Power station boiler coal ash generation amount online prediction method and system based on LSTM

Abstract

The invention discloses a power station boiler coal ash generation amount online prediction method and system based on LSTM. The method comprises the steps that the boiler coal ash generation amount and historical data of main influence parameters are collected to obtain incidence relation data, and normalization processing is conducted on the incidence relation data; dividing the incidence relation data after normalization processing into a training set and a test set; performing training fitting on a pre-established boiler coal ash generation quantity LSTM network model by using the data in the training set; combining the prediction data with the data in the test set, and performing overfitting evaluation on the boiler coal ash generation quantity LSTM network model after training and fitting; and sampling the current generated data on line, inputting the boiler coal ash generation quantity LSTM network model without overfitting, and predicting the boiler coal ash generation quantity value in the future time. Required data can be recorded for a long time, online prediction can be achieved, the prediction period is long, precision is high, and the requirement of power generation enterprises for dynamic prediction of the boiler coal ash generation amount is met.

Description

technical field [0001] The invention belongs to the technical field of solid waste monitoring, and in particular relates to an LSTM-based on-line prediction method and system for coal ash generation amount of a power station boiler. Background technique [0002] When coal is used as fuel in thermal power plants, the boiler will produce a large amount of coal ash after burning coal. Part of the coal ash (fly ash) in the flue is collected by dust removal for comprehensive utilization, and the other part is discharged into the atmosphere with the flue gas through the chimney. With the improvement of national environmental protection requirements, the coal ash emission indicators produced by boilers are undoubtedly becoming more and more strict, which requires power generation enterprises to accurately control the operation of coal ash emissions from boilers. The amount of coal ash produced by traditional boilers is given in the design stage based on the maximum / minimum operati...

AI Technical Summary

Problems solved by technology

The former is not comprehensive and has large errors; the latter formula needs to be matched with different boiler types and fuel types because the Q4 coefficient is an empirical value. The calculation is cumbersome and complicated, and there are many inconveniences in practical application.

[0004] Due to various factors such as different boiler forms, operating environment (combustion mode, flue gas flow rate, furnace heat load, boiler operating load, etc.) and coal quality, the generated coal ash presents complex changing characteristics, so that the amount of coal ash does not vary. It is a generally applicable online calculation model, and it is difficult to accurately predict it

Images