摘要
海底油气输送管道漏磁检测装置工作于高温高压环境下,其中的InSb霍尔传感器对温度敏感,需要补偿温度误差。该文构建了多传感器融合模型,将多个霍尔传感器和温度传感器的输出用径向基函数(RBF)神经网络进行融合,用遗传算法对网络进行训练。实验室检测数据和反演出的缺陷形状表明,采用神经网络融合方法进行误差补偿,简单方便,霍尔传感器输出的平均温度敏感系数降低了两个数量级。
The equipment to inspect submarine oil & gas transportation pipelines often works under high temperature and high pressure. The InSb Hall sensors in the equipment which are sensitive to temperature need to be compensated. A multi-sensor fusion model is built. The test data of multiple magnet sensors and a temperature sensor are processed by a radial basis function(RBF) neural network. Genetic algorithm is chosen to train the netowrk. The lab-tested data and the simulation shapes of defects show that the temperature error compensation made by neural network fusion is simple and convenient. The mean temperature sensitive coefficient is reduced sharply to less than 1/100.
出处
《工业仪表与自动化装置》
2005年第4期17-19,25,共4页
Industrial Instrumentation & Automation
基金
国家863计划(2001AA602021)资助
关键词
温度误差补偿
神经网络
数据融合
漏磁检测
temperature error compensation
neural network
data fusion
MFL detection