A Multi-View Image Feature Fusion Network Applied in Analysis of Aeration Velocity for WWTP

Li，Junchen1,2; Liu，Yuheng3,4; Jiang，Hongchuan2; Yang，Mengxi2; Lin，Sijie2; Hu，Qing2

2022-02-01

10.3390/w14030345

Water (Switzerland)   影响因子和分区

2073-4441

The instability of the aeration system brings a significant challenge to the management of wastewater treatment plants (WWTP). Using image recognition methods to monitor aeration conditions accurately and enhance management efficiency is a promising way to solve this problem. To improve the efficiency of aeration condition identification and provide support for troubleshooting, we propose a method for aeration velocity condition identification based on a multi-view image feature fusion network (MVNN). Firstly, an experimental platform for simulating aeration tanks is established, and two cameras are used to acquire aeration images from different perspectives. Secondly, an image data set with 10 aeration velocity gradients is constructed and applied to the network’s training. Finally, the MVNN is used to extract and fuse the features of aeration images, and the model’s performance is evaluated on the dataset. Experiments show that the average accuracy of the method is over 98.3%, and the AUC of aeration identification is above 0.98, which indicates that the model has the potential for practical application in WWTP.

Aeration process Computer vision Feature fusion Multi-view learning Wastewater treatment plant

SCI ; EI

英语

通讯

National Key R&D Program of China[2021YFC1809001]

Environmental Sciences & Ecology ; Water Resources

Environmental Sciences ; Water Resources

WOS:000756274700001

MDPI

20220511569566

Computer vision ; Efficiency ; Image enhancement ; Image fusion ; Image recognition ; Sewage pumping plants ; Sewage tanks ; Wastewater treatment

Water Treatment Techniques:445.1 ; Sewage Treatment:452.2 ; Industrial Wastes Treatment and Disposal:452.4 ; Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Vision:741.2 ; Production Engineering:913.1

2-s2.0-85123710885

Scopus

1.School of Environment,Harbin Institute of Technology,Harbin,150090,China
2.School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
3.Faculty of Environment and Life,Beijing University of Technology,Beijing,100124,China
4.Engineering Research Center of Intelligence Perception and Autonomous Control,Ministry of Education of China,Beijing,100124,China

Li，Junchen,Liu，Yuheng,Jiang，Hongchuan,et al. A Multi-View Image Feature Fusion Network Applied in Analysis of Aeration Velocity for WWTP[J]. Water (Switzerland),2022,14(3).

Li，Junchen,Liu，Yuheng,Jiang，Hongchuan,Yang，Mengxi,Lin，Sijie,&Hu，Qing.(2022).A Multi-View Image Feature Fusion Network Applied in Analysis of Aeration Velocity for WWTP.Water (Switzerland),14(3).

Li，Junchen,et al."A Multi-View Image Feature Fusion Network Applied in Analysis of Aeration Velocity for WWTP".Water (Switzerland) 14.3(2022).