基于随机森林与交叉验证模型的旋挖钻机作业阶段智能识别方法  

Intelligent Identification Method for Operation Stages of Rotary Drilling Rigs Based on Random Forest and CrossValidation Model

作　　者：王静 顾波 Wang Jing;Gu Bo

机构地区：[1]江苏徐工工程机械研究院有限公司 [2]徐州徐工基础工程机械有限公司

出　　处：《工程机械》2025年第3期1-7,I0001,共8页Construction Machinery and Equipment

摘　　要：旋挖钻机作业阶段的准确识别对其作业效率和节能减排有重要作用。现有的作业阶段识别方法存在准确率不高、适用性不佳等问题,为此提出一种随机森林与交叉验证模型的作业阶段智能识别方法。首先,通过分析旋挖钻机作业过程中动力头马达、主卷升马达等出口压力数据,利用随机森林算法对特征重要性进行评估,确定主卷升马达出口压力的均值与方差、回转方差、主卷降马达出口压力的均值与方差为关键特征。其次,运用这些特征,结合随机森林模型与10折交叉验证策略,构建能够高效识别旋挖钻机作业阶段的模型。最后,利用试验数据进行模型测试验证。结果表明,模型在测试中准确率可达0.978,优于PCA-SVM、GRU等模型。所提模型在旋挖钻机作业阶段智能识别中具有较高准确性和可靠性,可更好优化作业效率、更准确调整工作参数,从而达到节能减排效果。Accurate identification of operation stages of rotary drilling rigs plays an important role in their operational efficiency and energy saving and emission reduction.The existing identification methods for operation stages have problems such as low accuracy and poor applicability,and for this reason,an intelligent identification method for operation stages based on random forest and cross-validation models is proposed.Firstly,by analyzing the outlet pressure data of the power head motor and the main winch motor during operation of the rotary drilling rig,the importance of the features is evaluated by using the random forest algorithm,and the mean and variance of the outlet pressure of the main winch lifting motor,the rotary variance,and the mean and variance of the outlet pressure of the main winch lowering motor are identified as the key features.Secondly,these features are used to construct a model that can efficiently identify the operation stages of rotary drilling rigs by combining the random forest model with a 10-fold cross-validation strategy.Finally,the model is tested and validated by using experimental data.The results show that the accuracy of the model in the test can reach 0.978,which is superior to models such as PCA-SVM and GRU.The proposed model has high accuracy and reliability in intelligent identification of operation stages of rotary drilling rigs,which can better optimize the operational efficiency and more accurately adjust the working parameters,thus achieving energy saving and emission reduction effects.

关 键 词：旋挖钻机 随机森林模型 交叉验证 节能减排 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]