The prediction of pollution emission from a combined heat and power (CHP) system is very important for the production regulation and emergency response of a power system. The composition and structure of the CHP equipment are complex, and the production process is cumbersome. The fuel chemical reaction of the pulverized coal in the boiler represents a highly nonlinear and strongly interrelated process that is strongly affected by external environmental factors, which causes a certain level of volatility and uncertainty. In this study, a pollution emission prediction method of CHP systems based on feature engineering and a hybrid deep learning model is proposed. Feature engineering performs multi-step preprocessing on the original data, refines the correlation factors, and removes redundant variables. The hybrid deep learning model has a multi-variable input and is established by combining the convolutional neural network-long short-term memory network with the attention mechanism. The case study is conducted on the collected actual dataset. The influence of the prediction target periodicity on the prediction results is analyzed seasonally to verify the effectiveness of the hybrid model. The results show that the root mean square error of the proposed method is less than one, and the error is reduced compared to the other basic methods, which proves the superiority of the proposed pollution emission prediction method over the existing methods.