基于H-K聚类逻辑回归的贯流式机组水导轴承磨损性能评估研究

发布时间：2018-08-06 09:00

【摘要】：贯流式机组水导轴承性能对机组振动特性和稳定运行有很大影响,对此本文提出了一种基于H-K聚类逻辑回归模型用于实现贯流式机组水导轴承磨损性能评估。以黄河河口水电站3#机组振动、摆度幅值和工况参数等作为自变量,水导轴承运行状态作为因变量,同时为了增强模型泛化能力,引入H-K聚类方法对自变量进行离散化处理,通过建立变量之间的逻辑回归模型实现对机组水导轴承磨损性能评估。研究结果表明:机组轴系摆度信号和机组轴系振动信号可以更好地解释水导轴承性能变化,同时通过模型对水导轴承性能显著影响的特征信号频谱分析推断,机组水导轴承磨损的主要原因是机组轴线偏移和不平衡电磁拉力影响所致。
[Abstract]:The performance of water guide bearing of tubular unit has great influence on the vibration characteristic and stable operation of unit. In this paper, a kind of H-K clustering logic regression model is proposed to evaluate the wear performance of water guide bearing of tubular unit. In order to enhance the generalization ability of the model, H-K clustering method is introduced to discretize the independent variables, such as the unit vibration, the swing amplitude and the operating condition parameters of the hydro-electric unit in the Yellow River estuary hydropower station as independent variables, and the running state of the water guide bearing as the dependent variable, and in order to enhance the generalization ability of the model, the H-K clustering method is introduced. A logical regression model between variables is established to evaluate the wear performance of water guide bearing. The results show that the swing signal of shafting and vibration signal of shafting can better explain the change of hydraulic bearing performance, and at the same time, it can be inferred from the spectrum analysis of characteristic signal which has a significant effect on the performance of water guide bearing. The main cause of wear of hydraulic bearing is the influence of axis deviation and unbalanced electromagnetic pull.
【作者单位】：西安理工大学西北旱区生态水利工程国家重点实验室培育基地;西安理工大学水利水电学院;
【基金】：国家自然科学基金项目(51279161);国家自然科学基金重点项目(51339005) 陕西省水利科技计划项目(2015slkj-04)
【分类号】：TV738

【相似文献】