Cao Anye, Liu Yaoqi, Yang Xu, Li Sen, Liu Yapeng
School of Mines, China University of Mining and Technology, Xuzhou 221116, China.
Jiangsu Engineering Laboratory of Mine Earthquake Monitoring and Prevention, China University of Mining and Technology, Xuzhou 221116, China.
Sensors (Basel). 2022 Apr 18;22(8):3088. doi: 10.3390/s22083088.
Coal burst prediction is an important research hotspot in coal mine production safety. This paper presents FDNet, which is a knowledge and data fusion-driven deep neural network for coal burst prediction. The main idea of FDNet is to extract explicit features based on the existing mine seismic physical model and utilize deep learning to automatically extract the implicit features of mine microseismic data. The key innovations of FDNet include an expert knowledge indicator selection method based on a subset search strategy, a mine microseismic data extraction method based on a deep convolutional neural network, and a feature deep fusion method of mine microseismic data based on an attention mechanism. We conducted a set of engineering experiments in Gaojiapu Coal Mine to evaluate the performance of FDNet. The results show that compared with the state-of-the-art data-driven machines and knowledge-driven methods, the prediction accuracy of FDNet is improved by 5% and 16%, respectively.
煤岩动力灾害预测是煤矿安全生产领域的一个重要研究热点。本文提出了FDNet，这是一种基于知识与数据融合驱动的用于煤岩动力灾害预测的深度神经网络。FDNet的主要思想是基于现有的矿山地震物理模型提取显式特征，并利用深度学习自动提取矿山微震数据的隐式特征。FDNet的关键创新点包括基于子集搜索策略的专家知识指标选择方法、基于深度卷积神经网络的矿山微震数据提取方法以及基于注意力机制的矿山微震数据特征深度融合方法。我们在高家堡煤矿进行了一组工程实验，以评估FDNet的性能。结果表明，与当前最先进的数据驱动机器和知识驱动方法相比，FDNet的预测准确率分别提高了5%和16%。
