Near-infrared spectroscopy combined with deep convolutional generative adversarial network for prediction of component content in melt-cast explosive

Rapid and nondestructive prediction of component content is the key to improve industrial production efficiency. However, limited data sets also result in low generalization capabilities of the model, and it is time-consuming to obtain a large amount of content reference values and costly. Here, near infrared (NIR) spectroscopy technique combined with deep convolutional generated countermeasure network (DCGAN) was used to predict the trinitrotoluene (TNT) content of the melt-cast explosive. DCGAN was used to simultaneously extend its spectral data and content data. After several iterations, fake data were produced, which was very similar to the experimental data. The partial least squares (PLS) regression model was established and the performance was compared before and after data enhancement. The results showed that this method not only improved the performance of regression model, but also solved the problem of requiring large number of training data.