Deep learning-based rock type identification using drill vibration frequency spectrum images

Abstract

Rock identification is crucial in the mining industry. It provides useful information regarding the geological characteristics of an area, which can be applied to drill-bit selection, optimisation of drilling parameters, and selection of blasting materials. Common methods for this purpose are core drilling and core analysis. Although these methods are dependable, they lag and are expensive. Recent studies have highlighted a need for an automatic and reliable system for rock identification during the drilling process. Hence, this study establishes a new and reliable method for automatically identifying rocks using drill vibrations and deep-learning algorithms. The sample rocks were drilled using a rotary percussion rock drifter with accelerometers mounted on a guide cell. The fast Fourier transform algorithm was used to convert the drill vibration signals into frequency spectrum images, which were subsequently used as inputs to the deep-learning algorithms. Study rock-identification models were constructed using three convolutional neural networks: ResNet-50, Inception-v3, and DenseNet-201. The classification accuracy was used as a metric to assess the performance of the models. Subsequently, a Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm was used to identify noteworthy frequencies responsible for rock predictions. With the help of deep-learning algorithms, drill vibrations could be used to identify different rocks during the drilling process. The Inception-v3 model exhibited optimum performance, with a classification accuracy of 99.0%. Grad-CAM indicated that frequencies from 0 to 8000 Hz are important for rock classification. This approach offers an automatic, low-latency, and dependable rock-identification system.