欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
基于发酵生产的特点及建模要求，以某企业燃料乙醇生产过程为研究对象，利用工业生产中的参数及数据，建立了以乙醇发酵效果为目标的BP神经网络模型，以静态模型反映复杂的动态问题。探讨了乙醇发酵生产模型的误差产生原因，并提出改进方案，根据已有经验将相关参数进行了合理组合，调整神经网络模型的输入输出参数结构，以提高仿真模拟效果。通过多次模型改进，使模拟的平均相对误差从10％提高至5．4％，为进一步研究发酵生产建模提供了思路。
英文摘要：
With analyzing characteristics of industrial fermentation process, the artificial neural networks in static modeling of ethanol industrial fermentation have been attempted, The parameters in ethanol fermentation process were firstly investigated, with the input and output parameters of the models selected. Based on the historical production data from a bio-ethanol factory, a BP neural network model was trained, and improvements for another two models, with some reasonable combinations of selected parameters, were discussed to achieve satisfactory simulation results. The last result of the mean relative error has been raised from 10% to 5.4%, which is helpful for the further modeling research of industrial fermentation.
同期刊论文项目
同项目期刊论文
Process-based Graphical Approach (PGA) for Simultaneous Targeting and Design of Regeneration Recycli
Establishment and solution of eight-lump kinetic model for FCC gasoline secondary reaction using par
Synthesis of dimethyl carbonate from urea and methanol catalyzed by the metallic compounds at atmosp
On the use of Graphical Method to Determine the Targets of Single-contaminant Regeneration Recycling
Study on co-feed and co-production system based on coal and natural gas for producing DME and electr
Analysis on the Interactions of Parameters of Single-contaminant Regeneration Recycling Water System
期刊信息
位置：