CINF Engineering Co., Ltd., Changsha 410019, China;
2. School of Automation, Central South University, Changsha 410083, China

摘要

摘要: 工矿企业生产过程中不可避免地产生各类污染，其中水污染物排放始终是监控与防治的重要工作。当前工矿企业所采用的传统监控手段如视频或在线设备监控，存在应对突发性水污染事故适应性弱、效率低、成本高、准确性差等问题。针对流动性水体图像连续、动态、全前景、无背景的特点，采用深度学习算法建立动态加权灰度化模型优化彩色图像灰度处理，提出了图像光强信息（灰度值）分析方法；结合时/空间连续图像信息自检方法对水体图像进行在线分析，提出了1种通用水体污染监控方法，开发了基于智能视觉的动态水体污染监控系统，实现了污染状态的高效、准确的定性判断。在工矿企业投用该系统后，运行维护简便，相对于传统人工视频污染监控方式，污染识别准确率提高13%，有效识别率达到99%以上，平均污染识别时间减少3~5 h，实现突发性水污染事故快速响应，大幅降低环保事故发生率；且能够有效降低人员劳动强度，节约企业运营成本。
- 动态水体 /
- 动态优化 /
- 深度学习 /
- 动态加权 /
- 图像分析
Abstract: All kinds of pollutants are inevitably produced in the production process of industrial and mining enterprises, among which the discharge of water pollutants has been always an important work of monitoring and prevention. The traditional monitoring methods adopted by current industrial and mining enterprises, such as video or online equipment monitoring, are often weak in adaptability to the randomness, contingency, and uncertainty of sudden water pollution accidents, and have problems such as low efficiency, high cost, and poor accuracy. Combined with the time/space continuum image information self-check method to analyze the water image online, a universal water pollution monitoring method was proposed, and a dynamic water pollution monitoring system based on intelligent vision was developed, to realize the efficient and accurate qualitative judgment of the pollution state. After the industrial and mining enterprises put the system into use, the operation and maintenance were simple. Compared with the traditional manual video pollution monitoring method, the pollution identification accuracy was increased by 13%, the effective recognition rate was more than 99%, the average pollution identification time was reduced by 3 to 5 hours, the rapid response of sudden water pollution accidents was realized, and the incidence of environmental protection accidents was greatly reduced. This method can effectively reduce the labor intensity of personnel, and save enterprise operating cost.
- dynamic water /
- dynamic optimization /
- deep learning /
- dynamic weighting /
- image analysis

HTML全文

参考文献(26)

[1]	戴胜利, 段新.突发性水污染事件污染传导类型研究[J].环境保护科学, 2019, 42(2):107-112.
[2]	沈一凡.河流突发污染事故溯源关键技术研究[D].杭州:浙江大学, 2019.
[3]	王家彪, 河渠突发水污染溯源反问题研究[D].北京:清华大学, 2020.
[4]	王运鑫, 基于模糊贝叶斯网络的突发水污染事故风险评价研究[D].兰州:兰州交通大学, 2018.
[5]	冯强, 易境, 刘书敏, 等.城市黑臭水体污染现状、治理技术与对策[J].环境工程, 2020, 38(8):82-88.
[6]	陈卓然, 李思羽, 杨泽群.水质在线监测系统在二次供水设施管理中的应用[J].天津科技, 2021, 48(7):107-108.
[7]	兰翔.自动化监测技术在水质检测中的应用与研究[J].能源与环保, 2021, 43(7):269-274.
[8]	王先平.水污染控制工程中的水质参数在线监控[J].环境与开发, 1999, 14(2):38-40.
[9]	钱晓明, 谢康林.基于模糊PID控制的自动加矾系统[J].计算机工程, 2004, 30:445-447.
[10]	周小四, 杨杰, 朱一坦.用于监控智能报警系统的图像识别技术[J].上海交通大学学报, 2002, 36(4):498-501.
[11]	张便利, 常胜江, 李江卫, 等.基于彩色直方图分析的智能视频监控系统[J].物理学报, 2006(12):6399-6404.
[12]	刘鑫, 王忠, 秦明星.多机器人协同SLAM技术研究进展[J].计算机工程, 2022, 48(5):1-10.
[13]	陈学磊, 张品, 权令伟, 等.融合深度学习与成像模型的水下图像增强算法[J].计算机工程, 2022, 48(2):243-249.
[14]	HOU Q, CHENG M, HU X, et al.Deeply supervised salient object detection with short connections[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(4):815-828.
[15]	SANZANA M R, MAUL T, WONG J Y, et al.Application of deep learning in facility management and maintenance for heating, ventilation, and air conditioning[J].Automation in Construction, 2022, 141:1-13.
[16]	HAHNEL P, MARECEK J, MONTEIL J, et al.Using deep learning to extend the range of air pollution monitoring and forecasting[J].Journal of Computational Physics, 2020, 408:1-13.
[17]	SINGHA S, PASUPULETI S, SINGHA S S, et al.Effectiveness of groundwater heavy metal pollution indices studies by deep-learning[J].Journal of Contaminant Hydrology, 2020, 235:1-18.
[18]	CHEN H Z, CHEN A, XU L L, et al.A deep learning CNN architecture applied in smart near-infrared analysis of water pollution for agricultural irrigation resources[J].Agricultural Water Management, 2020, 240:1-8.
[19]	WAN H, XU R, ZHANG M, et al.A novel model for water quality prediction caused by non-point sources pollution based on deep learning and feature extraction methods[J].Journal of Hydrology, 2022:1-34.
[20]	刘华玲, 马俊, 张国祥.基于深度学习的内容推荐算法研究综述[J].计算机工程, 2021, 47(7):1-12.
[21]	尹根.基于IEC61850标准的智能变电站通信接口的研究与设计[D].株洲:湖南工业大学, 2019.
[22]	张晓瑜.基于改进深度信念网络的时间序列预测方法及负荷预测应用研究[D].长沙:国防科技大学, 2018.
[23]	李正权, 林媛, 李梦雅, 等.基于判别式受限玻尔兹曼机的数字调制识别[J].通信学报, 2021, 42(2):81-91.
[24]	张春祥, 李海瑞, 高雪瑶.一种受限玻尔兹曼机的词义消歧方法[J].哈尔滨理工大学学报, 2019, 24(5):116-121.
[25]	陈亚宇, 李建龙, 孙骥晟, 等.基于机器视觉的填埋场防渗层破损识别方法[J].环境工程, 2021, 39(8):136-149.
[26]	翟嘉琪, 杨希祥, 程玉强, 等.机器学习在故障检测与诊断领域应用综述[J].计算机测量与控制, 2021, 29(3):1-9.