转子机械故障诊断仪器系统

A NOVEL ROTOR FAULTS DIAGNOSIS INSTRUMENT

针对转子机械故障所具有的相关性和模糊性的特点 ,提出了基于组合式模糊神经网络的分布式转子故障诊断仪器系统。其中 ,分布式转子故障诊断仪器系统可以有效地对一机组的转子实现多通道振动信号同步、整周期、高速信号采集 ,通过信号处理进行特征提取 ;而基于组合式模糊神经基金项目 :中国石化总公司科技发展项目资助 (395 0 17)。网络转子故障诊断系统 ,可有效地提高对具有相关性和模糊性的转子故障的诊断能力。文中详细讨论了仪器系统的设计原理、故障诊断模型 ,并给出了实验结果。

With the view of the mechanical fault charac teristics of the rotor (such as correlation and fuzziness) , this paper puts forward a novel distributed rotor faults diagnosis instrument based on modular fuzzy neural networks . The distributed instrument system samples the multi channel vibration signals with synchronization and high speed, and then extracts the fault features with signal processing . A two level integration strategy is employed in the modular fuzzy neural networks based diagnosis model . The first level is composed of a fuzzy BP neural networks that determines which fuzzy neural networks block at the second level is activated according to the output member function values .The second level is composed of six fuzzy BP neural networks blocks , each of six blocks is further applied to diagnose some similar faults . The inference principle of the model is that the output node with larger member function value is first activated . With the input fault feature data , the model yields diagnosis conclusion that gives the possible faults with their corresponding member function value and inference route . The experimental results show that this model effectively improves the ability to diagnose the rotor faults and gives more information in the diagnosis conclusion . The instrument design , the fault diagnosis model, and experimental results are discussed in detail.