论文部分内容阅读
为了解决汽轮发电机组的性能检测和故障诊断问题,将独立主元分析引入汽轮机性能监控领域,提出了一种基于独立主元分析(ICA)的电厂机组性能监测与评估新方法。通过ICA算法计算数据的独立主元,进一步计算监控统计量I2,I2和SPE来监测和评估系统的运行。若监控统计量在控制置信限以下,则认为系统运行正常;若统计量超过控制限,则判断为系统有故障或异常发生,运行和维修人员可以根据监测结果及时排查故障发生的原因,消除安全隐患,从而确保机组的安全稳定运行。某电厂机组故障数据仿真研究试验验证了该方法的有效性和合理性。
In order to solve the problem of performance testing and fault diagnosis of turbogenerator units, an independent principal component analysis is introduced into the field of turbine performance monitoring. A new method for monitoring and evaluating the performance of power plant units based on Independent Principal Component Analysis (ICA) is proposed. ICA algorithm to calculate the independent elements of the data, and further calculate the monitoring statistics I2, I2 and SPE to monitor and evaluate the operation of the system. If the monitoring statistic is below the control confidence limit, the system is considered to be operating normally; if the statistic exceeds the control limit, it is determined that the system is faulty or abnormal, and the operation and maintenance personnel can timely investigate the cause of the fault according to the monitoring result and eliminate the safety Hidden trouble, thus ensuring the safe and stable operation of the unit. A power plant unit fault data simulation study verified the effectiveness and rationality of this method.