期刊文献+

滑油泵试验器流量修正参数确定方法研究 被引量:3

Research on the Determination Method for Corrected Parameter of Lubricating Pump Bench's Flow
下载PDF
导出
摘要 为提高低压大流量滑油泵试验器流量计量的准确性,针对计量过程中流量影响因素恒定控制难的问题,分析了流量计量过程的特性,确定了影响流量计量精度的主要因素:滑油泵出口压力、滑油温度和滑油泵转速^([1])。为消除这三种因素对计量的影响,提出了带回归系数的流量补偿方法。为确定回归参数,采用多元线性回归算法^([2]),建立多元线性回归模型,并结合大量的实验数据,利用Madab对回归模型求解,最终求得流量回归系数并应用到控制系统中。实践证明,该方法提高了试验器的计量精度,减少了实验次数,对两种标准泵计量20余次,计量误差均在±0.3 L之內,满足使用条件。 To improve the accuracy of flow measurement in the low pressure high flow lubricating pump test bench,and solve the difficult problem not constantly to control flow affecting in the metering process,the flow measurement characteristics are studied,and the main factors that affect the flow measurement accuracy such as outlet pressure of lubricating pump,temperature of lubricating oil and the speed of lubricating pump are determined.To eliminate the influence of three factors on the measurement,flow compensation method is presented with a regression coefficient.Using multiple linear regression algorithm and establishing test bench mathematical model of multiple linear regression,the rate regression parameters are determined.Moreover,by using the Matlab regression model and combining with a large number of experimental data,the final regression coefficients of flow are acquired and applied to the actual.Practice shows that this method reduces the number of experiments and improves the accuracy of test results.The two standard pumps are measured more than 20 times,as a result that the measurement errors are within ± 0.3 L,which satisfies the conditions of use.
出处 《测控技术》 CSCD 北大核心 2014年第11期118-121,125,共5页 Measurement & Control Technology
关键词 滑油泵试验器 流量计量 修正系数 线性回归 MATLAB lubricating pump test bench flow measurement correction factor linear regression Matlab
  • 相关文献

参考文献6

二级参考文献29

  • 1祁亨年.支持向量机及其应用研究综述[J].计算机工程,2004,30(10):6-9. 被引量:186
  • 2孙德山,吴今培,侯振挺,肖健华.单参数支持向量回归算法[J].系统工程学报,2005,20(1):109-112. 被引量:12
  • 3田玲,王传杰.虚拟仪器技术在液压泵性能测试系统的应用[J].液压与气动,2006,30(1):34-37. 被引量:8
  • 4王玲,穆志纯,郭辉.基于支持向量回归的批处理增量学习方法[J].计算机工程,2007,33(10):19-21. 被引量:2
  • 5Zeng W H, Ma J. A novel incremental SVM learning algorithm [A]. The 8th International Conference on Computer Supported Cooperative Work in Design Proceedings[C], 2003
  • 6Vapnik VN著,张学工译.统计学习理论的本质[M].清华大学出版社,2000
  • 7Cherkassky V, Ma Y Q. Practical selection of SVM parameters and noise estimationfor SVMRegression [ J ]. Neural Networks, 2004,17:113 -126
  • 8Duan K, Keerthi S, Poo A. Evaluation of simple performancemeasures for tuning SVM hyperparameters [ J ]. Neurocomputing, 2003,51:41 -59
  • 9Han Jiawei,Kamber M.数据挖掘:概念与技术(原书第2版).范明,孟小峰译.北京:机械工业出版社,2008:231-233.
  • 10Agrawal R,Imielinski T,Swami A.Mining association rules between sets of items in large databases.In Proc 1993 ACM-SIGMOD int 1 Conf Management of Data,Washington,DC,May l993:207-216.

共引文献19

同被引文献20

引证文献3

二级引证文献12

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部