摘要
根据小波包分析,获得了各频带能量的分布规律,构造了泵阀状态特征向量,训练了RBF神经网络。大量的现场试验证明,构造的故障特征向量与RBF神经网络配合使用的方法可以明显提高泵阀故障诊断的准确率。
According to wavelet analysis,the energy regularity of each frequency band is found,the characteristic vectors for values of pumps are constructed,the RBF neural network is trained.Through a lot of practices,both the characteristic vectors and the RBF neural network are proved to raise the diagnosis rate for valves of reciprocating pumps.
出处
《石油矿场机械》
2011年第1期24-27,共4页
Oil Field Equipment
基金
黑龙江省教育厅科研项目(11515001)
关键词
往复泵
故障诊断
故障特征向量
RBF神经网络
reciprocating pump
fault diagnosis
fault characteristic vector
RBF neural network
