梯级水电工程水温累积影响预测方法探讨

An Approach to Prediction Method of Cumulative Impact of Water Temperature on the Cascade Hydropower Project

根据梯级水电规划环评的需要并结合规划阶段工作深度特点,探讨改进了规范方法中的水温经验预测方法。在规范推荐水温计算方法基础上,采用考虑梯级水电工程叠加影响的人工神经网络模型,构造了"三层人工神经网络模型-统计方法-朱伯芳法-东勘院法"联合预测水温的综合经验模型。并将该模型应用到长江上游某规划河段,预测规划河段各梯级开发比选方案电站联合运行时,在典型水文年和典型气象条件下对河段水温时空分布规律的影响,以及规划河段末端梯级水温累积影响,同时可分析季调节以上性能大库容、深水型水库的水温分层现象及特点。

In this paper, according to the needs of the cascade hydropower planning and working with the depth features of planning stage, the experimental method of forecasting water temperature of the normative method is discussed. In this paper, in a regulated temperature calculation method recommended on the basis of considering cascade hydropower project superposition effects of artificial neural network model, constructed the “three-layered artificial neural network model; statistical methods , Zhu Bofang＇s methods and Northeast Investigation and Design Institute＇s methods” forecast the temperature comprehensive empirical model jointly. It can also forecast the impact of running joint-power station programs to the spatial and temporal distribution of the water temperature under the typical hydrological and meteorological conditions of each cascade development planning selection, as well as the accumulated impact of cascade water temperature in the end of the planning river section, and analyze the phenomena and characteristics of the layered water temperature of season-regulating reservoir with large quarter storage capacity or deep water.