为解决传统航空发动机异常检测方法准确率和泛化性能较低的问题，提出一种混合核最大相关熵的深度支持向量数据描述（mixed kernel maximum correntropy criterion-deep support vector data description, MKMCC-DSVDD）方法。首先，采用合成少数类过采样技术扩充异常样本规模，提高对非均衡样本的泛化性能；其次，建立基于混合核改进的最大相关熵损失函数，可以在无须数据分布假设的前提下提升准确率；最后，构建基于MKMCC-DSVDD的航空发动机异常检测方法。在航空发动机气路系统和滑油系统异常检测实验中，所提方法平均曲线下的面积（area under curve, AUC）达到98.53%，表明其具有较高的实用性和泛化性能。

In order to solve the problems that traditional aero-engine anomaly detection methods are difficult to deal with unbalanced samples, low accuracy and generalization performance, and insufficient data distribution consideration, a deep support vector data description based on mixed kernel maximum correntropy criterion (MKMCC-DSVDD) was proposed. Firstly, the synthetic minority oversampling technique (SMOTE) was used to expand the abnormal sample size and improve the generalization performance of non-equilibrium sample. Then, the maximum correlation entropy loss function based on hybrid kernel improvement was established and analyzed to improve the accuracy without data distribution assumption. Finally, an aero engine anomaly detection method based on MKMCC-DSVDD was constructed. The abnormal state average area under curve (AUC) reaches 98.53% in the test of anomaly detection of a certain aero-engine gas path system and oil system, which indicates that MKMCC-DSVDD anomaly detection method has high applicability and generalization performance.