Simulating and predicting the performance of a horizontal subsurface flow constructed wetland using a fully connected neural network
文献类型：期刊论文
| 作者 | Li, Pengyu; Zheng, Tianlong ; Li, Lin; Lv, Xiuyuan; Wu, WenJun; Shi, Zhining; Zhou, Xiaoqin; Zhang, Guangtao; Ma, Yingqun; Liu, Junxin
|
| 刊名 | JOURNAL OF CLEANER PRODUCTION
 |
| 出版日期 | 2022 |
| 卷号 | 380页码:134959-1-11 |
| 关键词 | Decentralized wastewater treatment Fully connected neural network Machine learning Horizontal subsurface flow constructed wetland |
| ISSN号 | 0959-6526 |
| 英文摘要 | Constructed wetland systems, as an engineered ecological system, are being increasingly employed for waste-water treatment. However, owing to the complex incentives for pollutant removal in ecological treatment sys-tems, it is challenging to simulate and optimize the operation of constructed wetlands to advance ecological wastewater treatment systems. In this study, a horizontal subsurface flow constructed wetland (HSCW) system was constructed and applied to a rural wastewater treatment system. Reeds (Phragmites australis) were planted in the HSCW to remove pollutants from the wastewater. Further, a fully connected neural network (FCNN) was designed based on the Adam optimization algorithm with weather conditions, quality, and quantity of influent and effluent as input to simulate and predict the performance of the HSCW. The results of the FCNN simulation analysis showed that the relative errors of the simulated concentrations of CODcr, NH4+-N, total nitrogen (TN), and total phosphorus (TP) for the FCNN model were 8.07 +/- 10.73%, 18.34 +/- 17.75%, 9.90 +/- 11.91%, and 9.47 +/- 10.98%, respectively. The mean absolute errors (MAEs) of CODcr, NH4+-N, TN, and TP for the FCNN model were 2.17, 1.06, 1.21, and 0.54, respectively. The root-mean-squared errors (RMSEs) of CODcr, NH4+-N, TN, and TP for the FCNN model were 3.91, 2.05, 2.22, and 0.80, respectively. The correlation coefficients (R2) of CODcr, NH4+-N, TN, and TP for the model were 0.99, 0.91, 0.92, and 0.82, respectively. These results indicate that the model performed well. Sensitivity analysis results also showed that temperature, solar radiation intensity, and rainfall had a strong impact on the model accuracy. This study verifies that an artificial neural network can effectively reflect the nonlinear function of each factor and is suitable for simulating HSCW treatment for wastewater under various conditions, providing a new optimization method for wastewater ecological treatment systems. |
| 源URL | [https://ir.rcees.ac.cn/handle/311016/48540]  |
| 专题 | 生态环境研究中心_水污染控制实验室 |
| 作者单位 | 1.Hohai University 2.University of Chinese Academy of Sciences, CAS 3.Research Center for Eco-Environmental Sciences (RCEES) 4.Chinese Academy of Sciences 5.University of Macau 6.University of Science & Technology Beijing 7.University of South Australia 8.Xi'an Jiaotong University |
| 推荐引用方式 GB/T 7714 | Li, Pengyu,Zheng, Tianlong,Li, Lin,et al. Simulating and predicting the performance of a horizontal subsurface flow constructed wetland using a fully connected neural network[J]. JOURNAL OF CLEANER PRODUCTION,2022,380:134959-1-11. |
| APA | Li, Pengyu.,Zheng, Tianlong.,Li, Lin.,Lv, Xiuyuan.,Wu, WenJun.,...&Liu, Junxin.(2022).Simulating and predicting the performance of a horizontal subsurface flow constructed wetland using a fully connected neural network.JOURNAL OF CLEANER PRODUCTION,380,134959-1-11. |
| MLA | Li, Pengyu,et al."Simulating and predicting the performance of a horizontal subsurface flow constructed wetland using a fully connected neural network".JOURNAL OF CLEANER PRODUCTION 380(2022):134959-1-11. |
入库方式： OAI收割
来源：生态环境研究中心
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。