论文部分内容阅读
为保证水电机组运行的可靠性,通常采用基于振动频率分析的故障诊断技术。但是水电机组故障类型间存在重叠的频率特征,仅凭频率分析不易确定故障类型。因此,文中采用信息融合技术,引入开机过程中的时间和空间特征信息,在特征层采用支持向量机作为信息融合手段,在决策层采用D-S证据理论进行信息融合。实验结果表明,信息融合增加了故障诊断的特征信息,提高了故障诊断系统的诊断能力。
In order to ensure the reliability of hydropower unit operation, fault diagnosis technology based on vibration frequency analysis is usually adopted. However, there are overlapping frequency characteristics between hydropower unit fault types, and it is not easy to determine the fault type only by frequency analysis. Therefore, this paper introduces the information fusion technology, introduces the time and space feature information in the boot process, uses the support vector machine as the information fusion method in the feature layer, and uses the D-S evidence theory to fuse the information in the decision-making layer. Experimental results show that information fusion increases the characteristic information of fault diagnosis and improves the diagnostic ability of fault diagnosis system.