Predicting Reliability Of Lithium Ion Batteries Using Deep Learning

ABSTRACT

Accurate prediction of Remaining Useful Life (RUL) of lithium-ion battery plays an increasingly crucial role in the intelligent battery health management systems. The advances in Deep Learning introduce new data-driven approaches to this problem. This paper proposes an integrated deep learning approach for RUL prediction of lithium-ion battery by integrating autoencoder with Deep Neural Network (DNN). Firstly, we present a multi-dimensional feature extraction method with autoencoder model to represent battery health degradation. Then, the RUL prediction model based DNN is trained for multi-battery remaining cycle life estimation. The proposed approach is applied to the real dataset of lithium-ion battery cycle life from NASA, and the experiment results show that the proposed approach can improve the accuracy of RUL prediction.

ACRONYM AND THEIR MEANING

RUL = Remaining useful life

RNN = Recurrent neural network

CNN = Convolution neural network

DFF = Deep feed forward network

Seq2Seq = Sequence to sequence

HI = health indicator

LSTM = long-short term memory

 CHAPTER ONE

• INTRODUCTION

 In the past, nickel–cadmium batteries were generally the only electrical power source for various portable equipment, until nickel metal hybrid and lithium-ion batteries were developed in the 1990s [1]. In the present-day, lithium-ion battery technology is rapidly growing, and it is the most reliable electrical power source for numerous appliances. Lithium-ion batteries are extensively equipped in both high-power applications and low-power electronics products, such as hybrid-motor engines, electric cars, smartphones, tablet, laptops, etc. To date, lithium-ion technology is considered to be a standard power source, and its performance continues to improve. There is currently no any other technology that has proven to perform better than the lithium-ion battery. Therefore, there will be no other battery technologies that lithium-ion anytime soon, and the main focus of the ongoing technology is still aimed at improving the lithium-ion system in term of both its performance and reliability. The following are the main advantages of lithium-ion batteries: (1) high energy density (up to 23–70 Wh/kg), (2) high efficiency (close to 90%), and (3) long life cycle (provides 80% capacity at 3000 cycles) [2].

To ensure that the lithium-ion battery system performing reliably, there must be a method that helps to track and to determine the state of health (SoH) of the battery system, along with its remaining useful life (RUL). This method gives useful information for the prediction of when the battery should be removed or replaced. This type of evaluation is known as the system’s prognostic and health management (PHM). There have been many advancements contributed by researchers from various disciplines to PHM of lithium-ion batteries. Downey et al. proposed a physics-based prognostic approach that considered multiple concurrent degradation mechanisms [3]. Susilo et al. studied the estimation of the lithium-ion battery SoH with the combination of Gaussian distribution data and the least square support vector machines regression approach [4]. Mejdoubi et al. employed the Rao-Blackwellization particle filter to evaluate the aging condition of lithium-ion batteries, and to estimate SoH and RUL of the battery system [5]. Bai et al. developed a generic model-free approach based on ANN and the Kalman filter, to help to improve the health management system of the lithium-ion battery [6]. Other filtering techniques, for example, particle filtering [7] or its variation of the unscented particle filtering technique [8] had been employed in the PHM aspect for lithium-ion batteries. Recently, Li et al. proposed Gauss–Hermite particle filter (GHPF) technique for battery state-of-charge estimation, which is another extension of the particle filter technique, which not only improves the estimation accuracy, but also reduces the number of sampling particles, which reduces the complexity of the algorithm [9]. Another interesting work also aims to predict the health state of the lithium-ion battery, as proposed by Wang et al. This work employed the Brownian motion technique, which is the combination of the Kalman filter and the Gaussian distribution state space technique, to determine battery prognostics based on the drift coefficient [10].

A data-driven model based on the deep learning approach for lithium-ion battery prognostics is the main focus of this paper. Although various approaches had been proposed to improve the PHM prediction of lithium-ion batteries, the deep learning approach for PHM is still limited. The advancement of computational tools and big data algorithms have largely impacted the development of this approach. The machine learning algorithms, in particular, ANN, have been proven to be able to empirically learn and recognize the more complex patterns of the system’s data in many applications. This feature of machine learning algorithms also benefits prognostic analysis modeling as well. This paper presents the preliminary development of a data-driven model using Deep Neural Networks (DNN) to predict the SoH and RUL of lithium-ion batteries. DNN is a deep learning approach that was developed based on Artificial Neural Networks with multiple hidden layers, to analyze more complex data and features. Although some deep learning algorithms, such as Recurrent Neural Network (RNN) and Long Short-Term Memory Network (LSTM), are employed to model prognostic of lithium-ion battery recently, to date, there is no work that has employed a DNN model to perform similar tasks. In addition, there are limited works that have performed a deep learning approach against other data-driven algorithms. For this reason, this paper can also act as a benchmarking reference for employing a deep learning approach to prognostic data in general. The effectiveness of the proposed approach was tested in the lithium-ion battery dataset derived from the NASA Ames Prognostics Center of Excellence (PCoE). A DNN approach was employed to predict the SoH and RUL and the results were compared against other machine learning algorithms such as Linear Regression (LR), k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), and ANN. This paper is constructed with the following sections: Section 2 discusses the overview of the PHM application and the characteristics of the lithium-ion battery used in this paper, Section 3 provides a concise literature review of the proposed approach for DNN analysis and modeling, Section 4 details the experimental results and the comparison of DNN and other machine learning algorithms, and Section 5 concludes the findings and investigates possible future work.

1.1                            BACKGROUND OF THE STUDY

Deep learning is the study of artificial neural networks and related machine learning algorithms that contain more than one hidden layer. Deep learning networks, such as deep feed forward network(DFF), convolution neural network(CNN), recurrent neural network(RNN), long-short term memory (LSTM), and sequence to sequence (Seq2Seq) have been applied to computer vision, speech recognition, natural language processing, and audio recognition fields, etc. and have achieved excellent results.

In this work, we present a case where I apply deep learning for a business problem. The particular application of deep learning in this work is using LSTM, which is a type of recurrent neural network, to predict Li-ion battery remaining useful life (RUL).

Deep learning can be solutions to many of problems in enterprises. Like any new technology, it will be a slow process for businesses to adopt deep learning technology. At present, some of the biggest problems faced by businesses in adopting deep learning, or machine learning in general, are following:

• Machine learning requires having high quality and structured data sets. To take advantage of machine learning, enterprises must first establish a standardized data management system.
• Shortage of Machine learning talents. Hiring data scientists is hard, and hiring data scientists with business domain knowledge is even more difficult.
• Lack of necessary products and tools. Although there are many open source deep learning frameworks, for example, Tensorflow, Caffe, CNTK and Keras, etc., but the learning curve is high. Most of the frameworks focus on building deep learning models and do not provide a solution as to how to deploy and use of models. It is still up to enterprises to develop what is lacking, making the development, deployment and use of deep learning a long cycle.

In this work, we address the above issues by introducing some of the work that have done in past years and recently. We are using Li-ion battery RUL prediction as an example to demonstrate an implementation.

There are many research on Li-ion battery RUL prediction using various techniques and algorithms. But the focus here is not on the accuracy of predicting model, but rather on design and implementation of a software system that makes it easy for businesses to apply deep learning to test data from the experiments.

PROBLEM STATEMENT

Li-ion batteries are widely used in consumer electronics, electric vehicles and space systems. However, a Li-ion battery has a useful life, that means with continuous charge and discharge cycles and material aging, battery performance will continue to decline until it fails to function.

Remaining life of a Li-ion battery is also known as battery cycle life, refer to the number of complete charge/discharge cycles that the battery can support before that its capacity falls under 70% of its original capacity.

It is known that capacity of a Li-ion battery is continuously declining after every charge and discharge cycle, and the degradation trend is very consistent. When a battery capacity drops under the failure threshold, the cell is considered to be not useable. Theoretically, it is possible to predict the remaining life of a Li-ion battery by establishing a life model of a battery. A battery life model can have many applications.

Many companies and research institutions have been conducting research and development of Battery Management Systems (BMS) for electric vehicles, ships, aircraft and spacecraft, in which the battery life model is an essential component and one of the challenges in developing BMS.

Many of mission-critical devices, such as GPS systems and satellites, use Li-ion batteries as the power source. Therefore, a battery life model is important for assessing the reliability of Li-ion batteries during operation of the devices.

Manufacturers of Li-ion batteries are required to perform many kinds of tests, including battery cycle life and calendar life tests, to ensure the reliability of Li-ion batteries, which are very time-consuming and costly. By using battery life models to predict remaining battery life, companies can shorten the test time by 20%.

The industry has been conducting research in establishing battery life model that can accurately predict remaining life of batteries. The methods vary from using battery physical model and data-driven model. Recently, machine learning techniques have been a trend in research, including the use of SVM, ANN, and RNN, etc.

However, the primary focus of the research has been on choosing modeling methods and algorithms to improve the accuracy of prediction, and the MATLAB tool has been used to implement the models.

Deep learning has shown very promising results in many fields, but the use of open source deep learning framework for Li-ion battery RUL prediction has just begun. The steep learning curve of deep learning frameworks and lack of application platform and tools for simplifying the development and deployment of deep learning models have been obstacles to the progress.

AIM OF THE STUDY

The aim of this work is to study Li-ion battery RUL prediction using deep learning to test data from the experiments.

OBJECTIVE OF THE STUDY

There are two different ways this study can be carried out: 1. Model driven method and data driven method. However, At the end of this study a data driven method of lithium-ion battery Remaining useful life (RUL) prediction shall be used.

SCOPE OF THE STUDY

The use of Lithium-ion batteries in the automobile sector has expanded drastically in the recent years. The foreseen increment of lithium to power electric and hybrid electric vehicles has provoked specialists to analyze the long term credibility of lithium as a transportation asset. To give a better picture of future accessibility, this paper exhibits a life cycle model for the key procedures and materials associated with the electric vehicle lithium-ion battery life cycle, on a worldwide scale. This model tracks the flow of lithium and energy sources from extraction, to generation, to on road utilization, and the role of reusing and scrapping. This life cycle evaluation model is the initial phase in building up an examination model for the lithium ion battery production that would enable the policymakers to survey the future importance of lithium battery recycling, and when in time setting up a reusing foundation be made necessary.