摘要
针对主动式激光跟踪仪跟踪测量系统复杂、研制成本高的问题,提出了被动式激光跟踪方法用于测量目标点的空间坐标。首先基于HTM方法建立被动式激光跟踪测量系统的误差分析模型,提出相关误差参数的检测方法,在对测量误差进行补偿后,被动式激光跟踪测量系统的空间坐标测量误差从581.5μm降低为150.8μm。为进一步提升测量准确度,采集经误差补偿后的残余误差作为样本数据,利用BP神经网络对样本数据进行训练;利用训练好的BP神经网络模型对被动式激光跟踪测量系统的残余误差进行补偿,空间坐标测量误差从150.8μm降低为51.6μm。相较HTM误差补偿方法,HTM+BP神经网络模型的补偿效果提升了65.8%。
Considering the complexity of tracking measurement system and the high development cost of active laser tracker,a passive laser tracking method is proposed to measure the spatial coordinates of target points.Firstly,the error analysis model of the passive laser tracking measurement system was established according to HTM principle,and the detection method for relevant error parameters was proposed.The measurement error of the passive laser tracking measurement system was reduced from 581.5μm to 150.8μm after error compensation.In order to further improve measurement accuracy,residual errors after compensation were collected as sample data,and BP neural network was used to train the sample data.After the residual error of the passive laser tracking system was compensated by the trained BP neural network model,the error of spatial coordinate measurement was reduced from 150.8μm to 51.6μm.Compared with HTM error compensation method,the compensation effect of HTM+BP neural network model improved 65.8%.
作者
娄志峰
耿万佳
张记云
林钰琪
范光照
王晓东
LOU Zhifeng;GENG Wanjia;ZHANG Jiyun;LIN Yuqi;FAN Kuangchao;WANG Xiaodong(School of Mechanical Engineering,Dalian University of Technology,Dalian 116000,China)
出处
《计测技术》
2021年第5期34-41,共8页
Metrology & Measurement Technology
基金
辽宁省“兴辽英才计划”项目(XLYC2002020)
辽宁省中央引导地方科技发展专项(2020JH6/10500017)
大连理工大学基本科研业务费项目(DUT21LAB109)。
关键词
被动式激光跟踪
空间坐标测量
误差分析
BP神经网络
passive laser tracking
spatial position measurement
error analysis
BP neural network