Thermal power plant condenser vacuum degree prediction method based on multi-layer LSTM

Abstract

The invention provides a thermal power plant condenser vacuum degree prediction method based on multilayer LSTM. Firstly, a sample data set is constructed, input data and output data in a sample are subjected to standardization processing respectively, then the input data sequentially enter a multi-layer long-short-term memory neural network, and model training is performed by using an adaptive moment estimation algorithm; and finally, to-be-predicted data is input into the trained prediction model, and the vacuum degree of the condenser is predicted. According to the method, the long-term andshort-term memory neural network structure is applied to condenser vacuum degree analysis, deep mining of big data is achieved, the accuracy and speed of data prediction are improved, and use of system resources is optimized. According to the two-layer LSTM structure designed by the invention, the model depth can be increased, the model capacity can be increased, the prediction precision can be improved, and meanwhile, the adaptive moment estimation algorithm is used for optimizing the traditional gradient descent algorithm, so that the problem of gradient explosion is avoided.

Description

technical field [0001] The invention relates to the fields of thermal power plant equipment operation optimization and power grid peak regulation assistance, and more specifically, a method for predicting the vacuum degree of a thermal power plant condenser based on a multi-layer long-short-term memory neural network. Background technique [0002] As the cold source of the thermal cycle of the thermal power plant, the performance of the condenser in a thermal power plant directly affects the peak-shaving capability, operational safety, and thermal economy of the unit. The vacuum degree of the condenser is an index that comprehensively reflects the operating state of the condenser. Accurate prediction of the vacuum degree of the condenser will not only help the power grid company to reasonably arrange power generation of the power plant, optimize the allocation of local power resources, and improve the coordination level of the machine network, but also Help power plants opti...

AI Technical Summary

Problems solved by technology

However, with the increase of data volume and input data dimension, on the one hand, the machine learning model has obvious deficiencies in computing speed and mining depth, mainly manifested in over-adjustment of hyperparameters during training, slow training speed, and poor generalization ability of the model; On the one hand, the existing prediction models do not take into account the relationship between the vacuum degree of the condenser in the time series, so there is a lack of modeling research to improve the prediction effect by mining the time series relationship

Images