Abstract: In order to make the assessment of the health condition of the bridge tower and the prediction of its remaining lifespan more convenient and secure,based on the existing evaluation methods,a series of analysis methods based on cracks-analytic hierarchy process-fuzzy comprehensive evaluation (C-AHP-FCE) were established in this paper,with a certain large-span cable-stayed bridge as the engineering background.The method combined multi-scale finite element modeling and analytic hierarchy process,and non dimensional processing of crack characteristic parameters.Subsequently,it assessed the impact of these parameters on the bearing capacity of the tower bridge,calculated the crack influence coefficient,and modified the bottom scale of the fuzzy analytic hierarchy process,which then enabled further assessment and judgment of the overall condition of the bridge tower.Subsequently,based on the C-AHP-FCE analysis method,seven different fuzzy operators were used to modify the final rating of the bridge tower.This helped mitigate subjective errors in the evaluation process.Additionally,a GA-BP neural network model was established to predict the rating of the bridge tower.The combination of the GA-BP neural network model and the probability transition matrix based on the Markov Chain was used to establish the bridge tower lifespan prediction model.The results indicated that compared to the prediction results using a single fuzzy operator,the GA-BP-MC combined model analysis method was more accurate,providing a reliable reference for the maintenance and upkeep of the bridge tower/>