Method for dynamically predicting drainage discharges at drainage outlets of urban rainwater system

Abstract

The invention discloses a method for dynamically predicting drainage discharges at drainage outlets of urban rainwater system. The method comprises the following steps of: (1) simulating a rainfall-runoff by utilizing a rainstorm flood management model pair, and taking drainage flow duration curves at outlets of a plurality of drainage pipe networks as training samples; (2) establishing an RBF neural network to carry out training, and in the training process, optimizing network hidden nodes and center widths Spread; (3) establishing an NARX neural network to carry out training; and (4) coupling the trained NARX neural network and the RBF neural network to obtain a coupled network, carrying out prediction, calculating mean square errors between the coupled network and the samples, returninga flow value with the minimum mean square error as an optimized coupling locus, randomly selecting rainfall data to input into the coupled network so as to obtain a predicted drainage flow duration curve. According to the method, advantages and characteristics of different neural networks are organically combined, the prediction results well accord with SWMM simulation, and the mean square errorsof the curves are 0.000458, so that favorable prediction precision is provided.

Description

technical field [0001] The invention relates to the technical field of urban rainwater resources management and drainage, in particular to a dynamic prediction method of drainage flow based on coupled radial basis neural network, nonlinear autoregressive model and numerical simulation. Background technique [0002] Storm Flood Management Model (SWMM) is a dynamic precipitation-runoff simulation model, mainly including runoff module, confluence module and water quality module, etc. It is mostly used to simulate a single precipitation event or long-term water quantity and water quality simulation in a city. The model can track and simulate the water quality and quantity of runoff produced by each sub-basin at any time at different time steps, as well as the flow, water depth and water quality of water in each pipeline and channel. SWMM model is widely used in urban drainage simulation. [0003] The radial basis function (RBF) neural network belongs to the type of forward neur...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above-mentioned problem in the prior art of "only using the method of neural network" that "it is difficult to realize the high-precision forecasting requirement of the dynamic drainage process", the present invention proposes a method to measure the drainage flow rate of the drainage outlet of the urban rainwater system. The dynamic prediction method realizes the outfall flow prediction of the non-linear dynamic drainage system based on the NARX-RBF coupling neural network

Images