基于原岩随钻振动信号的岩石力学参数快速预测实验研究 English Version
Experimental study on rapid prediction of rock mechanical parameters based on vibration signals of raw rock with drilling
-
摘要: 为了揭示随钻振动信号与岩石单轴抗压强度之间的响应关系，实现单轴抗压强度的快速感知预测，基于随钻振动信号提出了混合遗传算法优化（GA-BP）的单轴抗压强度人工神经网络快速预测方法。运用傅里叶变换及数学运算提取花岗岩、石灰岩、页岩、砂岩和煤五种原岩（煤）振动信号时域、频域的特征值，构建不同神经网络预测模型并分析比较各模型的预测性能。研究结果表明：经遗传算法优化的GA-BP神经网络模型决定系数R2为0.778，较之BP神经网络模型提升了9.4%；本文构建的模型对于单轴抗压强度有着较好的预测能力，所用方法为岩石力学参数快速获取技术的智能化和自动化发展提供了新的技术路径。Abstract: In order to reveal the response relationship between the vibration signal with drilling and the uniaxial compressive strength（UCS） of rock, and to realize the rapid sensory prediction of UCS, a hybrid genetic algorithm optimization (GA-BP) artificial neural network rapid prediction method of UCS is proposed based on the vibration signal with drilling. Fourier transform and mathematical operations are used to extract the eigenvalues of the vibration signals of granite, limestone, shale, sandstone and coal in the time and frequency domains, to construct different neural network prediction models and to analyze and compare the prediction performance of each model. The results of the study show that the coefficient of determination R2 of the GA-BP neural network model optimized by the genetic algorithm for the training set is 0.778, which is improved by 9.4% compared with the BP neural network model. The model constructed in this paper has a good prediction ability for UCS, and the method used provides a new technological path for the development of intelligent and automated techniques for rapid acquisition of rock mechanical parameters.
-
期刊类型引用(0)
其他类型引用(1)
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
- 被引次数: 1
下载:
