Residual Remaining Useful Life Prediction Method for Lithium-Ion Batteries in Satellite With Incomplete Healthy Historical Data

Abstract

Due to the strict requirements of satellite systems, accurate remaining useful life (RUL) prediction of the key components is very important to the reliability and security of satellite systems. Otherwise, a failure could lead to catastrophic consequences and enormous economic losses. Because of the complex structure of the satellite and its complex space environment, the factors that affect the satellite systems status are numerous. Moreover, as a result of the healthy historical data of key components in satellite are too few, which makes the traditional methods based on analysis model are not suitable for RUL prediction of key components in satellite. In this paper, in order to solve the RUL prediction problem of Lithium-ion batteries (LIBs) in satellite with incomplete healthy historical data, we propose an efficient RUL prediction method for key components of satellite, which is called Residual Remaining Useful Life Prediction Method (RRULPM), based on the study of Multivariate State Estimation Technique (MSET). The RRULPM is make up of degradation model based on MSET state estimation and criteria of failure based on historical degradation value, which is developed by improving MSET and combining the residuals with life cycle damage (LCD) prediction creatively when lacking healthy historical data. Experimental results demonstrate that the RRULPM is excellent to achieve the RUL prediction problems of LIBs through the actual in orbit telemetry data. Unlike previous RUL prediction methods, RRULPM provides good feasibility and effectiveness. This research can serve as guidance for prognostics and health management (PHM) of key components in satellite. INDEX TERMS Lithium-ion batteries, multivariate state estimation technique, remaining useful life, satellite.

Overview of Machine Learning Methods for Lithium-Ion Battery Remaining Useful Lifetime Prediction

“…The problem becomes the function y(x) in the minimization Equation (2), where n represents the number of samples and λ represents the regularization parameters. Specifically, SVM can also use the kernel function to transform the input low-dimensional vector into a high-dimensional feature space, and then use the hyperplane to separate the data, thereby applying the kernel method (the decision-making boundary element has Equations (3) and (4) as shown above, where ϕ is the mapping function).…”

“…Therefore, the forecasting method should consider uncertain factors. The performance of various RUL prediction methods can be evaluated from the following aspects: (1) activation function; (2) training algorithm;…”

“…With the development of the electrification era, the vigorous advancement of new energy vehicles, and the Internet of Things, the importance of energy storage system performance has become prominent. Lithium-ion batteries stand out among various energy storage solutions due to their high energy density, high power capability, and low selfdischarge rate [1,2]. At the same time, this also puts forward higher requirements and challenges for the development of battery management technology.…”

A Critical Review of Online Battery Remaining Useful Lifetime Prediction Methods

“…Among various energy storage solutions, Lithium-ion (Li-ion) batteries are widely regarded as promising candidates for various applications due to their advantages of high energy density and low self-discharge (Peng et al, 2019;Gao et al, 2020). However, the life span of Li-ion batteries is not unlimited, and the cost and aging of Li-ion batteries are the two main factors hindering their development (She et al, 2020;Zhang et al, 2021;Ren et al, 2021).…”

Adaptive Early Warning Method Based on Similar Proportion and Probability Model

“…From the perspective of fault warning, many researchers have performed relevant research. The fault warning is mainly studied from four aspects: sensitive feature [19][20][21], probability model [22,23], state classification [24][25][26][27][28][29], and time series prediction [30]. For example, Rostek et al [31] realized early detection and prediction of fluidized bed boiler leakage with the use of the artificial neural network (ANN) method.…”