An Intelligent Fault Diagnosis Based on Adversarial Generating Module and Semi-supervised Convolutional Neural Network

<div>Distributions of each pattern under different labeled samples. (a) size of labeled data: 100 (b) size of labeled data: 200. (c) size of labeled data: 300 (d) size of labeled data: 400.</div>

Computational Intelligence and Neuroscience

fig10

Figure 10

Figure 10: An Intelligent Fault Diagnosis Based on Adversarial Generating Module and Semi-supervised Convolutional Neural Network 