Identification of Acoustic Emission Spectrograms from Limestone Fracturing Based on a Novel Deep Learning Model

The progressive development of microscopic fractures within rock masses is a primary mechanism of macroscopic failure, threatening the structural integrity of rock engineering systems. In this paper, a novel deep learning model, Principal Component Analysis (PCA)-Visual Geometry Group 16 (VGG16), is developed to accurately identify spectrogram features associated with limestone fractures. In this architecture, a PCA-based convolution encoder is seamlessly integrated as a foundational preprocessing layer before feedforwarding into the deep neural network to execute linear feature purification. The model is first validated on standard image datasets comprising handwritten digits and facial images to evaluate classification performance. Subsequently, acoustic emission signals are acquired during triaxial compression tests on limestone specimens pretreated with cyclic acid-alkali exposure. The PCA-VGG16 framework is then employed to classify the corresponding acoustic spectrograms, and its performance is quantitatively compared with a conventional convolutional neural network (CNN) and the standard VGG16 model. The results indicate that the PCA-VGG16 model achieves classification accuracies that are 19.19% and 10.77% higher than the conventional CNN and standard VGG16 models, respectively. In terms of computational efficiency, the training time is reduced by 35.00% and 23.53% compared to CNN and VGG16. The superior classification performance of the proposed PCA-VGG16 model enables accurate identification of internal microscopic fracture characteristics in limestone. Furthermore, the integration of acoustic emission signals with deep learning models offers an effective approach for quantifying internal fracture levels and predicting the progressive failure of rocks.