Coal-fired boiler exhaust gas temperature prediction method and system based on LightGBM and random search method

Abstract

The invention discloses a coal-fired boiler exhaust gas temperature prediction method and system based on a LightGBM and a random search method, and solves the problems that an existing neural network model is liable to fall into a local minimum value and is liable to over-fit, and a support vector machine model is not suitable for large sample learning. The method comprises the steps of collecting historical operation data, performing data cleaning and normalization, performing feature selection according to mutual information entropy, constructing a model by adopting a LightGBM algorithm, optimizing hyper-parameters by adopting a random search algorithm, and obtaining an optimal model for verification application. According to the method, the LightGBM and the random search algorithm are adopted to establish and optimize the prediction model, the overfitting phenomenon is effectively prevented, the model generalization ability is excellent, a large sample learning strategy is supported, training is more efficient, the calculation speed is higher, lower model deviation can be achieved, meanwhile, the random search algorithm is combined, an optimal hyper-parameter combination is found, and the prediction accuracy is improved. The precision of the model is further improved, and a high-performance coal-fired boiler exhaust gas temperature prediction model is obtained.

Description

technical field [0001] The invention relates to the technical field of coal-fired boilers, in particular to a method and system for predicting the exhaust gas temperature of a coal-fired boiler based on LightGBM and random search method. Background technique [0002] Boiler efficiency is a key concern in the operation of coal-fired power plants, and is usually calculated by the back-balance method. Among them, the exhaust heat loss is the largest in the boiler heat loss, accounting for more than 80% of the boiler heat loss. For every 20 °C increase in the exhaust temperature of the coal-fired boiler, the exhaust heat loss increases by about 1%. [0003] The exhaust gas temperature is an operation index with very complex influencing factors, which is comprehensively affected by many factors such as coal type, coal quality, unit load, and combustion operating conditions. my country's coal-fired power stations usually use the method of blending coal and co-firing. Therefore, e...

AI Technical Summary

Problems solved by technology

[0005] The present invention is mainly to solve the existing neural network and support vector machine models commonly used in the prediction of exhaust gas temperature, but the neural network model has defects such as easy to fall into local minimum, easy to overfit, etc., and the support vector machine model is not suitable for large The problem of sample learning provides a coal-fired boiler exhaust gas temperature prediction method and system based on LightGBM and random search method

Images