量子电子学报 ›› 2026, Vol. 43 ›› Issue (2): 227-236.doi: 10.3969/j.issn.1007-5461.2026.02.006

• 先进光电检测与量子技术 • 上一篇    下一篇

水质化学需氧量高精度快速检测系统 (特邀)

刘婉婷 1, 罗丹妮 1, 张宇煊 1, 王浩然 1, 邓 俊 1, 姜 浩 1, 李美欣 1, 张赞允 1,2*   

  1. 1 天津工业大学电子与信息工程学院, 天津 300387; 2 天津工业大学, 天津市光电检测技术与系统重点实验室, 天津 300387
  • 收稿日期:2025-09-11 修回日期:2025-12-08 出版日期:2026-03-28 发布日期:2026-03-28
  • 通讯作者: E-mail: zhangzanyun@tiangong.edu.cn E-mail:E-mail: zhangzanyun@tiangong.edu.cn
  • 作者简介:刘婉婷 ( 2001 - ), 女, 河南周口人, 研究生, 主要从事机器学习方面的研究。E-mail: 2331081083@tiangong.edu.cn
  • 基金资助:
    国家自然科学基金 (62341508, 62575276), 天津市光电检测技术与系统重点实验室开放课题 (2024LODTS104)

High‑precision rapid detection systemfor chemical oxygen demand in water (Invited)

LIU Wanting 1 , LUO Danni 1 , ZHANG Yuxuan 1 , WANG Haoran 1 , DENG Jun 1 , JIANG Hao 1 , LI Meixin 1 , ZHANG Zanyun 1,2*   

  1. 1 School of Electronics and Information Engineering, Tiangong University, Tianjin 300387, China; 2 Tianjin Key Laboratory of Optoelectronic Detection Technology and System, Tiangong University, Tianjin 300387, China
  • Received:2025-09-11 Revised:2025-12-08 Published:2026-03-28 Online:2026-03-28

摘要: 化学需氧量 (COD) 作为衡量水体污染的重要指标, 传统的化学检测方法存在操作繁琐、周期长以及二次污染等问题。本文提出了一种基于双光源传感器的 COD 测量新方法, 该方法通过实验室配置水样, 利用 255 nm 和265 nm双紫外光源进行水质检测, 并结合随机森林 (RF) 模型对COD值进行预测。实验结果表明, RF模型测试集的决定系数R2 达到0.9910, 均方根误差ERMS仅为0.0804, 展现出其在COD预测中的优越性能。相较于传统光谱仪, 本研究实现了双光源传感器设备的轻量化, 并在显著降低硬件成本的同时, 显著提升了COD检测的实时性, 为水质在线检测提供了高效的技术支持。

关键词: 紫外-可见光谱, 化学需氧量, 朗伯-比尔定律, 随机森林

Abstract: Chemical oxygen demand (COD) is an important indicator for measuring water pollution, however, traditional chemical detection methods suffer from complicated operations, long durations, and secondary pollution. This paper presents a new COD measurement method based on a dual-light source sensor. The method involves preparing water samples in the laboratory, using dual ultraviolet light sources of 255 nm and 265 nm for water quality detection, and predicting COD values using a random forest (RF) regression model. Experimental results show that the coefficient of determination R2 of the test set for the RF regression model is 0.9910, and the root mean square error (ERMS) is only 0.0804, demonstrating the superior performance of the model in COD prediction. Compared to traditional spectrometers, the designed dual-light source sensor significantly achieves lightweight, reduces hardware costs and enhances the real-time performance of COD detection, providing efficient technical support for online water quality monitoring.

Key words: UV-Vis spectroscopy, chemical oxygen demand, Lambert-Beer law, random forest

中图分类号: