针对黄河水量统一调度工作中,中上游河段出现的水量不平衡问题,以刘家峡—头道拐河段为例,采用水量平衡公式计算1999~2012年刘家峡—头道拐河段的不平衡水量,并运用BP神经网络技术和方法研究了刘家峡—头道拐河段不平衡水量的变化规律,预测了刘家峡—头道拐河段的不平衡水量。结果表明,BP神经网络模型预测效果较好、精度较高。 In view of the unbalanced water volume in the middle and upper reaches of the Yellow River, a case study of Liujiaxia-Shandaohe Reach was used to calculate the imbalanced water amount from 1999 to 2012 The variation law of the unbalanced water volume in Liujiaxia - Toudangui Reverberation section was studied by BP neural network technology and method, and the imbalanced water volume of Liujiaxia - Toudaoai river section was predicted. The results show that BP neural network model has better prediction effect and higher accuracy.