<div class="section abstract"><div class="htmlview paragraph">As electric vehicles are becoming increasingly popular and necessary for the future mobility needs of civilization, further effort is continually made to improve the efficiency, cost, and safety of the lithium-ion battery packs that power these vehicles. To facilitate these goals, this paper introduces a data driven model to predict a distribution of surface temperatures for a lithium-ion battery pack: a long short-term memory (LSTM) neural network. The LSTM model is trained and validated with lithium-ion cells electrically connected to form a battery pack. Voltage, current, state of charge (SOC), and cell surface temperature from two arrays are used as inputs from a wide range of high and low temperature drive cycles. Additionally, ambient temperature is added as an input to the LSTM model. In summary the LSTM model can accurately characterize and predict a distribution of lithium-ion cell surface temperatures arranged in a battery pack under extreme conditions to an accuracy of 1.53<b>°</b>C. Furthermore, making use of an external sensor to measure the ambient temperature of the battery pack further increases the accuracy of the LSTM model. With this data driven model, fewer testing data is required to validate a battery pack during development, less sensors are needed in production to monitor the health of the battery pack, and data can be generated for a wide variety of applications which may or may not be possible in a lab environment.</div></div>

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 the implementation of a PINN with adaptive normalization in the loss function to predict lithium-ion battery cell temperature. In particular, the PINN was trained with the actual battery test data, and a lumped capacitance lithium-ion battery thermal relationship was applied to the loss function with the addition of a pre-layer and connection layer to the neural network architecture. The PINN architecture shows the most accurate battery temperature prediction compared with the fully connected neural network (FCN) and its variants evaluated in this study. The proposed PINN architecture has a mean square prediction error of 0.05 ºC with a limited number of training data and without battery thermal model identification.INDEX TERMS Physics-informed neural network, lithium-ion battery, battery temperature

No abstract

Physics-based models for battery temperature prediction are often not suitable for online applications due to the large number of fitted parameters, low fidelity results from parameter inaccuracy and unaccounted model dynamics, limited high quality experimental data, and slow convergence of predictions from unknown initial conditions. On the other hand, data-driven models require much less computation power but a large dataset to learn the time dependent behavior. This paper proposes a physics-informed neural network (PINN) to take full advantage of both physics-based and data-driven models. Four comparative studies were performed to investigate the effectiveness of including chamber temperature with two different activation functions, the optimal number of neurons and hidden layers, the dependance on reversible heat generation, and the performance of long short-term memory (LSTM)-PINN model. The results show that the LSTM-PINN with chamber temperature as one of the inputs delivers better prediction accuracy. The LSTM-PINN with an exponential activation function for the chamber temperature has a more accurate prediction for the direct current fast charge (DCFC) test profile and similar prediction accuracy for the grade load (GL) 100 test profile. The root mean square errors (RMSEs) of the LSTM-PINN are 0.57°C for DCFC and 0.52°C for GL 100, respectively. In addition, having 55 neurons and 4 hidden layers gives the lowest prediction error. Furthermore, the improvement by having reversible heat generation is negligible. At last, the LSTM-PINN model has less prediction error than the LSTM model, especially when the battery temperature range is enormous.

No abstract