Abstract
In this paper, a weak impulse signal detection method based on phase space reconstruction of chaotic time series and long-term and short-term memory neural network (LSTM) in the deep learning model is proposed. Reconstructing the phase space of chaotic signals can effectively extract the chaotic information in the sequence, and constructing LSTM neural network can effectively distinguish the signal points from the non-signal points to achieve better detection results. When detecting the weak pulse signal in Lorenz chaotic system and Rossler chaotic system, the model has high detection accuracy and can still maintain the detection performance when the signal-to-noise ratio is low. This paper compares it with other machine learning models and deep learning models, such as Support Vector Machine (SVM), Recurrent Neural Network (RNN), Extreme Learning Machine (ELM), and so on. The results show that the detection accuracy of this model is higher than other comparable models under different signal-to-noise ratios and has strong detection performance. In addition, the weak pulse signal in the sunspot sequence is detected, and the fault signal in the rolling bearing is diagnosed. These results show that this model can accurately detect the weak pulse signal in the chaotic background when the signal-to-noise ratio is low and is suitable for dealing with the weak signal detection problem in the chaotic background in real life and the fault diagnosis problem in the engineering application field. This not only reduces the detection threshold of weak signal detection but also widens the application field of weak signal detection.
Similar content being viewed by others
References
Ajeesh PK, Leung H (2008) Model based synchronization for weak signal detection. IEEE Instrum Meas Technol Conf 2008:1219–1222
Cai KH (2021) Detection and classification of abnormal dynamic RF signals based on deep learning. Electron Technol Softw Eng 2021(19):32–34
Cao LY (1997) Practical method for determining the minimum embedding dimension of a scalar time series. Phys D Nonlinear Phenomena 110(1):43–50
Chambon S, Thorey V, Arnal PJ (2019) A deep learning approach to detect multiple sleep micro-events in EEG signal. J Neurosci Methods 321:64–78
Chen ZY (2021) Electromagnetic interference signal detection and recognition system based on USRP and deep learning. Beijing University of Posts and Telecommunications. https://doi.org/10.26969/d.cnki.gbydu.2021.001675
Deng L (2020) Statistical detection and estimation of weak pulse signal under chaotic noise interference based on deep learning model. Chongqing University of Technology. https://doi.org/10.27753/d.cnki.gcqgx.2020.000079
Fan JQ, Yao QW (2008) Nonlinear time series. Higher Education Press, Beijing, pp 330
Feng H, Yang Y, Zhang RX (2008) Chaotic synchronization and its application. J Hebei North Univ (Nat Sci Ed) 24:29–35
Glenn CM, Hayes S (1996) Weak signal detection by small-perturbation control of chaotic orbits. In: IEEE MTT-S international microwave symposium digest. San Francisco, CA, United States. pp 1883–1886
Guo YJ (2017) Research on methodology of weak signal detection based on chaos theory. Xi'an University of science and technology. https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C475KOm_zrgu4lQARvep2SAk-6BvX81hrs37AaEFpExs0JAM7gJh4-sHtz3EZUt4-wSntNRJI62W4Kb5cRAS3LX2&uniplatform=NZKPT
Haykin S, Xiao BL (1995) Detection of signals in chaos. Proc IEEE 83(1):95–122
He JB, Liu Z, Hu SL (2011) Detection of weak signal based on the sea clutter scattering. Acta Phys Sin 60:50–52
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Hong TJ, Ding FJ (2021) Application of deep learning in bearing fault diagnosis. Sci Technol Eng 21(22):9203–9211
Hu JF, Zhang YX (2015) Research on harmonic signal detection method in strong chaotic background based on optimal filter. Acta Phys Sin 64(22):95–102
Huang WJ, Li YT (2021) Prediction of chaotic time series based on hybrid neural network and attention mechanism. Acta Phys Sin 70(01):235–243
Jiang KY, Cai ZM (2007) Harmonic signal extraction under chaotic background based on RBF neural network model. J Wuhan Univ Technol (Transport Sci Eng) 2007(05):850–853
Jin JT, Xu ZF (2022) Fault diagnosis of rolling bearing based on deep learning and chaotic feature fusion. Control Theory Appl 39(01):109–116
Leung H, Haykin S (1990) Is there a radar clutter attractor. Appl Phys Lett 56(6):593–595
Leung H, Huang XP (1996) Parameter estimation in chaotic noise. IEEE Trans Signal Process 44(10):2456–2463
Leung H, Lo T (1993) Chaotic radar signal processing over the sea. IEEE J Ocean Eng 18(3):287–295
Li M, He YG, Zhou SW, Liu ZR (2010) A differential evolution algorithm optimized wavelet neural network and its application in weak signal detection. Comput Appl Softw 27(03):29–31 + 39
Li Y, Yang B (2003) Chaotic system for the detection of periodic signals under the background of strong noise. Sci Bull 48:508–510
Lin JY, Wang YK (1999) Selection of time delay in speech signal phase space reconstruction--complex autocorrelation method. Signal Process 15(3):220–225
Liu HC (2021) Research on radar signal detection and interference recognition technology based on deep learning. University of Electronic Science and Technology of China. https://doi.org/10.27005/d.cnki.gdzku.2021.002354
Liu JZ, Ye FF, Xiong H (2021) Recognition of multi class motor imagery EEG signals based on convolutional neural network. J Zhejiang Univ (Eng Ed) 55(11):2054–2066
Loparok A Bearings vibration data set. case western reserve university [EB/OL]. http://csegroups.case.edu/bearingdatacenter/home
Lv H, Cao Z, Yan X (2009) A combined method of weak signal detection in proceedings of the Asia-pacific conference on computational intelligence and industrial applications. In: computational intelligence and industrial applications, Wuhan, China. pp 106–109
Niu YT (2019) Classification and parameter estimation of EEG signal based on deep learning. Dalian University of Technology. https://doi.org/10.26991/d.cnki.gdllu.2019.000532
Patricia HR, Jesus AB (2013) Application of the Teager-Kaiser energy operator in bearing fault diagnosis. ISA Trans 52(2):278–284
Ramsha A, Chen YY (2022) Deep residual learning-based cognitive model for detection and classification of transmitted signal patterns in 5G smart city networks. Digit Signal Process 120:103290
Short KM, Parker AT (1998) Unmasking a hyperchaotic communication scheme. Phys Rev E Stat Phys Plasmas Fluids Relat Interdiscip Top 58(1):1159–1162
Srinivasu PN, SivaSai JG (2021) Classification of skin disease using deep learning neural networks with MobileNet V2 and LSTM. Sensors (Basel) 21(8):2852
Su LY, Li XM (2021) Detection of pulse signal in chaotic noise background using extreme learning machine. J Phys Conf Ser 1738:012011
Su LY, Ling X (2020) Estimating weak pulse signal in chaotic background with Jordan neural network. Complexity 2020:14
Su LY, Sun HH (2017) Detection and recovery of weak pulse signal under chaotic noise. Acta Phys Sin 66(09):29–38
Su LY, Sun HH (2017) Hybrid algorithm for sinusoidal signal recovery under strong chaotic background based on local linear method and Kalman filter. Acta Electron Sin 45(04):837–843
Takens F (1981) Detecting strange attractors in turbulence. Lect Notes Math 898:366–381
Tu Y, Lin Y, Zha H et al (2022) Large-scale real-world radio signal recognition with deep learning. Chin J Aeronaut 35(9):35–48. https://doi.org/10.1016/j.cja.2021.08.016
Wang SY, Shi CF (2018) Prediction of chaotic time series based on fractional maximum correlation entropy algorithm. Acta Phys Sin 67(01):283–290
Xing HY, Qi ZD (2012) Weak signal detection in sea clutter background based on selective support vector machine integration. Acta Phys Sin 61(24):90–95
Xing HY, Xu W (2007) The neural networks method for detecting weak signals under chaotic background. Acta Phys Sin 2007(07):3771–3776
Xing HY, Zhu QQ, Xu W (2014) A weak signal detection method under the background of chaotic sea clutter. Acta Phys Sin 63(10):45–51
Xu SN (2019) Weak signal detection in chaotic background. Liaoning University of engineering and technology. https://doi.org/10.27210/d.cnki.glnju.2019.000185
Yang L, Wu YX (2018) Review of research on cyclic neural networks[J]. J Comput Appl 38(S2):1–6 + 26
Zhang KL, Zhu HM (2009) Weak signal detecting technology[J]. Avionics Technol 40:30–39
Zhao ZH, Li LH (2021) A multi task deep learning method for bearing fault diagnosis. J Electron Meas Instrum 35(12):108–115
Zhao SL, Zhang LZ, Su LY (2021) Detection fusion of weak signal under chaotic noise based on distributed system. J Sens 2021:14
Acknowledgments
This study is supported by the National Natural Science Foundation of China (Grant No.11871124) and the Chongqing Education Commission (Grant KJQN202101125).
Data and program availability
The data used to support the findings of this study and the program in this study are available from the corresponding author upon request.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflicts of interest regarding the publication of this paper.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Su, L., Yin, M. & Zhao, S. PSR-LSTM model for weak pulse signal detection. Multimed Tools Appl 82, 35853–35877 (2023). https://doi.org/10.1007/s11042-023-14987-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14987-w