基于样条权函数神经网络的传感器故障诊断  

Fault Diagnosis of Sensor Based on Spline Weight Function Neural Network

作　　者：杨海楠[1] 张代远[1,2,3] 

机构地区：[1]南京邮电大学计算机学院,江苏南京210003 [2]江苏省无线传感网高技术研究重点实验室,江苏南京210003 [3]南京邮电大学计算机技术研究所,江苏南京210003

出　　处：《计算机技术与发展》2014年第6期204-207,共4页Computer Technology and Development

基　　金：江苏高校优势学科建设工程资助项目(yx002001)

摘　　要：在技术高速发展的今天,传感器用于各行各业,加之这些年来,家用电器、汽车、信息产业三方面的飞速发展,传感器需求量增大,传感器故障诊断技术变得尤为重要,并且对提高系统的可靠性具有重要意义。利用神经网络对传感器故障进行诊断的方法克服了分析冗余方法需要的系统精确数学模型的问题,并且可以处理非线性数据。文中详细阐述了样条权函数神经网络的结构、原理,在分析传感器主要故障的基础上,提出了样条权函数神经网络的传感器故障诊断方案。Matlab仿真和模拟实验结果表明,样条权函数神经网络可以解决传感器故障检测问题。With rapid development of technology,the sensors has been used in various industries,coupled with the years,the fast development of three areas of household appliances,automobiles,information industry,increasing demand of sensor,the sensor fault diagnosis technology has become particularly important,and to improve system reliability is significant.Using neural network to analyze sensor faults overcomes the problem of redundancy methods which require accurate mathematical model of the system,and can handle non-linear data.It describes the spline weight function neural network structure,principle,and proposes spline weight function neural network means based on analyzing main sensor fault diagnosis.Matlab simulation and simulation results show that the spline weight function neural network can solve the problem of sensor fault detection.

关 键 词：样条权函数 神经网络 传感器 故障诊断 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]