论文部分内容阅读
针对当前水电机组故障样本少,难以对其开展有效诊断的难题,提出了一种综合考虑有功功率、工作水头等工况参数的基于最小二乘曲面的抽水蓄能电站机组异常状态检测模型,即在深入分析有功功率、工作水头对机组运行状态影响的基础上,确定了机组的健康标准状态,根据机组运行状态在不同功率和不同水头下的特性,划分了不同单元,在不同单元内选取能反映机组运行状态的敏感特征参数,分别建立了基于最小二乘曲面的分布式健康模型,将功率、水头等实时在线数据代入分布式健康模型,通过计算机组健康度建立最终的异常状态检测模型。实例应用结果表明,该模型能有效地挖掘机组海量状态数据和真实可靠地进行在线状态评估,从而实现机组异常状态的早期预警。
Aiming at the difficulty of less effective fault diagnosis for hydropower generating units, this paper presents a model based on least square surface for the abnormal state detection of pumped storage power station, which considers the active power and working head condition parameters Based on the analysis of the influence of active power and working head on the operating status of the unit, the health status of the unit is determined. According to the operating characteristics of the unit under different power and different water head, different units are divided into different units, Based on the least square surface distributed health model, the real-time on-line data such as power and water head are substituted into the distributed health model, and the final abnormal state detection model is established by the computer group health. The practical application shows that this model can effectively excavate the massive state data of the generating unit and evaluate the online state accurately and reliably so as to realize the early warning of the abnormal state of the generating unit.