Research And Realization Of Automatic Production Scheduling In Flexible Packaging Printing Workshop

With the progress of science and technology and the increasingly fierce market competition,the differences in quality,design,selling points between the products of various flexible packaging printing enterprises are gradually narrowing.If you want to increase the competitiveness of enterprises,you can start from the production of printing shop products.Therefore,in the validity period of customer production orders,how to efficiently carry out production and distribution is particularly important.More and more enterprises realize that automatic production scheduling is a key point to improve competitiveness.However,in our printing enterprises,there are still some problems in the automatic production scheduling system,such as weak production capacity,long time and poor accuracy of production,which have seriously affected the production and interests of enterprises.In view of the above problems,this thesis aims to improve the core algorithm of APS system,Grey Wolf optimization algorithm,by improving the generation mode of initial population,convergence factor,introduction of PSO individual memory and integration of artificial bee colony algorithm,so as to make it closer to the actual production workshop environment,improve the speed and accuracy of automatic production scheduling.To sum up,in this thesis the automatic production scheduling problem of flexible packaging printing enterprises are studied,mainly done the following work:(1)The basic situation and production type of printing enterprises are introduced,and the characteristics,environment and problems of the actual production scheduling workshop are analyzed and investigated.At the same time,the production process of flexible packaging printing enterprises is analyzed,and the mathematical model of workshop production is established by using these background analyses.(2)According to the actual production situation of flexible packaging printing workshop,this thesis proposes an improved Grey Wolf optimization algorithm,which makes some improvements to the traditional Grey Wolf algorithm,which is easy to fall into the local optimal solution,slow convergence speed and low population diversity.Firstly,starting from the generation of the initial population,the elite reverse learning and chaotic sequence are used to initialize the population to ensure the diversity of the initial population.Then,in order to balance global search and local search,the parameter formula of convergence factor is changed.Then,considering that Grey Wolf population could not learn its own experience when updating the decision level position,the individual memory of PSO algorithm was introduced to increase the convergence speed and the probability of jumping out of the local optimal solution.Finally,the artificial bee colony algorithm is introduced to screen the individual positions of decision level again,and strive to find the optimal position of the decision level Grey Wolf,so as to improve the ability of the improved Grey Wolf optimization algorithm to jump out of the local optimal solution and increase the global search ability.(3)In order to prove the effect of the improved Grey Wolf algorithm,experiments are designed in the standard examples,and the experimental results are compared with the traditional Grey Wolf algorithm.The results show that the improved Grey Wolf optimization algorithm proposed in this thesis is far better than the traditional Grey Wolf optimization algorithm in terms of convergence speed,accuracy of optimal value and stability.Then the improved Grey Wolf optimization algorithm is applied to APS system of production workshop in flexible packaging printing enterprises.The results show that the improved Grey Wolf optimization algorithm is suitable for automatic production scheduling in flexible packaging printing enterprises.Finally,this thesis summarizes the specific research and puts forward the new direction of future research.