Based on Process Neural Network Learning Algorithm for Prediction of Urban Water Consumption

For urban water consumption characteristics of the process will be applied to the neural network model for forecasting urban water demand. Describes the process of feed-forward neural network model and the feedback process neural network model; study of weight function based on orthogonal basis started learning algorithm, and describes the specific steps of the algorithm; drawn flowchart of urban water consumption forecast, according to the relevant historical data the training process of neural network model to analyze the data value prediction to generate predicted data and actual data of the fitting curve. The results showed that the process of neural network model for forecasting urban water demand has a certain theoretical and practical value.