摘要
光纤振动预警系统可自动采集周边振动信号,面对大量复杂的振动信号,如何准确识别目标振源是系统研究的难点。针对光纤振动安全预警系统采集到的振动信号进行属性特征分析,建立相应的特征模型,并建立振源属性特征模型,包括识别下雨振源的能量信息熵模型,以及区分机械施工和车辆经过振源的基频稳定性模型等。通过振源识别算法,提高了振源类型识别的准确性。测试结果表明,特征模型的设计和选择合理,识别准确率高。
The collected vibration signals can be detected by Optical Fiber Vibration pre-Warning System(OFVWS).It is difficulty that how to identify vibration source accurately from the collected vibration signals.The attribute features of the vibration signals collected by the OFVWS are researched,and attribute feature models are established respectively.The established attribute feature models mainly contain energy information entropy model to identify raindrop vibration source and the fundamental frequency stability model to distinguish construction machine et al.Test results show that vibration source attribute feature model can identify different kinds of vibration source accurately.The vibration source identification accuracy can be improved though the identification algorithm.Test results show that the design and selection of the feature model are reasonably,and the rate of identification is well.
出处
《光学技术》
CAS
CSCD
北大核心
2016年第1期89-96,共8页
Optical Technique
关键词
光纤振动安全预警系统
振源识别
属性特征
能量信息熵
基频稳定性
fiber optic vibration safety early warning system
vibration source identification
property characteristics
energy information entropy
fundamental frequency stability