Life span prediction of Huizhou architecture based on improved Elman neural network

doi:10.3969/j.issn.0253-2778.2017.10.003

Abstract

Abstract: Huizhou architecture comprises one of the four ancient architectural schools in China, with wood components being its core. The accurate prediction of Huizhou architectures wood life is of great significance for the protection of ancient buildings. At present, there are few studies have been conducted on the influence of various factors on the service life of the wood components. Elman neural network is typical multi-layer dynamic recurrent neural network, which has the function of mapping dynamic characteristics by storing internal state. This gives the network the ability to adapt to time-varying characteristics, which can be used to predict the complex nonlinear time-varying system. The basic Elman neural network has the characteristics of slow training speed and the tendency to fall into local minimums. Therefore the particle swarm optimization algorithm with adaptive mutation operator is used to improve the basic Elman neural network. The algorithm optimizes the weights of each layer in the network, improves the learning speed, and finds the optimal solution in the global range. The improved network can fit the training value more accurately and can effectively predict the test value. The simulation results show that the network structure can be well applied to the life span prediction of Huizhou architecture.

Key words: Elman neural network, particle swarm optimization;wood component;life prediction

CLC Number:

TP391

ZHANG Guangbin, ZHANG Runmei. Life span prediction of Huizhou architecture based on improved Elman neural network[J]. Journal of University of Science and Technology of China, 2017, 47(10): 817-822.

References

［1］
XUE J Y, WU Z J, ZHANG F L. Seismic damage evaluation model of Chinese ancient timber buildings[J]. Advances in Structural Engineering, 2015, 18(10): 1671-1683.
[2] LYU Mengning, ZHU Xinqun, YANG Qingshan. Dynamic field monitoring data analysis of an ancient wooden building in seismic and operational environments [J]. Earthquakes and Structures, 2016, 11(6): 1043-1060.
[3] BONALI E, PESCI A, CASULA G. Deformation of ancient buildings inferred by terrestrial laser scanning methodology: the cantalovo church case study[J]. Archaeometry, 2014, 56(4): 703-716.
[4] FREGONESE L, BARBIERI G, BIOLZI L, et al. Surveying and monitoring for vulnerability assessment of an ancient building[J]. Sensors, 2013, 13(8): 9747-9773.
[5] ROSOWSKY D V, BULLEIT W M. Load duration effects in wood members and connections: order statistics and critical loads[J]. Structural Safety, 2002, 24(2-4): 347-362.
[6] NGUYEN M N, LEICESTER R H, WANG c h, et al. Probabilistic procedure for design of untreated timber piles under marine borer attack[J]. Reliability Engineering and System Safety, 2008, 93(3): 482-488.
[7] DAI Lu, YANG Na, ZHANG Lei. Monitoring crowd load effect on typical ancient Tibetan building [J]. Structural Control & Health Monitoring, 2016, 23(7): 998-1014.
[8] 瞿伟廉, 王雪亮. 基于DOL强度衰减模型的古建筑木桁架的剩余寿命预测[J]. 华中科技大学学报, 2008, 25(3): 1-4.
[9] FANG Shiqiang, ZHANG Kun, ZHANG Hui, et al. A study of traditional blood lime mortar for restoration of ancient buildings[J].Cement and Concrete Research, 2015, 76: 232-241.
[10] YANG Na, LI Peng, LAW S S. Experimental research on mechanical properties of timber in ancient Tibetan building[J]. Journal of Materials in Civil Engineering, 2012, 24(6): 635-643.
[11] ZHANG Xicheng, XUE Jianyang, ZHAO Hongtie, et al. Experimental study on Chinese ancient timber-frame building by shaking table test[J]. Structural Engineering and Mechanics, 2011, 40(4): 453-469.
[12] WYSOCKI A, AWRYN′CZUK M. Elman neural network for modeling and predictive control of delayed dynamic systems[J]. Archives of Control Sciences, 2016, 26(1): 117-142.
[13] CHANDRA R. Competition and collaboration in cooperative coevolution of Elman recurrent neural networks for time-series prediction[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(12): 3123-3136.
[14] SHEIKHAN M, ARABI M A, GHARAVIAN D. Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: A comparative study[J]. 2015, 27(4): 340-357.
[15] 毛澄映, 喻新欣, 薛云志. 基于粒子群优化的测试数据生成及其实证分析[J]. 计算机研究与发展, 2013, 50(2): 260-268.
MAO Chengying, YU Xinxin, XUE Yunzhi. Algorithm design and empirical analysis for particle swarm optimization-based test data generation[J]. Journal of Computer Research and Development, 2013, 50(2): 260-268.
[16] CHOUIKHI N, AMMA, B, ROKBAN N, et al. PSO-based analysis of echo state network parameters for time series forecasting[J]. Applied Soft Computing, 2017, 55: 211-225.
[17] JAFARI M, HOSEYNI S A M, CHALESHTARI M H. Determination of optimal parameters for perforated plates with quasi-triangular cutout by PSO[J]. Structural Engineering and Mechanics, 2016, 60(5): 795-807.
[18] PALMER S, GORSE D, MUK-PAVIC E. Neural networks and particle swarm optimization for function approximation in Tri-SWACH hull design[C]// Proceedings of the 16th International Conference on Engineering Applications of Neural Networks. Rhodes, Greece: ACM, 2015: 32-36.
[19] RAZA S, MOKHLIS H, AROF H, et al. Minimum-features-based ANN-PSO approach for islanding detection in distribution system[J]. IET Renewable Power Generation, 2016, 10(9): 1255-1263.
[20] SITHARTHAN R, GEETHANJALI M. An adaptive Elman neural network with C-PSO learning algorithm based pitch angle controller for DFIG based WECS[J]. Journal of vibration and control, 2017, 23(5): 716-730.
[21] ZHOU C, DING L Y, HE R. PSO-based Elman neural network model for predictive control of air chamber pressure in slurry shield tunneling under Yangtze River[J]. Automation in construction, 2013, 36(5): 208-217.
[22] QIN Shanshan, WANG Jianzhou, WU Ji. A hybrid model based on smooth transition periodic autoregressive and Elman artificial neural network for wind speed forecasting of the Hebei region in China[J]. International Journal of Green Energy, 2016, 13(6): 595-607.

()
(