Prediction of breakdown voltage of transformer oil facilitates the early fault diagnosis, prevention and treatment of transformer. In this article, a prediction method of breakdown voltage via multi-parameter correlation was proposed considering the lack of research in this field. Through examining the routine monitoring data of transformer oil by gray correlation analysis, some parameters which have strong correlation with breakdown voltage were excavated, then a relational model of breakdown voltage and those parameters was further constructed using back-propagation neural network, since BP neural network has prominent fault-tolerant, non-linear approximation, and self-learning capabilities. The clustering centers which were used to train network were acquired through clustering the original monitoring data samples with fuzzy C-means clustering algorithm. The adoption of this method can resolve natural problems of neural networks caused by large sample capacity, such as complication of net construction, inferior astringency, poor generalization ability, and so on. Test results show that the precision of the prediction model is high and that the relative prediction errors of test samples are all less than 10%, which indicates the significant practical value of the model.