Research on an Improved Convolutional Neural Network Fault Diagnosis Method for Exciter System

Figures & data

Figure 1. CNN framework.

Figure 2. Dilation convolution layers with different dilated rates: (a) dilated rate is 1, (b) dilated rate is 2.

Figure 3. Schematic diagram of the Pythagorean triple spatial pyramid pooling layer.

Figure 4. Preprocessing flow chart.

Figure 5. Flowchart of PTSPP-DCNN algorithm.

Figure 6. Circuit diagram of excitation system.

Figure 7. 3D model diagram of exciter.

Table 1. Exciter fault type label.

Operation state of exciter	Classification	Tag
Normal	1	NO
Excitation failure	2	EF
Excitation instability	3	EI
Loss of magnetism fault	4	FF
Carbon brush overtemperature fault	5	CO

Table 2. PTSPP-DCNN parameter settings.

Structure of DCNN	Hyperparameter settings	value
Input layer	Size of input layer	64 × 64
The first expanded convolution layer	Number and size	16, 3 × 3
Max pooling layer	Core size	2 × 2
A second expanded convolution layer	Number and size	32, 3 × 3
Max pooling layer	Core size	2 × 2
The third expanded convolution layer	Number and size	64, 3 × 3
Pythagorean triple space pyramid pooling layer	level	（8,6）
The fourth expanded convolution layer	Number and size	128, 3 × 3
Max pooling layer	Core size	2 × 2
Fully connected layer	Number of neurons	50
Output layer	Number of neurons	5

Figure 8. Analysis results of fault classification accuracy of exciter in ten experiments.

Figure 9. Accuracy curve of five algorithms.

Figure 10. Contribution rate of each principal component.

Figure 11. Clustering results of five algorithms. (a) DCNN. (b) OCRNN. (c) CNN-LSTM. (d) SPP-CNN. (e) PTSPP-DCNN.