Joachim Schaeffer
10 Papers
Joachim Schaeffer is an academic researcher. The author has contributed to research in topics: Computer science & Identifiability. The author has an hindex of 1, co-authored 3 publications.
Chat about Author
Papers
Machine Learning Benchmarks for the Classification of Equivalent Circuit Models from Electrochemical Impedance Spectra
Joachim Schaeffer,Paul Gasper,E. García-Tamayo,Raymond James Gasper,Masaki Adachi,Simon Montoya-Bedoya,Anoushka Bhutani,Andrew C. Schiek,Rolf Findeisen,Richard D. Braatz,Simon Engelke +10 more
TL;DR: In this article , a gradient-boosted tree model utilizing a library to automatically generate features, followed by a random forest model using the raw spectral data is presented as an alternative, although it achieves a lower accuracy.
Latent Variable Method Demonstrator - Software for Understanding Multivariate Data Analytics Algorithms
TL;DR: The Latent Variable Demonstrator (LAVADE) as mentioned in this paper is a tool for teaching, learning, and understanding latent variable methods such as Partial Least Squares (PLS), Principal Component Regression (PCR) with other regression methods, such as Least Absolute Shrinkage and Selection Operator (lasso), Ridge Regression, and Elastic Net (EN).
Fast Charging of Lithium-Ion Batteries While Accounting for Degradation and Cell-to-Cell Variability
Minsu Kim,Joachim Schaeffer,Marc D. Berliner,Berta Pedret Sagnier,Martin Z. Bazant,Rolf Findeisen,Richard D. Braatz +6 more
TL;DR: This study develops a fast charging strategy for lithium-ion batteries that accounts for cell-to-cell variability and degradation, using a polynomial chaos expansion to identify key parameters and reduce degradation factors, enabling faster charging with minimal degradation.
2
Interpretation of High-Dimensional Linear Regression: Effects of Nullspace and Regularization Demonstrated on Battery Data
Joachim Schaeffer,Eric Lenz,William C. Chueh,Martin Z. Bazant,Rolf Findeisen,Richard D. Braatz +5 more
TL;DR: In conclusion, the insights gained from the nullspace perspective help to make informed design choices for building regression models on high-dimensional data and reasoning about potential underlying linear models, which are important for system optimization and improving scientific understanding.
Learning Model Predictive Control Parameters via Bayesian Optimization for Battery Fast Charging
Sebastian Hirt,Andreas Höhl,Joachim Schaeffer,Johannes Pohlodek,Richard D. Braatz,Rolf Findeisen +5 more
TL;DR: Learning model predictive control parameters via Bayesian optimization for battery fast charging improves closed-loop performance and safety by directly optimizing controller parameters, establishing a hierarchical control framework, and ensuring safe operation while maximizing performance.
1