Cambridge EnerTech’s
Battery Intelligence
(バッテリーインテリジェンス)
バッテリーデータのスマート分析機能による、新車発売・性能最適化・利潤率向上の促進
2023年6月21-22日
バッテリー市場の急速な成長と共に、その「一生涯の性能」を最適化する必要性も急速に拡大しています。自動車メーカーやバッテリーパックメーカー、EVフリート管理者などにとって、バッテリーの寿命を延ばすカギはデータにあります。機械学習やデータ分析の活用により、バッテリーデータの潜在力を引き出し、バッテリーの寿命を正確に測定・予測・改善することができます。人工知能がバッテリーの技術空間に破壊的影響をもたらすことから、バッテリーの効率性や運用上の信頼性を高めるには、予見的インテリジェンスやデータ分析が重要な役割を果たします。バッテリーインテリジェンスの部会では、業界のオピニオンリーダーや研究者が集結して、バッテリーの寿命を大幅かつ継続的に改善するために、バッテリーインテリジェンスを各企業がどう活用すれば良いのかについて議論します。
6月21日(水)
Registration Open12:40
Organizer's Remarks14:30
Victoria Mosolgo, Conference Producer, Cambridge EnerTech
MONITORING & SAFETY
モニタリング・安全性
Safety Risk Classification of Lithium-ion Batteries Based on Machine Learning Methodology
Jun Xu, PhD, Associate Professor, Mechanical Engineering & Engineering Science, University of North Carolina, Charlotte
Herein, we establish a battery safety risk classification modeling framework based on a machine learning algorithm that can accurately and rapidly classify the potential safety risk level. The model can identify defective cells, cells with internal short circuits (ISCs), and cells with possible thermal runaway (TR) using a small portion of one-cycle data. Classifiers in the ML model demonstrate satisfactory performance and robustness.

Stephan Rohr, PhD, Co-CEO, TWAICE Battery Analytics Platform
While virtual development and the use of simulations are increasingly adopted, combining the development phase with actual performance in the field remains difficult. Hybrid models are a unique technology that enable accurate development and in-life insights. As a result, the risks such as warranty cases can be mitigated and opportunities such as improved spare part management can be capitalized on. A current case from the automotive industry will be presented.
Refreshment Break in the Exhibit Hall with Poster Viewing16:00
LIFETIME & DEGRADATION
寿命と劣化
Advanced Model-Based Battery Lifetime Prediction for Vehicle Fleets
Alwin Tuschkan, Project Manager, IODP, AVL List GmbH
Make use of data from Battery Electric Vehicles. Use pre-trained data-driven models to analyze and optimize battery usage. Validate and verify the analysis, and prediction results by comparing them to simulation results of physics-based models and to battery test results by advanced event-driven data analytics.
Smart Battery Technology for Lifetime Improvement
Remus Teodorescu, PhD, Professor, IEEE Fellow, Villum Investigator, Aalborg University
The novel BMS concept of Smart Battery for transportation and grid storage with improved safety lifetime is introduced. The key feature is the bypass device, capable of cell-level load management with minimized load impact leading to pulsed current operation which is known to slow down degradation processes. An advanced AI-based lifetime optimizer capable of online training is recognizing the early signs of stress and inserts optimized relaxation time.
Synthetic Data Generation for Battery Degradation Prediction with Machine Learning
Weihan Li, Young Research Group Leader, RWTH Aachen University
In this work, we introduce a method for the synthetic generation of capacity fade curves based on limited battery test or operation data, aiming to augment the datasets used by data-driven models for degradation prediction. We validate our method by testing the performance of both a shallow machine learning and a deep learning model using different datasets incorporating realistic conditions such as cell-to-cell variations, measurement noise, varying charge-discharge conditions, and capacity recovery.
Session Wrap-Up
Jun Xu, PhD, Associate Professor, Mechanical Engineering & Engineering Science, University of North Carolina, Charlotte
Alwin Tuschkan, Project Manager, IODP, AVL List GmbH
One use case within AVLs Battery Life Cycle Management is the Battery Lifetime Prediction for Vehicle Fleets. Combining battery know-how and machine learning methods such as Long Short-Term Memory and Federated Learning the estimation of the state of health of a battery can be improved and even a prediction of future behavior is possible. The AVL Analytics Platform enables to make use of all data from vehicle fleets.
Networking Reception in the Exhibit Hall with Poster Viewing (Sponsorship Opportunity Available)17:50
Close of Day19:00
6月22日(木)
Registration and Morning Coffee08:30
Organizer's Remarks09:00
Victoria Mosolgo, Conference Producer, Cambridge EnerTech
MATERIALS DISCOVERY
資源の発見
Machine Learning-Driven Advanced Characterization of Battery Electrodes
Samuel J. Cooper, Senior Lecturer, Electrochemical Science & Engineering Group, Imperial College London
Advances in laboratory-based characterizationtechniques have yielded powerful insights into the structure-function relationship ofelectrodes, yet there is still far to go. Further improvements rely, in part, on gaining a deeperunderstanding of complex physical heterogeneities in the materials.
AI Accelerated Materials Discovery
Helge Stein, PhD, Tenure Track Professor, Applied Electrochemistry, Karlsruhe Institute of Technology
This presentation shows how to implement AI control in the lab and pilot plant, how we can measure materials acceleration, and ultimately demonstrate it for a couple of materials like electrodes, electrolytes, and some manufacturing processes. Our 10-30x acceleration is enabled by our unique platform for accelerated electrochemical energy storage research (PLACES/R) that covers the entire materials research value chain. Select discoveries will be shown on >100 cells.
Modeling of Solid-State Battery Materials with Machine Learning
Artrith Nongnuch, Assistant Professor, Materials Chemistry and Catalysis, Utrecht University
Here, we give an overview of recent methodological advancements of ML techniques for atomic-scale modeling and materials design. We review applications to materials for solid-state batteries, including electrodes, solid electrolytes, coatings, and the complex interfaces involved.
Session Wrap-Up
Samuel J. Cooper, Senior Lecturer, Electrochemical Science & Engineering Group, Imperial College London
In this talk, Sam will explain the various microstructural characterisation and analysis methods developed by his team, including some novel machine learning approaches. He will also propose a workflow for optimising the manufacturing parameters of these materials that use generative adversarial networks and Bayesian optimisation.
Coffee Break in the Exhibit Hall with Poster Viewing10:30
Online Control of Fast Charging of Lithium-ion Batteries Based on Monitoring of Internal Physical States Based on Physico-Chemical Models and Machine Learning
Dirk Uwe Sauer, Professor, Electrochemical Energy Conversion and Storage Systems, RWTH Aachen University
In this work, we introduce a method for the synthetic generation of capacity fade curves based on limited battery test or operation data, aiming to augment the datasets used by data-driven models for degradation prediction. We validate our method by testing the performance of both a shallow machine learning and a deep learning model using different datasets incorporating realistic conditions such as cell-to-cell variations, measurement noise, varying charge-discharge conditions, and capacity recovery.
Thermal Management and AI-Based Battery Management System for EV Application
Saeid Habibi, PhD, Professor Mechanical Engineering, Center for Mechatronics & Hybrid Technologies, McMaster University
This study presents a comprehensive review of the latest developments and technologies in battery design, thermal management, and the application of AI in Battery Management Systems (BMS) for Electric Vehicles (EV).
Sponsored Presentation (Opportunity Available)11:45
Networking Lunch12:25
Dessert Break in the Exhibit Hall with Poster Viewing - Last Chance for Viewing13:25
BIG DATA
ビッグデータ
Transforming Battery Data into Actionable Business Insight for the Automotive Industry
Tal Sholklapper, PhD, CEO & Co-Founder, Voltaiq, Inc.
Optimization of lifetime performance, early identification of anomalies during production, and description of the health of the fleet are just some of the imperative insights that a battery analytics solution should provide. Enterprise Battery Intelligence (EBI) leverages best-in-class battery data analytics to provide Automotive OEMs with a digital thread across their battery lifecycle. In this talk, we will discuss why this digital thread is business-critical and will provide use cases from the automotive industry.
Machine Learning for Lithium-ion Battery Manufacturing, Opportunities, and Challenges
Mona Faraji-Niri, Assistant Professor, Energy Systems, Energy Innovation Centre, University of Warwick
Estimating the state of health (SoH) of lithium-ion (Li-ion) batteries is a challenging task due to cross-coupling and dependency between aging mechanisms. An accurate estimation is particularly essential for second-life batteries to facilitate their successful implementation in the new application.
From Big Data to Actionable Battery Knowledge
Eibar J. Flores, Research Scientist, SINTEF Industry
Transforming battery data into operational decisions requires not only developing accurate machine learning (ML) models but also understanding how these models make predictions in the context of expert knowledge. In this contribution, we present our recent work on explainable machine learning applied to battery research, with an outlook on how semantic technologies - e.g., ontologies - can help to ingest the deluge of inputs, outputs, models, and patterns into actionable battery intelligence.
Coffee Break15:25
Sponsored Presentation (Opportunity Available)15:40
Can Advanced Lithium-ion Cell Production Data Simplify BMS Modeling?
Yue Guo, PhD, MBA, Professor of Battery Systems, Institute for Clean Growth and Future Mobility, Coventry University
Basic monitoring of the BMS is carried out by derived measurements during the validation of battery cells after development. The wide range of customer-specific and geographical usage profiles can only be tested or simulated in advance to a limited extent. For a comprehensive performance or health status, further metrics from the current cell state or effects from tolerable deviations from the target value during production and development are needed.
A Digital Twin for Inverse Design of Battery Manufacturing Processes
Close of Conference17:00
* 不測の事態により、事前の予告なしにプログラムが変更される場合があります。