Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 3
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

The problem of lithium-ion cells, which degrade in time on their own and while used, causes a significant decrease in total capacity and an increase in inner resistance. So, it is important to have a way to predict and simulate the remaining usability of batteries. The process and description of cell degradation are very complex and depend on various variables. Classical methods are based, on the one hand, on fitting a somewhat arbitrary parametric function to laboratory data and, on the other hand, on electrochemical modelling of the physics of degradation. Alternative solutions are machine learning ones or nonparametric ones like support-vector machines or the Gaussian process (GP), which we used in this case. Besides using the GP, our approach is based on current knowledge of how to use non-parametric approaches for modeling the electrochemical state of batteries. It also uses two different ways of dealing with GP problems, like maximum likelihood type II (ML-II) methods and the Monte Carlo Markov Chain (MCMC) sampling.
Go to article

Authors and Affiliations

Adrian Dudek
1
ORCID: ORCID
Jerzy Baranowski
1
ORCID: ORCID

  1. Department of Automatic Control and Robotics, AGH University of Science and Technology, Kraków, Poland
Download PDF Download RIS Download Bibtex

Abstract

Compared with the robots, humans can learn to perform various contact tasks in unstructured environments by modulating arm impedance characteristics. In this article, we consider endowing this compliant ability to the industrial robots to effectively learn to perform repetitive force-sensitive tasks. Current learning impedance control methods usually suffer from inefficiency. This paper establishes an efficient variable impedance control method. To improve the learning efficiency, we employ the probabilistic Gaussian process model as the transition dynamics of the system for internal simulation, permitting long-term inference and planning in a Bayesian manner. Then, the optimal impedance regulation strategy is searched using a model-based reinforcement learning algorithm. The effectiveness and efficiency of the proposed method are verified through force control tasks using a 6-DoFs Reinovo industrial manipulator.

Go to article

Authors and Affiliations

C. Li
Z. Zhang
G. Xia
X. Xie
Q. Zhu
Download PDF Download RIS Download Bibtex

Abstract

This paper presents a probabilistic machine learning approach to approximate wavelength values for unmeasured positions on an opto-semiconductor wafer after epitaxy. Insufficient information about optical and opto-electronic properties may lead to undetected specification violations and, consequently, to yield loss or may cause product quality issues. Collection of information is restricted because physical measuring points are expensive and in practice samples are only drawn from 120 specific positions. The purpose of the study is to reduce the risk of uncertainties caused by sampling and measuring inaccuracy and provide reliable approximations. Therefore, a Gaussian process regression is proposed which can determine a point estimation considering measuring inaccuracy and further quantify estimation uncertainty. For evaluation, the proposed method is compared with radial basis function interpolation using wavelength measurement data of 6-inch InGaN wafers. Approximations of these models are evaluated with the root mean square error. Gaussian process regression with radial basis function kernel reaches a root mean square error of 0.814 nm averaged over all wafers. A slight improvement to 0.798 nm could be achieved by using a more complex kernel combination. However, this also leads to a seven times higher computational time. The method further provides probabilistic intervals based on means and dispersions for approximated positions.
Go to article

Authors and Affiliations

Stefan M. Stroka
1 2
ORCID: ORCID
Christian Heumann
1
ORCID: ORCID
Fabian Suhrke
2
Kathrin Meindl
2

  1. Department of Statistics, Faculty of Mathematics, Informatics and Statistics, LMU Munich, 80539 Munich, Germany
  2. ams-OSRAM International GmbH, 93055 Regensburg, Germany

This page uses 'cookies'. Learn more