Comprehensive Performance Prediction of Concrete Based on Relevance Vector Machine Model

Abstract

Abstract: In order to quickly obtain and evaluate the comprehensive performance of concrete, a prediction model of the comprehensive performance of concrete was established based on the relevance vector machine (RVM), in which six main factors affecting the comprehensive performance of concrete were selected as input data and the comprehensive performances (28 d strength, slump extension and apparent density) of concrete were selected as the output data. Then the model was used to predict 5 groups of predicting samples through fitting traning of 14 groups of learning samples. The results show that under the same sample conditions, compared with BP neural network model, RVM model has higher prediction accuracy and less discreteness. Compared with the actual value, the average relative error of concrete comprehensive performance index predicted by RVM model is obviously smaller than that predicted by BP neural network model, which further verifies the reliability of RVM model to predict the comprehensive performance of concrete, and has good promotion value.

Key words: relevance vector machine, concrete, influence factor, mean relative error, comprehensive performance, predictive model

CLC Number:

TU528

ZHANG Yan, WANG Pengpeng, WU Zhekang. Comprehensive Performance Prediction of Concrete Based on Relevance Vector Machine Model[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2022, 41(1): 118-125.

References

[1] 李先顺,李刚.中、欧标准中混凝土结构基本要求的对比研究[J].建筑结构,2020,50(5):99-103+92.
LI X S, LI G. Comparative study on basic requirements of concrete structure between Chinese and European standards[J]. Building Structure, 2020, 50(5): 99-103+92 (in Chinese).
[2] 王瑜玲,王春福,张飞燕.3D打印混凝土性能要求及相关外加剂研究进展[J].硅酸盐通报,2021,40(6):1844-1854.
WANG Y L, WANG C F, ZHANG F Y. Review on performance requirements and related admixtures of 3D printed concrete[J]. Bulletin of the Chinese Ceramic Society, 2021, 40(6): 1844-1854 (in Chinese).
[3] SHAMSUDIN M M H, HAMID N H, FAUZI M A M. Compressive and flexural strength of concrete containing recycled polyethylene terephthalate (PET)[J]. Key Engineering Materials, 2021, 879: 13-21.
[4] 维利思,申向东,刘倩,等.不同风积沙混凝土强度的影响因素研究[J].硅酸盐通报,2019,38(9):2933-2940+2946.
WEI L S, SHEN X D, LIU Q, et al. Influencing factors of different aeolian sand concrete strength[J]. Bulletin of the Chinese Ceramic Society, 2019, 38(9): 2933-2940+2946 (in Chinese).
[5] 肖倍,安旭文,杨瑞,等.再生混凝土基本力学性能试验及其影响因素研究[J].混凝土,2018(11):32-36+40.
XIAO B, AN X W, YANG R, et al. Experimental research on basic mechanical characteristics of recycled aggregate concrete and influencing factors[J]. Concrete, 2018(11): 32-36+40 (in Chinese).
[6] 吴剑锋,李慧剑,王彩华,等.基于强度表征的混凝土脆性指标影响因素研究[J].力学季刊,2020,41(3):528-536.
WU J F, LI H J, WANG C H, et al. Study on influence factors of the brittleness index of concrete based on strength[J]. Chinese Quarterly of Mechanics, 2020, 41(3): 528-536 (in Chinese).
[7] 高冠一,张铖,麻凤海.混凝土抗碳化性能影响因素试验研究[J].混凝土,2020(6):30-32.
GAO G Y, ZHANG C, MA F H. Experimental study on influencing factors of concrete carbonation resistance[J]. Concrete, 2020(6): 30-32 (in Chinese).
[8] 谢吉程,张云,杜越明,等.机制砂混凝土耐磨性的主要影响因素分析及多因素计算模型[J].硅酸盐通报,2020,39(12):3812-3822.
XIE J C, ZHANG Y, DU Y M, et al. Analysis of major influence factors and multi-factor calculation model of abrasion resistance of manufactured sand concrete[J]. Bulletin of the Chinese Ceramic Society, 2020, 39(12): 3812-3822 (in Chinese).
[9] 李志新,赖志琴,龙云墨,等.基于模式识别神经网络的水资源配置评价模型研究[J].中国农村水利水电,2018(11):61-66.
LI Z X, LAI Z Q, LONG Y M, et al. Research on the evaluation model of water resources configuration based on pattern recognition neural network[J]. China Rural Water and Hydropower, 2018(11): 61-66 (in Chinese).
[10] ELHAKIM A F, EL KHOULY M A A, AWAD R. Three dimensional modeling of laterally loaded pile groups resting in sand[J]. HBRC Journal, 2016, 12(1): 78-87.
[11] 李地红,高群,夏娴,等.基于BP神经网络的混凝土综合性能预测[J].材料导报,2019,33(s2):317-320.
LI D H, GAO Q, XIA X, et al. Prediction of comprehensive performance of concrete based on BP neural network[J]. Materials Reports, 2019, 33(s2): 317-320 (in Chinese).
[12] CHEN S Y, GU C S, LIN C N, et al. Multi-kernel optimized relevance vector machine for probabilistic prediction of concrete dam displacement[J]. Engineering With Computers, 2021, 37(3): 1943-1959.
[13] TIPPING M E. Escaping the convex hull with extrapolated vector machines[M]//Advances in Neural Information Processing Systems 14. The MIT Press, 2002: 652-658.
[14] 郭珉,石洪波,冀素琴.贝叶斯网络结构稀疏学习研究进展[J].模式识别与人工智能,2016,29(10):907-923.
GUO M, SHI H B, JI S Q. Survey of sparse structure learning of Bayesian networks[J]. Pattern Recognition and Artificial Intelligence, 2016, 29(10): 907-923 (in Chinese).
[15] 金艳,田田,姬红兵.基于稀疏贝叶斯学习的码元速率估计[J].电子与信息学报,2018,40(7):1598-1603.
JIN Y, TIAN T, JI H B. Symbol rate estimation based on sparse Bayesian learning[J]. Journal of Electronics & Information Technology, 2018, 40(7): 1598-1603 (in Chinese).
[16] DEO R C, SAMUI P, KIM D. Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models[J]. Stochastic Environmental Research and Risk Assessment, 2016, 30(6): 1769-1784.
[17] CAMPS-VALLS G, MARTINEZ-RAMON M, ROJO-ALVAREZ J L, et al. Nonlinear system identification with composite relevance vector machines[J]. IEEE Signal Processing Letters, 2007, 14(4): 279-282.
[18] 邱思语,杨洪耕.稀疏贝叶斯回归及其在谐波电流异常检测中的应用[J].电力系统及其自动化学报,2017,29(5):104-107.
QIU S Y, YANG H G. Sparse Bayesian regression and its application to anomaly detection of harmonic current[J]. Proceedings of the CSU-EPSA, 2017, 29(5): 104-107 (in Chinese).
[19] 杨国鹏,周欣,余旭初.稀疏贝叶斯模型与相关向量机学习研究[J].计算机科学,2010,37(7):225-228.
YANG G P, ZHOU X, YU X C. Research on sparse Bayesian model and the relevance vector machine[J]. Computer Science, 2010, 37(7): 225-228 (in Chinese).
[20] 张研,邝贺伟.地震震级预测的相关向量机模型[J].世界地震工程,2020,36(1):212-221.
ZHANG Y, KUANG H W. Relevance vector machine model for earthquake magnitude prediction[J]. World Earthquake Engineering, 2020, 36(1): 212-221 (in Chinese).