Digital twin technology for sewage sludge smoldering process and CO/NOx emissions based on back propagation neural network: A laboratory experimental study

Smoldering has broad prospects for application in the treatment of sewage sludge with high moisture content, but it faces the problem of high CO/NOx emission concentrations. To improve smoldering velocity and reduce emission concentrations of gas pollutants, intelligent control and refined treatment of sewage sludge smoldering need to be achieved. In this paper, the digital twin-driven sewage sludge smoldering treatment system is proposed, and the overall framework, operational process and key technologies of the system are described in detail. A digital twin system based on the back propagation neural network model is constructed, which achieves the accurate prediction of the variation trends and average values of CO/NOx emission concentrations as well as smoldering temperature and velocity. Nondominated Sorting Genetic Algorithm II is used for multiobjective optimization, providing effective control strategies for sewage sludge with distinctive characteristics. Smoldering features, emission concentrations of gas pollutions and equipment operating status are visualized using WebGL technology. Results show the maximum increase in smoldering velocity is 49 %, whilst CO can be reduced by 8-60 % and the maximum reduction in NOx is 51 %. This system can assist in applications such as monitoring state of sewage sludge smoldering, timely warnings and intelligent control.