大型电子设备故障智能诊断技术研究

Research on Intelligent Diagnosis Technology for Large Electronic Equipment Faults

针对当前大型电子设备故障诊断过程中受干扰程度过高导致诊断结果存在误差等问题,结合特征提取算法,对设备运行故障特征参数进行采集和分类,并根据采集和分类结果定位设备故障区域,利用神经网络技术优化设备数据异常诊断流程,从而完成对大型电子设备故障智能诊断技术的研究。实验证实,相对于传统的故障诊断方法,结合特征提取和神经网络技术的大型电子设备故障智能诊断技术更符合研究要求。

In view of the problem that the diagnosis result is too large due to the high degree of interference caused by the current large-scale electronic equipment fault diagnosis process,the feature extraction algorithm is used to collect and classify the equipment operation fault characteristic parameters,and the equipment fault area is performed according to the collection and classification results.Positioning,combined with neural network technology to optimize the device data abnormal diagnosis process,thus completing the research on large-scale electronic equipment fault intelligent diagnosis technology.The experiment proves that compared with the traditional fault diagnosis method,the large-scale electronic equipment fault intelligent diagnosis technology combined with feature extraction and neural network technology is more in line with the research requirements.