基于D-S-CBR的燃料电池系统生产过程故障诊断

Fault diagnosis of the production process of fuel cell system based on D-S-CBR

氢能产业发展迅速,质子交换膜燃料电池系统已实现初步应用广,在车、船、电站领域的应用逐渐推广。由于燃料电池系统的产业化开始时间有限,产品标准化程度较低,在生产过程中容易出现各种故障问题,研发、生产人员难以定位故障点及故障原因,排查及解决故障的时间长,严重影响生产进度。本研究通过将证据融合理论与案例推理故障诊断方法结合,构建一种混合数据的D-S-CBR系统,实现两种类型异构数据的融合及故障诊断。并将此研究应用于燃料电池系统的生产中,辅助研发、生产人员进行生产过程故障诊断,减少故障诊断时间,降低生产成本,提高产品质量。

With the rapid development of hydrogen energy industry,the proton exchange membrane fuel cell system has been initially widely used,and its application in the field of vehicle,ship and power station is gradually promoted.Due to the limited start time of the industrialization of automotive fuel cell engines,the degree of product standardization is low,and various problems are prone to occur in the production process,it is difficult for research and production personnel to locate the fault point and the cause of the fault,and it takes a long time to troubleshoot and solve the fault,which seriously affects the production schedule.By combining the evidence fusion theory and case-based reasoning fault diagnosis method,this study builds a D-S-CBR system with mixed data to realize the fusion and fault diagnosis of two types of heterogeneous data.This research is applied to the production of automotive fuel cell systems to assist engineers in fault diagnosis of production process,reduce fault diagnosis time,reduce production cost and improve product quality.