摘要
基于关联规则的数据挖掘方法已在火电厂汽轮机组的性能优化中取得了较好的应用,但随着大数据时代的来临,传统的数据挖掘方法由于自身缺陷已不能胜任海量数据的挖掘工作。针对此问题,在云计算环境下,基于引入粗糙集中属性约简的基础,在Hadoop平台的Map Reduce架构上对经典关联规则算法Apriori算法进行改进,实现计算并行化以形成能够应对海量数据挖掘任务的新算法。以某1000MW超超临界机组的运行数据为挖掘对象,利用新算法对典型负荷下的历史数据进行挖掘,挖掘出运行参数与性能指标之间的关系,并得到一些可调控参数的运行优化目标值以指导优化运行。挖掘结果表明,新算法可以应用于汽轮机优化目标值的确定,达到节能减排的目的,其所求出的优化目标值来源于机组实际运行数据,具有代表性,能够反映机组的最佳运行状态。
Data mining based on association rules has achieved a good reputation in the performance optimization of the steam turbines in thermal power plant, but with the advent of the era of big data, traditional data mining methods cannot complete the data mining tasks with massive data due to its defects. To solve this problem, the paper introduced the attribute reduction in rough set theory, and then improved the classical Apriori association rules algorithm on the Map Reduce framework of the Hadoop platform under a cloud computing environment. Using this framework, a new algorithm that can deal with the massive data mining tasks was produced. This paper examined use of the CC.Apriori algorithm in mining the historical data under a number of typical loads for a 1000 MW ultra-supercritical unit. Then the relationship between operating parameters and performance indicators was produced and used to guide optimization operation of the stream turbines.Mining results show that the new algorithm can be effectively applied in the determination of the optimization targeted values to achieve the purpose of energy savings. The obtained optimization targeted values are from the actual operation of the unit and they are representative of optimum operation conditions.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2016年第2期459-467,共9页
Proceedings of the CSEE
基金
国家科技支撑计划课题(2013BAA02B01)~~
关键词
大数据
MAP
REDUCE
关联规则
性能优化
目标值
汽轮机组
运行
big data
Map Rreduce
association rules
performance optimization
targeted values
steam turbines
operation