垃圾焚烧发电污染物排放过程建模与优化  

Modeling and optimization of pollutants emission of waste incineration

作　　者：李大中[1] 唐影[1] 

机构地区：[1]华北电力大学自动化系,河北保定071003

出　　处：《可再生能源》2015年第1期118-123,共6页Renewable Energy Resources

基　　金：河北省自然科学基金资助项目(F2011502001)

摘　　要：提出了一种融入灰色关联度分析的最小二乘支持向量机建模方法,建立了垃圾焚烧发电污染物排放过程模型。验证结果表明,模型预测值与实际值的最大相对误差为7.8%,模型拟合平均绝对百分误差最大为4.67%,外推平均绝对百分误差最大为3.98%,模型能够较好地模拟垃圾焚烧过程中污染物排放过程特性。在此基础上,拟合设计了垃圾焚烧过程排放烟气污染物多目标优化函数,以二噁英排放值为主要评价指标,从Pareto最优解集合中选取出二噁英排放值较低的最优解子集。结果表明,优化计算值明显低于实际值,验证了设计方法的可行性和有效性。This paper presented a method of least squares support vector machine modeling which in- tegrated gray relational analysis, established model of pollutants emission of waste incineration power generation. Validation results showed that the maximum relative error of the model predicted value and the actual value was 7.8%, model＇s fitting mean absolute percentage error （MAPE） was 4.67% and ex- trapolation MAPE was 3.98%, the model could simulate the process characteristics of the pollutants e- mission of waste incineration. On this basis, the multi-objective optimization function of pollutants e- mission was designed .When dioxin emissions was the main evaluation index, the Pareto optimal subset was selected. The results showed that optimization results were lower than actual values of flue gas e- missions and verified the feasibility and effectiveness of this method.

关 键 词：垃圾焚烧发电 污染物排放 灰色关联度 建模 优化 

分 类 号：TK6[动力工程及工程热物理—生物能] X705[环境科学与工程—环境工程]