SS-MASVM: an advanced technique for assessing failure probability of high-dimensional complex systems using the multi-class adaptive support vector machine. (English) Zbl 1539.62307
Summary: The integrity of structures in contemporary engineering practices is heavily influenced by inherent uncertainties, which necessitates the development of reliable structural reliability analysis methods for uncertainty quantification and probabilistic analysis. This paper investigates the integration of surrogate models and subset simulation (SS) to accurately compute the failure probabilities of high-dimensional complex systems. Focus is placed on enhancing the computational efficiency and accuracy through using the multi-class adaptive support vector machine (MASVM). The proposed SS-MASVM method incorporates more efficient learning functions, integrates K-means clustering, and employs SS technology for precise estimation of failure probabilities of high-dimensional complex systems. Numerical and engineering structural examples validate the effectiveness of the proposed method and highlight its potential in practical reliability analysis, and the results disclose that the SS-MASVM is efficient and accurate for assessing the complex system reliability.
MSC:
| 62N05 | Reliability and life testing |
| 68T05 | Learning and adaptive systems in artificial intelligence |
| 90B25 | Reliability, availability, maintenance, inspection in operations research |
Keywords:
structural reliability analysis; failure probability; surrogate model; subset simulation; support vector machineReferences:
| [1] | Achintya, Haldar; Sankaran, Mahadevan, Probability, Reliability and Statistical Methods in Engineering Design (2000), John Wiley |
| [2] | Mooney Christopher, Z., Monte Carlo simulation. Sage (1997) · Zbl 0914.65148 |
| [3] | Meng, Zeng; Pang, Yongsheng; Wu, Zhigen; Ren, Shanhong; Yildiz, Ali Riza, A novel maximum volume sampling model for reliability analysis. Appl Math Model, 797-810 (2022) · Zbl 1525.90174 |
| [4] | Luo, Changqi; Keshtegar, Behrooz; Zhu, Shunpeng; Taylan, Osman; Niu, Xiaopeng, Hybrid enhanced Monte Carlo simulation coupled with advanced machine learning approach for accurate and efficient structural reliability analysis. Comput. Methods Appl. Mech. Eng. (2022) · Zbl 1507.65013 |
| [5] | Meng, Zeng; Li, Gang; Yang, Dixiong, Lichao Zhan. A new directional stability transformation method of chaos control for first order reliability analysis. Struct. Multidiscip. Optim., 601-612 (2017) |
| [6] | Yang, Dixiong; Li, Gang; Cheng, Gengdong, Convergence analysis of first order reliability method using chaos theory. Comput. Struct., 8-9, 563-571 (2006) |
| [7] | Armen, Der Kiureghian; Lin, Hongzong, Shyhjiann Hwang. Second-order reliability approximations. J. Eng. Mech., 8, 1208-1225 (1987) |
| [8] | Hurtado, Jorge E.; Alvarez, Diego A., An optimization method for learning statistical classifiers in structural reliability. Probab. Eng. Mech., 1, 26-34 (2010) |
| [9] | Afshari, Sajad Saraygord; Enayatollahi, Fatemeh; Xu, Xiangyang; Liang, Xihui, Machine learning-based methods in structural reliability analysis: a review. Reliab. Eng. Syst. Saf. (2022) |
| [10] | Meng, Zeng; Li, Changquan; Pang, Yongsheng; Li, Gang; He, Wanxin, New bubble sampling method for reliability analysis. Struct. Multidiscip. Optim., 8, 1-15 (2023) |
| [11] | Tee, Kong Fah; Khan, Lutfor Rahman; Li, Hongshuang, Application of subset simulation in reliability estimation of underground pipelines. Reliab. Eng. Syst. Saf., 125-131 (2014) |
| [12] | Li, Hongshuang; Ma, Yuanzhuo; Cao, Zijun, A generalized subset simulation approach for estimating small failure probabilities of multiple stochastic responses. Comput. Struct., 239-251 (2015) |
| [13] | Li, Hongshuang; Cao, Zijun, Matlab codes of subset simulation for reliability analysis and structural optimization. Struct. Multidiscip. Optim., 391-410 (2016) |
| [14] | Lee, Ikjin; Noh, Yoojeong; Yoo, David, A novel second-order reliability method (SORM) using noncentral or generalized chi-squared distributions. J. Mech. Des., 10 (2012) |
| [15] | Du, Xiaoping; Hu, Zhen, First Order Reliability Method With Truncated Random Variables. J. Mech. Des., 9 (2012) |
| [16] | Teixeira, Rui; Nogal, Maria; O’Connor, Alan, Adaptive approaches in metamodel-based reliability analysis: a review. Struct. Saf. (2021) |
| [17] | Lee, Ikjin; Lee, Ungki; Ramu, Palaniappan; Yadav, Deepanshu; Bayrak, Gamze; Acar, Erdem, Small failure probability: principles, progress and perspectives. Struct. Multidiscip. Optim., 11, 326 (2022) |
| [18] | Yadav, Vaibhav; Rahman, Sharif, Adaptive-sparse polynomial dimensional decomposition methods for high-dimensional stochastic computing. Comput. Methods Appl. Mech. Eng., 56-83 (2014) · Zbl 1296.62115 |
| [19] | Weng, Lili; Yang, Jiashu; Chen, Jianbing, Michael Beer. Structural design optimization under dynamic reliability constraints based on probability density evolution method and quantum-inspired optimization algorithm. Probab. Eng. Mech. (2023) |
| [20] | Chen, Hanshu; Chen, Guohai; Meng, Zeng; Zhang, Yahui, Dixiong Yang. Stochastic dynamic analysis of nonlinear MDOF systems under combined Gaussian and Poisson noise excitation based on DPIM. Mech. Syst. Signal Process (2022) |
| [21] | Faravelli, Lucia, Response-surface approach for reliability analysis. J. Eng. Mech., 12, 2763-2781 (1989) |
| [22] | Kim, Chwail; Wang, Semyung; Choi, Kyung K., Efficient response surface modeling by using moving least-squares method and sensitivity. AIAA J., 11, 2404-2411 (2005) |
| [23] | Taflanidis, Alexandros A.; Cheung, Sai-Hung, Stochastic sampling using moving least squares response surface approximations. Probab. Eng. Mech., 216-224 (2012) |
| [24] | Gaspar, Bruno; Teixeira, Angelo P.; Guedes Soares, C., Assessment of the efficiency of Kriging surrogate models for structural reliability analysis. Probab. Eng. Mech., 24-34 (2014) |
| [25] | Kaymaz, Irfan, Application of kriging method to structural reliability problems. Struct. Saf., 2, 133-151 (2005) |
| [26] | Echard, Benjamin; Gayton, Nicolas; Lemaire, Maurice, AK-MCS: an active learning reliability method combining Kriging and Monte Carlo simulation. Struct. Saf., 2, 145-154 (2011) |
| [27] | Meng, Zeng; Zhang, Zhuohui; Zhang, Dequan; Yang, Dixiong, An active learning method combining Kriging and accelerated chaotic single loop approach (AK-ACSLA) for reliability-based design optimization. Comput. Methods Appl. Mech. Eng. (2019) · Zbl 1442.74156 |
| [28] | Wang, Dapeng; Qiu, Haobo; Gao, Liang; Xu, Danyang; Jiang, Chen, Time-dependent system reliability analysis using adaptive single-loop Kriging with probability of rejecting classification. Struct. Multidiscip. Optim., 8, 186 (2023) |
| [29] | Papadrakakis, Manolis; Papadopoulos, Vissarion; Lagaros, Nikos D., Structural reliability analyis of elastic-plastic structures using neural networks and Monte Carlo simulation. Comput. Methods Appl. Mech. Eng., 1-2, 145-163 (1996) · Zbl 0893.73079 |
| [30] | Gomes, Herbert Martins; Awruch, Armando Miguel, Comparison of response surface and neural network with other methods for structural reliability analysis. Struct. Saf., 1, 49-67 (2004) |
| [31] | Papadrakakis, Manolis; Lagaros, Nikos D., Reliability-based structural optimization using neural networks and Monte Carlo simulation. Comput. Methods Appl. Mech. Eng., 32, 3491-3507 (2002) · Zbl 1101.74377 |
| [32] | Roy, Atin; Chakraborty, Subrata, Support vector machine in structural reliability analysis: a review. Reliab. Eng. Syst. Saf. (2023) |
| [33] | Lagaros, Nikos D.; Tsompanakis, Yiannis; Psarropoulos, Prodromos N.; Georgopoulos, Evaggelos C., Computationally efficient seismic fragility analysis of geostructures. Comput. Struct., 19-20, 1195-1203 (2009) · Zbl 1163.86311 |
| [34] | Rocco, Claudio M.; Moreno, José Alı́, Fast Monte Carlo reliability evaluation using support vector machine. Reliab. Eng. Syst. Saf., 3, 237-243 (2002) |
| [35] | Guo, Zhiwei; Bai, Guangchen, Application of least squares support vector machine for regression to reliability analysis. Chin. J. Aeronaut., 2, 160-166 (2009) |
| [36] | Zafar, Tayyab; Zhang, Yanwei; Wang, Zhonglai, An efficient Kriging based method for time-dependent reliability based robust design optimization via evolutionary algorithm. Comput. Methods Appl. Mech. Eng. (2020) · Zbl 1506.74312 |
| [37] | Wang, Zhonglai; Zhao, Dongyu; Guan, Yi, Flexible-constrained time-variant hybrid reliability-based design optimization. Struct. Multidiscip. Optim., 4, 89 (2023) |
| [38] | Couellan, Nicolas; Jan, Sophie; Jorquera, Tom; Georgé, Jean-Pierre, Self-adaptive support vector machine: a multi-agent optimization perspective. Expert Syst Appl, 9, 4284-4298 (2015) |
| [39] | Du, Shichang; Huang, Delin; Wang, Hui, An adaptive support vector machine-based workpiece surface classification system using high-definition metrology. IEEE Trans Instrum Meas, 10, 2590-2604 (2015) |
| [40] | Li, Hongshuang; Lv, Zhenzhou; Yue, Zhufeng, Support vector machine for structural reliability analysis. J. Appl. Math. Mech. (Engl. Transl.), 10, 1295-1303 (2006) · Zbl 1167.62469 |
| [41] | Hurtado, Jorge E., Filtered importance sampling with support vector margin: a powerful method for structural reliability analysis. Struct. Saf., 1, 2-15 (2007) |
| [42] | Chang, Chihchung; Lin, Chihjen, LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST), 3, 1-27 (2011) |
| [43] | Bourinet, J. M., Rare-event probability estimation with adaptive support vector regression surrogates. Reliab. Eng. Syst. Saf., 210-221 (2016) |
| [44] | Cheng, Kai; Lu, Zhenzhou, Adaptive Bayesian support vector regression model for structural reliability analysis. Reliab. Eng. Syst. Saf. (2021) |
| [45] | Song, Hyeongjin; Choi, K. K.; Lee, Ikjin; Zhao, Liang; Lamb, David, Adaptive virtual support vector machine for reliability analysis of high-dimensional problems. Struct. Multidiscipl. Optim., 479-491 (2013) · Zbl 1274.62429 |
| [46] | Steiner, Maria; Bourinet, J. M.; Lahmer, Tom, An adaptive sampling method for global sensitivity analysis based on least-squares support vector regression. Reliab. Eng. Syst. Saf., 323-340 (2019) |
| [47] | Wang, Yanzhong; Xie, Bin; Shiyuan, E., Adaptive relevance vector machine combined with Markov-chain-based importance sampling for reliability analysis. Reliab. Eng. Syst. Saf. (2022) |
| [48] | Roy, Atin; Chakraborty, Subrata, Reliability analysis of structures by a three-stage sequential sampling based adaptive support vector regression model. Reliab. Eng. Syst. Saf. (2022) |
| [49] | Basudhar, Anirban; Missoum, Samy, An improved adaptive sampling scheme for the construction of explicit boundaries. Struct. Multidiscip. Optim., 517-529 (2010) |
| [50] | Tong, Simon; Koller, Daphne, Support vector machine active learning with applications to text classification. J. Mach. Learn Res., Nov, 45-66 (2001) · Zbl 1009.68131 |
| [51] | Pan, Qiujing; Dias, Daniel, An efficient reliability method combining adaptive support vector machine and Monte Carlo simulation. Struct. Saf., 85-95 (2017) |
| [52] | Shi, Zhaoyin; Lu, Zhenzhou; Zhang, Xiaobo; Li, Luyi, A novel adaptive support vector machine method for reliability analysis. Proc Inst Mech Eng O J Risk Reliab, 5, 896-908 (2021) |
| [53] | Au, Siukui; Beck, James L., Estimation of small failure probabilities in high dimensions by subset simulation. Probab. Eng. Mech., 4, 263-277 (2001) |
| [54] | Zhao, Yinghao; Wang, Zeyu, Subset simulation with adaptable intermediate failure probability for robust reliability analysis: an unsupervised learning-based approach. Struct. Multidiscip. Optim., 6, 172 (2022) |
| [55] | Cortes, Corinna; Vapnik, Vladimir, Support-vector networks. Mach Learn, 273-297 (1995) · Zbl 0831.68098 |
| [56] | Vapnik, Vladimir N., An overview of statistical learning theory. IEEE Trans. Neural Networks, 5, 988-999 (1999) |
| [57] | Bourinet, Jean-Marc; Deheeger, Francois; Lemaire, Maurice, Assessing small failure probabilities by combined subset simulation and support vector machines. Struct. Saf., 6, 343-353 (2011) |
| [58] | Boser, Bernhard E.; Guyon, Isabelle M.; Vapnik, Vladimir N., A training algorithm for optimal margin classifiers |
| [59] | Franc, Vojtech; Hlavác, Václav, Multi-class support vector machine, 236-239 |
| [60] | Gunn, Steve R., Support vector machines for classification and regression. ISIS Tech. Rep., 1, 5-16 (1998) |
| [61] | Vapnik, Vladimir, The Nature of Statistical Learning Theory (1999), Springer Science & Business Media · Zbl 0833.62008 |
| [62] | Fan, Rongen; Chang, Kaiwei; Hsieh, Chojui; Wang, Xiangrui; Lin, Chihjen, LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res., 1871-1874 (2008) · Zbl 1225.68175 |
| [63] | Schueremans, Luc, Dionys Van Gemert. Benefit of splines and neural networks in simulation based structural reliability analysis. Struct. Saf., 3, 246-261 (2005) |
| [64] | Elegbede, Charles, Structural reliability assessment based on particles swarm optimization. Struct. Saf., 2, 171-186 (2005) |
| [65] | Gong, Jinxin; Yi, Ping; Zhao, Na, Non-gradient-based algorithm for structural reliability analysis. J. Eng. Mech., 6 (2014) |
| [66] | Ghalehnovi, Mansour; Rashki, Mohsen, Ala Ameryan. First order control variates algorithm for reliability analysis of engineering structures. Appl. Math. Model, 829-847 (2020) · Zbl 1443.74257 |
| [67] | Rackwitz, Rüdiger, Reliability analysis—A review and some perspectives. Struct. Saf., 4, 365-395 (2001) |
| [68] | Liu, Peiling; Armen Der, Kiureghian, Optimization algorithms for structural reliability. Struct. Saf., 3, 161-177 (1991) |
| [69] | Mahadevan, Sankaran; Shi, Pan, Multiple linearization method for nonlinear reliability analysis. J. Eng. Mech., 11, 1165-1173 (2001) |
| [70] | Hao, Peng; Wang, Yutian; Liu, Chen; Wang, Bo; Tian, Kuo; Li, Gang; Wang, Qun; Liangliang, Jiang, Hierarchical nondeterministic optimization of curvilinearly stiffened panel with multicutouts. AIAA J., 10, 4180-4194 (2018) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
