Predicted optimizing mixture ratio of composite curing agent for soft clay based on PSO-SVM coupling algorithm
1. School of Civil and Environmental Engineering, Ningbo University, Ningbo, Zhejiang 315211, China; 2. School of Civil Engineering and Architecture, Zhejiang University of Science and Technology, Hangzhou, Zhejiang 310023, China; 3. Research Center of Coastal and Urban Geotechnical Engineering, Zhejiang University, Hangzhou, Zhejiang 310058, China; 4. Taizhou Branch, Zhejiang-California International Nanosystems Institute, Taizhou, Zhejiang 318000, China
Abstract：To realize accurate prediction on the optimizing mixture ratio of composite curing agent for soft clay, according to the experimental data of unconfined compressive strength (qu) of solidified clay, a prediction model of qu for solidified clay was established based on SVM. The maximum unconfined compressive strength of solidified clay was taken as objective function, and the PSO-SVM coupling algorithm for the optimizing mixture ratio of composite curing agent for soft clay was proposed by combining particle swarm optimization algorithm (PSO). The effects of the maximum iteration number (Nmax) and the particle number (Np) on the prediction results of PSO-SVM algorithm were discussed. The results show that the accuracy of PSO-SVM algorithm is better than that of response surface method, and the proposed PSO-SVM algorithm is suitable for the determination of the optimizing mixture ratio of composite curing agent for any soft clay at a specific curing age. It is also suggested that using the proposed PSO-SVM algorithm, Nmax and Np should be greater than 60 and 40, respectively.
GUO Y, XU R Q, SHAO Y C. Study on mechanism of muddy soil stabilization\[J\]. Journal of Zhejiang University(Engineering Science),2008, 42(6): 1071-1075.(in Chinese)
YANG A W, ZHOU J, KONG L W. Experimental study of solidification of soft dredger fill in Tianjin Binhai New Area\[J\].Rock and Soil Mechanics,2013, 34（9）:2442-2448. (in Chinese)
TUO Q S, ZHU J F, RAO C Y. Experimental study on shear strength of stabilized organic soil\[J\].Journal of Sediment Research,2017, 42(5): 70-74. (in Chinese)
CHANG S, XU R Q, LI X G, et al. Optimization of formula for stabilizing muddy soil using response surface methodology \[J\]. Rock and Soil Mechanics, 2014, 35(1): 105-110. (in Chinese)
LI X G, XU R Q, CHANG S, et al. Application of response surface methodology on optimizing mixture ratio of composite curing agent used to improve organic matter soil stabilization\[J\]. Journal of Zhejiang University(Engineering Science), 2014, 48(5):843-849. (in Chinese)
ZHU J F, RAO C Y, TUO Q S, et al. Experimental study on the properties of the organic soil solidified by the composite magnesium oxysulfate cement-curing agent\[J\]. Chinese Journal of Rock Mechanics and Engineering, 2019, 38(S1): 3206-3214. (in Chinese)
［7］
YI P, WEI K T, KONG X J， et al. Cumulative PSO-Kriging model for slope reliability analysis\[J\]. Probabilistic Engineering Mechanics， 2015,39：39-45.
［8］
VAPNIK V N. The Nature of Statistical Learning Theory\[M\]. New York，USA： Springer, 1995.
［9］
HUANG Y, ZHAO L. Review on landslide susceptibility mapping using support vector machines\[J\]. Catena， 2018, 165: 520-529.
CHEN C F, LI X, GONG X N, et al. Composite foundation′s optimization design of settlement′s surrogate models based on support vector machines \[J\]. Journal of Railway Science and Engineering,2018,15(6): 1424-1429. (in Chinese)
CHEN C F, ZENG Y Y, XIAO S J, et al. Complex genetic method of active earth pressure based on thin-layer element method\[J\]. Rock and Soil Mechanics, 2006, 27(3): 398-402. (in Chinese)
［12］
ZHU J F, CHEN C F. Search for circular and noncircular critical slip surfaces in slope stability analysis by hybrid genetic algorithm \[J\]. Journal of Central South University of Technology, 2014, 21(1): 387-397.
WANG F, ZHOU Y H, ZHAO C J, et al. Inverse analysis of concrete dam thermal parameters based on an improved particle swarm optimization method\[J\].Journal of Vibration and Shock, 2019, 38(12):168-181. (in Chinese)
WAN Z, DONG H, LIU B C. On choice of hyper-parameters of support vector machines for time series regression and prediction with orthogonal design \[J\]. Rock and Soil Mechanics, 2010，31(2):503-515. (in Chinese)
［15］
SHI Y H,EBERHART R. A Modified Particle Swarm Optimizer\[C\]∥Proc of IEEE Icec Conference,1998：67-73.
ZHAO Y D, FANG Z H. Particle swarm optimization algorithm with weight function′s learning factor \[J\]. Journal of Computer Application, 2013，33(8): 2265-2268. (in Chinese)
2021, Vol. 42 
