Title: Application of EEMD and neural network in stress prediction of anchor bolt
Authors: Hui Xing; Xiaoyun Sun; Mingminig Wang; Haiqing Zheng; Jianpeng Bian
Addresses: School of Electrical and Electronics Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, China ' School of Electrical and Electronics Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, China ' School of Electrical and Electronics Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, China ' School of Electrical and Electronics Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, China ' School of Electrical and Electronics Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, China
Abstract: An estimation method for free bolt stress is described. Acoustic stress wave signals of free bolt were collected under different tensile forces and analysed in time domain and frequency domain after cross-correlation. The variations of wave propagation time, fundamental and secondary frequency of signals' spectrum are studied. Then signals are decomposed into intrinsic mode functions (IMFs) by ensemble empirical mode decomposition (EEMD). The normalised energy ratios and correlation coefficients of IMFs are also discussed. Propagation time, fundamental and secondary frequency of signals' spectrum, energy ratios and correlation coefficients of IMFs are influenced by applied tensile force. Thus they are selected as the components of eigenvector for inputs of neural network. Back propagation neural network (BPNN) and genetic algorithm (GA) optimised BPNN are used for tensile force prediction. Eleven sets of data were used to test the stress prediction effect of BPNN after training. The results indicate that the BPNN optimised by GA can achieve small errors for stress prediction.
Keywords: back propagation neural network; genetic algorithm; acoustic stress wave; ensemble empirical mode decomposition; stress prediction; bearing capacity detection.
DOI: 10.1504/IJCAT.2018.091639
International Journal of Computer Applications in Technology, 2018 Vol.57 No.2, pp.157 - 166
Received: 11 Feb 2017
Accepted: 19 Feb 2017
Published online: 10 May 2018 *