摘要
煤灰熔融温度对煤气化过程有很大影响。煤灰流动温度(FT)由灰成分决定,但两者之间的关系尚不明确。采用传统的BP神经网络和AdaBoost优化的BP神经网络来预测煤灰流动温度。结果表明,BP神经网络可以预测煤灰流动温度的变化趋势,但预测结果不是很理想。AdaBoost优化的神经网络的预测结果可以达到很高的精度,预测结果的平均绝对误差为5.81,准确度为99.2%,这也说明了利用AdaBoost优化BP神经网络预测模型预测煤灰流动温度的可行性。
The characteristic temperature of coal ash melting has a great influence on the coal gasification process.The ash flow temperature(FT)is determined by ash composition,but the relationship between them is not clear.In this paper,the traditional BP neural network and AdaBoost Optimized BP neural network are used to predict the ash flow temperature.The results show that BP neural network can predict the change trend of ash flow temperature,but the prediction result is not very ideal.The prediction result of AdaBoost optimized neural network can have better performance.The mean absolute error of the prediction result is 5.81 and the accuracy is 99.2%,which also shows the feasibility of using AdaBoost Optimized BP neural network prediction model to predict coal ash flow temperature.
作者
陈和荆
武成利
李寒旭
马旭龙
谢颖
Chen Hejing;Wu Chengli;Li Hanxu;Ma Xulong;Xie Ying(College of Chemical Engineering,Anhui University of Science and Technology,Huainan 232001,China;Hefei Comprehensive National Science Center Energy Research Insititute,Hefei 230031,China)
出处
《山东化工》
CAS
2022年第19期183-186,192,共5页
Shandong Chemical Industry
作者简介
陈和荆,硕士研究生,主要从事洁净煤技术的研究;通信作者:武成利,教授,博士,从事洁净煤技术的研究。
