【摘要】 本文提出了对机械设备运行状态进行评估的新方法———支持向量数据描述方法。该方法应用在机械故障诊断和状态监测中,仅仅依靠正常运行时的数据信号,而不需要故障数据,就可以监测机器的运行状态。给出了机组运行状态优劣的定量指标,从而为设备管理和预知维修提供科学的决策依据。将该方法应用于某炼油厂关键设备的运行状态评估中,及时、正确地评价出设备状态异常,为成功诊断出螺栓裂纹的早期故障提供帮助。更多还原

【Abstract】 A new method of condition evaluation of mechanical equipment——support vector data description is proposed.By applying this method to mechanical condition monitoring and fault diagnosis,machine conditions can be monitored only by using normal condition signals instead of abnormal condition signals.With this method the machine set conditions,normal or abnormal,can be described by using quantitative indexes,and the scientific decision-making basis for equipment management and predictive maintenance can be offered.This method is used to evaluate the condition of the key equipment of an oil refinery,and it evaluates an abnormal condition of the equipment correctly in time and contributes to a successfull diagnosis of the incipient fault of a bolt crack.更多还原