Translated Title
Multi-objective optimization control for wastewater treatment processing based on neural network
Translated Abstract
To solve the energy?extensive consumption problem of the wastewater treatment process ( WWTP ) , a dy?namic multi?objective optimization control strategy is proposed in this paper. The proposed method simultaneously optimizes the aerate energy and pumped energy consumption of WWTP , and the set?points of dissolved oxygen con?centration and nitrate level can be optimized dynamically using the NSGA?Ⅱ evolutionary algorithm. The propor?tion?integral?derivative( PID) is chosen to realize the tracking control task for the low layer. To overcome the diffi?culty of establishing an optimal model for WWTP , an online neural network modeling method was proposed for con?structing the multi?objective optimization model, which solves the problem that there is no accurate mathematical description with the optimization variables and performance indexes. The simulation results, based on the interna?tional benchmark simulation model No. 1, demonstrate that compared with the PID and the single?objective optimi?zation methods, energy consumption can be significantly reduced by using the proposed method while still assuring water quality.
Translated Keyword
benchmark simulation model
neural network
multi-objective optimization
wastewater treatment
energy consumption
Access Number
WF:perioarticalxdkjyc201605004
Corresponding authors email
