Comparison and Analysis of the Influence of Different Data Transformation Methods on the Fault Identification of Flexible DC Transmission Lines by Convolutional Neural Network

Table 1

The structure of CNN.

Layer	Structure
1	Input
2	Convolution layer + RELU activation layer (convolution kernel: 2 × 2, step length: 1)
3	Pooling layer (pool kernel: 2 × 2, step size: 2)
4	Convolution layer + RELU activation layer (convolution kernel: 2 × 2, step length: 1)
5	Pooling layer (pool kernel: 2 × 2, step size: 2)
6	Hidden layer + RELU activation layer (neuron number: 240)
7	Hidden layer + RELU activation layer (neuron number: 168)
8	Softmax layer (neuron number: 10)
9	Output