摘要
针对游梁式抽油机的故障诊断问题,提出了一种基于振动分析和改进集成学习模型的游梁式抽油机故障诊断方法。采用Stacking集成学习模型将随机森林(Random Forest,RF)、支持向量机(Support Vector Ma-chine,SVM)、梯度提升(Gradient Boosting,GB)和极端梯度提升(Ex-treme Gradient Boosting,XGboost)作为基学习器,多元线性回归作为元学习器,以提高单一模型的准确性和泛化能力。同时,提出了改进的沙猫群优化算法(improved sand cat swarm optimization algorithm,ISCSO),用于对模型超参数进行优化,解决手工调参难度大的问题。通过实验对比ISCSO-Stacking模型与其他模型的预测结果发现,ISCSO-Stacking模型的预测准确率达到了97%,优化后的超参数显著提升了模型性能,并降低了过拟合风险。
To address the challenge of fault diagnosis in beam pumping units,we propose a methodology based on vibration analysis and an enhanced integrated learning model.The Stacking integrated learning framework employs random forest(RF),support vector machine(SVM),gradient boos-ting(GB),and extreme gradient boosting(XGboost)as base learners,with multiple linear re-gression as the meta-learner,aiming to improve the accuracy and generalization capacity of a single model.Additionally,we introduce an improved sand cat swarm optimization(ISCSO)algorithm to optimize the hyperparameters of the model,addressing the challenges associated with manual pa-rameter tuning.Experimental comparisons of prediction results between the ISCSO-stacking model and other models demonstrate that the ISCSO-stacking model achieves a prediction accuracy of 97%.Furthermore,the optimized hyperparameters substantially enhance model performance and reduce the risk of overfitting.
作者
张强
李青
薛冰
胡月
ZHANG Qiang;LI Qing;XUE Bing;HU Yue(School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China)
出处
《信息与控制》
北大核心
2025年第5期696-709,共14页
Information and Control
基金
国家自然科学基金项目(42002138)
黑龙江省自然科学基金项目(LH2022F008)
黑龙江省博士后专项项目(LBH-Q20077)
黑龙江省优秀青年教师基础研究支持计划项目(YQJH2023073)。
关键词
Stacking集成学习模型
沙猫群优化算法
振动分析
故障诊断
游梁式抽油机
超参数优化
Stacking integrated learning model
sand cat swarm optimization algorithm
vibration analysis
fault diagnosis
beam pumping unit
hyperparameter optimization
