Affiliation:
1. Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
2. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
Abstract
The production of vanadium nitrogen alloys (VNs) is a chemical reaction process carried out in a closed pusher plate kiln, making real-time monitoring of key parameters challenging. Traditional methods for controlling process parameters are insufficient to meet the demands of production control. And the current production line heavily depends on workers’ experience and operates with a relatively low level of automation. In order to solve the above problems, this paper proposes a method for monitoring, predicting, and online controlling the production process parameters of VNs based on digital twins. Firstly, the process parameter affecting quality in the production process is experimentally selected as the target for prediction and control. Then, the ISSA-GRNN (Improved Sparrow Search Algorithm-Generalized Regression Neural Networks) fusion prediction model is constructed to predict the optimal values and intervals for the process parameter of movement interval. Finally, a digital twin system is developed to integrate the fusion prediction model to achieve real-time monitoring and online control of the production line. And the superiority of the algorithm and the feasibility of online control are verified through experiments. This paper achieves accurate prediction and online control of parameters in the VNs production process and has reduced reliance on workers’ production experience. Additionally, it has effectively lowered energy consumption and failure rates, facilitated the transition from traditional kiln production to intelligent production, and thereby supported sustainable development.
Funder
Shanghai Collaborative Innovation Special Fund Project
Reference40 articles.
1. Numerical simulation and artificial neural network modeling of natural circulation boiling water reactor;Garg;Nucl. Eng. Des.,2007
2. A simulated model for a once-through boiler by parameter adjustment based on genetic algorithms;Chaibakhsh;Simul. Model. Pract. Theory,2007
3. Steam turbine model;Chaibakhsh;Simul. Model. Pract. Theory,2008
4. A combined neural network and simulated annealing based inverse technique to optimize the heat source control parameters in heat treatment furnaces;Yadav;Inverse Probl. Sci. Eng.,2020
5. Rosso, M.M., Aloisio, A., Cucuzza, R., Pasca, D.P., Cirrincione, G., and Marano, G.C. (2022, January 6–9). Structural health monitoring with artificial neural network and subspace-based damage indicators. Proceedings of the International Conference on Trends on Construction in the Post-Digital Era, Guimarães, Portugal.