The accurate prediction and evaluation of coal combustion heat is an important basis for coal quality analysis and thermal engineering calculation. In this paper, for the problem that the oxygen bomb calorimetry method does not have real-time monitoring of coal quality changes, a coal-fired calorimetric prediction method by the bionic algorithm FA-GA jointly optimized BP neural network is proposed. The industrial analysis and elemental analysis data of 774 groups of coal commonly used in coal-fired boilers are preprocessed, and the characteristic variables of coal quality indexes are screened according to the average influence value, and the heat generation prediction model of FA-GA-BP is finally established, and the optimization algorithm's optimization-seeking ability and model prediction accuracy are tested in terms of error evaluation index and iteration number. The results show that the prediction accuracy of the model is improved to 0.9561 after the feature variable screening; the number of iterations of the joint FA-GA algorithm is significantly reduced compared with the single optimization algorithm FA, GA and PSO, and the global search ability of the algorithm is effectively improved; the FA-GA-BP model is compared with the single optimization models FA-BP, GA-BP, PSO-BP and the current commonly used heat generation The FAGA- BP model has higher accuracy and the correlation coefficient can reach 0.9845 compared with the single optimization models, such as FA-BP, GA-BP, PSO-BP and the currently used heat generation models, MLR and SVR, and can provide a new method to effectively monitor the real-time changes of incoming coal quality.