摘要
在分析高速电主轴功率与负载转矩关系的基础上,提出了一种负载扭矩软测量的方法。采用电主轴定子电压、定子电流、空载电流和主轴转速作为辅助变量,建立了基于BP神经网络的负载扭矩软测量模型。以航空发动机离合器轴承试验台扭矩检测为例,对软测量模型进行了仿真研究。仿真结果表明,该方法能够满足一定精度要求,为解决高速电主轴拖动系统扭矩传感器昂贵和不易安装等问题,提供了一种解决方法。
A method of soft-sensing is put forward after the relation between spindle's power and load torque is analysed. The soft-sensing model based on BP neural network is built up, using the spindle's stator-voltage, stator-current, no load current and spindle speed as secondary variables. With an example of aviation engine clutch bearing test-bed torque measurement, the simulation is done for the soft-sensing model. It is shown from the result that the proposed method can satisfy some given precision requirements. And a good method is provided to solve the difficulty of installing the valuable torque sensor.
出处
《计测技术》
2006年第2期9-12,共4页
Metrology & Measurement Technology
基金
上海师范大学青年基金资助项目(DKL412)
关键词
软测量
高速电主轴
负载扭矩
神经网络
soft-sensing
high-speed spindle
load torque
neural network