Focusing on the issue that Principal Component Analysis-Bayes Discriminant Analysis (PCA-BDA) only supports safety evaluation but can not detect the dangerous factors, by introducing the concept of attribute importance degree, an improved PCA-BDA algorithm was proposed and applied to the petroleum drilling safety evaluation. Firstly, the safety ranking of each record was evaluated by the initial PCA-BDA algorithm. Secondly, the attribute importance was computed with the eigenvector matrix in PCA, the classification function coefficient in BDA, and the weight of safety ranking. Finally, the attributes were regulated and controlled with referencing the attribute importance. In the comparison experiments with Analytic Hierarchy Process (AHP) and Fuzzy Comprehensive Evaluation (FCE), the accuracy rate of improved PCA-BDA reached 96.7%, which was obviously higher than that of the AHP and FCE method. In the simulation experiment, more than 70% of safety rankings of petroleum drilling were improved by regulating the 3 most important attributes, while the safety ranking had no change by adjusting the least 3 important attributes. The experimental results show that the improved PCA-BDA can accurately accomplish the safety evaluation, and find out the critical attributes to make the petroleum drilling safety management more targeted.