Multi-loop quasi-diagonal recurrent neural network PID control method for urban solid waste incineration process

Abstract

The invention designs a multi-loop quasi-diagonal recurrent neural network PID control method for an urban solid waste incineration process, and aims to solve the problems of multivariable coupling and difficult synchronous control of urban solid waste incineration. Firstly, model influence factors are analyzed, and key controlled variables and operation variables are extracted; then, a multi-input multi-output Takagi-Sugeno fuzzy neural network controlled object model is constructed based on a data driving method; then, constructing a quasi-diagonal recurrent neural network model with a self-feedback channel and an interconnection channel, and applying the quasi-diagonal recurrent neural network model to parameter self-tuning of the multi-loop PID controller; and finally, the feasibility and effectiveness of the controller are verified through experiments. A solution is provided for improving the intelligent degree of the urban solid waste incineration process and meeting the actual industrial control requirement.

Description

technical field [0001] Aiming at the problem of multi-variable coupling and difficulty in synchronous control of urban solid waste incineration, the present invention designs a multi-loop quasi-diagonal recurrent neural network PID controller for the urban solid waste incineration process. The controller analyzes the influencing factors of the model and extracts Based on the key controlled quantities and operation quantities, a multi-input and multi-output Takagi-Sugeno fuzzy neural network controlled object model was constructed based on data-driven, and a quasi-diagonal recurrent neural network model with self-feedback channels and interconnecting channels was constructed and applied to it. The parameter self-tuning used for multi-loop PID control solves the multi-variable control problem in the process of urban solid waste incineration. Background technique [0002] Urban solid waste incineration has become one of the main ways to dispose of urban solid waste due to its a...

AI Technical Summary

Problems solved by technology

However, in the face of the municipal solid waste incineration process with many uncertain characteristics such as multi-object, multi-variable, and strong coupling, only a single-loop PID controller cannot meet the control requirements of synchronously controlling multiple controlled quantities.

Images