A Data Fusion Fault Diagnosis Method Based on LSTM and DWT for Satellite Reaction Flywheel

Abstract

This paper presents a novel fault diagnosis method based on data fusion for a reaction flywheel of the satellite attitude system. Different from most traditional fault diagnosis techniques, the proposed solution simultaneously accomplishes fault detection and identification within parallel fusion blocks. The core of this method is independent fusion block, which uses a generalized ordered weighted average (GOWA) operator to complement the characteristics of output data from long short-term memory (LSTM) neural network and discrete wavelet transform (DWT) so as to enhance the reliability and rapidity of decision-making. Moreover, minibatch normalization is selected to address the problem of covariate shift, realize the adaptive processing of the dynamic information in the original data, and improve the convergence speed of the network. With the high-fidelity model of the reaction flywheel, three common faults are, respectively, injected to collect experimental data. Extensive experiment results show the efficacy of the proposed method and the excellent performance achieved by LSTM and DWT.

Enhancing Stock Price Prediction Using Stacked Long Short-Term Memory

“…LSTM networks, with their memory cells and gates, excel at handling long-term dependencies, making them well-suited for modeling and predicting time series data like stock prices [6]. Furthermore, stacking multiple LSTM layers allows for extracting more abstract and higher-level features from the data, potentially enhancing the model's predictive capabilities [7]. By utilizing Stacked LSTM, this research aims to leverage the strengths of this architecture to improve the accuracy and reliability of stock price predictions, thereby providing valuable insights for investment decision-making.…”

Employment of Intelligent Predictive Maintenance on Thermal Power Plant Component Parts Taking Condenser Vacuum as a Case Study

“…52339/tjet.v42i3.953 While the use of AI in power plant maintenance is beginning to take foothold, there has been a number of studies on the deployment of the technique in predictive maintenance applications in different environmental installations generally. In the literature abounds the applications of ML in facilities other than power systems (Bahri et al, 2009;Brahm de Jong, 2015;Bayoumi and McCaslin, 2017;Vuyyuru, 2018;Ahmad et al, 2018;Pai et al, 2019;Long et al, 2020;Niyonambaza et al, 2020;Girit et al, 2021;Miao, 2021;Li et al, 2021;Wei et al, 2021). In similarly vein, Hua et al (2020), Olesen and Shaker (2020) and Yang et al (2020) are instances of several cases of deploying ML in power systems infrastructures other than thermal generating plants.…”

Intelligent fault diagnosis method of spacecraft control system based on sequence data-image mapping

“…Liu et al [17] presented a satellite flywheel bearing fault intelligent diagnosis method based on CNN, and the input of CNN was made up of the time domain waveform maps drawn by single point radial vertical vibration signal. In [18], a novel fault diagnosis method based on data fusion for a reaction flywheel of the satellite attitude system is presented, which core of the method adopted a generalized ordered weighted average (GOWA) operator to complement the output from LSTM and discrete wavelet transform (DWT). All the above-mentioned papers are concentrated on the fault diagnosis study based on the parameters of a single satellite component.…”