An Estimation Method of Pick Distance Based on Artificial Neural Network

Abstract

The invention discloses a pick distance estimation method based on artificial neural network, comprising the following steps: (1) taking H , θ , q The input amount and the water tongue distance are the output quantities, and an integrated neural network system with appropriate input and output is constructed, and the forward neural network with the input layer, hidden layer, and output layer structure is selected to realize the modeling of the water tongue distance; (2) collect data , and preprocess the samples; (3) On the basis of the neural network model obtained in step (1) and the learning samples obtained in step (2), for each group of learning samples, sample the BP algorithm to train the neural network to obtain the individual network The optimal model parameters and their weights, and integrate the individual network; (4) the measured H , θ , q As an input quantity, it is input to the integrated neural network trained in step (3), and the size of the pick distance can be estimated. The present invention has the characteristics of simple and effective implementation by estimating the size of the pick distance based on the artificial neural network, and effectively improves the estimation accuracy.

Description

technical field [0001] The invention relates to a pick distance estimation method based on an artificial neural network, and belongs to the field of hydraulic engineering. Background technique [0002] Due to the simple structure, high energy dissipation rate and convenient construction, the flow deflecting energy dissipation is widely used in water conservancy and hydropower projects. The position of the downstream flushing pit for draught and energy dissipation is closely related to its water tongue pick distance. In engineering design, the pick distance is generally required to be more than 3-4 times the depth of the maximum flush pit, which is an important hydraulic parameter for the safety of drainage structures. The estimation methods of the distance mainly include theoretical derivation, empirical formula (non-linear regression analysis on the data of the model test) and numerical simulation. Although researchers have done a lot of research work on the estimation of ...

AI Technical Summary

Problems solved by technology

Although the researchers have done a lot of research work on the estimation of the water tongue pick distance from various angles, and have also proposed various forms of formulas, these formulas are all based on the prototype conditions under widely varying conditions when making estimates. Similar to idealization, averaging, and approximate processing, etc., resulting in large deviations between the results and the prototype

Images