| 摘 要: 为了提高枕式包装机纵封热封流程生产效率，降低人力成本，提出了一种基于径向基函数神经网络-遗传算法(Radial Basis Function Neural Network-Genetic Algorithm, RBFNN-GA)的工艺参数决策方法。根据热封材料断裂屈服强度确定加工目标热封强度；以热封距离、热封温度、热封速度为工艺参数变量，通过生产样本对RBF神经网络进行训练建立模型，并以此模型为基础，设计遗传算法寻优过程当中的适应度函数；通过遗传算法进行工艺参数的最优求解，并将结果输入到枕式包装机进行加工测试与热封强度的测定。结果表明：根据所述方法得到的测试结果满足实际加工需求，为枕式包装机的智能化升级提供了理论依据。 |
| 关键词: 枕式包装机纵封；热封强度；参数寻优；RBF神经网络；遗传算法 |
|
中图分类号: TP241
文献标识码: A
|
|
| Research on the Decision-Making Method of Process Parameter in Longitudinal and Heat Sealing based on RBFNN-GA |
|
PENG Laihu1,2, XU Qindong1
|
( 1.Zhejiang Sci -Tech University, Hangzhou 310000, China ;
2.Zhejiang Sci -Tech University Longgang Research Institute, Wenzhou 325000, China )
laihup@zstu.edu.cn; 202030605294@mails.zstu.edu.cn
|
| Abstract: In order to improve the production efficiency of the longitudinal and heat sealing process of the pillow packaging machine, and reduce the labor costs, this paper proposes a process parameter decision-making method based on Radial Basis Function Neural Network-Genetic Algorithm (RBFNN-GA). Firstly, the heat sealing strength of the processing target is determined based on the breaking yield strength of the heat sealing material. Then, taking heat sealing distance, heat sealing temperature and heat sealing speed as process parameter variables, the RBF neural network is trained through production samples to establish a model, based on which the fitness function in the optimization process of genetic algorithm is designed. Lastly, the optimization of process parameters is solved by genetic algorithm, and the results are input into the pillow packaging machine for processing test and heat sealing strength determination. The results show that the test results obtained by the proposed method meet the actual processing needs, and provide a theoretical basis for the intelligent upgrading of pillow packaging machine. |
| Keywords: longitudinal sealing of pillow packaging machine; heat sealing strength; parameter optimization; RBF neural network; genetic algorithm |
