English

应用科学学报 ›› 2006, Vol. 24 ›› Issue (3): 298-301.

• 论文 • 上一篇    下一篇

基于多层感知机神经网络的智能高度传感器设计

曲国福1,2, 刘宏昭1   

  1. 1. 西安理工大学机仪学院, 陕西西安 710048;
    2. 陕西理工学院仪器系, 陕西汉中 723003
  • 收稿日期:2004-10-12 修回日期:2005-01-07 出版日期:2006-05-31 发布日期:2006-05-31
  • 作者简介:曲国福,博士,副教授,研究方向:智能检测与虚拟仪器,E-mail:zf691105@163.com;刘宏昭,教授,博导,研究方向:机械设计及理论,E-mail:liu-hongzhao@163.com.

Intelligent Altitude Sensor Based on Artificial Neural Networks Using Multilayer Perceptron

QU Guo-fu1,2, LIU Hong-zhao1   

  1. 1. School of Mechanical and Precision Instrument Engineering, Xi'an University of Technology, Xi'an 710048, China;
    2. Department of Instrument, Shanxi University of Technology, Hanzhong 723003, China
  • Received:2004-10-12 Revised:2005-01-07 Online:2006-05-31 Published:2006-05-31

PDF

65

被引次数

3

摘要： 基于大气中的两个物理参量:大气静压力、大气温度以及它们和几何高度的关系,借助于压阻式压力传感器和温度传感器对大气静压力和温度进行测量,并以两个传感器作为多层感知机网络的输入,以几何高度作为网络的输出.利用标准数据采用动批量法(MOBP算法)对网络进行训练,得到网络各层的权值和偏置值,由此可以确定在任意静压力和温度输入作用下,网络输出的精确几何高度值,神经网络的算法可借助DSP芯片实现.实验表明采用该方法设计的传感器比采用曲面拟合的方法具有更高的精确度和抑制传感器的温度漂移和时间漂移的优势.

关键词: 多层感知机, 误差补偿, 高度传感器, MOBP算法

Abstract: Based on the atmospheric pressure and temperature measured by a piezoresistive sensor and a temperature sensor, and their relations with altitude, a novel algorithm for sensor design is proposed.The pressure and temperature sensors are treated as two inputs of a multi-layered perceptron in an artificial neural network, and the altitude as the output.To get weights and offsets for each layer, the ANN is trained with standard data using the MOBP algorithm, which can be implemented on DSP.It can produce accurate altitude at any given pressure and temperature.Experiments indicate that the new sensor provides a higher accuracy than using the curve fitting technique, and have advantages in suppression of sensors' temperature shift and time shift.

Key words: altitude sensor, error compensation, MOBP algorithom, multilayered perceptron

中图分类号: