共查询到20条相似文献,搜索用时 15 毫秒
1.
通过对补料时间、方式和补料液浓度变化(特别是补加氮源)对D-核糖发酵过程影响,确定了D-核糖发酵的补料工艺。按此工艺条件,发酵的时间为72 h,D-核糖的产量93.83 g/L,剩余葡萄糖浓度为4 g/L,转化率为0.284 3 g/g,生产强度为1.303 g/(L.h)。与不补料相比,D-核糖产量提高了95.9%。 相似文献
2.
Sun Tao Liu Beihui Li Zuohu 《Journal of chemical technology and biotechnology (Oxford, Oxfordshire : 1986)》1997,69(4):429-432
A novel fed-batch solid state fermentation process was developed in order to avoid problems associated with high initial nutrient concentration, while retaining advantages from high total effective salt concentration. Cellulase production by Trichoderma viride SL-1 was selected as the experimental model. Ammonium sulphate solution was atomized and fed to the culture by pneumatic transfer. Different feed modes were investigated that resulted in improved enzyme productivity. © 1997 SCI. 相似文献
3.
针对啤酒发酵温度控制过程的大惯性、大时滞及非线性等特点,将传统模糊PID控制算法进行优化并改进,提出了模糊PID智能控制算法,当偏差较大时采用响应速率快的模糊控制,偏差较小时采用多层神经网络PID控制算法。MATLAB仿真结果证实该控制算法提高了啤酒发酵温度控制过程的静态误差和动态响应速度,并且具有适应环境变化的学习能力。 相似文献
4.
以供应链多级库存为研究背景,建立以生产为中心的供应、生产和销售3个环节的多级库存集成化动态模型,并对模型进行仿真优化。结合训练神经网络的混合算法GA-BP算法,提出了基于遗传算法与人工神经网络相结合的优化预测模型。最后给出实例说明GA-BP算法优化预测模型的求解过程,验证了模型的可行性。 相似文献
5.
6.
7.
发酵过程中神经网络训练样本的选取 总被引:5,自引:1,他引:4
提出一种新的样本选择方法———统计平均法 ,并以三层BP网络青霉素产量预报为例进行验证 ,结果显示该方法在不降低预报精度的情况下 ,能显著减少训练样本数目。相比Kohonen网络法和Kennard Stone法等其它样本选择方法 ,该方法更为简单可行 相似文献
8.
9.
10.
11.
12.
The copper flash smelting process neural network model (CFSPNNM) was developed, its input layer includes eightnodes: oxygen grade (OG), oxygen volume per ton of concentrate (OVPTC), flux rate (FR) and quantities of Cu, S, Fe, SiO2and MgO in copper concentrate; output layer includes three nodes: matte grade, matte temperature and Fe/SiO2 in slag, andnet structure was 8-13-10-3. Then, the internal relationship between the technological parameters and the objectiveparameters was built after the CFSPNNM was trained by using GA-BP algorithm. Moreover, the technological parameterswere optimized by using genetic algorithms (GA) to make energy consumption the lowest. Simulation results showed that theCFSPNNM had high prediction precision and good generalization performance. Compared with the practical average data, theenergy consumption can be reduced by 6.8% if the smelting process is controlled by adopting the optimized technologicalparameters. 相似文献
13.
基于修正的离心压缩机性能的模糊建模方法 总被引:1,自引:0,他引:1
提出利用压缩机运行数据样本建立压缩机性能的模糊控制模型的方法,并将神经网络引入到压缩机性能模型当中,修正模糊控制模型的输出,提高模型精度。仿真结果表明,该方法有效且建模精度优于Elman网络和单纯的模糊控制,模型的输出精度较高,实现了压缩机高精度模型的建立。 相似文献
14.
15.
利用啤酒废酵母间歇发酵合成谷胱甘肽的研究 总被引:3,自引:0,他引:3
研究利用啤酒废酵母生产谷胱甘肽的目的是降低谷胱甘肽生产成本、提高啤酒废酵母附加值。研究考察了在2升通气搅拌罐中通气量、搅拌速度、初始葡萄糖浓度以及废酵母加入量对谷胱甘肽合成的影响。实验表明,好氧活化可以显著提高酵母细胞内的谷胱甘肽含量。由于啤酒废酵母的添加量较大,使得反应液中菌体浓度较高,发酵过程中保持较大的通气量和搅拌速率有利于提高细胞活性和促进谷胱甘肽的积累。通过实验确定了2L发酵罐中较佳的操作参数为搅拌速度500rmin-1,通气量6 LL-1min-1。过高的初始葡萄糖浓度对谷胱甘肽的合成有一定的抑制作用,比较合适的初始葡萄糖用量为加入的废酵母湿重的10%。废酵母加入量增大会导致胞内谷胱甘肽含量下降,但由于细胞干重的大幅度增加,在实验范围内,最终单位反应器体积的谷胱甘肽产量则随废酵母加入量增大而增大。实验表明,废酵母加入量在湿酵母为100~300gL-1之间是合适的。 相似文献
16.
In this paper, a new approach using artificial neural network and genetic algorithm for the optimization of the thermally coupled distillation is presented. Mathematical model can be constructed with artificial neural network based on the simulation results with ASPEN PLUS. Modified genetic algorithm was used to optimize the model. With the proposed model and optimization arithmetic, mathematical model can be calculated, decision variables and target value can be reached automatically and quickly. A practical example is used to demonstrate the algorithm. 相似文献
17.
基于全面关注间歇发酵过程中间状态的思想,提出由求解一系列端点时间不固定最优控制子问题形成的新型优化控制策略,并在优化目标函数中加入了菌体平均生长速率和流加时间间隔对发酵产量的影响因素.在此基础上提出基于遗传算法的最优控制策略实现算法,同时获得了最优流加时间间隔及相应的最优流加速率.将该方法在青霉素发酵过程进行仿真,将仿... 相似文献
18.
豆粕水解液为氮源细菌厌氧流加发酵生产L-乳酸 总被引:9,自引:0,他引:9
采用细菌厌氧发酵法生产L-乳酸,由实验确定了最佳接种量、发酵温度和pH调节剂,考察了初始葡萄糖浓度对L-乳酸生产的影响,确定初始糖浓度为70~90 g/L时得率、产率、最终生物量分别达到92.68 g/g, 3.17 g/(L×h)和8.5′107 mL-1. 为进一步降低L-乳酸生产成本,以豆粕水解液为氮源代替酵母粉,同时应用流加发酵技术,L-乳酸产量、得率、产率及转化率分别达到155 g/L, 95.5 g/g, 1.64 g/(L×h)和96.9%. 在保证L-乳酸最终浓度的同时可降低生产成本,为进一步工业化奠定了基础. 相似文献
19.
20.
《分离科学与技术》2012,47(10):1472-1484
Poly (vinyl alcohol) membranes were prepared by in-situ crosslinking of poly(vinyl alcohol) with glutaraldehyde as crosslinking agent and hydrochloric acid as catalyst and used for dehydration of IPA mixtures. Effects of feed composition, operating temperature, vacuum pressure, and Reynolds number on the permeation performance of the membranes were evaluated. Eighty-nine experimental data was applied to investigate ANN modeling. A multi layered feedforward neural network was applied to model the PV membranes. Two major training algorithms and optimum number of neurons and layers were investigated. As a result, Bayesian regularization successfully predicted experimental data. Different network structures were optimized, using multi object genetic optimization algorithm. The results concluded that the network with structure composing two hidden layers performs better than the other with one hidden layer, and also there is an excellent compatibility between the experimental data and the predicted values of optimum network structure (4:3:2:2). Furthermore, the optimum network was applied to predict extrapolation data and the results showed that this network can extrapolate data as well as interpolating. 相似文献