Saehong Park

• University of California, Berkeley

This paper demonstrates a novel, compact-sized hardware-in-the-loop system, and its verification using machine learning and artificial intelligence features in battery controls. Conventionally, a battery management system involves algorithm development for battery modeling, estimation, and control. These tasks are typically validated by running the...

One of the most crucial challenges faced by the Li-ion battery community concerns the search for the minimum time charging without damaging the cells. This goal can be achieved by solving a large-scale constrained optimal control problem which relies on accurate electrochemical models. However, these models are limited by their high computational c...

This paper presents a provably convergent battery estimation scheme based on a single particle model with electrolyte dynamics (SPMe), by proposing a systematic methodology to estimate critical information such as electrode-level states, electrolyte dynamics, and cyclable lithium. Electrode-level state estimation suffers from weak observability ori...

This article presents a novel methodology for tractably solving optimal control and offline reinforcement learning (RL) problems for high-dimensional systems. This work is motivated by the ongoing challenges of safety, computation, and optimality in high-dimensional optimal control. We address these key questions with the following approach. First,...

A constrained feedback control strategy designed on the basis of a simplified electrochemical-thermal model is considered for the fast and healthy charging of a lithium-ion battery cell. The constraints ensure avoidance of side reactions and operating modes that yield premature aging (healthier charging). They are enforced through a reference gover...

We develop reinforcement learning (RL) boundary controllers to mitigate stop-and-go traffic congestion on a freeway segment. The traffic dynamics of the freeway segment are governed by a macroscopic Aw–Rascle–Zhang (ARZ) model, consisting of 2 $\times $ 2 quasi-linear partial differential equations (PDEs) for traffic density and velocity. The bou...

This paper presents a novel methodology for tractably solving optimal control problems for high-dimensional systems. This work is motivated by the ongoing challenge of computational complexity and optimality in high-dimensional non-convex optimal control. We address these key challenges with the following approach. First, we identify a surrogate mo...

One of the most crucial challenges faced by the Li-ion battery community concerns the search for the minimum time charging without irreversibly damaging the cells. This can fall into solving large-scale nonlinear optimal control problems according to a battery model. Within this context, several model-based techniques have been proposed in the lite...

Advanced Lithium-ion battery management systems rely on accurate cell-level state of charge (SOC) and parameter estimation for safe and efficient real-time monitoring. However, the design of combined state and parameter estimators that are provably convergent is notoriously difficult. A robust observer framework based on a coupled equivalent circui...

This article develops a Reinforcement Learning (RL) boundary controller of stop-and-go traffic congestion on a freeway segment. The traffic dynamics are governed by a macroscopic Aw-Rascle-Zhang (ARZ) model, consisting of $2\times 2$ nonlinear Partial Differential Equations (PDEs) for traffic density and velocity. The boundary actuation of traffic...

The poor performance of lithium-ion batteries in extreme temperatures is hindering their wider adoption in the energy sector. A fundamental challenge in battery thermal management systems (BTMSs) is that hot and cold environments pose opposite requirements: thermal transmission at high temperature for battery cooling, and thermal isolation at low t...

Batteries are ubiquitous. However, today’s batteries are expensive, range-limited, power-restricted, die too quickly, charge too slowly, and susceptible to safety issues. For this reason, model-based battery management systems (BMS) are of extreme interest. In this talk, we discuss eCAL’s open code for electrochemical-thermal battery models. Specif...

We consider the problem of optimally designing an excitation input for parameter identification of an electrochemical Li-ion battery model. The conventional approach to performing parameter identification uses standard test cycles. In contrast, we optimally design the input trajectory to maximize parameter identifiability in the sense of Fisher inf...

This paper examines a hybrid battery system modeling framework, where data-oriented recurrent neural network (RNN) and first-principle electrochemical battery model are combined. The data-driven RNN model captures un-modeled dynamics in the electrochemical model. We specifically study a simple RNN model called an Elman network, which has feedback l...

The advent of advanced metering infrastructure (AMI) generates a large volume of data related with energy service. This paper exploits data mining approach for customer baseline load (CBL) estimation in demand response (DR) management. CBL plays a significant role in measurement and verification process, which quantifies the amount of demand reduct...

In this paper we propose a framework of customer baseline load (CBL) estimation for demand response in Smart Grid. The introduction of demand response requires quantifying the amount of demand reduction. This process is called the measurement and verification. The proposed framework of CBL estimation is based on the unsupervised learning technique...