基于T-S模糊神经网络的齿槽效应补偿方法研究*

摘要

针对齿槽效应带来的齿槽误差问题,提出在传感器探头内布设齿槽位置检测线圈,建立传感器齿槽特性模型和基于T-S模糊神经网络的齿槽补偿系统模型,依据齿槽位置信号对传感器进行齿槽误差补偿。利用附加动量的BP学习方法对网络进行学习和测试。仿真结果表明补偿模型的输出不再随齿槽位置波动,最大误差为依0.2mm,该种方法可以有效地消除齿槽效应并提高传感器的检测精度,满足高速磁浮车悬浮控制系统要求。%A method is proposed to solve the slot effect problem. In this method,coils are arranged in probe of the gap sensor to detect the relative position in a tooth-groove period. A compensator based on T-S fuzzy neural network is designed to compensate the output of the gap sensor by using the relative position signal. Simulation results show that this compensator could provide correct gap data with the error less than±0. 2 mm and the output of the compensator is independent to the tooth-groove position. The precision accuracy of the sensor is increased with this method and the compensated output of the gap sensor may meet the requirement of levitation control system perfectly.