As a key facility for energy conversion

coal-fired units still occupy an important position in power production. However

their complexity significantly increases the difficulty of predicting carbon dioxide emissions. A carbon dioxide emission prediction model is proposed in the paper. This model combines principal component analysis with backpropagation neural network. Firstly

methods such as missing value processing and outlier processing are used to preprocess the data related to carbon emissions of coal-fired power plants. Then

variables with strong correlation to carbon emissions are screened out through correlation analysis. Combined with the principal component analysis method

the data dimension is further reduced on the premise of ensuring that key information is not lost

and a carbon dioxide emission prediction model for coal-fired power plants is constructed. Taking a coal-fired generator set with an installed capacity of 660 MW as an example

simulation verification is carried out based on its operating parameters. The prediction results show small errors and good fitting effects. This shows that this model can effectively predict carbon dioxide emissions and can provide a reference for carbon dioxide emission reduction in coal-fired power plants.