收藏切换
Optimization of total phosphorus removal process in artificial percolation system based on BP-ANN
收藏切换
PDF
Yuan-kun LIU*, Yuan-qi CAO, Ai-xin YU, Xing LI, Xiao-tian GUO
China Environmental Science | 2025, 45(6) : 3151 - 3160
Less
收藏切换
China Environmental Science | 2025, 45(6): 3151-3160
Water Pollution Control
Optimization of total phosphorus removal process in artificial percolation system based on BP-ANN
Full
Yuan-kun LIU*, Yuan-qi CAO, Ai-xin YU, Xing LI, Xiao-tian GUO
Affiliations
  • College of Architecture and Civil Engineering, Beijing University of Technology, Beijing 100124, China
Published: 2025-06-20
Outline
收藏切换

Box-Behnken response surface methodology (BBD-RSM) and back propagation artificial neural network (BP-ANN) algorithms were used to model and predict the process parameters (contact time, initial concentration, temperature, pH) of activated carbon adsorption of total phosphorus (TP), and the reaction conditions in the BP-ANN model were optimized in combination with genetic algorithms (GA). The results showed that in the BBD-RSM model, the P<0.0001, which could better predict the TP removal process, and contact time was the most significant parameter for TP removal, with the relative influence order of the factors in the TP adsorption process being: contact time > pH > temperature > initial concentration. The BP-ANN model was used for optimization, and the optimal network structure was 4-8-1. Sensitivity analysis showed that the factors affecting the TP removal rate were ranked as contact time (34.05%) > pH (28.67%) > temperature (19.56%) > initial concentration (17.72%). Based on the BP-ANN model, the GA was used to optimize the operating conditions of the artificial percolation system, and the optimization results for the TP removal process were: contact time of 720.53min, initial concentration of 2.75mg/L, temperature of 30.62℃, and pH value of 5, achieving the optimal removal rate (99.63%). Experimental validation analysis showed that BP-ANN-GA had a higher R2 (0.9939) and lower RMSE (1.2851) compared with BBD-RSM when predicting against the experimental values, indicating that this model had better predictive ability and could better describe the TP removal process in the constructed rapid infiltration (CRI) system.

box-behnken design response surface methodology (BBD-RSM)  /  back propagation artificial neural network (BP-ANN)  /  genetic algorithm (GA)  /  total phosphorus (TP)  /  constructed rapid infiltration (CRI) system
Yuan-kun LIU, Yuan-qi CAO, Ai-xin YU, Xing LI, Xiao-tian GUO. Optimization of total phosphorus removal process in artificial percolation system based on BP-ANN[J]. China Environmental Science, 2025 , 45 (6) : 3151 -3160 .
Year 2025 volume 45 Issue 6
PDF
39
16
Cite this Article
BibTeX
Article Info
  • Receive Date:2024-11-06
  • Online Date:2026-02-27
  • Published:2025-06-20
Article Data
Affiliations
History
  • Received:2024-11-06
Funding
Affiliations
    College of Architecture and Civil Engineering, Beijing University of Technology, Beijing 100124, China
References
Share
https://castjournals.cast.org.cn/joweb/zghjkx/EN/
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT