往复泵故障智能诊断系统的设计  

Design of Intelligent Fault Diagnostic System for Reciprocating Pumps

作　　者：赵志华[1] 吴力[2] 

机构地区：[1]东北石油大学电气信息工程学院,黑龙江大庆163318 [2]大庆油田天然气分公司培训中心,黑龙江大庆163412

出　　处：《化工自动化及仪表》2013年第6期701-705,共5页Control and Instruments in Chemical Industry

基　　金：黑龙江省教育厅科技攻关项目(12531063)

摘　　要：开发了往复泵故障的智能诊断系统,以故障诊断系统为核心,软件部分用Visual C++语言来开发,由软件控制同步进行压力、位置及流量等信号的数据采集和数据库管理。由于不同故障类型对应的信号曲线也不同,所以以压力信号为主,以流量信号为辅作为故障信息;然后应用基于人工智能理论的小波神经网络和小波包分解技术进行数据处理、保存和故障诊断。从小波神经网络诊断的结果可以看出:往复泵故障智能诊断系统诊断速度快,准确性高。The intelligent fault diagnostic system for reciprocating pumps was developed,as for the system software,the Visual C＋ ＋ was used in the software development so as to have data acquisition of pressure,position and flow signal controlled and the data base managed synchronously.Regarding the signal curves from different faults,the pressure signal can be taken as the main fault signal and the flow signal for auxiliary,and then having both wavelet neural network which based on artificial intelligence theory and the wavelet packet decomposition technique applied to data processing,preservation and fault diagnosis.The diagnosis results from wavelet neural network show that this intelligent fault diagnostic system for reciprocating pumps has fast speed and high accuracy.

关 键 词：小波神经网络 往复泵 故障诊断 诊断系统 

分 类 号：TH165.3[机械工程—机械制造及自动化]