This paper proposes a single building damage assessment method based on improved genetic algorithm optimized back propagation(BP)neural network,after reviewing the latest research progress in machine learning algorithms. Taking the Sichuan area as an example,the improved genetic algorithm optimized BP neural network is used to establish an assessment model and to output the damage levels of single buildings with different structural types in the assessment area under the combined effect of various seismic damage influencing factors. The validity of the model is verified through the analysis of practical examples,and the results show that the method can quickly and accurately assess the seismic damage of single buildings.