| 查看: 310 | 回复: 4 | |||
| 当前主题已经存档。 | |||
515825903931银虫 (正式写手)
|
[交流]
10金币求助翻译润色
|
||
|
摘要如下,软件翻译拒绝 基于神经网络的传爆药废水COD去除率预测研究 摘要:为预测超临界水氧化法处理二硝基重氮酚生产废水的COD(chemicalo xygen demand)去除率,采用HXDK-01-A间歇式超临界水氧化实验装置处理实际工业生产废水,主要考察反应温度、反应压力、停留时间和过氧量对COD去除率的影响。采用实验数据,以反应温度、反应压力、停留时间和过氧量为网络输入,COD去除率为网络输出,以Matlab为平台建立了Elman神经网络预测模型。神经网络模型预测的均方差为0.0418,单个最大误差为-0.3231,最小误差为0.0296;多元回归分析拟合数据的均方差为0.3149,单个最大误差为0.8830,最小误差为0.2200,神经网络预测结果明显优于多元回归分析结果。说明采用神经网络模型预测超临界水氧化法的废水COD去除率是可行的。 关键词:环境科学;超临界水氧化;二硝基重氮酚;Elman神经网络;废水处理 Elman Model in The Prediction of The COD Removal Rate of The Booster explosive wastewater Abstract: In order to predict the COD (chemical oxygen demand)removal rate of the DDNP wastewater which was carried out by supercritical water oxidation(SCWO), uses the HXDK-01-A intermittence type supercritical water oxidation device deal with the actual industrial production wastewater, main inspection reaction temperature,reaction pressure,residence time,oxygen excess to COD removal rate influence. Using experimental data,a single hidden layer Elman prediction model is established using the reaction temperature,reaction pressure,residence time,oxygen excess as input variables,the COD removal rate as output. The MSE of the Elman model is 0.0418,the biggest error is - 0.3231, the least error is 0.0296;compared with Elman model, the MSE of the multiple regression is 0.3149, he biggest error is 0.8830, the least error is 0.2200,the Elman Neural network prediction results are better than the results of multiple regression analysis.The result shows that the Elman model can be adopted to the prediction of the COD removal rate of the wastewater carried out by SCWO. Key words:Supercritical water oxidation;Diazodinitrophenol;Elman neural network;wastewater treatment |
» 猜你喜欢
不要再数国自然申请书的 filecode 的分隔符个数了
已经有21人回复
投英文期刊如何查重
已经有5人回复
伯胺上甲基求助
已经有7人回复
生命口面上会评结束了吗大家有知道结果吗?现在还没有结果正常不?
已经有8人回复
跨出版社商投稿
已经有5人回复
5个%2F,非固定段22个字母
已经有7人回复
生命口C13面上会评时间
已经有10人回复
生生命学部会评
已经有4人回复
H口,面上,时间戳7月7日。
已经有3人回复
小木虫没落了,除了祈祷帖子,几乎看不到有价值的帖子
已经有14人回复
myhaoqq
铁杆木虫 (著名写手)
小木虫警备司令员
- 翻译EPI: 1
- 应助: 17 (小学生)
- 金币: 6846.9
- 散金: 100
- 红花: 1
- 帖子: 1859
- 在线: 47.8小时
- 虫号: 334363
- 注册: 2007-03-30
- 性别: GG
- 专业: 能源化工

2楼2009-04-22 21:25:36
515825903931
银虫 (正式写手)
- 应助: 0 (幼儿园)
- 金币: 356
- 散金: 10
- 红花: 1
- 帖子: 366
- 在线: 15.9小时
- 虫号: 376450
- 注册: 2007-05-19
- 专业: 化工
3楼2009-04-22 21:44:40
myhaoqq
铁杆木虫 (著名写手)
小木虫警备司令员
- 翻译EPI: 1
- 应助: 17 (小学生)
- 金币: 6846.9
- 散金: 100
- 红花: 1
- 帖子: 1859
- 在线: 47.8小时
- 虫号: 334363
- 注册: 2007-03-30
- 性别: GG
- 专业: 能源化工
★ ★ ★ ★ ★ ★ ★ ★ ★ ★
515825903931(金币+10,VIP+0): 4-22 22:08
515825903931(金币+10,VIP+0): 4-22 22:08
|
The prediction for the COD removal rate of The booster explosive wastewater based on Elman neural network Abstract: In order to predict for the COD (chemical oxygen demand) removal rate of the DDNP wastewater carried out by supercritical water oxidation(SCWO), the HXDK-01-A Interval supercritical water oxidation device was used to dispose the actual industrial production wastewater, reaction temperature,reaction pressure,residence time,oxygen excess were inspected for the influence of COD removal rate. Employing experimental data, a single hidden layer Elman prediction model was established by the reaction temperature,reaction pressure,residence time,oxygen excess as input variables,the COD removal rate as output.The MSE of the Elman model is 0.0418,the biggest error is - 0.3231, the least error is 0.0296; the MSE of the multiple regression is 0.3149, he biggest error is 0.8830, the least error is 0.2200, compared with the multiple regression, ,the prediction result of the Elman Neural network was better. The result illuminated that the Elman model can feasible for the prediction of the COD removal rate of the wastewater performed by SCWO. Key words:environmental science; Supercritical water oxidation; Diazodinitrophenol; Elman neural network; wastewater treatment 改好了,感觉实验文章应该用被动态和过去时比较好 |

4楼2009-04-22 21:52:12
515825903931
银虫 (正式写手)
- 应助: 0 (幼儿园)
- 金币: 356
- 散金: 10
- 红花: 1
- 帖子: 366
- 在线: 15.9小时
- 虫号: 376450
- 注册: 2007-05-19
- 专业: 化工
5楼2010-03-29 09:07:15











回复此楼