基于神经网络多参数融合的钻井过程状态监测与故障诊断

复杂系统状态监测与故障诊断是系统安全运行过程中的重要保障,分析了钻井系统事故状态下特征参数的变化,给出了用神经网络进行故障诊断的流程,在利用样本数据对网络进行训练的基础上建立了稳定的神经网络诊断模型。输入各种状态下的新样本数据,能够得到正确的系统状态识别,通过改进网络算法改进了网络性能。对生产数据的处理结果表明,基于神经网络的多参数融合算法可以很好地识别钻井过程中的不同状态,能够实现状态检测与故障诊断。

Drilling state monitoring and fault diagnosis based on multi-parameter fusion by neural network

State monitoring and fault diagnosis of complicated systems is the significant support for system safe working.The change of characteristic parameters in drilling accident was analyzed.A diagnosis flow chart of neural network was given.A steady diagnosis model of neural network was developed by training the neural network using sample data.The right recognition result of system's state can be gained by imputing new sample data of system's state.The network performance was improved by improving the network algorithm. The data processing results show that the multi-parameter fusion algorithm based on neural network can recognize the different drilling states very well and implement the state monitoring and fault diagnosis.