提出改进非劣分类遗传算法(NSGA-Ⅱ)在燃煤锅炉多目标燃烧优化中的应用,优化的目标是锅炉热损失及NOx排放最小化.首先,采用BP神经网络模型分别建立了300MW燃煤锅炉的NOx排放特性模型和锅炉热损失模型,同时利用锅炉热态实验数据对模型进行了训练和验证,结果表明,BP神经网络模型可以很好地预测锅炉的排放特性和锅炉的热损失特性.在建立的锅炉排放特性和热损失BP神经网络模型基础上,采用非劣分类遗传算法对锅炉进行多目标优化,针对NSGA-Ⅱ在燃煤锅炉燃烧多目标优化问题应用中Pareto解集分布不理想、易早熟收敛的问题,在拥挤算子及交叉算子上进行了相应改进.优化结果表明,改进NSGA-Ⅱ方法与BP神经网络模型结合可以对锅炉燃烧实现有效的多目标寻优、得到理想的Pareto解,是对锅炉燃烧进行多目标优化的有效工具,同改进前的NSGA-Ⅱ优化结果比较,其Pareto优化结果集分布更好、解的质量更优.%This paper discussed the application of improved non-dominated sorting genetic algorithm-Ⅱ (NSGA-Ⅱ) to multi-objective optimization of a coal-fired combustion, the two objectives considered are minimization of overall heat loss and NOx emissions from coal-fired boiler. In the first step,this paper proposed the back propagation(BP) neural network to establish a mathematical model predicting the functional relationship between outputs (NOx emissions & overall heat loss of the boiler) and inputs (operational parameters of the boiler) of a coal-fired boiler. It used a number of field test data from a full-scale operating 300MW boiler to train and verify the BP model. The NOx emissions & heat loss predicted by the BP neural network model shows good agreement with the measured. Then, combined BP model and the non-dominated sorting genetic algorithm Ⅱ (NSGA- Ⅱ) to gain the optimal operating parameters which led to lower NOx emissions and overall heat loss boiler. According to the problems such as premature convergence and uneven distribution of Pareto solutions exist in the application of NSGA- Ⅱ , this paper performed corresponding improvements in the crowded operator and crossover operator. The optimal results show that hybrid algorithm by combining BP neural network and improved NSGA- Ⅱ can be a good tool to solve the problem of multi-objective optimization of a coal-fired combustion, which can reduce NOx emissions and overall heat loss effectively for the coal-fired boiler. Compared with non-improved NSGA- Ⅱ , the Pareto set obtained by the improved NSGA- II shows a better distribution and better quality.
展开▼
