Comprehensive Prediction and Discriminant Model for Rockburst Intensity Based on Improved Variable Fuzzy Sets Approach

Hong Wang,Yuanyuan He,Lei Nie,Tao Zhang,Yuzheng Wang,Yan Lv,Chao Du,Yan Xu

doi:10.3390/app9153173

Abstract

Rockburst intensity prediction is one of the basic works of underground engineering disaster prevention and mitigation. Considering the dynamic variability and fuzziness in rockburst intensity prediction, variable fuzzy sets (VFS) are selected for evaluation and prediction. Here, there are two problems in the application of traditional VFS: (i) the relative membership degree (RMD) calculation process is complex and time-consuming, and the RMD matrix of all indexes can be only obtained by using the RMD function repeatedly; (ii) unreasonable weights of indicators have great impact on the synthetic relative membership degree (SRMD), so it is difficult to guarantee the correctness of the final prediction result. In view of the above problem, this paper established three simplified feature relationship expressions of RMD based on VFS principle and used the SRMD function to establish a BP neural network model to optimize SRMD. The improved VFS method is more efficient and the prediction results are more stable and reliable than the traditional VFS method. The main advantages are as follows: (1) the improved VFS method has higher computational efficiency; (2) the improved VFS method can verify the correctness of RMD at all times; (3) the improved VFS method has higher prediction accuracy; and (4) the improved VFS method has higher fault tolerance and practicability.

Highlights

The frequent occurrence of rockburst disasters has been acknowledged as one of the most serious problems in underground projects all over the world because it directly threatened the safety of underground constructors, equipment, and buildings and even induced mine earthquakes [1]
The primary objectives of this research are (1) to explore the characteristic relationship of relative membership degree (RMD) in different classifications, of which these features are used to simplify the calculation process of RMD, and (2) to establish a BP neural network model based on synthetic relative membership degree (SRMD) function in order to optimize the SRMD value and to improve the prediction accuracy and practicability of the model
What are the advantages of the new method compared with the traditional variable fuzzy sets (VFS) method after such improvement? The following are discussed in detail: (1)

Summary

Introduction

The frequent occurrence of rockburst disasters has been acknowledged as one of the most serious problems in underground projects all over the world because it directly threatened the safety of underground constructors, equipment, and buildings and even induced mine earthquakes [1]. In addition to finding reliable prevention and control measures, it is important to establish an accurate rockburst prediction model in order to resist the occurrence of rockburst disasters [5,6,7,8]. Many scholars have studied the mechanism of rockburst from different perspectives and put forward corresponding prediction methods of rockburst intensity, for example, based on single factor strength theory, rigidity theory, energy theory, catastrophe theory, bifurcation theory, instability theory, Russeenes criterion [7], Wang Yuanhan criterion [8] and Lu Jiayou criterion [9], and random forest classification [10], cloud model theory [11], attribute comprehensive evaluation method [12], artificial neural network [13], matter-element extension theory [14], etc.

Objectives

Discussion

Conclusion