| 基于人工神经网络模型的岩石特性预测 |
| 投稿时间：2018-07-05 修订日期：2018-07-05 点此下载全文 |
| 引用本文：陈晓君,陈小根,宋刚,等.基于人工神经网络模型的岩石特性预测[J].钻探工程,2019,46(1):34-38.CHEN Xiaojun,CHEN Xiaogen,SONG Gang,et al. Prediction of rock characteristics based on artificial neural network model[J]. Drilling Engineering, 2019,46(1):34-38. |
| 摘要点击次数: 1251 |
| 全文下载次数: 787 |
|
| 基金项目:国家重点研发计划资助“多金属矿岩心钻探关键技术装备联合研发及示范”（编号：2016YFE0202200）、国家自然科学基金“金刚石钻进过程中岩体基本力学参数实时确定方法研究”(编号：51574015) |
|
| 中文摘要:近年来，软计算技术被用作替代的统计工具。如人工神经网络（ANN）被用于开发预测模型来估计所需的参数。在本研究中，通过利用冲击钻进过程中的一些钻进参数（气压、推力、钻头直径、穿透率）和所产生的声级，建立了预测岩石性质的神经网络模型。在实验室中所产生的数据，用于开发预测岩石特性（如单轴抗压强度、耐磨性、抗拉强度和施密特回弹数）的神经网络模型，并使用各种预测性能指标对所建模型进行检验，结果表明人工神经网络模型适用于岩石性质的预测。 |
| 中文关键词:声级 钻头参数 人工神经网络 岩石特 |
| |
| Prediction of rock characteristics based on artificial neural network model |
|
|
| Abstract:In recent years, soft computing technology has been used as an alternative statistical tool. The artificial neural network (ANN) is used to develop predictive models to estimate the required parameters. In this study, a neural network model for predicting rock properties was established by using some of the drilling parameters (pressure, thrust, bit diameter, penetration) and the resulting sound level during the impact drilling process. Data generated in the laboratory was used for the development of neural network models that predict rock properties such as uniaxial compressive strength, wear resistance, tensile strength, and Schmidt rebound number. The models were tested with various predictive performance indicators and the results show that the artificial neural network model is suitable for the prediction of rock properties. |
| keywords:sound level bit parameters artificial neural network rock characteristics |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
