Abstract
Intelligent prediction of rock bursts has great significance in rock mechanics research and a high value in engineering applications. An intelligent rockburst prediction method based on a Bayes-optimized convolutional neural network (BOCNN) was proposed. First, an exploratory analysis of data was conducted using joint distribution diagrams and the heat map of the correlation matrix to establish a high-quality data set of rockburst engineering cases and a parameter system for rockburst prediction. Second, six rockburst prediction models were built by combining machine learning algorithms, such as random forest, k-nearest neighbor (KNN), and Bayes, deep learning (CNN1d and CNN2d), and BOCNN. In addition, we used accuracy, precision, recall, F1 score, receiver operating characteristic curve, Taylor diagram, and the probability indicator of prediction results as indicators to evaluate the accuracy of the models. A comparative analysis of the six rockburst prediction models was conducted to explore rockburst prediction models with good robustness, generalization performance, and high accuracy. Moreover, 11 comparative models were established for comparative analysis. Then, we used the MATLAB tool to build an intelligent rockburst prediction system and applied the findings to the Jiangbian Hydropower Station in Sichuan Province, China. The results of the study show that the intelligent rockburst prediction system can provide technical support for predicting rockburst hazards in mining, transportation, and water conservancy and hydropower projects and a scientific basis for later construction and the design of support structures.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.