Application of EEMD and neural network in stress prediction of anchor bolt Online publication date: Mon, 30-Apr-2018
by Hui Xing; Xiaoyun Sun; Mingminig Wang; Haiqing Zheng; Jianpeng Bian
International Journal of Computer Applications in Technology (IJCAT), Vol. 57, No. 2, 2018
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.
Online publication date: Mon, 30-Apr-2018
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email firstname.lastname@example.org