Ultra supercritical unit high temperature superheater wall temperature prediction method based on neural network

Abstract

The invention belongs to the field of power plant safety control systems, and particularly relates to an ultra supercritical unit high temperature superheater wall temperature prediction method basedon a neural network. The ultra supercritical unit high temperature superheater wall temperature prediction method based on the neural network is characterized by comprising the following steps of (1)building a temperature measuring system; (2) utilizing a back propagation algorithm for predicting, building a neural network structure, preprocessing data, building a training model, and obtaining aprediction model; (3) after standardizing a validation set, bringing into the trained prediction model, carrying out model measurement on the data, finally obtaining a prediction value of the validation set, comparing the prediction value of the validation set with an actual value of the validation set, and obtaining a residual error; and (4) utilizing guiding fault early warning. A hearth inner wall temperature prediction model is built by adopting a BP neural network, the potential faults of the equipment are further identified, and the state prediction of unconventional monitoring equipmentsuch as a high-temperature superheater is realized.

Description

technical field [0001] The invention belongs to the field of power plant safety control systems, and in particular relates to a method for predicting the wall temperature of a high-temperature superheater of an ultra-supercritical unit based on a neural network. Background technique [0002] Tube burst in superheater of large thermal power unit is one of the important reasons for unplanned shutdown. The causes of superheater tube bursting are very complicated, mainly including: (1) superheater tubes are operated at high temperature for a long time, and the inner wall of the tube produces scale, which accumulates at the elbow of the tube and causes tube bursting; (2) superheater tubes are exposed to high temperature for a long time (3) The pipe wall is frequently overheated for a short time during the operation of the unit, which reduces the design life and safety margin of the pipe; (4) The temperature distribution of the pipe row and pipe section along the width and depth o...

AI Technical Summary

Problems solved by technology

It involves temperature prediction, but the disadvantage is that the prediction error is large, which has a great impact on subsequent control

Images