装载机载重动态测量的LS-SVM速度补偿方法  

LS-SVM method for dynamic weighing velocity compensation about loaders

作　　者：王田苗[1] 王伟[1] 魏洪兴[1] 陈殿生[1] 

机构地区：[1]北京航空航天大学机械工程及自动化学院,北京100083

出　　处：《北京航空航天大学学报》2007年第11期1340-1344,共5页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家863高技术计划资助项目(2003AA430110)

摘　　要：能否合理补偿动臂举升速度对所测油压信号的影响是制约装载机载重动态测量精度的关键问题.在给出载重测量的实现方法后,建立了实现载重测量速度补偿和载重量计算的框架模型,然后详细阐述了贝叶斯证据框架下最小二乘支持向量机(LS-SVM,Least Square Support Vector Machines)参数的推断优化过程,以及基于贝叶斯证据框架下的LS-SVM速度补偿方法.试验结果表明,采用该方法进行速度补偿后的载重测量误差均能控制到1%以下,验证了其有效性.Whether or not to compensate the oil pressure because.of lift crane velocity reasonably, i. e. , the velocity compensation was thought to be the key to obtain accurate dynamic weighing about loaders. After the method of dynamic weighing was given, the parameter inferring course of least square support vector machines （LS-SVM） within Bayesian evidence framework was introduced. Then the flame model of velocity compensation based on LS-SVM was given, and the means Of velocity compensation and the course of weight computing were introduced in detail. Test results indicate that using LS-SVM within Bayesian evidence framework for solving velocity compensation, a relative measuring error within 1% can be obtained, which verifies that the validity of the method.

关 键 词：最小二乘支持向量机 贝叶斯证据框架 装载机 动态载重测量 速度补偿 

分 类 号：TH715.1[机械工程—测试计量技术及仪器]