摘要
针对某电厂350MW机组W火焰锅炉进行了220～320MW共4个典型负荷的燃烧优化试验，根据试验数据建立了基于不同核函数的基于支持向量机的锅炉性能预测模型，并对其进行了详细对比。结果表明，加法混合核函数预测性能较好，可为可靠准确的燃烧优化奠定基础。目前，基于该模型开发的计算机软件系统已经在350MW机组投入在线试运行，对锅炉运行调节具有一定的指导意义。
Experimental research on combustion optimization of a 350 MW W-flame boiler was performed under four typical conditions with the unit load ranging from 220 MW to 320 MW. According to the test data, the support vector machine based boiler performance prediction models were established on the basis of different kernel functions. Moreover, these models were compared with each other in detail. The results indicate that, the addition mixed kernel function predicts best,which can lay the foundation for reliable and accurate combustion optimization. Currently, this model based computer software system has been put into online trial service for the 350 MW units, which is of guiding significance for boilers＂ operation regulation.
出处
《热力发电》
CAS
北大核心
2014年第3期30-36,共7页
Thermal Power Generation
关键词
W火焰锅炉
燃烧优化
性能预测
支持向量机
核函数
W-flame boiler
combustion optimization
performance prediction
support vector machine
kernel function
