摘要
提出了一种光纤传感报警信号的处理技术,光纤传感具有高灵敏度、抗电磁干扰、耐高压抗腐蚀等优点,但报警信号的误报问题一直是光纤周界系统需要解决的问题,而传统的时域门限分析方法对信号的识别准确率不高,不利于降低安防系统报警信号的误报率。利用小波降噪技术,结合信号的时频域特征,构建基于概率的神经网络分类器,可以在很大程度上减少信号的误报。
A fiber-optic sensing alarm signal processing technology is presented.It has great market demand because of the Optical-fiber sensor with high sensitivity,anti-electromagnetic interference,high corrosion resistance,etc.However,it is a problem with the false alarm for the system.Wavelet noise reduction technology combined with time-frequency domain features is used to construct the probabilistic neural network classifiers.The result shows it can largely reduce the false signals alarm.
出处
《中国电子科学研究院学报》
2011年第4期436-440,共5页
Journal of China Academy of Electronics and Information Technology
基金
国家自然科学基金项目(60971078)
关键词
光纤传感
小波降噪
神经网络
optical fiber sensor
wavelet denoising
neural network
