针对锅炉炉渣含碳量难以在线实时测量及测量精度低等问题,采用了基于神经网络结合遗传算法的新型软测量模型,通过遗传算法训练BP神经网络权值的方法,实现了对某热电厂220 t/h四角切圆煤粉锅炉炉渣含碳量的软测量。以锅炉实际运行数据为输入值得到的模型输出结果表明,该方法具有较好的软测量效果。 Aiming at the problem that the carbon content of boiler slag is difficult to be measured online in real time and the measuring accuracy is low, a new type of soft sensor model based on neural network and genetic algorithm is adopted. By using genetic algorithm to train the weight of BP neural network, Soft horizons of carbon content in square tangential pulverized coal. The output of the model obtained from the actual operating data of the boiler shows that this method has a good soft-sensing effect.