Subspace identification based forecasting method for superheated steam output of boiler of firepower power station

Abstract

The invention discloses a subspace identification based forecasting method for superheated steam output of a boiler of a firepower power station, which comprises the following steps: firstly, acquiring production data from plant-level DCS (Distributed Control System) configuration software at regular time; secondly, correcting bad points, filtering and denoising; thirdly, calculating input and output variables required by model identification; fourthly, constructing an Hankel matrix by utilizing continuous acquired and processed data and rolling to update; fifthly, approximating the boiler process to a linear state space model; sixthly, using a subspace theory to identify a matrix of the state space model [A, B, C and D]; seventhly, utilizing the latest input energy information as the obtained input variables of the state space model after the identification and calculating output energy of future moments; eighthly, calculating the mean value at the same time by utilizing a historical forecast value and a current forecast result and correcting by utilizing the past forecast deviation; and ninthly, rolling to update the data of identification of the model. The forecasting method is applicable to online forecast of superheated steam output energy in the boiler production process and provides guidance and reference for the optimization control of boiler combustion.

Description

technical field [0001] The invention relates to a method for forecasting superheated steam output by thermal power plant boilers based on subspace identification. Background technique [0002] The goal of boiler combustion optimization control is to obtain high-efficiency superheated steam output energy and a stable and safe operating state by adjusting the operating parameters of the boiler such as coal feeding, air distribution, and induced air under a certain unit load. The transfer of energy from coal feed to superheated steam is a very complex production process, and it is difficult to determine the model structure and model parameters when using mechanism modeling. Therefore, more research is currently focused on data-driven black-box models or half-mechanism and half-data gray boxes Model. At present, the boiler modeling methods based on data-driven mainly include artificial neural network and support vector machine. For example, the modeling method for boiler combu...

AI Technical Summary

Problems solved by technology

However, this method only establishes the static correlation between the various operating data of the boiler. If the production site encounters a special working condition of load fluctuation, the hybrid model may constantly switch between the neural network and the support vector machine, which cannot guarantee The continuity of the process data required for model identification, the dynamic accuracy is low

In addition, the measurement points of the primary air / secondary air flow and induced air flow used in the above method do not consider the influence of temperature and pressure information, so the application of the built model will also be affected by seasons and climate

Images