In the mining process of underground metal mines, the misjudgment of rock types by on-site technicians will have a serious negative impact on the stability evaluation of rock mass and the formulation of support schemes, which will result in the loss of economic benefits and potential safety hazards of mining enterprises. In order to realize the precise and intelligent identification of rock types, the image data of peridotite, basalt, marble, gneiss, conglomerate, limestone, granite, magnetite quartzite are amplified. Under the target detection framework of Faster R-CNN deep learning, the extraction network based on simplified VGG16 is used to extract and learn features of rock images, and finally the rock type identification system is successfully trained. The experimental verification shows that the system is correct for single-type rock image recognition and the accuracy is more than 96%. In order to realize accurate and intelligent identification of the surrounding rock surface under complex lithological conditions, the multi-type rocks hybrid images are also identified. The results show that the recognition effect is great and the accuracy rate is over 80%. Therefore, this system can accurately identify rock types with similar image features, which proves that the model has strong robustness and generalization ability. It has broad application prospects in rock mass stability evaluation and rock classification in underground mining.

The analysis of crosscut stability is an indispensable task in underground mining activities. Crosscut instabilities usually cause geological disasters and delay of the project. On site, mining engineers analyze and predict the crosscut condition by monitoring its convergence and stress; however, stress monitoring is time-consuming and expensive. In this study, we propose an improved extreme learning machine (ELM) algorithm to predict crosscut’s stress based on convergence data, for the first time in literature. The performance of the proposed technique is validated using a crosscut response by means of the FLAC^3D finite difference program. It is found that the improved ELM algorithm performs higher generalization performance compared to traditional ELM, as it eliminates the random selection for input weights. Furthermore, a crosscut construction project in an underground mine, Yanqianshan iron mine, located in Liaoning Province (China), is selected as the case study. The accuracy and efficiency of the improved ELM algorithm has been demonstrated by comparing predicted stress data to measured data on site. Additionally, a comparison is conducted between the improved ELM algorithm and other commonly used artificial neural network algorithms.

In rock engineering such as mine engineering and tunnel engineering, the rock mass structure plays a key role in the strength, seepage and stability of the rock mass. Therefore, the geometric parameter statistics of structural planes in rock mass engineering is an important geological survey work. Traditional rock mass structural plane measurement methods are limited by various on-site conditions. With the application of advanced measurement technologies in underground mines, the measurement methods of rock mass structural planes have also been updated. Among them, photogrammetry and 3D laser scanning measurement are new methods suitable for measuring the structural planes of underground rock mass. Through the detailed comparison and analysis of three typical structural plane measurement methods, the 3D laser scanning technology has proven to have an incomparable advantage in the collection of rock mass structure measurement. It has explored a new way for the rapid collection of rock mass structure plane occurrence in areas with harsh geological conditions.