Prediction Method of Algae Coagulation Removal Rate Based on Deep Learning

被引：0
|
作者：
Zhou S. [1 ]
Ma W. [1 ]
Sheng D. [1 ]
Wu Y. [1 ]
Bu L. [1 ]
机构：
[1] College of Civil Engineering, Hunan University, Changsha
来源：
Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences | 2022年 / 49卷 / 09期
基金：
中国国家自然科学基金;
关键词：
algae floc image; coagulation; deep learning; image classification; removal rate prediction;
D O I：
10.16339/j.cnki.hdxbzkb.2022105
中图分类号：
学科分类号：
摘要：
Aiming at the problem that it is difficult to determine the dosage of coagulant for algae outbreak in waterworks, a prediction method of algae coagulation removal rate based on deep learning is proposed. DenseNet convolution neural network and floc image are used to predict the algae coagulation removal rate, so as to adjust the dosage. The specific method is to coagulate the high algae water under laboratory conditions, and record the floc image and the corresponding removal rate range after coagulation. The floc image data set was constructed with the removal rate interval as a label, and the DenseNet-121 model was trained with this data set. The results show that the prediction accuracy of the trained model for the test set reaches 89.5%. Compared with VGG and RESNET convolution neural network, the DenseNet convolution neural network has higher recognition accuracy on the data set established in this paper and has obvious advantages over the other two models in identifying floc images with a removal rate of 60%~ 90%. At the same time, the recognition of Microcystis aeruginosa floc image outside the data set verifies the good generalization of the model. © 2022 Hunan University. All rights reserved.
引用
收藏
页码：215 / 220
页数：5
相关论文
共 16 条
  • [1] LIU J L, HE Y., Discussion on present situation and formation of eutrophication in urban landscape water［J］, Journal of Green Science and Technology, 12, pp. 73-74, (2017)
  • [2] SONG X F, WU Y Q, FU H L, Et al., Characteristic analysis of raw water pollution and its removal during low temperature outbreak of cyanobacteria in a water plant in North China［J］, China Water & Wastewater, 36, 19, pp. 46-49, (2020)
  • [3] LI G P, QI J, LAN H C., Review on research progress of algae removal technology in water treatment plant［J］, Water Purification Technology, 37, 11, pp. 32-39, (2018)
  • [4] LUO Y P, SHI Z, ZHANG L J, Et al., Study of the enhanced removal of microsystis aeruginosa by adding kaolin and PAM in PAC flocculation process［J］, Journal of Hunan University（Natural Sciences）, 36, 2, pp. 22-26, (2009)
  • [5] ZHANG Y, LIU H Y, CUI F Y., Application of streaming current control system to treatment of slightly-polluted raw water［J］, Environmental Science and Technology, 25, 1, pp. 4-5, (2002)
  • [6] YU S L, LI G B, TIAN Y P., An on-line monitoring technology for transmitted light fluctuation in high-turbidity water and its application—a theory of monitoring for transmitted light fluctuating particles［J］, Industrial Water & Wastewater, 1, pp. 1-5, (2001)
  • [7] LIU H Y, ZHOU X L, ZHU H T, Et al., Application of online particle counter to water quality monitoring at waterworks［J］, China Water & Wastewater, 30, 3, pp. 44-47, (2014)
  • [8] BAI H, LI G B., Neural networks control method for coagulant dosage［J］, Water & Wastewater Engineering, 27, 11, pp. 83-86, (2001)
  • [9] CHEN Y, FENG Y M, YANG X F, Et al., Application of on-line flocculation control technology in water and wastewater treatment ［J］, Water & Wastewater Engineering, 56, pp. 453-458, (2020)
  • [10] SHENG D F, CHEN J P, ZHOU Y, Et al., Building and application of urban water supply network information management system ［J］, Water & Wastewater Engineering, 57, 1, pp. 96-102, (2021)
12