Abstract
The modern equipment is developing in the direction of complexity and integration, and the traditional diagnosis methods can’t adapt to the changes of equipment. With the development of deep learning, deep learning algorithms are gradually used in the field of fault diagnosis. Most of these algorithms ignore the correlation between data when extracting features from multi-source data. In response to the above problem, this paper proposes a fault diagnosis algorithm based on Bi-directional Long Short-Term Memory, which can extract the correlation features between multi-source data. Through the experiment on the simulated operating data of the heating furnace of steel rolling, the algorithm of this paper has a high fault recognition rate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, L.: Application research of statistical clustering and particle filter in fault diagnosis, pp.3–4. Northwestern Polytechnic University (2014)
Xiong, J., Zhang, Q., Li, Z.: An information fusion fault diagnosis method based on dimensionless indicators with static discounting factor and KNN. IEEE Sens. J. 16(7), 2060–2069 (2016)
Ge, Q.: Research on data driven fault diagnosis method based on deep belief networks. Harbin Institute of Technology (2016)
Mengshi, L., Yu, D., Ziming, C., et al.: Fault diagnosis method of wind turbine based on deep belief networks. J. Electr. Mach. Control 02, 114–122 (2019)
Cabrera, D., Sancho, F., Li, C., et al.: Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation. Appl. Soft Comput. 58, 53–64 (2017)
Chen, S., Yu, J.: Feature learning and fault diagnosis of multivariable processes based on convolutional neural networks. J. Harbin Inst. Technol. 1–11 (2020)
Li, H., Zhang, Q., Qin, X., et al.: Bearing fault diagnosis method based on short time fourier transform and convolution neural networks. Vibr. Shock 37(19), 124–131 (2018)
Yang, L., Wu, Y., Wang, J., Liu, Y.: Research review of cyclic neural networks. Comput. Appl. 38(S2), 1–6+26 (2018)
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Networks 5(2), 157–166 (1994)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Wang, X., Wu, J., Liu, C., Yang, H., Du, Y., Niu, W.: Fault time series prediction based on LSTM recurrent neural network. J. Beijing Univ. Aeronaut. Astronaut. 44(04), 772–784 (2018)
Acknowledgements
The authors would like to express appreciation to mentors in Shanghai University and Huayu-intelligent Equipment Technology Co., Ltd for their valuable comments and other helps. Thanks for the pillar program supported by Shanghai Science and Technology Committee of China (No. 19511105200).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yin, B., Li, X., Liu, L., Wu, F. (2021). Research on Fault Diagnosis Algorithm Based on Bi-directional Long Short-Term Memory. In: Wang, Y., Martinsen, K., Yu, T., Wang, K. (eds) Advanced Manufacturing and Automation X. IWAMA 2020. Lecture Notes in Electrical Engineering, vol 737. Springer, Singapore. https://doi.org/10.1007/978-981-33-6318-2_34
Download citation
DOI: https://doi.org/10.1007/978-981-33-6318-2_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6317-5
Online ISBN: 978-981-33-6318-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)