基于随机森林的钻机泵控推进系统故障诊断方法  

Fault Diagnosis Method of Pump-controlled Propulsion System of Drilling Rig Based on Random Forest

在线阅读下载全文

作  者:张孟辉 耿蒲龙[1] 魏琦[1] 栗林波 ZHANG Menghui;GENG Pulong;WEI Qi;LI Linbo(National and Provincial Joint Engineering Laboratory of Mining Intelligent Electrical Apparatus Technology,Taiyuan University of Technology,Taiyuan 030024,China;Shanxi Jinding Gaobao Drilling Co.,Ltd.,Jincheng 048000,China)

机构地区:[1]太原理工大学矿用智能电器技术国家地方联合工程实验室,太原030024 [2]山西金鼎高宝钻探有限责任公司,山西晋城048000

出  处:《煤炭技术》2024年第11期222-226,共5页Coal Technology

基  金:山西省重点研发计划项目(202003D111008)。

摘  要:针对煤矿井下水平定向钻机恒压泵控推进系统故障复杂多变、监测变量繁多而导致的诊断效率低和诊断精度不高的问题,提出基于随机森林的钻机恒压泵控液压推进系统故障诊断方法。首先,采用AMESim软件建立钻机推进系统模型,结合系统常见故障模式和故障机理,在不同工况下通过改变液压元件关键参数完成了常见故障模拟;然后,用预处理后的仿真样本验证故障诊断模型的有效性。结果表明:随机森林(RF)故障诊断模型,可以实现钻机泵控推进系统故障的有效分类,与决策树(CART)、支持向量机(SVM)、十折交叉验证SVM(10-CV-SVM)相比有着更高的准确率,为定向钻机智能运维发展奠定了基础。Aiming at the problems of low diagnostic efficiency and low diagnostic accuracy caused by complex and changeable faults and various monitoring variables of constant pressure pump-controlled propulsion system of horizontal directional drilling rig in coal mine,a fault diagnosis method of constant pressure pump-controlled hydraulic propulsion system of drilling rig based on random forest is proposed.Firstly,the model of drlling rig propulsion system is established by AMESim software.Combined with the common fault mode and fault mechanism of the system,the common fault simulation is completed by changing the key parameters of hydraulic components under different working conditions.Then,the effectiveness of the fault diagnosis model is verified by the pre-processed simulation samples.The results show that the random forest(RF)fault diagnosis model can effectively classify the pump-controlled propulsion system faults of drilling rigs,and has higher accuracy than decision tree(CART),support vector machine(SVM)and ten-fold cross-validation SVM(10-CV-SVM),which lays a foundation for the development of intelligent operation and maintenance of directional drilling rigs.

关 键 词:随机森林 AMESIM 故障诊断 钻机泵控推进系统 

分 类 号:TD421[矿业工程—矿山机电]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象