基于工程师打样中确定合理工艺参数组合的工程背景，借鉴三元蜜蜂算法开发了用于工艺参数寻优的快速蜜蜂试验法. 针对304不锈钢板激光焊中获得较高抗拉强度需求，比较了响应面法、基于响应面法拟合方程的蜜蜂算法优化求解和快速蜜蜂试验法3种方法下所获优化结果. 结果表明，前两种方法所预测最优工艺参数获得抗拉强度均近似于688 MPa，而快速蜜蜂试验法求解的最优工艺参数获得抗拉强度734 MPa. 快速蜜蜂试验法划分清晰及针对性强的优化特点，使其相比响应面法减少试验次数的同时避免了忽略不同区域中概率密度不同的问题. 所开发的快速蜜蜂试验法能够作为一种学习成本低与重视结果突出试验点的试验方法，帮助工程师在打样过程中快速获得更优工艺参数组合.
Based on the engineering background of determining the reasonable combination of process parameters in engineers' proofing, a fast bees test method for optimizing process parameters was developed with reference to the ternary bees algorithm. Aiming at the high tensile strength requirement of 304 stainless steel plate in laser welding, the optimization results obtained by response surface method, bees algorithm optimization solution based on the fitting equation of response surface method and fast bees test method were compared. The optimal solutions predicted by the previous two methods were approximately 688 MPa, while the optimal process parameters obtained by the fast bees test method obtain the tensile strength of 734 MPa. The results show that compared with the response surface method, the fast bees test method can reduce the number of tests and avoid the problem of ignoring the different probability density in different regions. The fast bees test method can be used as a test method with low learning cost and emphasis on the result to highlight the test point, which can help engineers quickly obtain a better combination of process parameters in the process of proofing.
[1] 吴晓红. 电池连接片紫铜激光焊工艺研究[J]. 应用激光, 2020, 40(1): 62-66
Wu Xiaohong. Research on laser welding process of copper in battery connector[J]. Applied Laser, 2020, 40(1): 62-66
[2] 曹海涛, 张鹏, 杜云慧, 等. Mg-Gd-Y-Zr激光焊工艺优化及高温力学性能[J]. 焊接学报, 2020, 41(10): 87-96
Cao Haitao, Zhang Peng, Du Yunhui, et al. Optimization of Mg-Gd-Y-Zr laser welding process parameters and study on high temperature mechanical properties[J]. Transactions of the China Welding Institution, 2020, 41(10): 87-96
[3] 王传洋, 郝云, 沈璇璇, 等. 工艺参数对激光透射焊接聚碳酸酯影响[J]. 焊接学报, 2016, 37(7): 57-60
Wang Chuanyang, Hao Yun, Shen Xuanxuan, et al. Effect of process parameters on laser transmission welding polycarbonate[J]. Transactions of the China Welding Institution, 2016, 37(7): 57-60
[4] 李莉, 张赛, 何强, 等. 响应面法在试验设计与优化中的应用[J]. 实验室研究与探索, 2015, 34(8): 41-45
Li Li, Zhang Sai, He Qiang, et al. Application of response surface methodology in experimental design and optimization[J]. Research and Exploration in Laboratory, 2015, 34(8): 41-45
[5] Chelladurai S J S, Murugan K, Ray A P, et al. Optimization of process parameters using response surface methodology: A review[J]. Materials Today: Proceedings, 2021, 37: 1301-1304.
[6] 丁亚茹, 陈芙蓉, 杨帆, 等. 响应面法分析7075铝合金激光焊参数对焊接质量的影响规律[J]. 材料导报, 2021, 35(2): 2103-2108
Ding Yaru, Chen Furong, Yang Fan, et al. Analyzing the influence of laser welding parameters on the welding quality of 7075 aluminum alloy by response surface methodology[J]. Materials Reports, 2021, 35(2): 2103-2108
[7] 褚振涛, 于治水, 张培磊, 等. 基于响应面分析的T型接头激光深熔焊焊缝形貌预测及工艺参数优化[J]. 中国激光, 2015, 42(2): 108-116
Chu Zhengtao, Yu Zhishui, Zhang Peilei, et al. Weld profile prediction and process parameters optimization of T-joints of laser full penetration welding via response surface methodology[J]. Chinese Journal of Lasers, 2015, 42(2): 108-116
[8] 成奇, 郭宁, 付云龙, 等. 基于响应曲面法的铝合金激光封边焊接[J]. 焊接学报, 2022, 43(10): 1-10
Cheng Qi, Guo Ning, Fu Yunlong, et al. Study on laser edge sealing welding of aluminum alloy based on response surface method[J]. Transactions of the China Welding Institution, 2022, 43(10): 1-10
[9] Goswami S, Ghosh S, Chakraborty S. Reliability analysis of structures by iterative improved response surface method[J]. Structural Safety, 2016, 60: 56-66.
[10] Guimarães H, Matos J C, Henriques A A. An innovative adaptive sparse response surface method for structural reliability analysis[J]. Structural Safety, 2018, 73: 12-28.
[11] Choudhary A, Kumar M, Gupta M K, et al. Mathematical modeling and intelligent optimization of submerged arc welding process parameters using hybrid PSO-GA evolutionary algorithms[J]. Neural Computing and Applications, 2020, 32(10): 5761-5774.
[12] Vedrtnam A, Singh G, Kumar A. Optimizing submerged arc welding using response surface methodology, regression analysis, and genetic algorithm[J]. Defence Technology, 2018, 14(3): 204-212.
[13] 王霄, 张成, 王凯, 等. 基于遗传算法-响应曲面方法的激光透射焊接聚碳酸酯工艺的多目标优化[J]. 中国激光, 2012, 39(6): 75-81
Wang Xiao, Zhang Cheng, Wang Kai, et al. Multi-objective optimization of laser transmission welding of polycarbonate process based on genetic algorithm-response surface methodology[J]. Chinese Journal of Lasers, 2012, 39(6): 75-81
[14] 余果, 尹玉环, 高嘉爽, 等. 基于正交试验-BP神经网络的GH4169膜片微束TIG焊接工艺优化[J]. 焊接学报, 2018, 39(11): 119-123,128
Yu Guo, Yin Yuhuan, Gao Jiashuang, et al. Orthogonal experiment method and BP neural networks in optimization of microbeam TIG welded GH4169[J]. Transactions of the China Welding Institution, 2018, 39(11): 119-123,128
[15] Pham D T, Castellani M. A comparative study of the Bees Algorithm as a tool for function optimisation[J]. Cogent Engineering, 2015, 2(1): 1091540.
[16] Laili Y, Tao F, Pham D T, et al. Robotic disassembly re-planning using a two-pointer detection strategy and a super-fast bees algorithm[J]. Robotics and Computer-Integrated Manufacturing, 2019, 59: 130-142.
