基于自适应神经网络的多模式小失效概率分析方法

doi:10.3901/JME.2022.23.039

摘要/Abstract

摘要： 针对水陆两栖飞机的襟翼运动机构小失效概率可靠性分析问题，首先通过开展气动载荷模拟分析得到注水灭火典型剖面的载荷历程曲线，并将其简化加载于襟翼运动机构模型中进行仿真分析。然后考虑摩擦系数、装配位置等因素的随机不确定性，建立了具有襟翼机构卡滞和运动精度不足两种失效模式的可靠性模型。为了提升分析效率，建立了一种基于自适应神经网络的可靠性分析方法。通过引入超球抽样使得样本点在整个标准正态空间内均匀分布，利用最优超球面将样本空间进行划分，大大缩减了样本空间。同时提出了一种新的学习函数来避免对不重要的区域进行探索，以找到最佳训练点进行模型更新。最后通过数值算例验证算法的计算效率和精度，进而实现了水陆两栖飞机襟翼运动机构可靠性的高效高精度分析。

关键词: 襟翼, 运动机构, 可靠性, 超球抽样, 神经网络

Abstract: For the small failure probability reliability assessment of the flap mechanism of amphibious aircraft, firstly, the load curve for the water injection and fire extinguishing profile is obtained by carrying out an aerodynamic simulation analysis, which is simplified and loaded into the model of flap motion mechanism. Then, the random uncertainty of friction coefficient and assembly position is considered, and the reliability models of two failure modes including flap mechanism jamming and insufficient movement accuracy are established. To improve the computational efficiency, a reliability analysis method based on the adaptive neural network is proposed. The hypersphere sampling is introduced to make the sample points evenly distributed in the whole standard normal space, and the sample space is divided by using the optimal hypersphere, which greatly reduces the sample space. Meanwhile, a new learning function is proposed to avoid exploring unimportant areas, then the best training point is found to update the surrogate model. Finally, a numerical example is given to verify the efficiency and accuracy of the algorithm, and then an efficient and high-precision reliability analysis of the flap motion mechanism of amphibious aircraft is realized.

Key words: flaps, motion mechanism, reliability, hypersphere sampling, neural network

中图分类号:

V224

王攀, 辛富康, 邓亚权, 张浩. 基于自适应神经网络的多模式小失效概率分析方法[J]. 机械工程学报, 2022, 58(23): 39-50.

WANG Pan, XIN Fukang, DENG Yaquan, ZHANG Hao. Adaptive Neural Network Based Approach for the Analysis of Small Failure Probability with Multiple Modes[J]. Journal of Mechanical Engineering, 2022, 58(23): 39-50.

参考文献

[1] 黄领才,雍明培. 水陆两栖飞机的关键技术和产业应用前景[J]. 航空学报,2019,40(1):18-34. HUANG Lingcai,YONG Mingpei. Key technologies and industrial application prospects of amphibian aircraft[J]. Acta Aeronautica et Astronautica Sinica,2019,40(1):18-34.
[2] 申蒸洋,陈孝明,黄领才. 大型水陆两栖飞机特殊任务模式对总体设计的挑战[J]. 航空学报,2019,40(1):200-209.SHEN Zhengyang,CHEN Xiaoming,HUANG Lingcai. Challenges for aircraft design due to special mission models of large-scale amphibious air-craft[J]. Acta Aeronautica et Astronautica Sinica,2019,40(1):200-209.
[3] 王妙香,孙卫平,秦何军. 水陆两栖飞机内吹式襟翼优化设计[J]. 航空学报,2016,37(1):300-309.WANG Miaoxiang,SUN Weiping,QIN Hejun. Optimization design of an internal blown flap used in large amphibian[J]. Acta Aeronautica et Astronautica Sinica,2016,37(1):300-309.
[4] 田文朋,夏峰,宋鹏飞,等. 水陆两栖飞机静力试验优化机翼变形的载荷配平[J]. 航空学报,2020,41(11):358-366.TIAN Wenpeng,XIA Feng,SONG Pengfei,et al. Load balancing for wing deformation optimization in amphibious aircraft static test[J]. Acta Aeronautica et Astronautica Sinica,2020,41(11):358-366.
[5] 李京虎,付国强,武斌.两段式仿生扑翼机构设计及仿真分析[J].机床与液压,2020,48(2):144-148.LI Jinghu,FU Guoqiang,WU Bin.Design and simulation analysis of two stage bionic flapping wing mechanism[J].Machine Tool & Hydraulics,2020,48(2):4-148.
[6] 孟敏,蒋献,贾天娇. 基于虚拟载荷校准试验的襟翼曲柄测载方法[J]. 航空学报,2020,41(2):243-249.MENG Min,JIANG Xian,JIA Tianjiao. A flap crank load measurement method based on virtual load calibration test[J]. Acta Aeronautica et Astronautica Sinica,2020,41(2):243-249.
[7] SUDRET B. Global sensitivity analysis using polynomial chaos expansions[J]. Reliability Engineering and System Safety,2008,93(7):964-979.
[8] SADOVSKÝ Z,SOARES C G. Artificial neural network model of the strength of thin rectangular plates with weld induced initial imperfections[J]. Reliability Engineering and System Safety,2011,96(6):713-717.
[9] BOURINET J M. Rare-event probability estimation with adaptive support vector regression surrogates[J]. Reliability Engineering and System Safety,2016,150:210-221.
[10] BICHON B J,JOHN M,SANKARAN M. Efficient surrogate models for reliability analysis of systems with multiple failure modes[J]. Reliability Engineering and System Safety,2011,96(10):1386-1395.
[11] ECHARD B,GAYTON N,LEMAIRE M. AK-MCS:An active learning reliability method combining Kriging and Monte Carlo Simulation[J]. Structural Safety,2011,33(2):145-154.
[12] BICHON B J,ELDRED M S,SWILER L P. Efficient global reliability analysis for nonlinear implicit performance functions[J]. AIAA Journal,2008,46(10):2459-2468.
[13] LÜ Z,LU Z,PAN W. A new learning function for Kriging and its applications to solve reliability problems in engineering-ScienceDirect[J]. Computers & Mathematics with Applications,2015,70(5):1182-1197.
[14] YANG X,LIU Y,ZHANG Y,et al. Probability and convex set hybrid reliability analysis based on active learning Kriging model[J]. Applied Mathematical Modeling,2015,39(14):3954-3971.
[15] SHI Y,LU Z,HE R,et al. A novel learning function based on Kriging for reliability analysis[J]. Reliability Engineering and System Safety,2020,198(2):106857.
[16] SUN Z,WANG J,LI R,et al. LIF:A new Kriging based learning function and its application to structural reliability analysis[J]. Reliability Engineering and System Safety,2017,157:152-165.
[17] ZHANG X,WANG L,SRENSEN J D. REIF:A novel active-learning function toward adaptive Kriging surrogate models for structural reliability analysis[J]. Reliability Engineering and System Safety,2019,185:440-454.
[18] DUBOURG V,SUDRET B,DEHEEGER F. Metamodel-based importance sampling for structural reliability analysis[J].Probabilistic Engineering Mechanics,2013,33:47-57.
[19] IVAN D,THI M H L,GORDON F,et al. Reliability analysis with metamodel line sampling[J]. Structural Safety,2016,60:1-15.
[20] HUANG X X,CHEN J Q,ZHU H P. Assessing small failure probabilities by AK-SS:An active learning method combining Kriging and subset simulation[J]. Structural Safety,2016,59:86-95.
[21] YUN W Y,LU Z Z,JIANG X,et al. AK-ARBIS:An improved AK-MCS based on the adaptive radial-based importance sampling for small failure probability[J]. Structural Safety,2020,82:101891
[22] FAURIAT W,GAYTON N. AK-SYS:An adaptation of the AK-MCS method for system reliability[J]. Reliability Engineering and System Safety,2014,123:137-144.
[23] YUN W,LU Z,ZHOU Y,et al. AK-SYSi:An improved adaptive Kriging model for system reliability analysis with multiple failure modes by a refined U learning function[J]. Structural and Multidisciplinary Optimization,2019,59(1):263-278.
[24] YANG X,LIU Y,MI C,et al. System reliability analysis through active learning Kriging model with truncated candidate region[J]. Reliability Engineering and System Safety,2017,169:235-241.
[25] JIANG C,QIU H,GAO L,et al. EEK-SYS:System reliability analysis through estimation error-guided adaptive Kriging approximation of multiple limit state surfaces[J]. Reliability Engineering and System Safety,2020,198:106906.
[26] PERRIN G. Active learning surrogate models for the conception of systems with multiple failure modes[J]. Reliability Engineering and System Safety,2016,149:130-136.
[27] WEI P,LIU F,TANG C. Reliability and reliability-based importance analysis of structural systems using multiple response Gaussian process model[J]. Reliability Engineering and System Safety,2018,175:183-195.
[28] XIAO N C,YUAN K,ZHOU C. Adaptive kriging-based efficient reliability method for structural systems with multiple failure modes and mixed variables[J]. Computer Methods in Applied Mechanics and Engineering,2019,359:112649.
[29] 胡茑庆,陈徽鹏,程哲,等. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报, 2019, 55(7):9-18.HU Niaoqing,CHEN Huipeng,CHENG Zhe,et al. Fault diagnosis method of planetary gearbox based on empirical mode decomposition and deep convolutional neural network[J]. Journal of Mechanical Engineering,2019,55(7):9-18.
[30] ECHARD B,GAYTON N,LEMAIRE M,et al. A combined importance sampling and Kriging reliability method for small failure probabilities with time-demanding numerical models[J]. Reliability Engineering and System Safety,2013,111:232-240.
[31] XIAO N C,ZUO M J,ZHOU C C. A new adaptive sequential sampling method to construct surrogate models for efficient reliability analysis[J]. Reliability Engineering and System Safety,2018,169:330-338.
[32] KLEIJNEN J,VAN B. Application-driven sequential design for simulation experiments:Kriging metamodelling[J]. Journal of the Operational Research Society,2004,55(8):876-883.
[33] KIM J, SONG J. Probability-adaptive Kriging in n-Ball (PAK-B-n) for reliability analysis[J]. Structural Safety,2020,85:101924.
[34] 陈放,李欣玲,佘霞,等. 平面轨迹机构时变可靠性分析的联合概率方法[J]. 机械工程学报,2017,53(15):119-124.CHEN Fang,LI Xinling,SHE Xia,et al. Joint probability method to time-dependent reliability for planar path mechanisms[J]. Journal of Mechanical Engineering,2017,53(15):119-124.
[35] 何正嘉,曹宏瑞,訾艳阳,等. 机械设备运行可靠性评估的发展与思考[J]. 机械工程学报,2014,50(2):171-186. HE Zhengjia,CAO Hongrui,ZI Yanyang,et al. Developments and thoughts on operational reliability assessment of mechanical equipment[J]. Journal of Mechanical Engineering,2014,50(2):171-186.
[36] 张义民. 机械可靠性设计的内涵与递进[J]. 机械工程学报,2010,46(14):167-188. ZHANG Yimin, Connotation and development of mechanical reliability-based design[J]. Journal of Mechanical Engineering,2010,46(14):167-188.
[37] 张政,周长聪,戴志豪,等. 基于重要性测度降维的液压管路稳健优化设计[J]. 航空学报,2018,39(8):281-289.ZHANG Zheng,ZHOU Changcong,DAI Zhihao,et al. Robust optimization of hydraulic piping system based on importance measure dimension-reduction[J]. Acta Aeronautica et Astronautica Sinica,2018,39(8):281-289.