Improved support vector machine regression in multi-step-ahead prediction for rock displacement surrounding a tunnel

A dependable long-term prediction of rock displacement surrounding a tunnel is an eective way to predict rock displacement values in the future. A multi-step-ahead prediction model, which is based on a Support Vector Machine (SVM), is proposed for predicting rock displacement surrounding a tunnel. To improve the performance of SVM, parameter identication is used for SVM. In addition, to treat the time-varying features of rock displacement surrounding a tunnel, a forgetting factor is introduced to adjust the weights between new and old data. Finally, data from the Chijiangchong tunnel are selected to examine the performance of the prediction model. Comparative results presented between SVMFF (SVM with a forgetting factor) and an Articial Neural Network with a Forgetting Factor (ANNFF) show that SVMFF is generally better than ANNFF. This indicates that a forgetting factor can eectively improve the performance of SVM, especially for time-varying problems.