Search

To solve the problem that the poor accuracy of long-term prediction relying on model accuracy for the filter-based prediction method, a fusion fault prediction algorithm based on filter and long short-term memory (LSTM) network is proposed to achieve the prediction of spacecraft flywheel slowly growing faults. Firstly, a mini-batch normalization LSTM network and a trend recognition module are designed, which are connected in series to form a neural network predictor to improve the time series prediction accuracy. Then, the Kalman filter update process is improved by the recursive least square (RLS) parameter estimation principle to enhance the robustness for time series prediction error. On this basis, the predicted values output by the neural network predictor are fused with the improved filter. Prediction residual can be obtained for iterative updating and prediction, overcoming the dependence of the filter algorithm on the model and improving prediction accuracy. Finally, the time series predictive performance of three neural network predictors are analyzed by simulation experiments. And considering the degradation fault of flywheel bearing performance, the proposed fusion prediction algorithm is used to determine that the flywheel degrades to a threshold at 856 s, with a prediction time error of 36 s. The simulation results verify the effectiveness of the proposed algorithm for slowly growing fault.

Copyright of Aero Weaponry is the property of Aero Weaponry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

【Objective】Optical fiber dispersion, nonlinear impairments, and bandwidth limitation in high-speed passive optical access networks result in significant power budget loss with traditional intensity modulation and direct detection schemes, failing to meet the requirements of high-speed passive optical access networks.【Methods】In order to enhance the rate and performance of the intensity modulation and direct detection optical access system, this study explores the channel equalization method of VDFE-RLS based on Recursive Least Squares (RLS) algorithm, building upon the Volterra Decision Feedback Equalizer (VDFE), This equalizer uses RLS algorithm to update its tap coefficients. It includes a three-order Volterra series, allowing it to compensate for both linear and nonlinear impairments. VDFE-RLS is applied to the downlink optical access system with a single wavelength of 200 Gbit/s based on O-band intensity modulation and direct detection scheme after 20 km transmission.【Results】The experimental results show that the RLS outperforms the conventional Least Mean Square (LMS) algorithm in the equalization process. Moreover, VDFE-RLS achieves a power budget greater than 29 dB. When the length of the equalizer is the same, VDFE-RLS can increase the power budget by 2.2 dB compared with the conventional Volterra Feed Forward Equalization (VFFE)-RLS equalizer. When the length of VDFE-RLS equalizer is half that of VFFE-RLS, the VDFE-RLS can increase the power budget by 0.5 dB compared with the VFFE-RLS equalizer.【Conclusion】Compared with other traditional methods, the proposed method can shorten the length of the equalizer and increase the power budget of the system, ultimately restoring signals with better performance.

Copyright of Journal of Engineering for Thermal Energy & Power / Reneng Dongli Gongcheng is the property of Journal of Engineering for Thermal Energy & Power and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Engineering for Thermal Energy & Power / Reneng Dongli Gongcheng is the property of Journal of Engineering for Thermal Energy & Power and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Piezoelectrics & Acoustooptics is the property of Piezoelectric & Acoustooptic and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)