基于最小二乘支持向量机的混合动力挖掘机负载功率预测

发布时间：2018-01-16 08:27

本文关键词：基于最小二乘支持向量机的混合动力挖掘机负载功率预测　出处：《吉林大学学报(工学版)》2015年01期 　论文类型：期刊论文

【摘要】：为实现液压挖掘机并联式混合动力总成与负载功率的精确匹配,在对变量泵工作原理分析的基础上,提出基于最小二乘支持向量机(LS-SVM)算法的双联式恒功率变量泵功率预测模型。以液压挖掘机实际挖掘作业时采集的载荷谱作为训练样本,以泵出口压力、负流量控制压力和极限载荷控制压力作为训练模型的输入,以泵的排量作为输出建立模型,从而使模型对于作业环境具有更好的适用性。用网格搜索和交叉验证的方法对LS-SVM的参数进行了优化,研究结果表明该模型具有良好的预测精度和泛化能力。
[Abstract]:In order to realize the accurate matching between the parallel hybrid power assembly and the load power of the hydraulic excavator, the working principle of the variable pump is analyzed. A dual coupled constant power variable pump power prediction model based on least squares support vector machine (LS-SVM) algorithm is proposed. The load spectrum of hydraulic excavator is taken as the training sample. The pump outlet pressure, negative flow control pressure and limit load control pressure are taken as the input of the training model, and the pump displacement is taken as the output to establish the model. So that the model has better applicability to the job environment. The parameters of LS-SVM are optimized by grid search and cross-validation. The results show that the model has good prediction accuracy and generalization ability.
【作者单位】：吉林大学机械科学与工程学院;
【基金】：“863”国家高技术研究发展计划项目(2009AA044403)
【分类号】：TP18;TU621
【正文快照】： 0引言随着混合动力技术的出现,液压挖掘机的全局功率匹配有望实现,通过引入辅助动力源,解决动力源-泵功率匹配环节对泵排量调节的依赖。国外各大挖掘机研究机构和制造商如日本的小松、神户制钢所和神户建机,德国的利勃海尔,美国的卡特彼勒等率先开展了相关的研究工作并取得了

【参考文献】