A review of lithium ion battery failure mechanisms and fire prevention strategies

Lithium-ion battery is an appropriate choice for electric vehicle (EV) due to its promising features of high voltage, high energy density, low self-discharge and long lifecycles. The successful operation of EV is highly dependent on the operation of battery management system (BMS). State of charge (SOC) is one of the vital paraments of BMS which signifies the amount of charge left in a battery. A good estimation of SOC leads to long battery life and prevention of catastrophe from battery failure. Besides, an accurate and robust SOC estimation has great significance towards an efficient EV operation. However, SOC estimation is a complex process due to its dependency on various factors such as battery age, ambient temperature, and many unknown factors. This review presents the recent SOC estimation methods highlighting the model-based and data-driven approaches. Model-based methods attempt to model the battery behavior incorporating various factors into complex mathematical equations in order to accurately estimate the SOC while the data-driven methods adopt an approach of learning the battery's behavior by running complex algorithms with a large amount of measured battery data. The classifications of model-based and data-driven based SOC estimation are explained in terms of estimation model/algorithm, benefits, drawbacks, and estimation error. In addition, the review highlights many factors and challenges and delivers potential recommendations for the development of SOC estimation methods in EV applications. All the highlighted insights of this review will hopefully lead to increased efforts toward the enhancement of SOC estimation method of lithium-ion battery for the future high-tech EV applications.

http://dspace.uniten.edu.my/jspui/bitstream/123456789/13358/1/State%20of%20Charge%20Estimation%20for%20Lithium-Ion%20Batteries%20Using%20Model-Based%20and%20Data-Driven%20Methods%20A%20Review.pdf

State of Charge Estimation for Lithium-Ion Batteries Using Model-Based and Data-Driven Methods: A Review

This paper presents a novel hybrid Elman-LSTM method for battery remaining useful life prediction by combining the empirical model decomposition algorithm and long short-term memory and Elman neural networks. The empirical model decomposition algorithm is employed to decompose the recorded battery capacity verse cycle number data into several sub-layers. The recurrent long short-term memory and Elman neural networks are then established to predict high- and low-frequency sub-layers, respectively. Comprehensive battery test datasets have been collected and used for model parameterization and performance evaluation. The comparison results indicate that the proposed hybrid Elman-LSTM model yields superior performance relative to the other counterparts and can predict the battery remaining useful life with high accuracy. The relative prediction errors are 3.3% and 3.21% based on two unseen datasets, respectively.

Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks

A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals

/pdf/a-perspective-survey-on-deep-transfer-learning-for-fault-m5e3nrkv.pdf

A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges

On-line life cycle health assessment for lithium-ion battery in electric vehicles

Hybrid state of charge estimation for lithium-ion battery under dynamic operating conditions

Lithium-ion battery has been widely applied as an energy storage component in various industrial applications including electric vehicles, distributed grids and space crafts. However, the battery performance degrades gradually due to the SEI growth, li-plating and other irreversible electro-chemical reactions. These inevitable reactions directly influence the reliability of the energy storage system and may further cause catastrophic consequences to the host system. Remaining useful life (RUL) is one of critical indicators to evaluate the battery performance. This paper proposes a battery RUL prediction approach based on a new recurrent neural network (RNN), i.e. the RNN with Gated Recurrent Unit (GRU). The proposed method overcomes the drawback on dealing with long term relationship of RNN. The structure of the RNN-GRU is much simpler which contributes to a higher computational complexity. The experiments based on the NMC lithium-ion battery cycle life testing data are conducted and the results indicate that the mean error of different battery cells are both less than 3% which means the proposed method is accurate and robust for battery RUL predictions.

Lithium-Ion Battery Remaining Useful Life Prediction Based on GRU-RNN

As lithium-ion battery is widely applied, lithium-ion battery reliability has received widespread attention in recent years. Remaining useful life (RUL) prediction is an effective way to ensure the battery reliability. The loss of actual capacity of a battery is usually used to reflect the battery RUL. However, the capacity degradation is complex and non-linear. For the longer capacity prediction horizon, the accuracy of traditional methods becomes lower which would cause error in RUL prognosis. To address this problem, this paper proposed a deep belief networks (DBN) method for lithium-ion battery RUL prediction. The proposed method is trained with historical battery capacity data. With the powerful fitting ability of DBN, the proposed method can track capacity degradation and predict the RUL. Experiments are conducted based on commercial lithium-ion batteries. The results show that the proposed method has high accuracy in capacity fade prediction and RUL prediction.

Lithium-Ion Battery Remaining Useful Life Prognostics Using Data-Driven Deep Learning Algorithm

Lithium-ion battery cells are connected in series and parallel to meet the demand for voltage and capacity of the battery energy storage system (BESS). However, with the battery cell degrading gradually, the performance of the battery pack also degrades. Therefore, it has to be focused on battery pack degradation state prognosis to ensure the system working safely and reliably. On the other hand, accurate degradation state prediction of battery pack is also helpful for conditional based maintenance which decreases the maintenance cost. The terminal voltage of the battery pack is utilized as the character presenting the battery degradation in this paper. The relationship between cycle number and the terminal voltage is described by an empirical double exponential function. Particle filter (PF) algorithm is applied to identify and update the parameters in the model. The battery degradation state can be directly predicted with the predefined cycle number. The battery remaining useful life (RUL) can also be estimated with the given failure threshold of the degradation feature. The experimental results indicate that the proposed prediction framework can get high prediction accuracy. At the same time, for the different operating conditions, this approach is of great robustness.

Lyu Li

Papers

On-line life cycle health assessment for lithium-ion battery in electric vehicles

Hybrid state of charge estimation for lithium-ion battery under dynamic operating conditions

Lithium-Ion Battery Remaining Useful Life Prediction Based on GRU-RNN

Lithium-Ion Battery Remaining Useful Life Prognostics Using Data-Driven Deep Learning Algorithm

Lithium-Ion Battery Pack On-Line Degradation State Prognosis Based on the Empirical Model