Nondestructive Detection Of Anchorage Quality Of Rock Bolt Based On DS-DBN-SVM
Haiqing Zheng, Yaru Yang, Xiaoyun Sun, Cheng Wen · 2018
Deep learning is a hot topic in the field of machine learning, which provides a new method for the nondestructive testing of bolt anchorage. Aiming at the importance of identifying the type of bolt defects, this paper proposes a DS-DBN-SVM(Differential Search-Deep belief network-Support vector machine) model for identifying the type of bolt anchorage defects. The DS algorithm is used to optimize the weights and thresholds of the DBN network. The original acceleration signal of the anchor is used as the input of the DS-DBN model to extract the high-level features of the signal. Finally, the SVM classifier is used for defect identification. To assess the effectiveness of the method, and compare it with the traditional classification methods. The results show that the defect recognition effect of this method is better than the traditional defect recognition method, and the recognition rate reaches 95.45%.