Abstract
Acceleration can be used as the parameter of fault diagnosis of large-scale recreational facilities. For it can not only reflect on the overall running condition of recreational facilities in the macroscopic view, but also analyze the impact in the process of running in the microscopic view. Firstly, evolutional wavelet based threshold denoising algorithms was used to deal with the acceleration signal and six characteristic values of the signal were extracted. Then the BP neural network was used for fault diagnosis. Finally the results were compared with FFT analysis results. The simulation was made by Matlab. The conclusion is that the results of fault diagnosis are reliable.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Liu, A., Yin, X., Liu, A., Yang, M., Chen, J., Zhou, S.: Establishment and Analysis of Safety Regulatory System for China’s Recreation Facilities. China Safety Science Journal 19(5), 195–197 (2009)
Standards of People’s Republic of China: Amusement Device Safety Code. GB, 8408–2008 (2008)
Li, G., Zhang, G., Ling, X., Huang, K., Qiang, T., Li, X.: Remote Security Monitoring and Warning - Forecasting System for Large - Scale Amusement Ride Based on Multi – Agent. Computer Measurement & Control 18(4), 824–826 (2010)
Jiang, K., Tang, X., Zhu, D.: Automobile Wheel Speed Signal Processing Based on Wavelet Algorithm of Improved Threshold. Chinese Journal of Scientific Instrument 31(4), 736–740 (2010)
Wang, S., Zhu, Y.: A Comparative Simulation Study of Evolutional Wavelet Based Denoising Algorithms. Noise and Vibration Control 32(1), 128–132 (2012)
Yuan, J., Zhang, D., Li, J.: Wavelet Denoising Algorithm Based on Improved Thresholding Method. Journal of North China Electric Power University 37(5), 92–97 (2010)
Bari, A., Bhasin, K., Karnawat, D.N.: Introduction to Neural Network and Improved Algorithm to Avoid Local Minima and Faster Convergence. In: Das, V.V. (ed.) CIIT 2011. CCIS, vol. 250, pp. 396–400. Springer, Heidelberg (2011)
Chen, T., Han, D., Au, F.T.K., Than, L.G.: Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate. IEEE Trans. on Neural Network 3, 1873–1878 (2003)
Zhang, Z., Zhang, J., Ye, L., Zheng, Y.: Research on the Application of Neural Network in Diaphragm Icing Sensor Fault Diagnosis. In: Yu, W., He, H., Zhang, N. (eds.) ISNN 2009, Part I. LNCS, vol. 5551, pp. 589–600. Springer, Heidelberg (2009)
Zhao, C., He, M.: Short Time Fourier Analysis Based on the Special Frequency Component. Automation of Electric Power Systems 28(14), 41–44 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, G., Zhu, Yt., Wang, Sz. (2012). Fault Diagnosis Based on Low-Frequency Acceleration Signals towards Large-Scale Recreational Facilities. In: Liu, C., Wang, L., Yang, A. (eds) Information Computing and Applications. ICICA 2012. Communications in Computer and Information Science, vol 307. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34038-3_64
Download citation
DOI: https://doi.org/10.1007/978-3-642-34038-3_64
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34037-6
Online ISBN: 978-3-642-34038-3
eBook Packages: Computer ScienceComputer Science (R0)