Method for predicting and controlling awater level of a series water conveyance canal on a basis of a fuzzy neural network

A method for predicting and controlling a water level of a series water conveyance canal on a basis of a fuzzy neural network, comprising the following steps:

• S1, generating a one-dimensional hydrodynamic model, generating different upstream water level change processes by changing sluice opening degree in the one-dimensional hydrodynamic model, saving the sluice opening degree and upstream water level data,
• establishing a multi-input single-output fuzzy neural network with four layers of a forward topology connection form, and training the multi-input single-output fuzzy neural network based on operation data of the series water conveyance canal and the sluice opening degree and the upstream water level data, so as to obtain a fuzzy neural network prediction model that can perform prediction on the water level of a canal pool based on a sluice opening degree value and an initial water level;
• S2, constructing an upstream water level controller of a coupled predictive control algorithm based on the fuzzy neural network prediction model in step S1;
• S3, solving an optimal control rate of the upstream water level controller using a gradient optimization algorithm based on a control target of the upstream water level controller constructed in step S2;
• and
• S4, generating a control strategy by collecting actually measured water level change information and multiplying the actually measured water level change information by the optimal control rate, based on the optimal control rate solved in step S3, and controlling the water level of the series water conveyance canal based on the control strategy.