Online soft measurement for wastewater treatment system based on hybrid deep learning

doi:10.1007/s11783-024-1780-y

Front. Environ. Sci. Eng.

2024, Vol. 18

Issue (2) : 20 https://doi.org/10.1007/s11783-024-1780-y

RESEARCH ARTICLE

Online soft measurement for wastewater treatment system based on hybrid deep learning

Wenjie Mai¹, Zhenguo Chen¹, Xiaoyong Li¹, Xiaohui Yi^1,⁴, Yingzhong Zhao², Xinzhong He², Xiang Xu², Mingzhi Huang^1,^3,⁵(

)

¹. SCNU Environmental Research Institute, Guangdong Provincial Key Laboratory of Chemical Pollution and Environmental Safety & MOE Key Laboratory of Theoretical Chemistry of Environment, School of Environment, South China Normal University, Guangzhou 510006, China
². Fujian Environmental Protection Design Institute Co. Ltd., Fuzhou 350000, China
³. Huashi (Fujian) Environment Technology Co. Ltd., Quanzhou, 362001, China
⁴. SCNU Qingyuan Institute of Science and Technology Innovation Co. Ltd., Qingyuan 511517, China
⁵. Econ Technology Co. Ltd., Yantai 265503, China

Download: PDF(3496 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

● A hybrid model is proposed to overcome limitations of single model with time series.

● CNN and bidirectional NLSTM are combined to solve complex nonlinear monitoring issue.

● Attention mechanism is suitably introduced to hybrid model for better convergence.

● TPE is used to find the optimal parameter combination faster rather than manual.

The existing automated wastewater treatment control systems encounter challenges such as the utilization of specialized testing instruments, equipment repair complications, high operational costs, substantial operational errors, and low detection accuracy. An effective soft measure model offers a viable approach for real-time monitoring and the development of automated control in the wastewater treatment process. Consequently, a novel hybrid deep learning CNN-BNLSTM-Attention (CBNLSMA) model, which incorporates convolutional neural networks (CNN), bidirectional nested long and short-term memory neural networks (BNLSTM), attention mechanisms (AM), and Tree-structure Parzen Estimators (TPE), has been developed for monitoring effluent water quality during the wastewater treatment process. The CBNLSMA model is divided into four stages: the CNN module for feature extraction and data filtering to expedite operations; the BNLSTM module for temporal data’s temporal information extraction; the AM module for model weight reassignment; and the TPE optimization algorithm for the CBNLSMA model’s hyperparameter search optimization. In comparison with other models (TPE-CNN-BNLSTM, TPE-BNLSTM-AM, TPE-CNN-AM, PSO-CBNLSTMA), the CBNLSMA model reduced the RMSE for effluent COD prediction by 25.4%, decreased the MAPE by 32.9%, and enhanced the R² by 14.9%. For the effluent SS prediction, the CBNLSMA model reduced the RMSE by 26.4%, the MAPE by 21.0%, and improved the R² by 35.7% compared to other models. The simulation results demonstrate that the proposed CBNLSMA model holds significant potential for real-time effluent quality monitoring, indicating its high potential for automated control in wastewater treatment processes.

Keywords Prediction model Soft measurement CNN-BNLSTM-AM model TPE optimization algorithm

Corresponding Author(s): Mingzhi Huang

Issue Date: 12 October 2023

Cite this article:

Wenjie Mai,Zhenguo Chen,Xiaoyong Li, et al. Online soft measurement for wastewater treatment system based on hybrid deep learning[J]. Front. Environ. Sci. Eng., 2024, 18(2): 20.

URL:

https://academic.hep.com.cn/fese/EN/10.1007/s11783-024-1780-y
https://academic.hep.com.cn/fese/EN/Y2024/V18/I2/20

Fig.1 Modeling the paper-making wastewater treatment process using CBNLSTMA.

Tab.1 The prediction performance of TPE-CNN-BNLSTM, TPE-BNLSTM-AM, TPE-CNN-AM, TPE-CBNLSTMA, and PSO-CBNLSTMA for COD_eff

Tab.2 The prediction performance of TPE-CNN-BNLSTM, TPE-BNLSTM-AM, TPE-CNN-AM, TPE-CBNLSTMA, and PSO-CBNLSTMA for SS_eff

Tab.3 The prediction performance of CNN, BNLSTM, CNN-BNLSTM, and CBNLSTMA for COD_eff

Tab.4 The prediction performance of CNN, BNLSTM, CNN-BNLSTM, and CBNLSTMA for SS_eff

Fig.2 Predicted results of effluent COD and SS.

Fig.3 Attention weights for 50 runs of COD_eff.

Fig.4 Attention weights for 50 runs of SS_eff.

Fig.5 MIC Histogram for COD_eff and SS_eff.

1	O Abdeljaber, O Avci, S Kiranyaz, M Gabbouj, D J Inman. (2017). Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. Journal of Sound and Vibration, 388: 154–170 https://doi.org/10.1016/j.jsv.2016.10.043
2	A N Ahmed, F B Othman, H A Afan, R K Ibrahim, C M Fai, M S Hossain, M Ehteram, A Elshafie (2019). Machine learning methods for better water quality prediction. Journal of Hydrology, 578: 124084 https://doi.org/10.1016/j.jhydrol.2019.124084
3	J Bergstra, B Komer, C Eliasmith, D Yamins, D D Cox. (2015). Hyperopt: a Python library for model selection and hyperparameter optimization. Computational Science and Discovery, 8(1): 014008–014024 https://doi.org/10.1088/1749-4699/8/1/014008
4	M Chate, V Gohokar (2020). Vehicle Detection Using Faster Recurrent Convolution Neural Network. ICDSMLA 2019. Proceedings of the 1st International Conference on Data Science, Machine Learning and Applications. Lecture Notes in Electrical Engineering, (LNEE 601): 1190–1195 https://doi.org/10.1007/978-981-15-1420-3
5	Q P Chen, Q S Xie, Q N Yuan, H S Huang, Y T Li. (2019). Research on a real-time monitoring method for the wear state of a tool based on a convolutional bidirectional LSTM model. Symmetry, 11(10): 1233 https://doi.org/10.3390/sym11101233
6	Z B Chen, D X Hu, N Q Ren, Z P Zhang. (2008). Simultaneous removal of organic substances and nitrogen in pilot-scale submerged membrane bioreactors treating digested traditional Chinese medicine wastewater. International Biodeterioration & Biodegradation, 62(3): 250–256 https://doi.org/10.1016/j.ibiod.2008.01.010
7	H Choi, K Cho, Y Bengio. (2018). Fine-grained attention mechanism for neural machine translation. Neurocomputing, 284: 171–176 https://doi.org/10.1016/j.neucom.2018.01.007
8	N Farhi, E Kohen, H Mamane, Y Shavitt. (2021). Prediction of wastewater treatment quality using LSTM neural network. Environmental Technology & Innovation, 23(2): 101632 https://doi.org/10.1016/j.eti.2021.101632
9	B D Fulcher, M A Little, N S Jones. (2013). Highly comparative time-series analysis: the empirical structure of time series and their methods. Journal of the Royal Society, Interface, 10: 20130048 https://doi.org/10.1098/rsif.2013.0048
10	A Galassi, M Lippi, P Torroni. (2021). Attention in natural language processing. IEEE Transactions on Neural Networks and Learning Systems, 32(10): 4291–4308 https://doi.org/10.1109/TNNLS.2020.3019893
11	L L Gao, X P Li, J K Song, H T Shen. (2020). Hierarchical lstms with adaptive attention for visual captioning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(5): 1112–1131 https://doi.org/10.1109/TPAMI.2019.2894139
12	H G Han, H J Zhang, Z Liu, J F Qiao. (2020). Data-driven decision-making for wastewater treatment process. Control Engineering Practice, 96: 104305 https://doi.org/10.1016/j.conengprac.2020.104305
13	S Y Hao, E O R Lee, D Zhao. (2019). Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system. Transportation Research Part C, Emerging Technologies, 107: 287–300 https://doi.org/10.1016/j.trc.2019.08.005
14	L L Hu, J L Wang, X G Wen, Y Qian. (2005). Study on performance characteristics of SBR under limited dissolved oxygen. Process Biochemistry (Barking, London, England), 40(1): 293–296 https://doi.org/10.1016/j.procbio.2004.01.015
15	Y X HuC K GuoN MeiJ ZhangZ K Gong J Zhao (2022). Prediction of Boiler Control Parameters Based on LSTM Neural Network. 2022 4th Asia Energy and Electrical Engineering Symposium (AEEES), Chengdu, China, 2022: 451−457 https://doi.org/10.1109/AEEES54426.2022.9759772
16	T Inoue, C N Mulligan, E M Zadeh, M Fukue. (2009). Effect of contaminated suspended solids on water and sediment qualities and their treatment. Journal of ASTM International, 6(3): JAI102185 https://doi.org/10.1520/JAI102185
17	N Jin, Y K Zeng, K Yan, Z W Ji. (2021). Multivariate air quality forecasting with nested long short term memory neural network. IEEE Transactions on Industrial Informatics, 17(12): 8514–8522 https://doi.org/10.1109/TII.2021.3065425
18	S Khullar, N Singh. (2022). Water quality assessment of a river using deep learning Bi-LSTM methodology: forecasting and validation. Environmental Science and Pollution Research International, 29(9): 12875–12889 https://doi.org/10.1007/s11356-021-13875-w
19	S Kiranyaz, O Avci, O Abdeljaber, T Ince, M Gabbouj, D J Inman. (2021). 1D convolutional neural networks and applications: a survey. Mechanical Systems and Signal Processing, 151: 107398 https://doi.org/10.1016/j.ymssp.2020.107398
20	J B Kong, J Minseok. (2019). Association analysis of convolution layer, kernel and accuracy in cnn. Journal of the Korea Institute of Electronic Communication Sciences, 14(6): 1153–1160 https://doi.org/10.1109/TPAMI.2019.2894139
21	R Li, S Y Zheng, C X Duan, Y Yang, X Q Wang (2020). Classification of hyperspectral image based on double-branch dual-attention mechanism network. Remote Sensing (Basel), 12(3): 582 https://doi.org/10.3390/rs12030582
22	X Y Li, X H Yi, Z H Liu, H B Liu, T Chen, G Q Niu, B Yan, C Chen, M Z Huang, G G Ying. (2021). Application of novel hybrid deep leaning model for cleaner production in a paper industrial wastewater treatment system. Journal of Cleaner Production, 2: 126343 https://doi.org/10.1016/j.jclepro.2021.126343
23	J Li, Z Chen, X Li, X Yi, Y Zhao, X He, Z Huang, M A Hassaan, A E Nemr, M Huang. (2023). Water quality soft-sensor prediction in anaerobic process using deep neural network optimized by Tree-structured Parzen Estimator. Frontiers of Environmental Science & Engineering, 17(6): 67 https://doi.org/10.1007/s11783-023-1667-3
24	J Liang, F Luo, Y G Xu (2009). Wastewater DO concentration control through NH4 prediction based on evolutionary radial basis function neural network. Proceedings of the 2009 Fifth International Conference on Natural Computation, Tianjian, China, 2009. (ICNC 2009): 378–381
25	L Liu, J Chen, P Fieguth, G Y Zhao, R Chellappa, M Pietikainen. (2019). From bow to CNN: two decades of texture representation for texture classification. International Journal of Computer Vision, 127(1): 74–109 https://doi.org/10.1007/s11263-018-1125-z
26	R M Liu, X Ning, W W Cai, G J Li (2021). Multiscale dense cross-attention mechanism with covariance pooling for hyperspectral image scene classification. Mobile Information Systems, 2021(4): 9962057 https://doi.org/10.1155/2021/9962057
27	X L Ma, H Y Zhong, Y Li, J Y Ma, Z Y Cui, Y H Wang. (2021). Forecasting transportation network speed using deep capsule networks with nested LSTM models. IEEE Transactions on Intelligent Transportation Systems, 22(8): 4813–4824 https://doi.org/10.1109/TITS.2020.2984813
28	J Moniz, D Krueger (2018). Nested LSTMs. JMLR: Workshop and Conference Proceedings, 15−17 Nov., Yonsei University, Seoul, Republic of Korea https://doi.org/10.48550/arXiv.1801.10308
29	H P Nguyen, J Liu, E Zio (2020). A long-term prediction approach based on long short-term memory neural networks with automatic parameter optimization by tree-structured parzen estimator and applied to time-series data of NPP steam generators. Applied Soft Computing, 165: 89
30	G Q Niu, X H Yi, C Chen, X Y Li, D H Han, B Yan, M Z Huang, G G Ying. (2020). A novel effluent quality predicting model based on genetic-deep belief network algorithm for cleaner production in a full-scale paper-making wastewater treatment. Journal of Cleaner Production, 265: 121787 https://doi.org/10.1016/j.jclepro.2020.121787
31	Y Q Peng, N S Kondo, T Fujiura, T Suzuki, S Ouma, Y Wulandari, I Hidetsugu, I Erina. (2020). Dam behavior patterns in Japanese black beef cattle prior to calving: automated detection using lstm-rnn. Computers and Electronics in Agriculture, 169: 105178 https://doi.org/10.1016/j.compag.2019.105178
32	H Phan, L Hertel, M Maass, A Mertins, A Int Speech Commun (2016). Robust audio event recognition with 1-Max pooling convolutional. Neural Networks, 2016: 3653–3657,
33	Z Pu, J Yan, L Chen, Z Li, W Tian, T Tao, K Xin. (2023). A hybrid Wavelet-CNN-LSTM deep learning model for short-term urban water demand forecasting. Frontiers of Environmental Science & Engineering, 17(2): 1–14 https://doi.org/10.1007/s11783-023-1622-3
34	N M Ragi, R Holla, G Manju (2019). Predicting Water Quality Parameters Using Machine Learning. 2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT) , Bangalore, India, 2019: 1109–1112 https://doi.org/10.1109/RTEICT46194.2019.9016825
35	R Roscher, B Bohn, M F Duarte, J Garcke. (2020). Explainable machine learning for scientific insights and discoveries. IEEE Access: Practical Innovations, Open Solutions, 8: 42200–42216 https://doi.org/10.1109/ACCESS.2020.2976199
36	J Schmidt-Hieber. (2020). Nonparametric regression using deep neural networks with ReLU activation function. Annals of Statistics, 48(4): 1875–1897 https://doi.org/10.1214/19-AOS1875
37	J Sha, X Li, M Zhang, Z L Wang (2021). Comparison of forecasting models for real-time monitoring of water quality parameters based on hybrid deep learning neural networks. Water (Basel) 13: 1547 https://doi.org/10.3390/w13111547
38	N Srivastava, G Hinton, A Krizhevsky, I Sutskever, R Salakhutdinov. (2014). Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15: 1929–1958
39	W W Tan, J J Zhang, J Wu, H Lan, X Liu, K Xiao, L Wang, H J Lin, G Sun, P Guo. (2022). Application of CNN and long short-term memory network in water quality predicting. Intelligent Automation and Soft Computing, 34(3): 1943–1958 https://doi.org/10.32604/iasc.2022.029660
40	J Q Wan, M Z Huang, Y W Ma, W J Guo, Y Wang, H P Zhang, W J Li, X F Sun. (2011). Prediction of effluent quality of a paper mill wastewater treatment using an adaptive network-based fuzzy inference system. Applied Soft Computing, 11(3): 3238–3246 https://doi.org/10.1016/j.asoc.2010.12.026
41	X Wang, S H Chen, J S Su (2020). Real network traffic collection and deep learning for mobile app identification. Wireless Communications and Mobile Computing, 2020, : 4707909: 1–4707909:14 https://doi.org/10.1155/2020/4707909
42	Z F Wang, Y Man, Y S Hu, J G Li, M N Hong, P Z Cui. (2019). A deep learning-based dynamic COD prediction model for urban sewage. Environmental Science. Water Research & Technology, 5(12): 2210–2218 https://doi.org/10.1039/C9EW00505F
43	C Wu, L Guo. (2017). Influence of temperature and dissolved oxygen on nitrogen and phosphorus removal of integrated bioreactor. International Journal Bioautomation, 21(2): 207–216
44	J Wu, Z B Li, L Zhu, G Y Li, B S Niu, F Peng (2018). Optimized BP neural network for dissolved oxygen prediction, 596–601 https://doi.org/10.1016/j.ifacol.2018.08.132
45	L Q Xu, S Y Liu. (2013). Study of short-term water quality prediction model based on wavelet neural network. Mathematical and Computer Modelling, 58(3–4): 807–813 https://doi.org/10.1016/j.mcm.2012.12.023
46	C G Yan, Y B Tu, X Z Wang, Y B Zhang, X H Hao, Y D Zhang, Q H Dai (2020). STAT: spatial-temporal attention mechanism for video captioning. 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass, CO, USA, 2020, 1606–1615 https://doi.org/10.1109/WACV45572.2020.9093291
47	F Yang, H Xie, H X Li. (2019). Retracted article: video associated cross-modal recommendation algorithm based on deep learning. Applied Soft Computing, 82: 105597 https://doi.org/10.1016/j.asoc.2019.105597
48	L Yang, A Shami. (2020). On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing, 415: 295–316 https://doi.org/10.1016/j.neucom.2020.07.061
49	Y R Yang, Q Y Xiong, C Wu, Q H Zou, Y Yu, H L Yi, M Gao. (2021). A study on water quality prediction by a hybrid CNN-LSTM model with attention mechanism. Environmental Science and Pollution Research International, 28(39): 55129–55139 https://doi.org/10.1007/s11356-021-14687-8
50	Y Yu, X S Si, C H Hu, J X Zhang. (2019). A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 31(7): 1235–1270 https://doi.org/10.1162/neco_a_01199
51	J Zhang, Y Peng, B Ren, T Li. (2021). PM2.5 concentration prediction based on CNN-BiLSTM and attention mechanism. Algorithms, 14(7): 208 https://doi.org/10.3390/a14070208
52	J F Zhao, X Mao, L J Chen. (2018). Learning deep features to recognize speech emotion using merged deep CNN. IET Signal Processing, 12(6): 713–721 https://doi.org/10.1049/iet-spr.2017.0320

[1]

FSE-23067-OF-MWJ_suppl_1

Download

[1]	Qiyue Wu, Yun Geng, Xinyuan Wang, Dongsheng Wang, ChangKyoo Yoo, Hongbin Liu. A novel deep learning framework with variational auto-encoder for indoor air quality prediction[J]. Front. Environ. Sci. Eng., 2024, 18(1): 8-.

Viewed

Full text

Abstract

Cited

Shared

Discussed