TY - JOUR
T1 - Soft-sensing of Wastewater Treatment Process via Deep Belief Network with Event-triggered Learning
AU - Wang, Gongming
AU - Jia, Qing Shan
AU - Zhou, Meng Chu
AU - Bi, Jing
AU - Qiao, Junfei
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China ( 62003185 and 62073182 ), in part by the National Science and Technology Major Project ( 2018ZX07111005 ). No conflict of interest exits in this manuscript and it has been approved by all authors for publication.
Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/5/14
Y1 - 2021/5/14
N2 - Due to the complex dynamic behavior of a Wastewater Treatment Process (WWTP), the existing soft-sensing models usually fail to efficiently and accurately predict its effluent water quality. Especially when a lot of practical data is provided and we do not know which data-pair is more valuable, WWTP modeling becomes a time-consuming process. The main reason is that the existing soft-sensing models update their parameters at each data-pair in one iteration, while some update operations are meaningless. To address this thorny problem, this paper proposes a Deep Belief Network with Event-triggered Learning (DBN-EL) to improve the efficiency and accuracy of soft-sensing model in WWTP. First, some events are defined according to different running condition during the process of training DBN-based soft-sensing model. The different running condition is dominated by the fluctuation of error-reduction rate. Second, an event-triggered learning strategy is designed to construct DBN-EL, whose parameters are updated only when a positive event is triggered. Thirdly, we present the convergence analysis of DBN-EL based on the optimization in a Markov process. Finally, the effectiveness of DBN-EL is demonstrated on soft-sensing of total phosphorus concentration in a practical WWTP system. In experiment, DBN-EL is compared with nine different models on soft-sensing of WWTP. The experimental results show that the efficiency of DBN-EL is 27.6%–64.9% higher than that of nine competitive models, which indicates that the proposed model is readily available for industrial deployment.
AB - Due to the complex dynamic behavior of a Wastewater Treatment Process (WWTP), the existing soft-sensing models usually fail to efficiently and accurately predict its effluent water quality. Especially when a lot of practical data is provided and we do not know which data-pair is more valuable, WWTP modeling becomes a time-consuming process. The main reason is that the existing soft-sensing models update their parameters at each data-pair in one iteration, while some update operations are meaningless. To address this thorny problem, this paper proposes a Deep Belief Network with Event-triggered Learning (DBN-EL) to improve the efficiency and accuracy of soft-sensing model in WWTP. First, some events are defined according to different running condition during the process of training DBN-based soft-sensing model. The different running condition is dominated by the fluctuation of error-reduction rate. Second, an event-triggered learning strategy is designed to construct DBN-EL, whose parameters are updated only when a positive event is triggered. Thirdly, we present the convergence analysis of DBN-EL based on the optimization in a Markov process. Finally, the effectiveness of DBN-EL is demonstrated on soft-sensing of total phosphorus concentration in a practical WWTP system. In experiment, DBN-EL is compared with nine different models on soft-sensing of WWTP. The experimental results show that the efficiency of DBN-EL is 27.6%–64.9% higher than that of nine competitive models, which indicates that the proposed model is readily available for industrial deployment.
KW - Deep belief network
KW - Efficient learning process
KW - Event-triggered learning
KW - Soft-sensing model
KW - Wastewater Treatment Process (WWTP)
UR - http://www.scopus.com/inward/record.url?scp=85100231557&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100231557&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2020.12.108
DO - 10.1016/j.neucom.2020.12.108
M3 - Article
AN - SCOPUS:85100231557
SN - 0925-2312
VL - 436
SP - 103
EP - 113
JO - Neurocomputing
JF - Neurocomputing
ER -