Structural reliability analysis using enhanced cuckoo search algorithm and artificial neural network

doi:10.21629/JSEE.2018.06.19

Journal of Systems Engineering and Electronics ›› 2018, Vol. 29 ›› Issue (6): 1317-1326.doi: 10.21629/JSEE.2018.06.19

• Reliability • Previous Articles Next Articles

Structural reliability analysis using enhanced cuckoo search algorithm and artificial neural network

Qiang QIN^1,*(), Yunwen FENG²(), Feng LI^1,³()

¹ Aerospace Science and Industry Corporation Defense Technology Research and Test Center, Beijing 100854, China
² School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, China
³ CASIC Space Engineering Development Co., Ltd, Beijing 100854, China

Received:2018-01-19 Online:2018-12-25 Published:2018-12-26
Contact: Qiang QIN E-mail:johnnystyle@126.com;fengyunwen@nwpu.edu.cn;15210164875@163.com
About author:QIN Qiang was born in 1986. He received his B.S. degree in safety engineering, M.S. degree and Ph.D. degree in aircraft design from Northwestern Polytechnical University in 2009, 2012 and 2016, respectively. He is now an engineer in Aerospace Science and Industry Corporation Defense Technology Research and Test Center. His research interests are meta-heuristic algorithms and structural reliability. He has published four research papers about the application of the cuckoo search algorithm. E-mail: johnnystyle@126.com|FENG Yunwen was born in 1968. She received her Ph.D. degree in School of Aeronautics from Northwestern Polytechnical University, Xi'an, China, in 2000. Now she is a professor of this university. Her current research interests include structural and mechanical reliability. E-mail: fengyunwen@nwpu.edu.cn|LI Feng was born in 1991. He received his B.S. degree and M.S. degree in solid mechanics from Northwestern Polytechnical University in 2014 and 2017, respectively. He is now an engineer in CASIC Space Engineering Development Co., Ltd. His research interest is structural optimization analysis. E-mail: 15210164875@163.com
Supported by:
the National Natural Science Foundation of China(51875465);This work was supported by the National Natural Science Foundation of China (51875465)

Abstract

Abstract:

The present study proposed an enhanced cuckoo search (ECS) algorithm combined with artificial neural network (ANN) as the surrogate model to solve structural reliability problems. In order to enhance the accuracy and convergence rate of the original cuckoo search (CS) algorithm, the main parameters namely, abandon probability of worst nests p_aand search step size α₀ are dynamically adjusted via nonlinear control equations. In addition, a global-best guided equation incorporating the information of global best nest is introduced to the ECS to enhance its exploitation. Then, the proposed ECS is linked to the well-trained ANN model for structural reliability analysis. The computational capability of the proposed algorithm is validated using five typical structural reliability problems and an engineering application. The comparison results show the efficiency and accuracy of the proposed algorithm.

Key words: structural reliability, enhanced cuckoo search (ECS), artificial neural network (ANN), cuckoo search (CS) algorithm

Qiang QIN, Yunwen FENG, Feng LI. Structural reliability analysis using enhanced cuckoo search algorithm and artificial neural network[J]. Journal of Systems Engineering and Electronics, 2018, 29(6): 1317-1326.

Figures/Tables 14

Fig 1

Fig 2

Table 1

Fig 3

Table 2

Fig 4

Table 3

Fig 5

Table 4

Fig 6

Table 5

Fig 7

Table 6

Table 7

References 35

1	GUIMARÃES H, MATOS J C, HENRIQUES A A. An innovative adaptive sparse response surface method for structural reliability analysis. Structural Safety, 2018, 73, 12- 28. doi: 10.1016/j.strusafe.2018.02.001
2	GROOTEMAN F. An adaptive directional importance sampling method for structural reliability. Probabilistic Engineering Mechanics, 2011, 26 (2): 134- 141. doi: 10.1016/j.probengmech.2010.11.002
3	HADIDI A, AZAR B F, RAFIEE A. Efficient response surface method for high-dimensional structural reliability analysis. Structural Safety, 2017, 68, 15- 27. doi: 10.1016/j.strusafe.2017.03.006
4	ELEGBEDE C. Structural reliability assessment based on particles swarm optimization. Structural Safety, 2005, 27 (2): 171- 186.
5	YI P, WEI K T, KONG X J. Cumulative PSO-Kriging model for slope reliability analysis. Probabilistic Engineering Mechanics, 2015, 39, 39- 45. doi: 10.1016/j.probengmech.2014.12.001
6	LUO X, LI X, ZHOU J, et al. A Kriging-based hybrid optimization algorithm for slope reliability analysis. Structural Safety, 2012, 34 (1): 401- 406.
7	CHENG J, LI Q. Reliability analysis of structures using artificial neural network based genetic algorithms. Computer Methods in Applied Mechanics and Engineering, 2008, 197, 3742- 3750. doi: 10.1016/j.cma.2008.02.026
8	CHENG J. An artificial neural network based genetic algorithm for estimating the reliability of long span suspension bridges. Finite Elements in Analysis and Design, 2010, 46, 658- 667. doi: 10.1016/j.finel.2010.03.005
9	DENG J, GU D, LI X, et al. Structural reliability analysis for implicit performance functions using artificial neural network. Structural Safety, 2005, 27 (1): 25- 48.
10	ELHEWY A H, MESBAHI E, PU Y. Reliability analysis of structure using neural network method. Probabilistic Engineering Mechanics, 2006, 21 (1): 44- 53. doi: 10.1016/j.probengmech.2005.07.002
11	KROETZ H M, TESSARI R K, BECK A T. Performance of global metamodeling techniques in solution of structural reliability problems. Advances in Engineering Software, 2017, 114, 394- 404. doi: 10.1016/j.advengsoft.2017.08.001
12	ALBANESI A, ROMAN N, BRE F, et al. A metamodel-based optimization approach to reduce the weight of composite laminated wind turbine blades. Composite Structures, 2018, 194, 345- 356. doi: 10.1016/j.compstruct.2018.04.015
13	XIAO N C, ZUO M J, ZHOU C N. A new adaptive sequential sampling method to construct surrogate models for efficient reliability analysis. Reliability Engineering and System Safety, 2018, 169, 330- 338. doi: 10.1016/j.ress.2017.09.008
14	YANG X S, DEB S. Cuckoo search via Lévy flights. Proc. of the World Congress on Nature & Biologically Inspired Computing, 2009: 210-214.
15	YANG X S, DEB S. Engineering optimisation by cuckoo search. International Journal of Mathematical Modeling and Numerical Optimisation, 2010, 1 (4): 330- 343. doi: 10.1504/IJMMNO.2010.035430
16	KAVEH A, BAKHSHPOORI T. An efficient multi-objective cuckoo search algorithm for design optimization. Advances in Computational Design, 2016, 1 (1): 87- 103.
17	ABDEL-BASET M, HEZAM I. Cuckoo search and genetic algorithm hybrid schemes for optimization problems. Applied Mathematics, 2016, 10 (3): 1185- 1192.
18	YANG B, MIAO J, FAN Z C, et al. Modified cuckoo search algorithm for the optimal placement of actuators problem. Applied Soft Computing, 2018, 67, 48- 60. doi: 10.1016/j.asoc.2018.03.004
19	RAKHSHANI H, RAHATI A. Snap-drift cuckoo search: a novel cuckoo search optimization algorithm. Applied Soft Computing, 2017, 52, 771- 794. doi: 10.1016/j.asoc.2016.09.048
20	DHABALA S, VENKATESWARANB P. An efficient gbestguided Cuckoo Search algorithm for higher order two channel filter bank design. Swarm and Evolutionary Computation, 2017, 33, 68- 84. doi: 10.1016/j.swevo.2016.10.003
21	VALIAN E, TAVAKOLI S, MOHANNA S, et al. Improved cuckoo search for reliability optimization problems. Computers & Industrial Engineering, 2013, 64 (1): 459- 468.
22	KANAGARAJ G, PONNAMBALAM S, JAWAHAR N. A hybrid cuckoo search andgenetic algorithm for reliabilityredundancy allocation problems. Computers & Industrial Engineering, 2013, 66 (4): 1115- 1124.
23	WALTON S, HASSAN O, MORGAN K, et al. Modified cuckoo search: a new gradient free optimisation algorithm. Chaos Solitons & Fractals, 2011, 44 (9): 710- 718.
24	MOHAMMAD S, AHAMAD T K, MOHAMMED A A. A survey on applications and variants of the cuckoo search algorithm. Applied Soft Computing, 2017, 61, 1041- 1059. doi: 10.1016/j.asoc.2017.02.034
25	HARUNA C, TUTUT H, IZTOK J F, et al. Bio-inspired computation: recent development on the modifications of the cuckoo search algorithm. Applied Soft Computing, 2017, 61, 149- 173. doi: 10.1016/j.asoc.2017.07.053
26	ZHU G P, KWONG S. Gbest-guided artificial bee colony algorithm for numerical function optimization. Applied Mathematics and Computation, 2010, 217, 3166- 3173. doi: 10.1016/j.amc.2010.08.049
27	OMRAN M G H, MAHDAVI M. Global-best harmony search. Applied Mathematics & Computation, 2008, 198 (2): 643- 656.
28	RAJABIOUN R. Cuckoo optimization algorithm. Applied Soft Computing Journal, 2011, 11 (8): 5508- 5518. doi: 10.1016/j.asoc.2011.05.008
29	CHOJACZYK A A, TEIXEIRA A P, NEVES L C. Review and application of artificial neural networks models in reliability analysis of steel structures. Structural Safety, 2015, 52, 78- 89. doi: 10.1016/j.strusafe.2014.09.002
30	MIRJALILI S, LEWIS A. The whale optimization algorithm. Advances in Engineering Software, 2016, 95, 51- 67. doi: 10.1016/j.advengsoft.2016.01.008
31	MIRJALILI S. SCA: a sine cosine algorithm for solving optimization problems. Knowledge-Based Systems, 2016, 96, 120- 133. doi: 10.1016/j.knosys.2015.12.022
32	MIRJALILI S, GANDOMI A H, MIRJALILI S Z, et al. Salp swarm algorithm: a bio-inspired optimizer for engineering design problems. Advances in Engineering Software, 2017, 114, 163- 191. doi: 10.1016/j.advengsoft.2017.07.002
33	HASOFER A M, LIND N C. Exact and invariant secondmoment code format. Journal of the Engineering Mechanics Division, 1974, 100 (1): 111- 121.
34	GARG H. A hybrid PSO-GA algorithm for constrained optimization problems. Applied Mathematics & Computation, 2016, 274 (11): 292- 305.
35	TAN X H, BI W H, HOU X L, et al. Reliability analysis using radial basis function networks and support vector machines. Computers & Geotechnics, 2011, 38 (2): 178- 186.

Algorithm	β				P_f ×10^?4	CUP time/s	error1/%	error2/%
Algorithm	Best	Worst	Mean	Standard	P_f ×10^?4	CUP time/s	error1/%	error2/%
GA	3.360 53	3.610 80	3.407 20	0.0784 65	3.282	2.091	0.813	8.833
PSO	3.360 59	3.739 12	3.476 82	0.1106 76	2.540	1.319	2.864	29.44
CS	3.360 53	3.364 06	3.360 80	7.63E-03	3.886	1.485	0.568	8.056
WOA	3.360 57	3.766 47	3.442 04	0.132 409	2.887	0.899	1.835	19.81
SCA	3.368 82	3.812 99	3.636 64	0.146 909	1.381	0.922	7.593	61.64
SSA	3.360 53	3.705 60	3.471 64	0.126 271	2.586	0.924	2.711	28.17
ECS	3.360 53	3.361 01	3.360 91	8.81E-05	3.884	1.525	0.565	7.889

Algorithm	β				P_f	CUP time/s	error1/%	error2/%
Algorithm	Best	Worst	Mean	Standard	P_f	CUP time/s	error1/%	error2/%
GA	3.123 69	4.633 08	3.597 65	0.324 72	1.61×10^?4	2.242	19.92	88.07
PSO	3.031 80	4.687 98	3.574 49	0.345 75	1.75×10^?4	1.328	19.15	87.04
CS	3.009 72	3.092 25	3.034 06	0.022 53	1.21×10^?3	1.799	1.135	10.67
WOA	3.028 44	5.836 12	4.130 06	0.537 30	1.81×10^?5	1.266	37.67	98.66
SCA	3.671 27	6.044 14	0.557 48	4.970 71	3.34×10^?7	1.301	65.69	99.98
SSA	3.246 75	5.802 25	4.253 09	0.675 74	1.05×10^?5	1.336	41.77	99.22
ECS	3.008 76	3.018 05	3.009 75	0.002 52	1.31×10^?3	1.821	0.325	3.185

Algorithm	β				P_f×10^?3	CUP time/s	error1/%	error2/%
Algorithm	Best	Worst	Mean	Standard	P_f×10^?3	CUP time/s	error1/%	error2/%
GA	2.712 98	3.335 09	2.853 26	0.163 97	2.163	1.389	6.227	40.23
PSO	2.710 13	3.141 63	2.832 99	0.121 81	2.305	0.621	5.472	36.31
CS	2.712 90	3.131 47	2.851 21	0.117 81	2.177	0.682	6.151	39.84
WOA	2.717 67	3.427 56	3.006 10	0.161 52	1.323	0.215	11.91	63.45
SCA	3.116 08	32 767.2	1 645.66	5 928.02	NA	0.218	NA	NA
SSA	2.709 94	3.082 30	2.905 09	0.127 47	1.835	0.251	8.157	49.29
ECS	2.710 27	3.059 65	2.832 82	0.099 51	2.307	0.794	5.466	36.27

Algorithm	β				P_f×10^?3	CUP time/s	error1/%	error2/%
Algorithm	Best	Worst	Mean	Standard	P_f×10^?3	CUP time/s	error1/%	error2/%
GA	2.023 80	4.031 46	2.47012	0.51761	6.753×10	1.323	23.506	70.315
PSO	2.000 00	3.736 83	2.245 32	0.415 84	1.237×10	0.621	12.266	45.609
CS	2.000 02	2.228 83	2.025 06	0.059 23	2.143×10	0.652	1.2531	5.799 5
WOA	2.000 18	3.759 90	2.420 99	0.502 09	7.739×10	0.220	21.049	65.982
SCA	2.023 97	6.945 43	3.165 94	1.155 36	7.728×10	0.217	58.297	96.602
SSA	2.000 05	3.993 36	2.436 57	0.524 51	7.413×10	0.250	21.828	67.412
ECS	2.000 00	2.047 98	2.012 35	0.015 35	2.209×10	0.791	0.6175	2.894 4

Algorithm	β				P_f×10^?3	CUP time/s	error1/%	error2/%
Algorithm	Best	Worst	Mean	Standard	P_f×10^?3	CUP time/s	error1/%	error2/%
GA	2.500 65	3.115 52	2.696 49	0.200 57	3.503	1.388	8.292	45.08
PSO	2.500 12	3.091 67	2.682 11	0.189 91	3.657	0.626	7.715	42.66
CS	2.499 99	2.502 24	2.500 13	0.000 43	6.207	0.633	0.407	2.705
WOA	2.501 11	3.183 43	2.752 91	0.260 85	2.953	0.235	10.56	53.71
SCA	2.512 54	18.01 33	4.380 43	3.138 55	0.006	0.208	75.92	99.91
SSA	2.500 03	3.170 48	2.714 77	0.221 61	3.316	0.235	9.026	48.02
ECS	2.497 50	2.497 50	2.497 50	1.355E–15	6.253	0.785	0.301	1.981

Structural reliability analysis using enhanced cuckoo search algorithm and artificial neural network

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 14

References 35

Related Articles 0

Recommended Articles

Metrics

Comments

Variable	Mean	Variation coef?cient	Unit	Distribution
F_h	90	0.05	MPa	Normal
E_h	196.5	0.05	GPa	Normal
L_h	40	0.05	mm	Normal
R_h	15	0.05	mm	Normal

Algorithm	β				P_f×10^?4	CUP time/s	error1/%	error2/%
Algorithm	Best	Worst	Mean	Standard	P_f×10^?4	CUP time/s	error1/%	error2/%
GA	3.214 57	3.259 64	3.223 16	0.406 74	6.339	3.215	0.755	8.060
PSO	3.201 69	3.225 48	3.214 47	0.444 87	6.534	1.744	0.484	5.231
CS	3.201 69	3.205 87	3.202 41	0.052 46	6.814	1.986	0.107	1.173
WOA	3.201 78	5.937 26	4.239 59	0.845 93	11.196	1.340	41.32	99.17
SCA	4.889 42	39 051.9	5 210.48	8.084 52	NA	1.372	NA	NA
SSA	3.201 83	5.893 19	4.0268 6	0.767 34	28.262	1.412	25.773	95.90
ECS	3.201 69	3.201 74	3.201 70	0.003 24	6.831	2.014	0.084	0.933