武大AiFlow视觉测流技术在南水北调中线工程渠首陶岔水文站的应用研究

Wuhan University’s AiFlow Visual Flowmeter Technology: An Application Study at the Taocha Hydrological Station of the South-to-North Water Diversion Project’s Middle Route Headworks

摘要: 南水北调中线调水主干渠陶岔出水口的流量监测数据，对于丹江口水库水资源跨流域水量调度具有重要意义。本文将武大AiFlow视觉测流产品在陶岔水文站应用，针对陶岔水文站复杂水流流态和夜间光线不足的问题，提出了多算法融合策略和夜间补光方案。研究结果表明：基于多算法融合策略可提高视觉测流流量测验精度，通过一定角度红外补光及特定相机可提高相机在夜间对水面纹理的捕捉能力，视觉测流换算流量与ADCP实测流量相比，相对误差在±7%以内。

Abstract: The flow monitoring data of the Taocha outlet of the main channel of the South-to-North Water Diversion Project is of indispensable importance for the water resources allocation of Danjiangkou Reservoir. In this paper, Wuhan University’s AiFlow visual flowmeter product is applied at the Taocha hydrological station. A multi-algorithm fusion strategy and nighttime light supplement scheme were proposed to address the complex flow regime and insufficient nighttime light at the Taocha hydrological station. The results show that based on the multi-algorithm fusion strategy, the accuracy of visual flowmeter can be improved, and through infrared light supplement at a certain angle and specific cameras, the ability of the camera to capture water surface texture at night can be improved. Compared with that of the ADCP measured flow, the relative error of the visual flowmeter conversion flow is within ±7%.