Physics-Informed Neural Networks for State of Health Estimation in Lithium-Ion Batteries

Abstract

One of the most challenging tasks of modern battery management systems is the accurate state of health estimation. While physico-chemical models are accurate, they have high computational cost. Neural networks lack physical interpretability but are efficient. Physics-informed neural networks tackle the aforementioned shortcomings by combining the efficiency of neural networks with the accuracy of physico-chemical models. A physics-informed neural network is developed and evaluated against three different datasets: A pseudo-two-dimensional Newman model generates data at various state of health points. This dataset is fused with experimental data from laboratory measurements and vehicle field data to train a neural network in which it exploits correlation from internal modeled states to the measurable state of health. The resulting physics-informed neural network performs best with the synthetic dataset and achieves a root mean squared error below 2% at estimating the state of health. The root mean squared error stays within 3% for laboratory test data, with the lowest error observed for constant current discharge samples. The physics-informed neural network outperforms several other purely data-driven methods and proves its advantage. The inclusion of physico-chemical information from simulation increases accuracy and further enables broader application ranges.

Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis

“…Among them, an obvious feature of the Sequential Integration method is that the physical model and the machine learning model are standalone, while the Hybrid method fuses the two together. Within this framework, some works has been published 39 – 43 . Nascimento et al 39 directly implemented the numerical integration of principle-based governing equations through recurrent neural networks to simulate the dynamic response of the battery.…”

“…Wang et al 42 proposed a battery neural network (BattNN) for discharge voltage prediction based on the equivalent circuit model (ECM). Hofmann et al 43 used the pseudo-two-dimensional (P2D) Newman model to generate data at different health status points and combined it with experimental data and field data to train the neural network model, which takes advantage of the correlation between internal states and measurable SOH. According to the categories proposed by Aykol et al 38 , these methods belong to the A2 40 , 41 , 43 and A3 39 , 42 categories.…”

Method for Evaluating Degradation of Battery Capacity Based on Partial Charging Segments for Multi-Type Batteries

“…Wen et al [13] proposed a semi-physical and semi-empirical dynamic model to capture the capacity degradation of batteries, and based on this, they introduced a PINN to fuse the prior information of the dynamic model with the information extracted from monitoring data. Hofmann et al combined simulated data generated by the pseudo-2-dimensional (P2D) model with real-world data for datadriven model training to reduce the computational cost of traditional physical and chemical models [14].…”

Data-Driven Diagnosis of PV-Connected Batteries: Analysis of Two Years of Observed Irradiance

“…This lack of diversity can be alleviated by supplementing experimental data with synthetic data and leveraging the benefits of transfer learning [15]. Besides physic-based models [16][17][18][19][20][21], the other main modeling approach considered for generating synthetic data is the mechanistic approach [22][23][24]. Because this approach simulates the impact of degradation modes [24,25] rather than trying to replicate every possible degradation, it offers fast simulations with high fidelity, making it an excellent candidate to simulate a large number of data samples.…”