论文部分内容阅读
分析了凝汽器的传热特性,利用660MW机组DCS采集到的数据,通过多元回归分析了凝汽器真空与其影响因素之间的关联关系,得到了偏相关系数,为真空预测模型提供了理论依据.应用主元分析与粒子群BP神经网络相结合的方法,给出了凝汽器真空预测模型,实现了对真空值的提前预测.通过凝汽器预测真空值与监测值的对比,判断此时的真空运行状态是否合理,实现凝汽器运行状况的软测量,为凝汽器的故障诊断提供理论依据,从而提高了机组的运行效率,保证机组的安全可靠运行.
The heat transfer characteristics of the condenser were analyzed. Using the data collected by 660MW unit DCS, the correlation between the condenser vacuum and its influencing factors was analyzed by multiple regression and the partial correlation coefficient was obtained, which provided the theory for the vacuum prediction model Based on the combination of principal component analysis and particle swarm optimization BP neural network, the condenser vacuum prediction model is proposed to predict the vacuum value in advance. By comparing the predicted value of vacuum with the monitored value of the condenser, At this time, whether the vacuum operation status is reasonable and the soft measurement of the condenser operating condition is realized, which provides a theoretical basis for the fault diagnosis of the condenser, thereby improving the operation efficiency of the unit and ensuring the safe and reliable operation of the unit.