Prediction of microseismic events in rock burst mines based on MEA-BP neural network

Abstract

Microseismic monitoring is an important tool for predicting and preventing rock burst incidents in mines, as it provides precursor information on rock burst. To improve the prediction accuracy of microseismic events in rock burst mines, the working face of the Hegang Junde coal mine is selected as the research object, and the research data will consist of the microseismic monitoring data from this working face over the past 4 years, adopts expert system and temporal energy data mining method to fuse and analyze the mine pressure manifestation regularity and microseismic data, and the "noise reduction" data model is established. By comparing the MEA-BP and traditional BP neural network models, the results of the study show that the prediction accuracy of the MEA-BP neural network model was higher than that of the BP neural network. The absolute and relative errors of the MEA-BP neural network were reduced by 247.24 J and 46.6%, respectively. Combined with the online monitoring data of the KJ550 rock burst, the MEA-BP neural network proved to be more effective in microseismic energy prediction and improved the accuracy of microseismic event prediction in rock burst mines.

Prediction Model of Water Abundance of Weakly Cemented Sandstone Aquifer Based on Principal Component Analysis–Back Propagation Neural Network of Grey Correlation Analysis Decision Making

“…This function uses the gradient method to iteratively update the weight threshold of each layer connection until the minimum error is obtained. The learning function of the neural network uses the gradient descent momentum function learned [17] or [28][29][30]. The target mean square error is set to 0.001, and the maximal frequency of training is 5000.…”

Financial big data management and intelligence based on computer intelligent algorithm

“…The famous “error backpropagation” neural network was proposed in 1985, which is a forward-forward neural network with one or more layers 28 . It not only has the characteristics of parallel processing, distributed storage, fault tolerance, etc., but also has the characteristics of self-learning, self-organization, and adaptability 29 , 30 .…”

Application of deep learning classification model for regional evaluation of roof pressure support evolution effects over time in coal mining face

“…Gao et al [ 32 ] introduced a multi-scale feature extraction-based neural network for predicting pressurization data in coal mine hydraulic supports, enhancing prediction accuracy by capturing temporal features across scales. Lan et al [ 33 ] employed expert systems and time-energy data mining to analyze mine pressure and microseismic data, creating a noise-reduced data model. Their MEA-BP neural network effectively enhances microseismic event prediction accuracy in rockburst mines.…”