Chaotic Ensemble of Online Recurrent Extreme Learning Machine for Temperature Prediction of Control Moment Gyroscopes

Abstract

Control moment gyroscopes (CMG) are crucial components in spacecrafts. Since the anomaly of bearing temperature of the CMG shows apparent correlation with nearly all critical fault modes, temperature prediction is of great importance for health management of CMGs. However, due to the complicity of thermal environment on orbit, the temperature signal of the CMG has strong intrinsic nonlinearity and chaotic characteristics. Therefore, it is crucial to study temperature prediction under the framework of chaos time series theory. There are also several other challenges including poor data quality, large individual differences and difficulty in processing streaming data. To overcome these issues, we propose a new method named Chaotic Ensemble of Online Recurrent Extreme Learning Machine (CE-ORELM) for temperature prediction of control moment gyroscopes. By means of the CE-ORELM model, this proposed method is capable of dynamic prediction of temperature. The performance of the method was tested by real temperature data acquired from actual CMGs. Experimental results show that this method has high prediction accuracy and strong adaptability to the on-orbital temperature data with sudden variations. These superiorities indicate that the proposed method can be used for temperature prediction of control moment gyroscopes.

Brain-inspired emotional learning algorithm enhanced with type-one and interval type-two fuzzy extreme learning machine in noisy data

“…In addition to the above, several derivations of ELM have been suggested. Some of them include a fast and accurate online sequential ELM (OS-ELM) (Liang et al 2006) and online sequential fuzzy ELM (OS-FELM) (Rong et al 2009), an ensemble of OS-ELM (EOS-ELM) with a forgetting mechanism (Jianwei Zhao et al 2012), weighted ELM for imbalance learning (Zong et al 2013), hierarchical extreme learning machine (Han et al 2014), ELM with two hidden neurons (Qu et al 2016), Rough-ELM with uncertainty measures (Feng et al 2019), a chaotic ensemble of online recurrent ELM (ORELM) (Luhang Liu et al 2020), and a new structure of deep autoencoder based on ELM (Najafi et al 2022;Tissera and McDonnell 2016).…”