为解决常规特征作为变压器故障诊断模型输入特征时诊断准确率低的问题，提出一种基于高斯核Fisher判别分析（Gaussian kernel Fisher discriminant analysis, GKFDA）与牛顿-拉夫逊算法（Bewton-Raphson-based optimization, NRBO）优化双向长短期记忆网络（bidirectional long short-term memory network, BiLSTM）的变压器故障诊断方法。首先，构建了能够反映变压器故障的23维特征量，并采用GKFDA确定了最优特征集；其次，建立了NRBO优化BiLSTM的变压器故障诊断模型；然后，通过算例对所提方法进行了验证，验证结果表明，所提方法的诊断准确率为98.4%，优于常规特征方法和其他优化诊断模型。最后，采用IECTC10数据对所提模型进行了诊断测试，结果表明所提方法在变压器故障诊断上具有较好的泛化性。

In order to solve the problem of low diagnostic accuracy when conventional features are used as input features of transformer fault diagnosis model, a transformer fault diagnosis method based on Gaussian kernel Fisher discriminant analysis (GKFDA) and Newton-Raphson-based optimization (NRBO) algorithm optimized bidirectional long short-term memory network (BiLSTM) was proposed. Firstly, a 23-dimensional feature that can reflect transformer faults was constructed, and the optimal feature set was determined by GKFDA. Secondly, a transformer fault diagnosis model based on NRBO optimized BiLSTM was established. Then, the proposed method was verified by an example. The results show that the diagnostic accuracy of the proposed method is 98.4%, which is better than conventional feature method and other optimization diagnosis models. Finally, the proposed method was tested using IECTC10 data. The results show that the proposed method has good generalization in transformer fault diagnosis.