This study investigates the relationship between anchor cable drilling parameters and roadway roof strata properties. The goal is to enable rapid and accurate rock type identification. Field-measured drilling data were processed using data cleaning and wavelet transform noise reduction. Four recognition models were developed and compared: LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), DBO-LSTM (Dung Beetle Optimizer), and DBO-BiLSTM. The results demonstrate a strong correlation between vibration, pressure signals and rock strength, enabling the effective differentiation of rock types. All models performed exceptionally for coal seams with distinct features, achieving 100% accuracy, precision, recall, and F1 scores. Model performance improved with increased complexity for strata with subtle differences, such as sandstone and mudstone. The DBO-BiLSTM model outperformed others, showing significant improvements in accuracy, recall, and F1 score compared to LSTM, BiLSTM, and DBO-LSTM models. Specifically, accuracy improved by up to 9%, recall by 12.48%, and F1 score by 13.06%. These findings highlight the DBO-BiLSTM model’s superior recognition capability for roof strata drilling signals. This method provides a robust technical foundation for lithology identification in Measurement While Drilling (MWD) systems. It supports more precise and efficient roadway design in complex geological conditions.

Currently, most of the roadways adopt one support design strategy, which leads to high stress and insufficient support parameters in some crushed areas of the roadways and excess support parameters in some stable regions. There is an urgent need for a reliable method of grading the roadway perimeter rock to realize a reasonable support design for the whole area and cycle of the roadways. Taking Xiaobaodang No.1 coal mine as the background, Based on previous research, we utilized SPSS to analyze the data and selected ten indicators that significantly influence roof stability and are easily obtainable. The relatIVe weights between the influencing factors were determined using the hierarchical analysis method. The results showed that fIVe key factors, namely, roadway depth, roof strength, direct roof thickness, mining height, and rock integrity, emphatically affect the roof's stability. Based on the borehole data in the study area of the mine, 40 sets of borehole data were processed using normalization, and based on the weights of the influencing factors, a classification formula for the stability of the roadway perimeter rock was proposed to classify the boreholes initially. The roadway roof stability classification model of the BP neural network is constructed. The accuracy of the training set of 40 sets of drill hole data is 92.8%, and the accuracy of the test set is 91.7%. The classification results of the model are verified by using the mine pressure data of the mined face, and the mine pressure data shows a noticeable step change with the classification results, which puts forward theoretical references for the subsequent differentiated support of the working face. Numerical simulation software is used to analyze the vertical stress of different types of roof layers and the vertical stress of coal pillars, and the vertical stress of coal pillars at the roof layers that are highly prone to collapse of the roof is higher than that at other roof layers, so it is necessary to strengthen the support.