【摘要】 调节阀作为控制系统的重要组成部分,它的故障诊断对于指导控制过程安全稳定地运行至关重要。为提高故障诊断的精确率,解决电动调节阀不同故障间可能存在相互关联的问题,提出一种基于特征指标信息融合的诊断方法。利用电动调节阀可测变量间的关系,计算能够反映电动调节阀不同故障特点的指标,并建立与之对应的神经网络;然后将每个神经网络的输出看作独立的证据体进行D-S证据融合,得到最终的诊断结果。实验结果及现场分析表明:该方法充分利用数据的有效信息,从不同侧面对故障进行诊断,能够有效地应用于电动调节阀的故障诊断,具有较高的应用价值。更多还原

【Abstract】 The control valve acts as an important part of control system, and it’s fault diagnosis is essential to guide the safe and stable operation of the control process. In order to improve the accuracy of fault diagnosis and solve the problem that there may be correlation between different faults of electric control valve, a fault diagnosis method based on information fusion of feature index is proposed. First, using the relationship between measurable variables of electric control valve to calculate indexes that can reflect different fault characteristic of the electric control valve, and neural network corresponding is established. Then the output of each neural network is regarded as an independent evidence body for D-S evidence fusion to obtain the final diagnosis result. Experimental results and on-site analysis show that this method makes full use of the effective information of the data and diagnoses the fault from different sides, it can be effectively applied to the fault diagnosis of electric control valve, and has high application value.更多还原