The ice coating on the transmission line is extremely destructive to the safe operation of the power grid. Under natural conditions, the thickness of ice coating on the transmission line shows a nonlinear growth trend and many influencing factors increase the difficulty of forecasting. Therefore, a hybrid model was proposed in this paper, which mixed Ensemble Empirical Mode Decomposition (EEMD), Random Forest (RF) and Chaotic Grey Wolf Optimization-Extreme Learning Machine (CGWO-ELM) algorithms to predict short-term ice thickness. Firstly, the Ensemble Profit Mode Decomposition model was introduced to decompose the original ice thickness data into components representing different wave characteristics and to eliminate irregular components. In order to verify the accuracy of the model, two transmission lines in 'hunan' province were selected for case study. Then the reserved components were modeled one by one, building the random forest feature selection algorithm and Partial Autocorrelation Function (PACF) to extract the feature input of the model. At last, a component prediction model of ice thickness based on feature selection and CGWO-ELM was established for prediction. Simulation results show that the model proposed in this paper not only has good prediction performance, but also can greatly improve the accuracy of ice thickness prediction by selecting input terminal according to RF characteristics.Energies 2019, 12, 2163 2 of 21 model, Imai model, Goodwin model, etc. [3,4]. However, as important as parameters in the model, which are difficult to collect, the prediction effect of the physical model is poor. The other is based on factors affecting the ice sheet and its development, and intelligent algorithms are used to predict the ice sheet thickness data fit. Lan, D.L and Zheng, Z.H used Generalized Regression Neural Network (GRNN) method to forecast ice thickness, with the results suggesting that the GRNN method shows good performance in ice coating thickness [5]. Xiao-min ma proposed a forecasting model based on grey Support Vector Machine (SVM) short-term ice thickness of transmission line [6], and the results showed that the SVM method can accurately predict the short-term ice thickness. However, GRNN and SVM methods all have systematic errors in simulation. The GRNN model relies too much on the sample data. When the sample data set is not sufficient, the GRNN neural network may lead to poor adaptability; for the SVM method, the kernel function and kernel parameters affect the fitting accuracy and generalization ability to varying degrees.Due to the faster convergence speed and less human interference compared with the traditional neural network, the Extreme Learning Machine (ELM) proposed by huang in 2004 has been widely used in many prediction fields. Zhang ning, huang yuanyu, li wanhua et al. [7][8][9] used the ELM model to predict short-term load based on various influencing factors, whose results showed that compared with the traditional Back Propagation (BP) neural network model, the ELM model coul...