基于GA-WNN模型的差动螺管电感式位移传感器的温度补偿  

Temperature Compensation for Differential Coil Inductance Displacement Sensor Based on GA-WNN

作　　者：乔岩 卢文科[1] 左锋[1] 丁勇[1] QIAO Yan;LU Wen-ke;ZUO Feng;DING Yong(College of Information Science and Technology,Donghua University,Shanghai 201620,China)

机构地区：[1]东华大学信息科学与技术学院,上海201620

出　　处：《自动化与仪表》2020年第3期73-76,共4页Automation & Instrumentation

基　　金：国家自然科学基金项目(61274078);中国纺织工业联合会“纺织之光”应用基础研究项目(J201618)。

摘　　要：针对差动螺管式电感位移传感器温度漂移的问题,提出了一种遗传优化小波神经网络(GA-WNN)算法的温度补偿模型。用差动螺管式电感位移传感器的位移和温度的二维标定试验数据,建立GA-WNN模型。该模型利用遗传算法对小波神经网络的参数进行全局优化,克服了小波神经网络易陷入局部最优解的不足。试验结果表明,优化后的零点温度系数提高了2个数量级,灵敏度温度系数提高了1个数量级,实现了对传感器的温度补偿。In order to solve the problem of temperature drift of differential coil inductance displacement sensor,a genetic optimization wavelet neural network(GA-WNN) algorithm temperature compensation model is proposed. The GAWNN model is established with the two-dimensional calibration experiment data of displacement and temperature of the differential coil inductance displacement sensor. The GA-WNN model uses genetic algorithm to optimize the parameters of wavelet neural network globally,improving the defect that wavelet neural network is easily trapped in local optimal solution. The experimental results show that the temperature coefficient of zero point after compensation is increased by two orders of magnitude,and the sensitivity temperature coefficient is increased by one order of magnitude. The GA-WNN model implements temperature compensation.

关 键 词：差动螺管式电感位移传感器 温度补偿 遗传优化小波神经网络算法 预测精度 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]