针对利用信息熵评价焊接疲劳性能影响因素所存在的问题，引入信息增益率的概念，建立了碳钢与不锈钢电阻点焊接头疲劳性能影响因素分析模型，对各因素的信息熵和信息熵占比以及信息增益率等进行分析，以研究各因素对焊接疲劳性能的影响程度. 结果表明，板厚与焊接时间的信息熵以及信息熵占比最大，不确定性最高，电极直径与电极力刚好相反，各因素的信息熵差异较大导致对信息增益有很大影响. 电极直径与电极力的信息增益率为59.34%，对疲劳性能的影响最大；板宽的信息增益率为38.89%，对疲劳性能的影响最小；板厚与焊接时间的信息增益率为52.33%，对疲劳性能的影响仅次于电极直径与电极力.
Aiming at the problems of using information entropy to evaluate the influence factors of welding fatigue performance, this paper introduces the concept of information gain rate and establishes an analysis model for analyzing the influencing factors of fatigue performance of carbon steel and stainless steel resistance spot welded joints. The information entropy, information entropy proportion and information gain rate of each factor are analyzed to study the influence of each factor on welding fatigue performance. The results show that the information entropy and its proportion of plate thickness and welding time is the largest, and the uncertainty is the highest, however electrode diameter and electrode pressure is just the opposite, the large difference in information entropy of each factor leads to a great influence on the information gain. The information gain rate of electrode diameter and electrode pressure is 59.34%, which has the greatest impact on fatigue performance. The information gain rate of plate width is 38.89%, which has the least impact on fatigue performance. The information gain rate of plate thickness and welding time is 52.33%, the impact on fatigue performance is second to the electrode diameter and electrode pressure.
[1] 杨新岐, 张艳新, 霍立兴, 等. 焊接接头疲劳评定局部法研究进展[J]. 机械强度, 2003(6): 675 - 681
Yang Xinqi, Zhang Yanxin, Huo Lixin, et al. Review of fatigue assessment of welded joints by local approaches[J]. Journal of Mechanical Strength, 2003(6): 675 - 681
[2] 霍立兴. 焊接结构的断裂行为及评定[M]. 中国建筑工业出版社, 2000.
Huo Lixing. Fatigue behavior and evaluation of welded structure[M]. China Architecture & Building Press, 2000.
[3] 张彦华. 焊接结构疲劳分析[M]. 化学工业出版社, 2013.
Zhang Yanhua. Fatigue analysis of welded structure[M]. Chemical Industry Press, 2013.
[4] Shi Y, Guo H. Fatigue performance and fatigue damage parameter estimation of spot welded joints of aluminium alloys 6111‐T4 and 5754[J]. Fatigue & Fracture of Engineering Materials & Structures, 2014, 36(10): 1081 - 1090.
[5] Armansyah, Saedon J, Ho H C, et al. Investigation on parameter contribution to the property of weld joint AA5052-H112 sheets in friction stir spot welding under fatigue load and failure mode[J]. Applied Mechanics and Materials, 2020, 899: 117 - 125.
[6] Yu Huiping, Hu Mingqing, Liu Yuehua, et al. Analysis of the effect of geometrical parameters on fatigue performance of spot-weld joint for ultra-high strength steel[J]. China Welding, 2016, 25(4): 34 - 41.
[7] Ertas A H, Sonmez F O. A parametric study on fatigue strength of spot‐weld joints[J]. Fatigue & Fracture of Engineering Materials & Structures, 2008, 31(9): 766 - 776.
[8] Murugan R, Venugobal P R, Ramaswami T P, et al. Studies on the effect of weld defect on the fatigue behavior of welded structures[J]. China Welding, 2018, 27(1): 53 - 59.
[9] Fricke W. Fatigue analysis of welded joints state of development[J]. Marine Structures, 2003, 16(3): 185 - 200.
[10] Hobbacher A F. The new IIW recommendations for fatigue assessment of welded joints and components-a comprehensive code recently updated[J]. International Journal of Fatigue, 2009, 31(1): 50 - 58.
[11] Radaj D, Sonsino C M, Fricke W. Recent developments in local concepts of fatigue assessment of welded joints[J]. International Journal of Fatigue, 2009, 31(1): 2 - 11.
[12] 彭凡, 姚云建, 顾勇军. 热点应力法评定焊接接头疲劳强度的影响因素[J]. 焊接学报, 2010, 31(7): 83 - 86
Peng Fan, Yao Yunjian, Gu Yongjun. Influence factors of fatigue strength assessment for welded joints by hot spot stress approach[J]. Transactions of the China Welding Institution, 2010, 31(7): 83 - 86
[13] 刘刚, 唐柳伦, 黄一. 基于场强法的焊接接头疲劳寿命影响因素研究[J]. 船舶力学, 2014, 18(Z1): 158 - 164
Liu Gang, Tang Liulun, Huang Yi. A study on the influence factors of fatigue in welded joints based on field intensity approach[J]. Journal of Ship Mechanics, 2014, 18(Z1): 158 - 164
[14] 王东坡, 曹舒, 邓彩艳. 基于缺口应力法的场桥导轨焊接结构疲劳性能评估[J]. 焊接学报, 2016, 37(4): 5 - 8
Wang Dongpo, Cao Shu, Deng Caiyan. Notch stress concepts for fatigue assessment of welded portal crane rail structure[J]. Transactions of the China Welding Institution, 2016, 37(4): 5 - 8
[15] Yang X H, Zou L, Deng W. Fatigue life prediction for welding components based on hybrid intelligent technique[J]. Material Science and Engineering A, 2015, 642: 253 - 261.
[16] 邹丽, 杨鑫华, 孙屹博, 等. 基于变精度粗糙集的铝合金焊接接头疲劳寿命预测[J]. 焊接学报, 2013, 34(4): 65 - 68
Zou Li, Yang Xinhua, Sun Yibo, et al. Fatigue life prediction of aluminum alloy welded joint based on variable precision rough set[J]. Transactions of the China Welding Institution, 2013, 34(4): 65 - 68
[17] 王春生, 邹丽, 杨鑫华. 基于邻域粗糙集的铝合金焊接接头疲劳寿命影响因素分析[J]. 吉林大学学报(工学版), 2017, 47(6): 1848 - 1853
Wang Chunsheng, Zou Li, Yang Xinhua. Analysis of fatigue life factors of aluminum alloy welded joints based on neighborhood rough set theory[J]. Journal of Jilin University(Engineering and Technology Edition), 2017, 47(6): 1848 - 1853
[18] 刘亚良, 孙屹博, 邹丽, 等. 基于信息熵的铝合金焊接接头疲劳寿命分析方法[J]. 焊接学报, 2018, 39(4): 67 - 72
Liu Yaliang, Sun Yibo, Zou Li, et al. Fatigue life analysis method of aluminum alloy welded joints based on information entropy[J]. Transactions of the China Welding Institution, 2018, 39(4): 67 - 72
[19] Shannon C E. The mathematical theory of communication[J]. Bell Labs Technical Journal, 1950, 3(9): 31 - 32.
[20] Quinlan J R. Induction of decision trees[J]. Machine Learning, 1986, 1(1): 81 - 106.
[21] Quinlan, J R. C4.5: Programs for machine learning[M]. San Mateo: Morgan Kaufmann Publishers Incorporated, 1993.
[22] Roman F, Nalewajski. Entropy descriptors of the chemical bond in information theory. I. Basic concepts and relations[J]. Molecular Physics, 2004, 102(6): 531 - 546.
[23] Ghayab H R A, Li Y, Siuly S, et al. Epileptic seizures detection in EEGs blending frequency domain with information gain technique[J]. Soft Computing, 2019, 23(1): 227 - 239.
