Short residence time of the sorbent in the gas stream and formation of a dense layer of reaction product surrounding its surface influence the sulfur removal efficiency. A practical means of improving the process perf...Short residence time of the sorbent in the gas stream and formation of a dense layer of reaction product surrounding its surface influence the sulfur removal efficiency. A practical means of improving the process performance is to employ fluidized bed reaction in replacement of entrained bed reaction on normally used in cool side desulfurizaiton. This paper describes cold modeling study of a circulating fluidized bed reactor. Several aspects of the problem are discussed: fluidization behavior of CaO, attrition of the sorbent and solids entrainment from the fluidized bed. Mechanisms and key controlling parameters are identified, and an integral model based on rate of attrition and mass balance is developed for predicting steady state mass flows and particle size distributions of the system. A process flow scheme is finally presented for conducting desulfurization tests in the second stage of the study.展开更多
为提高柴油机装配质量和冷试性能,基于柴油机装配冷试基础数据集,选取加州大学欧文分校(University of California Irvine,UCI)机器学习资料库标准数据集中的Seeds、Wine、Wdbc三种数据集,对比支持向量机(support vector machines,SVM)...为提高柴油机装配质量和冷试性能,基于柴油机装配冷试基础数据集,选取加州大学欧文分校(University of California Irvine,UCI)机器学习资料库标准数据集中的Seeds、Wine、Wdbc三种数据集,对比支持向量机(support vector machines,SVM)模型、组合智能算法改进后SVM模型、Transformer模型应用于冷试异常数据的分析效果。结果表明:SVM、改进后SVM,Transformer模型对正常数据和异常数据分类的准确率分别为85.20%、92.54%、97.94%;相比SVM、改进SVM模型,Transformer模型的分类准确率有较大的提高,可用于分析参数异常;排气压力与转矩关系密切,排气压力较大造成转矩增大;排气门开启时间过长导致进气真空度异常,验证了Transformer模型对发动机装配异常识别方法的有效性。展开更多
文摘Short residence time of the sorbent in the gas stream and formation of a dense layer of reaction product surrounding its surface influence the sulfur removal efficiency. A practical means of improving the process performance is to employ fluidized bed reaction in replacement of entrained bed reaction on normally used in cool side desulfurizaiton. This paper describes cold modeling study of a circulating fluidized bed reactor. Several aspects of the problem are discussed: fluidization behavior of CaO, attrition of the sorbent and solids entrainment from the fluidized bed. Mechanisms and key controlling parameters are identified, and an integral model based on rate of attrition and mass balance is developed for predicting steady state mass flows and particle size distributions of the system. A process flow scheme is finally presented for conducting desulfurization tests in the second stage of the study.
文摘为提高柴油机装配质量和冷试性能,基于柴油机装配冷试基础数据集,选取加州大学欧文分校(University of California Irvine,UCI)机器学习资料库标准数据集中的Seeds、Wine、Wdbc三种数据集,对比支持向量机(support vector machines,SVM)模型、组合智能算法改进后SVM模型、Transformer模型应用于冷试异常数据的分析效果。结果表明:SVM、改进后SVM,Transformer模型对正常数据和异常数据分类的准确率分别为85.20%、92.54%、97.94%;相比SVM、改进SVM模型,Transformer模型的分类准确率有较大的提高,可用于分析参数异常;排气压力与转矩关系密切,排气压力较大造成转矩增大;排气门开启时间过长导致进气真空度异常,验证了Transformer模型对发动机装配异常识别方法的有效性。
