The invention discloses an insulator flashover voltage prediction method based on support vector machine regression. The insulator flashover voltage prediction method comprises the steps: calculatinga characteristic parameter value distributed along a surface electric field, and recording the characteristic parameter value as an input; calculating the flashover voltage of the test insulator sample and the corresponding breakdown probability, and recording the flashover voltage and the corresponding breakdown probability as output; preprocessing input and output data; classifying the preprocessed data into training set data and test set data; inputting the training set data into a support vector machine regression model for training, and performing optimization processing in the training process to obtain the support vector machine regression model with an optimal training result; and inputting the input data of the test set into the support vector machine regression model with the optimal training result for verification, and predicting the insulator flashover voltage by using the verified model. The insulator flashover voltage prediction method is simple in prediction process andhigh in prediction accuracy, is helpful for guiding and optimizing insulator gas-solid insulation structure, and improves the economy and reliability of the gas insulation equipment.