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.
出处
《化工自动化及仪表》
CAS
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)
关键词
小波神经网络
往复泵
故障诊断
诊断系统
wavelet neural network, reciprocating pump, fault diagnosis, diagnostic system
