| 查看: 819 | 回复: 6 | ||
| 本帖产生 1 个 翻译EPI ，点击这里进行查看 | ||
hwjok木虫 (正式写手)
|
[求助]
请帮忙改正摘要翻译中的错误
|
|
|
The online measurement of Dioxins in the waste incineration is difficult and could only be analyzed with small samples offline. Aimed at the problem, a novel soft sensing methodology with good generalization is studied. Firstly, the small samples are increased with diversity by injecting noise and using the bootstrap resampling approach. Then, the neural network with maximum entropy is presented by introducing information entropy to error rule function for the unknown distributing of original samples. Finally, a soft sensing model of dioxins is built with this entropy neural network. Simulations show that the model has good generalization and precision. The mean and maxim values of relative error between true and prediction of dioxins is 0.167% and 1.21%, respectively. It provides a referenced method for detecting dioxins online in the waste to energy. 垃圾焚烧过程中的二恶英难以在线测量, 只能通过离线分析获得少量样本. 针对该问题, 研究了一种在小样本条件下仍然具有推广能力的软测量建模方法. 首先对小样本进行Bootstrap重抽样和噪声注入处理, 增加样本的数量和改善其多样性. 然后将信息熵引入误差准则函数, 构建出最大熵神经网络. 最后基于熵神经网络建立二恶英软测量回归模型. 仿真结果表明, 该二恶英软测量模型具有较好的精度和泛化能力, 实际值和预测值的相对误差均值为0.167%, 最大相对误差为1.21%, 为在线测量垃圾焚烧发电过程中的二恶英提供了一种参考方法. [ Last edited by hwjok on 2013-5-19 at 22:56 ] |
回复此楼» 猜你喜欢
一志愿北交大材料工程总分358求调剂
已经有6人回复
-
312求调剂
已经有7人回复
-
材料334求调剂
已经有19人回复
-
生物与医药273求调剂
已经有6人回复
-
301求调剂
已经有10人回复
-
专硕0854初试考材科基，求调剂
已经有5人回复
-
0703化学
已经有15人回复
-
0703调剂，一志愿天津大学319分
已经有9人回复
-
085600材料与化工301分求调剂院校
已经有10人回复
-
求调剂
已经有8人回复
yili_90
金虫 (正式写手)
- 翻译EPI: 17
- 应助: 37 (小学生)
- 贵宾: 0.013
- 金币: 3136.5
- 散金: 400
- 红花: 11
- 帖子: 464
- 在线: 117.7小时
- 虫号: 2157293
- 注册: 2012-11-30
- 性别: MM
- 专业: 动物遗传学
2楼2013-05-19 23:30:21
hwjok
木虫 (正式写手)
- 应助: 2 (幼儿园)
- 金币: 5334.1
- 红花: 7
- 帖子: 419
- 在线: 411.1小时
- 虫号: 296037
- 注册: 2006-11-12
- 性别: GG
- 专业: 控制理论与方法
3楼2013-05-20 15:48:54
hwjok
木虫 (正式写手)
- 应助: 2 (幼儿园)
- 金币: 5334.1
- 红花: 7
- 帖子: 419
- 在线: 411.1小时
- 虫号: 296037
- 注册: 2006-11-12
- 性别: GG
- 专业: 控制理论与方法
4楼2013-05-20 15:51:32
yili_90
金虫 (正式写手)
- 翻译EPI: 17
- 应助: 37 (小学生)
- 贵宾: 0.013
- 金币: 3136.5
- 散金: 400
- 红花: 11
- 帖子: 464
- 在线: 117.7小时
- 虫号: 2157293
- 注册: 2012-11-30
- 性别: MM
- 专业: 动物遗传学
5楼2013-05-20 17:58:33
yili_90
金虫 (正式写手)
- 翻译EPI: 17
- 应助: 37 (小学生)
- 贵宾: 0.013
- 金币: 3136.5
- 散金: 400
- 红花: 11
- 帖子: 464
- 在线: 117.7小时
- 虫号: 2157293
- 注册: 2012-11-30
- 性别: MM
- 专业: 动物遗传学
6楼2013-05-20 18:00:34
bhcsu
金虫 (小有名气)
- 翻译EPI: 23
- 应助: 0 (幼儿园)
- 金币: 9064.8
- 帖子: 137
- 在线: 64.2小时
- 虫号: 531634
- 注册: 2008-03-23
- 性别: MM
- 专业: 材料
【答案】应助回帖
★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★
hwjok: 金币+30, 翻译EPI+1, ★★★很有帮助 2013-05-21 22:36:13
hwjok: 金币+30, 翻译EPI+1, ★★★很有帮助 2013-05-21 22:36:13
| Since the online measurement of Dioxins during waste incineration is difficult, it could only be analyzed offline with small samples obtained. Aimed at this problem, a novel soft sensing methodology that can be well generalized is studied. Firstly, bootstrap resampling approach and noise injection are performed for small samples in order to increase the amount of the samples and improve the diversity. Then, the information entropy is introduced to the error rule function for the unknown distributing of original samples and construct a neural network with the maximum entropy. Finally, a soft sensing regression model of dioxins is built based on the entropy neural network. Simulation results show that this model has a high precision and a good ability of generalization. The mean and maximum of relative error between actual and predicted values are 0.167% and 1.21%, respectively. This method provides a reference for detecting dioxins online during incinaerating waste. |
7楼2013-05-21 20:11:51
