岸桥金属材料与焊接结构寿命预测

陈琛; 潘文超

doi:10.13433/j.cnki.1003-8728.20180062

岸桥金属材料与焊接结构寿命预测

doi: 10.13433/j.cnki.1003-8728.20180062

陈琛,
潘文超

1.
上海海事大学物流工程学院, 上海 201306

基金项目:

上海科委科技创新行动计划项目（17DZ1101401）资助

详细信息

作者简介:
陈琛(1993-),硕士研究生,研究方向为机电控制技术,m13818289275@163.com

计量
- 文章访问数: 280
- HTML全文浏览量: 27
- PDF下载量: 122
- 被引次数: 0
出版历程
- 收稿日期: 2017-10-24
- 刊出日期: 2018-10-05

Life Prediction of Metal Material and Welded Structure of Quayside Container Crane

1.
Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China

摘要

摘要: 基于不同损伤理论，利用人工智能技术来预测岸桥金属结构疲劳寿命的智能算法已经成为岸桥领域新的热点。为提高寿命预测精度，分别利用神经网络算法和支持向量机算法进行仿真实验，估算在两级载荷下的疲劳寿命。根据前人给出的实验数据，分别运用基于遗传算法优化的神经网络和基于粒子群优化的支持向量机算法对正火35#钢和调质45#钢进行疲劳仿真，描述应力与累积损伤之间的非线性关系，以及应力加载顺序对疲劳寿命的影响；并对海洋平台中最为常见的焊接管接头结构进行疲劳参数的预测，以验证经过优化的智能算法的实用性。同时与优化过的BP神经网络和支持向量机预测结果进行比较，表明优化方法对于提高智能算法的预测精度有较大作用。
- 岸桥 /
- 非线性 /
- 智能算法优化 /
- 疲劳预测
Abstract: Based on the different damage theory, the intelligent algorithm, which can predict the fatigue life of crane metal structure via artificial intelligence technology has become a new hot point in the crane field. In practice, some intelligent algorithms are often used to solve some complex nonlinear problems. Therefore, the neural network algorithm and the support vector machine algorithm are used to simulate the experiment, and the fatigue life under the two stage load is estimated, respectively. According to the experimental data given by predecessors, the fatigue simulation of normalizing No. 35 steel and the quenched and tempered No. 45 steel is carried out by using the neural network and genetic algorithm and the support vector machine algorithm based on the particle swarm optimization, respectively. Besides, the nonlinear relationship between the stress and cumulative damage and the influence of stress loading sequence on the fatigue life are described. The fatigue parameters of the most common welded pipe joints in offshore platforms are predicted to verify the practicability of the optimized intelligent algorithm. At the same time, the results are compared with the optimized BP neural network and support vector machine to verify. The optimization method has the great effect on the improvement of the prediction precision of the intelligent algorithm.
- quayside container crane /
- nonlinear /
- intelligent optimization /
- fatigue prediction

HTML全文

参考文献(15)

[1]	李有根,吴晓玲.起重机械钢结构剩余寿命估算中常用理论及应用[J].中国新技术新产品,2013,(1):112-113 Li Y G, Wu X L. Common theory and application of life estimation for steel structure of hoisting machinery[J]. China New Technologies and Products, 2013,(1):112-113(in Chinese)
[2]	张小丽,陈雪峰,李兵,等.机械重大装备寿命预测综述[J].机械工程学报,2011,47(11):100-116 Zhang X L, Chen X F, Li B, et al. Review of life prediction for mechanical major equipments[J]. Journal of Mechanical Engineering, 2011,47(11):100-116(in Chinese)
[3]	黄海.港口起重机金属结构安全性评价方法研究[D].武汉:武汉理工大学位,2008 Huang H. Research on security evaluation method of port crane metal structure[D]. Wuhan:Wuhan University of Technology, 2008(in Chinese)
[4]	Tam V W Y, Fung I W H. Tower crane safety in the construction industry:a Hong Kong study[J]. Safety Science, 2011,49(2):208-215
[5]	Swuste P. A ‘normal accident’ with a tower crane? an accident analysis conducted by the Dutch Safety Board[J]. Safety Science, 2013,57:276-282
[6]	康健,刘新福,肖文雷.工程机械结构疲劳寿命预测的相对应力谱方法[C]//第一届国际机械工程学术会议论文集.天津:河北工业大学机械学院,2000 Kang J, Liu X F, Xiao W L. Relative stress spectrum method for fatigue life prediction of construction machinery[C]//The First International Conference on Mechanical Engineering. Tianjin:Hebei University of Technology, 2000(in Chinese)
[7]	张国庆,王成焘,徐滨士.几种疲劳寿命预测方法的探讨及评价[J].机械强度,2011,33(3):469-474 Zhang G Q, Wang C T, Xu B S. On assessment of several fatigue life prediction methods[J]. Journal of Mechanical Strength, 2011,33(3):469-474(in Chinese)
[8]	Seed G M, Murphy G S. The applicability of neural networks in modelling the growth of short fatigue cracks[J]. Fatigue & Fracture of Engineering Materials & Structures, 1998,21(2):183-190
[9]	Etube L S. Fatigue and fracture mechanics of offshore structures[M]. London:Professional Engineering Publishing, 2001
[10]	Kudva J N, Munir N, Tan P W. Damage detection in smart structures using neural networks and finite-element analyses[J]. Smart Materials and Structure, 1992,1(2):108-112
[11]	Caglayan O, Ozakgul K, Tezer O, et al. Fatigue life prediction of existing crane runway girders[J]. Journal of Constructional Steel Research, 2010,66(10):1164-1173
[12]	任如飞,赵明,段丽慧.基于神经网络的涡轮盘榫接触部位疲劳寿命可靠性仿真[J].机械科学与技术,2007,26(5):585-588 Ren R F, Zhao M, Duan L H. Reliability simulation of fatigue life of the contact region of a turbine using neural network[J]. Mechanical Science and Technology for Aerospace Engineering, 2007,26(5):585-588(in Chinese)
[13]	刘竞.现役桥式起重机金属结构安全性分析评估方法[D].上海:上海交通大学,2011 Liu J. Safety assessment for metallic structure of in-service gantry crane[D]. Shanghai:Shanghai Jiaotong University, 2011(in Chinese)
[14]	范小宁,徐格宁,王爱红.基于人工神经网络获取起重机当量载荷谱的疲劳剩余寿命估算方法[J].机械工程学报,2011,47(20):69-74 Fan X N, Xu G N, Wang A H. Evaluation method of remaining fatigue life for crane based on the acquisition of the equivalent load spectrum by the artificial neural network[J]. Journal of Mechanical Engineering, 2011,47(20):69-74(in Chinese)
[15]	史朝阳,王爱红,高有山,等.基于MCMC的桥式起重机疲劳寿命可靠性灵敏度分析[J].中国安全科学学报,2014,24(3):47-52 Shi Z Y, Wang A H, Gao Y S, et al. Bridge crane fatigue life reliability sensitivity analysis based on MCMC method[J]. China Safety Science Journal, 2014,24(3):47-52(in Chinese)