CAJ | 학술논문

以120种煤样为数据基础，采用布谷鸟算法（ CS）优化BP（ BackP ropagatino ）神经网络，建立了CSBP模型对单煤、煤掺添加剂和配煤等3类样本的煤灰变形温度（ DT）样本进行预测。模型以煤灰化学成分及其组合参数等13个变量作为输入量，以变形温度（ DT）作为输出量。 CSBP模型预测结果与BP神经网络模型预测结果进行对比发现，无论是单煤、煤掺添加剂还是配煤，CSBP模型较BP模型对煤灰变形温度（ DT）的预测都更加精准，平均相对误差分别达到了3．11％、4．08％和4．22％。另外，对比3类样本预测结果发现，无论是CSBP模型还是BP模型，相比单煤预测而言，煤掺添加剂及配煤的预测误差都有明显的增加。
이120충매양위수거기출，채용포곡조산법（ CS）우화BP（ BackP ropagatino ）신경망락，건립료CSBP모형대단매、매참첨가제화배매등3류양본적매회변형온도（ DT）양본진행예측。모형이매회화학성분급기조합삼수등13개변량작위수입량，이변형온도（ DT）작위수출량。 CSBP모형예측결과여BP신경망락모형예측결과진행대비발현，무론시단매、매참첨가제환시배매，CSBP모형교BP모형대매회변형온도（ DT）적예측도경가정준，평균상대오차분별체도료3．11％、4．08％화4．22％。령외，대비3류양본예측결과발현，무론시CSBP모형환시BP모형，상비단매예측이언，매참첨가제급배매적예측오차도유명현적증가。
On the basi of 120 coal ash samples, a CSBP model basedo n BP ( Back Propaga tion) Neural Ne twork optimized by Cuckoo Search ( CS ) was proposde for predicting the ash deformation temperature of single coals, coals mixed witha ddictives and mixed coals.The thirteen chemical composition parameters and combined parameters were employed as inputs, and the ash deformation temperature was used as output of the CSBP model.The results show that whether single coal, coal mixed with additivesor mixed cola s, CSBP modleahsa bettre perfor mance compared with BP model and the average relative errors are reduced to 3.11%, 4.08%and 4.22%, respectively.In addition, comparing the prediction results of three kinds of samples,both the CSBP model and BP model haveh igher prediction errors for coals mixed with addicit ves and mixed coals more ht an that for single coals.