Operation Optimization Of Continuous Annealing Production Proces

The continuous annealing production process,as an important process in cold rolling,is the most indispensable link in strip production.The process is often accompanied by various environmental changes during operation,which is prone to problems such as low strip quality,low production efficiency,and high energy consumption.Optimizing the process can save resources and improve production efficiency for enterprises.Therefore,in this paper,in order to effectively optimize the continuous annealing production process.It mainly include the following contents:Firstly,the strip quality and production utilization are determined.Secondly,the relevant decision variables and constraint conditions are determined by mechanism analysis.Finally,the multi-objective optimization model is established.The model is complex and Multi-Objective Dragonfly Algorithm is used to solve the model.The experimental results show that the strip quality and production utilization have been improved.Aiming at the noise interference factors in the actual production process,a robust multi-objective optimization model is carried out for the continuous annealing process.We proposed a robustness index based on the coefficient of variation,which is used for guiding the model.The model becomes more complex and it is difficult to solve this model due to the noise factors.The Adventure Circuitous strategy is introduced to enhance the convergence of the algorithm.Firstly,the experiment verifies the validity by the robust test functions.Secondly,the proposed algorithm is used to solve the continuous annealing process and the results show that the robustness of the proposed index is more strong.At the end,the robust and stable strip quality and production capacity are obtained.Aiming at the dynamic environment change problem in the control system,a time variable is introduced to establish a dynamic multi-objective optimization model for the continuous annealing process.In order to predict whether the dynamic environment will change,the long and short-term memory network model is utilized to predict the strip hardness at the next moment.At the same time,to make the population adapt to the environment quickly,we proposed the information fusion strategy for improving the diversity of the population.The experiment verifies the accuracy of the prediction model.Then the improved algorithm is verified by the dynamic test functions.The result shows it can track changes in the environment effectively and obtain the dynamic frontier.Finally,the proposed algorithm is used to solve the continuous annealing problem.The optimized results enhance the stability of the production process and improve the strip quality and production capacity.To further optimize the continuous annealing process effectively,the noise factors and environmental changes are both considered.Therefore,the dynamic robust multi-objective optimization model is established.A new definition about the dynamic robust solutions is given by analyzing the characteristics of noise in actual process.We proposed a multi-objective dragonfly algorithm with adaptive evolutionary mutation for improving the performance of the MODA.Firstly,the test functions are used to verify the performance.The results show that the improved algorithm is effective and can obtain high-quality dynamic robust solutions.Then the improved algorithm is used to solve the dynamic robust model.The results show that the strip hardness and production capacity can remain stable in the dynamic environment.At the end,Python and Py Qt are used to develop optimization software for continuous annealing process control system.The software is helpful for the companies to save energy,reduce consumption and improve production efficiency.