In this paper, in order to improve the existing lightning strike fault identification accuracy, a lightning strike fault identification model for distribution grid overhead lines based on adaptive weighting strategy enhanced sparrow search algorithm optimized support vector machine (SVM) is proposed. Firstly, the lightning strike types of distribution overhead lines are clarified and their characteristic differences are analyzed. Second, the transient current data of different fault types are obtained through PSCAD simulation, and the key feature quantities are extracted as model inputs. Then, an adaptive weighting strategy is introduced to improve the sparrow search algorithm and enhance its search capability, and then the penalty factor and kernel function parameters of SVM are optimized using the improved algorithm to construct the AWS-SSA-SVM recognition model. Finally, the performance of the model is verified by example analysis, and the results show that the combined correct rate of the model for the identification of short-circuit faults, non-fault lightning strikes, winding faults, counter-strike faults and induced lightning reaches 97%, which is better than that of the other models, proving its correctness and practicability, and providing an effective method for the accurate identification of lightning faults in distribution networks.