Recently, lithium-ion batteries (LIBs) have achieved wide acceptance for various energy storage applications, such as electric vehicles (EVs) and smart grids. As a vital component in EVs, the performance of lithium-ion batteries in the last few decades has made significant progress. The development of a robust battery management system (BMS) has become a necessity to ensure the reliability and safety of battery packs. In addition, state of charge (SOC) estimation and thermal models with high-fidelity are essential to ensure efficient BMS performance. The SOC of a LIB is an essential factor that should be reported to the vehicle’s electronic control unit and the driver. Inaccurate reported SOC impacts the reliability and safety of the lithium-ion battery packs (LIBP) and the vehicle. Different algorithms are used to estimate the SOC of a LIBP, including measurement-based, adaptive filters and observers, and data-driven; however, there is a gap in feasibility studies of running these algorithms for multi-cell LIBP on BMS microprocessors. On the other hand, temperature sensors are utilized to monitor the temperature of the cells in LIBPs. Using a temperature sensor for every cell is often impractical due to cost and wiring complexity. Robust temperature estimation models can replace physical sensors and help the fault detection algorithms by providing a redundant monitoring system. In this thesis, an accurate SOC estimation and thermal modeling for lithium-ion batteries (LIBs) are presented using deep neural networks (DNNs). Firstly, two DNN-based SOC estimation algorithms, including a feedforward neural network (FNN) enhanced with external filters and a recurrent neural network with a long short-term memory layer (LSTM), are developed and benchmarked versus an extended Kalman filter (EKF) and EKF with recursive least squares filter (EKF-RLS) SOC estimation algorithms. The execution time of EKF, EKF-RLS, FNN, and LSTM SOC estimation algorithms with similar accuracy was found to be 0.24 ms, 0.25 ms, 0.14 ms, and 0.71 ms, respectively. The DNN SOC estimation algorithms were also demonstrated to have lower RAM use than the EKFs, with less than 1 kB RAM required to run one estimator. The proposed FNN and LSTM models are also used to predict the surface temperature of different lithium-ion cells. These DNN models are shown to be capable of estimating temperature with less than 2 ⁰C root mean square error for challenging low ambient temperature drive cycles and just 0.3 ⁰C for 4C rate fast charging conditions. In addition, a DNN model which is trained to estimate the temperature of a new battery cell, is found to still have a very low error of just 0.8 ⁰C when tested on an aged cell. Finally, an integrated physics, and neural network-based battery pack thermal model (LP+FNN) is developed and used to detect and identify different thermal faults of a LIBP. The proposed fault detection and identification method is validated using various thermal faults, including fan system failure, airflow lower and higher than setpoint, airflow blockage of submodule and temperature sensor reading faults. The proposed method is able to detect different cooling system faults within 10 to 35 minutes after fault occurrence. In addition, the proposed method demonstrated being capable of detecting temperature sensor reading offset and scale faults of ±3 ⁰C and ±0.15% or more, respectively with 100% accuracy. / Thesis / Doctor of Philosophy (PhD)

Indiana University-Purdue University Indianapolis (IUPUI) / Lithium-ion batteries are widely used for portable electronics due to high energy density, mature processing technology and reduced cost. However, their applications are somewhat limited by safety concerns. The lithium-ion battery users will take risks in burn or explosion which results from some internal components failure. So, a practical method is required urgently to find out the failures in early time. In this thesis, a new method based on temperature difference between internal point and surface (TDIS) of the battery is developed to detect the thermal failure especially the thermal runaway in early time. A lumped simple thermal model of a lithium-ion battery is developed based on TDIS. Heat transfer coefficients and heat capacity are determined from simultaneous measurements of the surface temperature and the internal temperature in cyclic constant current charging/discharging test. A look-up table of heating power in lithium ion battery is developed based on the lumped model and cyclic charging/discharging experimental results in normal operating condition. A failure detector is also built based on TDIS and reference heating power curve from the look-up table to detect aberrant heating power and bad parameters in transfer function of the lumped model. The TDIS method and TDIS detector is validated to be effective in thermal runaway detection in a thermal runway experiment. In the validation of thermal runway test, the system can find the abnormal heat generation before thermal runaway happens by detecting both abnormal heating power generation and parameter change in transfer function of thermal model of lithium ion batteries. The result of validation is compatible with the expectation of detector design. A simple and applicable detector is developed for lithium ion battery catastrophic failure detection.

<h4>A generalized physics-based modeling framework is presented to analyze: (a) the effects of temperature on identified degradation mechanisms, (b) interfacial debonding processes, including deterministic and stochastic mechanisms, and (c) establishing model performance benchmarks of electrochemical porous electrode theory models, as a necessary stepping stone to perform valid battery degradation analyses and designs. Specifically, the effects of temperature were incorporated into a physics-based, reduced-order model and extended for a LiCoO₂ -graphite 18650 cell. Three dimensionless driving forces were identified, controlling the temperature-dependent reversible charge capacity. The identified temperature-dependent irreversible mechanisms include homogeneous SEI, at moderate to high temperatures, and the chemomechanical degradation of the cathode at low temperatures. Also, debonding of a statistically representative electrochemically active particle from the surrounding binder-electrolyte matrix in a porous electrode was modeled analytically, for the first time. The proposed framework enables to determine the space of C-Rates and electrode particle radii that suppresses or enhances debonding and is graphically summarized into performance–microstructure maps where four debonding mechanisms were identified, and condensed into power-law relations with respect to the particle radius. Finally, in order to incorporate existing or emerging degradation models into porous electrode theory (PET) implementations, a set of benchmarks were proposed to establish a common basis to assess their physical reaches, limitations, and accuracy. Three open source models: dualfoil, MPET, and LIONSIMBA were compared, exhibiting significant qualitative differences, despite showing the same macroscopic voltage response, leading the user to different conclusions regarding the battery performance and possible degradation mechanisms of the analyzed system.</h4>