Considering the characteristics of large time variation, strong coupling, large time delay, and serious interference of wastewater treatment system, this article proposes an offline modeling and online controlling method based on long short-term memory network to improve multivariable control and prediction accuracy under disturbance. First, a prediction model of dissolved oxygen and nitrate nitrogen concentrations is established, and the stability of this long short-term memory-based modeling method is proven via the limitation of learning rate. Second, based on the prediction model, a multivariable long short-term memory-based controller is designed to improve the control accuracy by gradient descent algorithm, and the stability of the long short-term memory-based controller is proved by Lyapunov principle. Finally, based on the Benchmark Simulation Model No.1, the simulation experiments of long short-term memory-based modeling and controlling method, the default proportion–integration control method (proposed in the Benchmark Simulation Model No.1), and model predictive control method are conducted and compared, respectively. The results show the long short-term memory-based method owns both better approximating and controlling performance, and compared with the default proportion–integration and model predictive control, the long short-term memory-based controller reduces the integral squared error of dissolved oxygen and nitrate nitrogen concentrations by more than 94% and 80%, respectively.
ShannonMBohnPElimelechM, et al. Science and technology for water purification in the coming decades. Nature2008; 452(7185): 301–310.
2.
HanHZhangLQiaoJ.Data-based predictive control for wastewater treatment process. IEEE Access2018; 6: 1498–1512.
3.
HanGHanHQiaoJ.A GPRFNN-based control system for wastewater treatment process. In: Proceedings of the 2016 35th Chinese control conference (CCC), Chengdu, China, 27–29 July 2016, pp.891–896. New York: IEEE.
4.
NahiunKMSarkerBKeyaKN, et al. A review on the methods of industrial waste water treatment. Sci Rev2021; 7(3): 20–31.
5.
WangNZhengTZhangG, et al. A review on Fenton-like processes for organic wastewater treatment. J Environ Chem Eng2016; 4(1): 762–787.
6.
GarrettM.Instrumentation, control and automation progress in the united states in the last 24 years. Water Sci Technol1998; 37(12): 21–25.
7.
HanHQiaoJ.Nonlinear model-predictive control for industrial processes: an application to wastewater treatment process. IEEE Trans Ind Electron2014; 61(4): 1970–1982.
8.
XueFFanZ.Kinematic control of a cable-driven snake-like manipulator for deep-water based on fuzzy PID controller. Proc IMechE, Part I: J Systems and Control Engineering2022; 236(5): 989–998.
9.
LiuYLiuY.Sensor controller parameter optimizing of sewage treatment system. Sens Lett2013; 11(11): 2164–2167.
10.
MendesJAraujoRMatiasT, et al. Automatic extraction of the fuzzy control system by a hierarchical genetic algorithm. Eng Appl Artif Intell2014; 29(3): 70–78.
11.
OuyangQWangZLiuK, et al. Optimal charging control for lithium-ion battery packs: a distributed average tracking approach. IEEE Trans Ind Inform2020; 16(5): 3430–3438.
12.
LiuKLiKZhangC.Constrained generalized predictive control of battery charging process based on a coupled thermoelectric model. J Pow Source2017; 347: 145–158.
13.
DuJKondakKZhangY, et al. Modelling and control of a small-scale unmanned helicopter. Proc IMechE, Part I: J Systems and Control Engineering2008; 222(6): 481–492.
14.
CorriouJPPonsMN.Model predictive control of wastewater treatment plants: application to the BSM1 benchmark. Comput Aid Chem Eng2004; 32(4): 625–630.
15.
HolendaBDomokosERédeyÁ, et al. Dissolved oxygen control of the activated sludge wastewater treatment process using model predictive control. Comput Chem Eng2008; 32(6): 1270–1278.
16.
BaruchISGeorgievaPBarrera-CortesJ, et al. Adaptive recurrent neural network control of biological wastewater treatment. Int J Intell Syst2005; 20(2): 173–193.
17.
LinMLuoF.Adaptive neural control of the dissolved oxygen concentration in WWTPs based on disturbance observer. Neurocomputing2016; 185: 133–141.
18.
MaT.Recursive filtering adaptive neural fault-tolerant control for uncertain multivariable nonlinear systems. Eur J Control2021; 59: 274–289.
19.
HalitZZenginNFidanB, et al. Blending based multiple-model adaptive control of multivariable systems with application to lateral vehicle motion control. Eur J Control2021; 58: 1–10.
QiaoXLuoFXuY.Robust PID controller design using genetic algorithm for wastewater treatment process. In: Proceedings of the 2016 IEEE advanced information management, communicates, electronic and automation control conference (IMCEC), Xi’an, China, 3–5 October 2016, pp.1081–1086. New York: IEEE.
22.
KatebiRJohnsonMWilkieJ.Control and instrumentation for wastewater treatment plants. Berlin: Springer, 1999.
23.
NejjariFDahhouBBenhammouA, et al. Non-linear multivariable adaptive control of an activated sludge wastewater treatment process. Int J Adapt Control Signal Process1999; 13(5): 347–365.
24.
SantínIPedretCVilanovaR.Model predictive control and fuzzy control in a hierarchical structure for wastewater treatment plants. In: Proceedings of the 2014 18th international conference on system theory, control and computing (ICSTCC), Sinaia, 17–19 October 2014, pp.375–380. New York: IEEE.
25.
SantínIPedretCVilanovaR.Fuzzy control and model predictive control configurations for effluent violations removal in wastewater treatment plants. Ind Eng Chem Res2015; 54(10): 2763–2775.
26.
HanHChenCSunH, et al. Multi-objective integrated optimal control for a wastewater treatment process. Control Eng Pract2022; 128: 105296.
27.
NugaliyaddeASohelFWongKW, et al. Language modeling through long-term memory network. In: Proceedings of the 2019 international joint conference on neural networks (IJCNN), Budapest, 14–19July2019, pp.1–6. New York: IEEE.
28.
TaxNVerenichIRosaML, et al. Predictive business process monitoring with LSTM neural networks. In: Proceedings of the international conference on advanced information systems engineering, Ljubljana, 13–17 June 2016, pp.477–492. Cham: Springer.
29.
ZhouFZhangZChenD.Real-time fault diagnosis using deep fusion of features extracted by parallel long short-term memory with peephole and convolutional neural network. Proc IMechE, Part I: J Systems and Control Engineering2021; 235(10): 1873–1897.
30.
WenSWeiHYangY, et al. Memristive LSTM network for sentiment analysis. IEEE Trans Syst Man Cyb Syst2021; 51(3): 1794–1804.
31.
FuXYangJLiJ, et al. Lexicon-enhanced LSTM with attention for general sentiment analysis. IEEE Access2018; 6: 71884–71891.
32.
WangHZhangXLiangB, et al. Gated hierarchical LSTMs for target-based sentiment analysis. Int J Softw Eng Knowl Eng2019; 28(12): 1719–1737.
33.
ZhouYLuoJFengL, et al. Long-short-term-memory-based crop classification using high-resolution optical images and multi-temporal SAR data. GISci Rem Sens2019; 56(8): 1170–1191.
34.
YangYJieZAiJ, et al. Video captioning by adversarial LSTM. IEEE Trans Imag Process2018; 27(11): 5600–5611.
35.
ZhangDHllandELindholmG, et al. Hydraulic modeling and deep learning based flow forecasting for optimizing inter catchment wastewater transfer. J Hydrol2017; 567: 792–802.
36.
HuTLiKMaH, et al. Quantile forecast of renewable energy generation based on Indicator Gradient Descent and deep residual BiLSTM. Control Eng Pract2021; 114(99): 1–14.
37.
PisaIMorellAVilanovaR, et al. Transfer learning in wastewater treatment plant control design: from conventional to long short-term memory-based controllers. Sensors2021; 21(18): 6315.
38.
LiuKShangYOuyangQ, et al. A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery. IEEE Trans Ind Electron2021; 68(4): 3170–3180.
39.
YanJChenXYuY, et al. Application of a parallel particle swarm optimization-long short term memory model to improve water quality data. Water2019; 11(7): 1317.
40.
PisaIMorellAVicarioJL, et al. Denoising autoencoders and LSTM-based artificial neural networks data processing for its application to internal model control in industrial environments: the wastewater treatment plant control case. Sensors2020; 20(13): 3743.
41.
OlssonG.ICA and me: a subjective review. Water Res2012; 46(6): 1585–1624.
42.
EjraeiAAroonMZiaratiA.Wastewater treatment using a hybrid system combining adsorption, photocatalytic degradation and membrane filtration processes. J Water Process Eng2019; 28: 45–53.
43.
LamichhaneKLewisWRongK, et al. Treatment of high strength acidic wastewater using passive pH control. J Water Process Eng2017; 18: 198–201.
44.
HenzeMGradyJCPLGujerW, et al. Activated sludge model no. 1. London: IWA Publishing, 1987.
45.
HanHWuXQiaoJ.A self-organizing sliding-mode controller for wastewater treatment processes. IEEE Trans Control Syst Technol2019; 27: 1480–1491.
GujerWHenzeM.Activated sludge modelling and simulation. Water Sci Technol1991; 23(46): 1011–1023.
48.
TakácsIPatryGGNolascoD.A dynamic model of the clarification-thickening process. Water Res1991; 25(10): 1263–1271.
49.
YuW.Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms. Inform Sci2004; 158: 131–147.
50.
HenzeMvan LoosdrechtMEkamaG, et al. Biological wastewater treatment: principles, modeling and design. London: IWA Publishing, 2008.
51.
PanHGaoHSunY, et al. The algorithm and software implementation for double-layered model predictive control based on multi-priority rank steady-state optimization. Acta Autom Sin2014; 40(3): 405–414.
