A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells

Abstract

Battery Management System (BMS) design for Lithium-ion batteries State of Charge (SoC) prediction has a crucial role in Electric Vehicles (EVs) and smart grids development. The need to design compact, light and fast devices requires finding a suitable trade-off between effectiveness and efficiency. In the literature, it is well emphasized that the application of electrochemical-based methods such as the Pseudo-Two-Dimensional (P2D) model is computationally prohibitive and requires significant simplifications. Conversely, plain Equivalent Circuit Models (ECM) are too simple and unable to represent the cell dynamics. The application of an Ensemble Neural Network (ENN) as Equivalent Neural Network Circuit (ENNC) emerged as a promising solution able to synthesize expressive and computationally efficient models. Indeed, with the support of a suitable dataset, an ENN can be configured to represent a given ECM, modeling each lumped parameter through an assigned Neural Network (NN). Accordingly, the ENNC system is able to keep a physical description of the battery cell while approximating the non-linear dynamic of each component. The paper proposes a novel ENNC battery named Physical Inspired-Equivalent Neural Network Circuit (PI-ENNC) whose ensemble architecture relies on a fractional-order Extended Single Particle (ESP) Lithium-ion cell formulation. The PI-ENNC is designed to approximate the ESP transfer functions referred to the ohmic effects, the electrolyte diffusion and the non-uniform charge distribution in the cell. The proposed model has been tested with three publicly available datasets, investigating the model behavior according to two different training strategies and with different input configurations. In order to prove its effectiveness, results have been compared with a simpler version proposed in a previous work. Results highlight the effectiveness of PI-ENNC in SoC prediction, underlining the importance of designing an ENN architecture that leverages on equations and constraints that reflect the physical phenomena of the cell.

Analytical computation of driving point impedance in mutually coupled inhomogeneous ladder networks

“…The ladder networks have found effective use in various biological applications, including the respiratory system, 35 DNA/RNA strings, 10 cancer prediction, 36 and neurons. 37 For instance, in respiratory physiology, the lung can be represented as a fractional model consisting of a bifurcation arborescent structure, further simplified into a cascade of gamma RLC cells. 35 These model parameters correspond to important physiological factors: Resistance represents turbulence viscosity energy losses, inductance accounts for moving air's inertial effects, and capacitance reflects the combined elasticity of lung tissue and air.…”

“…The ladder networks have found effective use in various biological applications, including the respiratory system, 35 DNA/RNA strings, 10 cancer prediction, 36 and neurons 37 . For instance, in respiratory physiology, the lung can be represented as a fractional model consisting of a bifurcation arborescent structure, further simplified into a cascade of gamma RLC cells 35 .…”

A Novel Methodology Based on a Deep Neural Network and Data Mining for Predicting the Segmental Voltage Drop in Automated Guided Vehicle Battery Cells

“…The proposed system was tested in real production conditions with an average absolute error of less than 1%. The authors of [56] developed a control system for lithium-ion batteries based on SOC prediction. They used a synthetic neural network system that was capable of maintaining the physical description of a battery by approximating the nonlinear dynamics of each component.…”

Prediction of Lithium Battery Health State Based on Temperature Rate of Change and Incremental Capacity Change

“…Energies 2023, 16, 7581 2 of 17 Currently, the primary methods for lithium battery health prediction are categorized into two main groups: model-based methods and data-driven methods [5]. The modelbased approach focuses mainly on analyzing the aging mechanism of lithium batteries by analyzing the states and variables inside the lithium batteries and establishing equivalent aging models using electronic components such as resistors, capacitors, and inductors [6,7]. However, since the lithium battery is a system integrated by a variety of complex physical and chemical reactions during operation, different lithium batteries are accompanied by different chemical reactions during operation due to the different electrode materials, diaphragms, and solutions.…”