Multi-objective Cold Rolling Load Distribution Based On Improved Firefly Algorithm

In recent decades,China ’s economic and technological development is very rapid,and many fields have moved to the forefront of the world.In some manufacturing fields,cold rolled strip steel occupies a crucial position.In the production process of cold rolled strip,setting load distribution scheme is an important link.An accurate and reasonable load distribution scheme can improve the utilization rate of cold rolling mill,reduce loss and cost,and improve the quality and output of finished strip.Based on the five-stand cold tandem rolling of a steel mill,this thesis uses the improved firefly algorithm to optimize the load distribution design.The main research contents are as follows :Aiming at the problems of uneven distribution of initial population and poor flexibility of optimization process in firefly algorithm,a chaotic adaptive weighted multi-objective firefly algorithm is proposed.Firstly,in order to solve the problem that the random initialization strategy cannot ensure that the initialized population is evenly distributed in space,which affects the optimization speed and search ability of the algorithm,the random initialization strategy is improved to the Tent chaotic mapping reverse initialization strategy.The diversity of the initial population is improved and the convergence speed of the algorithm is accelerated by using the distribution uniformity,ergodicity of Tent chaotic map and the reverse learning strategy which can be closer to the optimal individual.Secondly,in order to solve the problem that the speed and step length factor are fixed in the firefly movement formula,which leads to the poor search flexibility of the algorithm,the chaotic inertia weight and adaptive step length factor changing with the number of iterations are introduced into the movement formula,which improves the global search ability of the algorithm in the early stage of optimization and the local search ability in the later stage of optimization.Finally,the CAWMOFA algorithm is compared with other multi-objective optimization algorithms in a variety of test functions.The simulation results show that the optimal solution obtained by CAWMOFA algorithm can better converge to the real Pareto front and has good spatial distribution.The relevant mathematical model of tandem cold rolling is selected.According to the calculation process of load distribution,the objective function of equal relative load,the objective function of preventing slipping and the objective function of good shape of last stand are established,and the corresponding constraints are given.The CAWMOFA algorithm is introduced into the cold rolling load distribution optimization model,and the obtained Pareto optimal solution sets are better than the original rules.A variety of optimizations based on different preferences can be calculated to meet production requirements in different situations,and have been improved compared to the original schedule in terms of balancing the power of each rack,preventing slippage,and maintaining good end-rack profile.