摘要
厂用电是反应火电机组经济性与能效性的重要指标,该文提出一种加权模糊C均值聚类和主客观赋权法结合的厂用电关联特征挖掘方法。首先,针对火电机组辅机设备的历史运行数据,利用因子分析法获取运行指标之间的强弱相关性及对厂用电目标值的影响力,提取影响机组能耗的重要指标,进而对提取出的运行指标进行对应权重的赋值,再进行加权模糊C均值聚类;其次,为克服单一赋权法的缺点,进一步利用层次分析法与熵权法相结合来修正机组能耗评估中各项指标的权重值;最后,通过对某火电厂600 MW机组的10个月历史数据、6个典型负荷区间进行文中方法验证,表明文中模型和算法正确有效。
Power consumption is an important indicator of the economic and energy efficiency of thermal power units,in this paper,an improved weighted fuzzy C-means clustering algorithm is proposed.First of all,according to the historical operation data of auxiliary equipment of thermal power units,the factor analysis method is used to obtain the strong and weak correlation between the operation indicators and the influence on the target value of plant power,and extract the important indicators that affect the energy consumption of the unit,the operating indexes are assigned to the corresponding weights,and the weighted fuzzy C-means clustering is performed.Secondly,to overcome the shortcomings of the single weighting method,the combination of the analytic hierarchy process and the entropy weight method is further used to modify the indicators in the unit energy consumption assessment weight value.Finally,a six-point load interval of 10 months of historical data of a 600 MW unit in a thermal power plant is verified to that the model and algorithm are correct and effective.
作者
秦佳倩
唐海国
张帝
张志丹
朱吉然
马瑞
QIN Jiaqian;TANG Haiguo;ZHANG Di;ZHANG Zhidan;ZHU Jiran;MA Rui(School of Electric&Information Engineering,Changsha University of Science&Technology,Changsha 410114,China;Electric Power Research Institute of State Grid Hunan Electric Power Co.,Ltd.,Changsha 410007,China)
出处
《电力科学与技术学报》
CAS
北大核心
2020年第4期122-127,共6页
Journal of Electric Power Science And Technology
基金
国家自然科学基金(51277015)
国网湖南省电力有限公司科技项目(5216A5180014)。
关键词
火电厂
厂用电
加权模糊C均值聚类算法
主客观赋权
关联特征
thermal power plant
power consumption
weighted fuzzy C-means clustering algorithm
subjective and objective weighting
correlation characteristics
