具备自动特征提取能力的智能监测系统  

An intelligent monitoring system with the capability of automated features selection

作　　者：申志刚[1] 何宁[1] 李亮[1] 

机构地区：[1]南京航空航天大学机电学院,南京210016

出　　处：《哈尔滨工业大学学报》2010年第9期1495-1499,共5页Journal of Harbin Institute of Technology

基　　金：国际科技合作项目(2008DFA71750);国家科技支撑计划重点项目2008BAF32B00

摘　　要：为了减少加工状态监测系统开发的时间和成本,提出自动敏感特征提取方法,自动选择合适的传感器和信号处理技术来提取出"敏感特征".针对高速铣削过程中的刀具磨损监测,采用切削力、振动、声音和声发射传感器来采集信号,并运用时域、频域和小波分析技术对信号进行处理.试验结果表明:该方法可自动地进行传感器和信号处理技术的选择,提取出的敏感特征适合于自学习监测系统应用.To reduce the development time and cost, an automatic sensory feature selection method is proposed for the systematic design of condition monitoring systems for machining operations. Force, acceleration, sound and acoustic emission sensors were used in high-speed milling operations. The time domain, frequency domain and wavelet analysis technique were employed to process the signals. Gradual tool wear was used for evaluating the proposed self-learning automated sensory feature selection approach. The experimental results show that the suggested algorithm can be applied in an automated, self-learning monitoring system for the selection of the most sensitive sensors.

关 键 词：智能监测 传感器 信号处理 特征量 高速铣削 

分 类 号：TG506.1[金属学及工艺—金属切削加工及机床] TN911[电子电信—通信与信息系统]