论文部分内容阅读
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。
The performance of tubular flow guide bearing has a great influence on the vibration characteristics and stable operation of the turbine. In this paper, a H-K clustering logic regression model is proposed to evaluate the wear performance of tubular guide. Taking the vibration, swing amplitude and operating parameters of Unit 3 of the Yellow River Hekou Hydropower Station as independent variables, the operating status of hydroconductive bearings is taken as the dependent variable. In order to enhance the model generalization ability, HK clustering method is introduced to discretize the independent variables Through the establishment of logistic regression model between variables, the bearing performance evaluation of turbine guide bearing is realized. The results show that the turbine shaft slewing signal and the generator shaft vibration signal can better explain the change of the performance of the hydrofoil bearing. At the same time, through the spectrum analysis of the characteristic signal that the model has a significant influence on the performance of the hydrostatic bearing, the hydrostatic bearing wear The main reason is the offset of the unit axis and the unbalanced electromagnetic tension.