目的 旨在优化铝塑热封加热辊的关键结构参数,以提升其工作表面温度均匀性。方法 建立加热辊关键结构的温度场仿真模型,数值模拟出不同结构参数（δ1、δ2）下的工作表面温度均匀性,获得工作表面温度均匀性离散数据;基于仿真结果构建BP神经网络预测模型,精确映射结构参数与温度均匀性指标（ΔTmax、Tf、Tu）之间的复杂非线性关系;以BP神经网络预测结果为适应度函数,采用NSGA-Ⅱ非支配排序遗传算法对关键结构参数进行多目标寻优。结果 优化后的加热辊在工作表面最大温差ΔTmax为1.13 ℃、温度波动度Tf为0.50 ℃、温度均匀性指数Tu为0.995 4时,对应内部结构参数δ1为14 mm、δ2为10 mm,相较于企业现有的加热辊ΔTmax降低了6.39 ℃、Tf降低了2.19 ℃、Tu提升了0.014 6。结论 基于BP-NSGA-Ⅱ构建的加热辊关键结构参数多目标优化模型,能够系统分析工作表面温度均匀性与结构参数之间的关系;有效降低传统研究中多因素耦合引起的误差,可为铝塑热封包装行业智能化升级提供理论支撑。
Abstract
The work aims to optimize the key structural parameters of the aluminum-plastic heat sealing heating roller to improve the uniformity of its working surface temperature. A temperature field simulation model was established for the key structure of the heating roller and the uniformity of the working surface temperature under different structural parameters (δ1, δ2) was numerically simulated to obtain the discrete data of the temperature uniformity on the working surface. Based on the simulation results, a BP neural network prediction model was constructed to precisely map the complex nonlinear relationship between the structural parameters and the temperature uniformity indicators (ΔTmax, Tf, Tu). With the BP neural network prediction results as the fitness function, the NSGA Ⅱ non-dominated sorting genetic algorithm was adopted to conduct multi-objective optimization for the key structural parameters. After optimization, when the maximum temperature difference ΔTmax on the working surface of the heating roller was 1.13 ℃, the temperature fluctuation degree Tf was 0.50 ℃, and the temperature uniformity index Tu was 0.995 4 and the corresponding internal structure parameters were δ1 = 14 mm and δ2 = 10 mm. Compared with the existing heating rollers of the enterprise, ΔTmax was reduced by 6.39 ℃, Tf was reduced by 2.19 ℃, and Tu increased by 0.014 6. The multi-objective optimization model for key structural parameters of the heating roller, constructed based on BP-NSGA-II, can systematically analyze the relationship between the uniformity of the working surface temperature and the structural parameters, effectively reduce the errors caused by the coupling of multiple factors in traditional research, and provide theoretical support for the intelligent upgrade of the aluminum-plastic heat-sealing packaging industry.
关键词
铝塑热封 /
BP神经网络 /
NSGA-Ⅱ算法 /
温度均匀性
Key words
aluminum-plastic heat sealing /
BP neural network /
NSGA-Ⅱ algorithm /
temperature uniformity
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈永安, 罗清华, 向全生, 等. 影响药品铝塑泡罩包装质量的因素探讨[J]. 广东化工, 2020, 47(12): 100-101.
CHEN Y A, LUO Q H, XIANG Q S, et al.Explore the Factors that Affect the Quality of Aluminum-Plastic Blister Packaging of Drugs[J]. Guangdong Chemical Industry, 2020, 47(12): 100-101.
[2] 孙怀远, 顾青青, 孙波, 等. 铝塑泡罩包装机及其应用[J]. 机电信息, 2015(17): 22-26.
SUN H Y, GU Q Q, SUN B, et al.Aluminum-Plastic Blister Packaging Machine and Its Application[J]. Mechanical and Electrical Information, 2015(17): 22-26.
[3] HSIEH M, LIN J.Research on Design of Heating System of Continuous Heat Transfer Machine[C]//Proceedings of the 2018 International Conference on Mathematics, Modeling, Simulation and Statistics Application (MMSSA 2018). Shanghai, China. Atlantis Press, 2019: 179-182.
[4] 张北龙, 张志强, 尹晓岚, 等. 铝塑热封加热辊温度场仿真及其结构优化[J]. 包装工程, 2025, 46(15): 238-245.
ZHANG B L, ZHANG Z Q, YIN X L, et al.Simulation of Temperature Field and Structure Optimization of Aluminum-Plastic Heat Sealing Heating Roll[J]. Packaging Engineering, 2025, 46(15): 238-245.
[5] 任世鹏, 安元, 娄春, 等. 融合深度学习算法的炉内燃烧温度场分布在线重建[J]. 化工进展, 2025, 44(4): 1923-1933.
REN S P, AN Y, LOU C, et al.Online Reconstruction of Combustion Temperature Field Distribution in Furnace by Integrating Deep Learning Algorithm[J]. Chemical Industry and Engineering Progress, 2025, 44(4): 1923-1933.
[6] 周世玉, 杜光月, 褚鑫, 等. 地采暖木地板释热温度场的BP神经网络预测[J]. 林业科学, 2018, 54(11): 158-163.
ZHOU S Y, DU G Y, CHU X, et al.Prediction of Thermal Released Field by the Wood Flooring for Ground with Heating System Based on BP Network[J]. Scientia Silvae Sinicae, 2018, 54(11): 158-163.
[7] 贾永会, 杜建桥, 汪潮洋, 等. 基于BP神经网络的燃煤锅炉温度分布预测[J]. 热能动力工程, 2020, 35(7): 130-138.
JIA Y H, DU J Q, WANG C Y, et al.Prediction Model of Temperature Distribution in Combustion Zone of Coal-Fired Boiler Based on BP Neural Network[J]. Journal of Engineering for Thermal Energy and Power, 2020, 35(7): 130-138.
[8] HONG T J, HUANG D, DING F J, et al.Multi-Objective Optimization of Injection Molding Process Parameters for Junction Boxes Based on BP Neural Network and NSGA-II Algorithm[J]. Materials, 2025, 18(3): 577.
[9] MIAO J Q, LI P H, LV M C, et al.Resonant MEMS Accelerometer with Low Cross-Axis Sensitivity—Optimized Based on BP and NSGA-II Algorithms[J]. Micromachines, 2024, 15(8): 1049.
[10] 何世明, 石光林, 刘文选, 等.基于NSGA-Ⅱ算法和BP神经网络的轮辋焊接工艺参数优化[J/OL]. 广西科技大学学报, 1-15[2025-12-24]. https://link.cnki.net/ urlid/45.1395.t.20250223. 1910.004.
HE S M, SHI G L, LIU W X, et al.Optimization of Rim Welding Process Parameters Based on NSGA- II Algorithm and BP Neural Network [J/OL] Journal of Guangxi University of Science and Technology,1-15[2025-12-24]. https://link.cnki. net/ urlid/45.1395.t. 20250223.1910.004.
[11] BAO J F, YU C K W, WANG J H, et al. Modified Inexact Levenberg-Marquardt Methods for Solving Nonlinear Least Squares Problems[J]. Computational Optimization and Applications, 2019, 74(2): 547-582.
[12] 李骅, 吕大伟, 王永健, 等. 基于BP-NSGA-Ⅱ算法的小麦低损脱粒自适应调控方法[J]. 农业机械学报, 2025, 56(11): 243-252.
LI H, LYU D W, WANG Y J, et al.Adaptive Regulation of Low-Loss Threshing in Wheat Based on BP-NSGA-Ⅱ Algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2025, 56(11): 243-252.
[13] 王乐恒, 蔡玉强, 袁鵾, 等. 基于BP神经网络和改进NSGA-II算法的龙门横梁结构优化[J]. 机床与液压, 2025, 53(19): 56-63.
WANG L H, CAI Y Q, YUAN K, et al.Structure Optimization of Beam of Large Gantry Equipment Based on BP Neural Network and Improved NSGA-II Algorithm[J]. Machine Tool & Hydraulics, 2025, 53(19): 56-63.
基金
2025年锦州市指导性科技计划项目成果（JZ2025B003）; 辽宁省科技厅联合计划博士启动基金项目（2024BSLH118）; 辽宁省教育厅基本科研项目（JYTQN2023216）
PDF(7756 KB)
渝公网安备 50010702501716号 渝ICP备15012534号-2
