水电能源科学

水电站的尾水水位是计算机组出力的重要参数，当存在下游水库顶托影响时，电站尾水的设计曲线与实际观测值往往存在较大误差，增加了机组出力—流量的计算误差。为此，根据最新历史观测数据，分析了BHT水电站尾水水位与其出库流量及下游水库XLD顶托水位的关系，建立了基于多情景划分的贝叶斯优化-长短期记忆网络(BO-LSTM)预测模型，并分析了调峰和泄洪工况下模型的应用效果。结果表明，XLD水位高于585 m后对BHT电站的尾水水位有显著的顶托影响。相比于水位—流量曲线和非线性曲线拟合方法，基于多情景划分的BO-LSTM模型在精度上有显著提升，平均绝对误差(M_MAE)降低了68.1%。BO-LSTM模型在多种工况下均能更准确地捕捉水位的起伏变化过程。研究结果对水电站精细化调度具有重要意义。

The tailwater level of hydropower station is a critical parameter for calculating the unit's output. When influenced by the downstream reservoir's backwater effect, discrepancies often arise between the designed tailwater curve and the actual observed values, leading to increased errors in the output-flow calculations. Utilizing the latest historical observation data, this study explores the relationship between the tailwater level of BHT Hydropower Station, its discharge, and the water level of the downstream XLD Reservoir. A Bayesian optimized long short-term memory(BO-LSTM) prediction model is developed based on multi-scenario analysis. The applied effect is analyzed under conditions of peak load and flood discharge. The results indicate that when the water level of XLD exceeds 585 meters, the tailwater level of BHT Hydropower Station is significantly influenced. Compared to the nonlinear curve fitting method, the BO-LSTM model based multi-scenario analysis demonstrates a substantial improvement in accuracy, with an average absolute error(M_MAE) reduced by 68.1%. The BO-LSTM model more accurately captures the fluctuations and changes in water levels under various operating conditions. The research results have important significant for refined operation of hydropower stations.