Detecting thermal faults is critical to the safety of lithium-ion batteries. This article, therefore, proposes a neural network-based approach. The approach relies on long short-term memory network, in conjunction with an alteration walk-forward technique, accurately estimate surface temperature cell. It also residual monitor detect real time. data-driven method introduced expand available options fault detection. offers easy-to-implement option that does not require expert understanding...

Traditionally health monitoring techniques in lithium-ion batteries rely on voltage and current measurements. A novel method of using a mechanical rather than electrical signal the incremental capacity analysis (ICA) is introduced this paper. This derives curves based measured force (ICF) instead (ICV). The surface cell under compression fixture that replicates battery pack assembly preloading. performed data collected from cycling encased prismatic Lithium-ion Nickel-Manganese-Cobalt Oxide...

A phenomenological model of the bulk force exerted by a lithium ion cell during various charge, discharge, and temperature operating conditions is developed. The measured modeled resembles carbon expansion behavior associated with phase changes intercalation, as there are ranges state charge (SOC) gradual increase SOC very small change in force. includes influence on observed capturing underlying thermal phenomena. Moreover capable describing transients, when internal battery heating due to...

All-solid-state batteries (ASSBs) are considered to be the next generation of lithium-ion batteries. Physics-based models (PBMs) can effectively simulate internal electrochemical reactions and provide critical states for battery management. In order promote onboard applications PBMs ASSBs, in this article, parameter sensitivity a typical PBM is analyzed, joint estimation method parameters based on sigma-point Kalman filtering (SPKF) proposed. First, obtain accurate analysis results,...

The commercialization of lithium-ion batteries enabled the widespread use portable consumer electronics and serious efforts to electrify trans-portation. Managing potent brew in large quantities necessary for vehicle propulsion is still challenging. From space applications a billion miles from Earth daily commute hybrid electric automobile, these require sophisticated battery management systems based on accurate estimation internal states. This system brain responsible estimating state...

The physics-informed neural network (PINN) has drawn much attention as it can reduce training data size and eliminate the need for physics equation identification. This paper presents implementation of a PINN with adaptive normalization in loss function to predict lithium-ion battery cell temperature. In particular, was trained actual test data, lumped capacitance thermal relationship applied addition pre-layer connection layer architecture. architecture shows most accurate temperature...

Only a very limited amount of the high theoretical energy density LiCoO 2 as cathode material has been realized, due to its irreversible deterioration when more than 0.6 mol lithium ions are extracted. In this study, new insights into origin such low electrochemical reversibility, namely structural collapse caused by electrostatic repulsion between oxygen during charge process suggested. By incorporating partial cation migration LiNiO , which produces screen effect cations in 3 b ‐Li site,...

Lithium (Li)-ion battery cells suffer from significant performance degradation at subzero temperatures. This paper presents a predictive control-based technique that exploits the increased internal resistance of Li-ion temperatures to increase cell's temperature until desired power can be delivered. Specifically, magnitude sequence bidirectional currents is optimized such as minimize total energy discharged. The current determined by solving an optimization problem satisfies manufacturer's...

This paper proposes a predictive equivalent consumption minimization strategy (P-ECMS) for plug-in hybrid electric vehicle (PHEV), assuming the availability of two levels traffic information. The information include 1) segmented available from mobile mapping applications, and 2) detailed velocity information, possibly obtained by short-term speed forecasting. Battery state-of-charge (SOC) reference waypoints are simplified profile constructed that proposed P-ECMS adjusts its co-state or...

Enforcing constraints on the maximum deliverable power is essential to protect lithium-ion batteries and maximize resource utilization. This paper describes an algorithm address estimation of capability battery systems accounting for thermal electrical constraints. The based model inversion compute limiting currents and, hence, capability. adequacy significantly depends accuracy states parameters. Herein, these are estimated by designing cascading estimators whose structure determined...

This paper presents a study of the energy-efficient operation all-electric vehicles leveraging route information, such as road grade, to adjust velocity trajectory. First, Pontryagin's maximum principle (PMP) is applied derive necessary conditions and determine possible operating modes. The analysis shows that only five modes are required achieve minimum energy consumption: full propulsion, cruising, coasting, regeneration, regeneration with conventional braking. Then, consumption problem...

This paper addresses the problem of estimating SOC-imbalance between two battery cells connected in series. Particularly, effectiveness using force measurements for detection against pack/total voltage is studied. SOC imbalance estimation during charging pack measurement was previously demonstrated LiFePO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sub> /graphite chemistry. However, Li-ion with LiNiMnCoO...

Forecasting the speed trajectories of driving vehicles is essential for vehicle/powertrain predictive optimal control. This paper proposes a simple and effective forecasting method generating short-term future using vehicle-to-vehicle (V2V) information. Specifically, series lead vehicles' speeds locations are considered to be potential that following car would drive in near future. Polynomial regression based on weighted least-squares estimation used determine trajectory over short...

Enhanced single-particle models (eSPMs) have been extensively studied in the development of advanced battery management systems for their accuracy and capability tracking physical quantities, as well reduced computational load. This article proposes an optimal discretization approach to model reduction eSPM using a particle swarm optimization algorithm. The diffusion dynamics were solved different finite difference approaches, that is, even (baseline model) uneven (optimized model). Because...

Accurate health diagnostics of lithium-ion batteries are critical for ensuring safe, reliable, and prolonged battery operation. This study presents a data-driven approach to estimating electrode-level state-of-health (eSOH) using Deep Neural Network (DNN), enabling the assessment loss active material (LAM) in both electrodes lithium inventory (LLI). To construct DNN models, essential features extracted from differential voltage incremental capacity analyses open-circuit (OCV), derived...

Enforcement of constraints on the maximum deliverable power is essential to protect lithium-ion batteries from over-charge/discharge and overheating. This paper develops an algorithm address often overlooked temperature constraint in determining capability battery systems. A prior knowledge provides dynamic currents affords additional control authority batteries. Power estimated using a lumped electro-thermal model for cylindrical cells that has been validated over wide range operating...