【摘要】 为优化泵站的工作方式,降低能耗,建立一种基于长短期记忆网络(Long Short-Term Memory,LSTM)的神经网络模型来对泵站的能耗进预测,优化学习率、时间步长、批处理、隐含层层数、训练次数等参数。将LSTM网络模型的预测结果与BP模型、RNN模型进行对比,研究结果表明,基于LSTM神经网络模型的预测具有较高的精度和泛化能力。更多还原

【Abstract】 A neural network model based on Long Short-Term Memory(LSTM) is established to predict the energy consumption of pumping stations,which optimizes the working methods and reduces energy consumption,and the learning rate,time step,batch size,the number of layers,training times are optimized.The prediction results of the LSTM network model are compared with the BP model and the RNN model,and the research results show that the prediction based on the LSTM neural network model has high accuracy and generalization ability.更多还原