Missing projectile base pressure signals often occur due to extreme environments during artillery testing. To address this issue, a time-frequency feature fusion imputation method is proposes based on LSTM and GAIN to enhances the accuracy of signal reconstruction. The adversarial training principle of the GAIN network is utilized to learn the complex internal patterns and potential distributions of the signal and to ensure consistency between the global structure and local features during the imputation process. A time-frequency feature fusion strategy and a dual-branch parallel and serial structure are adopted to extract and integrate both time-domain and frequency-domain features of the base pressure signal. As a result, the critical signal information of the signal is comprehensively captured. LSTM networks with sequential processing capability is incorporated to learn and capture temporal patterns and long-term dependencies within the signal, as well as ensure the temporal completeness and coherence of the reconstructed signal. Experimental results show that the reconstructed signals are highly similar to the complete signals. The goodness-of-fit reach 0.973 6 under a 15 dB signal-to-noise ratio(SNR)and 0.996 8 under a 30 dB SNR, respectively.
XUHao, RUIXiaoting, FENGBinbin, et al. Measuring method for big area projectile base compression stress of propellant charge based PVDF piezoelectric film[J]. Journal of Vibration and Shock, 2012, 31(22): 20-23. (in Chinese)
YANGHui, SHENDawei, ZUJing. The acceleration effect and calibration method of pressure sensors in the test of pressure on the bottom of the projectile[J]. Chinese Journal of Sensors and Actuators, 2011, 24(9): 1256-1259. (in Chinese)
PEIDongxing, SHENDawei, ZHANGYu, et al. The research of projectile bottom pressure measuring technology[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2012, 32(5): 196-198. (in Chinese)
YOUWenbin, DINGYonghong, MATiehua, et al. Testing technology of projectile base pressure[J]. Journal of Gun Launch & Control, 2012, 33(3): 64-67. (in Chinese)
[10]
WANGH, ZHOUC, WANGH, et al. A novel contact model for rough surfaces using piecewise linear interpolation and its application in gear wear[J]. Wear, 2021, 476: 203685.
[11]
NIJMANS W J, GROENHOFT K J, HOOGLANDJ, et al. Real-time imputation of missing predictor values improved the application of prediction models in daily practice[J]. Journal of Clinical Epidemiology, 2021, 134: 22-34.
CHENBo, HEYouhua. Estimation method of moving average model with missing data[J]. Journal of Shanghai University (Natural Science Edition), 2020, 26(2): 181-188. (in Chinese)
[14]
YESILBUDAKM, SAGIROGLUS, COLAKI. A novel implementation of kNN classifier based on multi-tupled meteorological input data for wind power prediction[J]. Energy Conversion and Management, 2017, 135: 434-444.
[15]
YANGD X, KHERAR, CHANGE, et al. Comparison of machine learning approaches for missing data imputation among non-small cell lung cancer patients[J]. International Journal of Radiation Oncology Biology Physics, 2021, 111(3): 115.
[16]
CHEZ, PURUSHOTHAMS, CHOK, et al. Recurrent neural networks for multivariate time series with missing values[J]. Scientific Reports, 2018, 8(1): 6085.
[17]
CAOW, ZHANGH, HEW, et al. Autoencoder in autoencoder network based on low-rank embedding for anomaly detection in hyperspectral images[C]//2022 IEEE International Geoscience and Remote Sensing Symposium, 2022: 3263-3266.
[18]
ZHAOL Y, WANGZ Y, CHENT X, et al. Missing interpolation model for wind power data based on the improved CEEMDAN method and generative adversarial interpolation network[J]. Global Energy Interconnection, 2023, 6(5): 517-529.
GUOJunhang, LIYanli. A study on initial pressure of projectile engraving process for large caliber gun[J]. Journal of Ballistics, 2022, 34(2): 80-85. (in Chinese)
ZHOUMengdi, CAOCongyong, QIANLinfang. Research on prediction theoretical model of projectile base pressure during aftereffect period[J]. Acta Armamentarii, 2019, 40(6): 1304-1309. (in Chinese)
YUQingbo, YANGGuolai, GEJianli, et al. Artillery firing dynamics based on spatial variation of propellant gases pressure[J]. Journal of Vibration and Shock, 2018, 37(17): 141-147. (in Chinese)
SUNChuanmeng, CHENJiaxin, YUANYue, et al. Shockwave signal reconstruction method based on a serial-parallel double branch network[J]. Journal of Vibration and Shock, 2024, 43(6): 38-49. (in Chinese)