Predicting expressway subsidence based on niching genetic algorithm and Holt–Winters model
- 32 Downloads
Mining subsidence prediction based on monitoring data is a vital task in engineering construction over underground mines. To improve the accuracy of predicting mining subsidence, a method based on the niching genetic algorithm (NGA) and the Holt–Winters model is proposed here. The NGA including niche selection methodology is chosen due to the defects of the genetic algorithm. The NGA is applied to optimize the parameters of the Holt–Winters model. The NGA–Holt–Winters model was applied to mining subsidence prediction on two sides of the Siping–Changchun expressway. The results show that the NGA enhances the convergence speed and precision of the algorithm, with both the convergence speed and forecast accuracy being superior to those of the grey model and the support vector machine model. The relative errors of the NGA–Holt–Winters model are less than 2% and the mean error is − 0.18%. The proposed model has better long-term prediction accuracy for mining subsidence than the support vector machine model, showing lower mean errors of between − 0.49 and − 0.79%.
KeywordsExpressway subsidence Niching genetic algorithm Holt–Winters model Mining subsidence prediction
The authors thank the participants who contributed to this work.
This project was funded by the China Postdoctoral Science Foundation (Grant No. 20100471265).
- Brady BHG, Brown ET (2011) Rock Mechanics for Underground Mining, 3rd edn. Science Press, BeijingGoogle Scholar
- Fang YB (2007) Analysis and processing of settlement data based on time series analysis. Journal of Shandong University of Technology (Natural Science Edition) 21(5):32–35Google Scholar
- Holt CC (1957) Forecasting trends and seasonals by exponentially weighted averages. Carnegie Institute of Technology, PittsburghGoogle Scholar
- Li PX, T ZH, Yan LL, Deng KZ (2010a) Calculation method of probability integration method parameters based on support vector machine. China Coal Soc 35(8):1247–1251 in ChineseGoogle Scholar
- Liu ZX, Liu C, Liu Q, Yue YL (2010) Chaotic time series reconstruction and security alarm system of rock mass deformation in undersea mining. Chinese Journal of Geotechnical Engineering 32(10):1530–1534Google Scholar
- Nie L, Peng W, Yuan MZ, Zhou NJ (2011) Ground collapse prediction of mined-out area based on EMD and WLS-SVM. J Jilin Univ (Earth Sci Ed) 41(3):799–804Google Scholar
- Shi B, Li YX, Yu XH, Niu YL (2010) Long-term runoff forecast method based on dynamic adjustment particle swarm optimizer algorithm and holt-winters linear seasonal model. Transactions of the Chinese Society of Agricultural Engineering 26(7):8–13Google Scholar
- Wang Z (2000) Practical method for system prediction. Nationalities Press, Beijing, pp 125–126Google Scholar
- Wang QR (2010) Combination forecast of railway freight volume based on Holt-Winter model and neural network. Journal of Lanzhou Jiaotong University 29(4):122–125Google Scholar
- Wu DH (2008) Dynamic exponential smoothing prediction method and its applications. J Syst Manag 17(2):151–155Google Scholar
- Xia QQ, An PY, He YG, Wu SC (2010) Subsidence prediction of mining area based on the grey theory. Journal of Transport Science and Engineering 26(3):52–55Google Scholar
- Yin GZ, Zhang WZ, Zhang DM, Kang QR (2007) Forecasting of landslide displacement based on exponential smoothing and nonlinear regression analysis. Rock Soil Mech 28(8):1725–1728Google Scholar
- Zhang L, Yan SF (2006) Comparison of Holt-Winters and ARIMA methods for forecasting charge of China Airline passengers. Journal of Shanghai University of Engineering Science 20(3):280–283Google Scholar
- Zhu GY, Xu ZH, Xie C, Guo Y (2014) Study on influence functions of surface residual movement and deformation above old goaf (in Chinese). Chin J Rock Mech Eng 33(10):1962–1970Google Scholar