A Machine Learning Based Method to Efficiently Analyze the Cogging Torque Under Manufacturing Tolerances

Gerd Bramerdorfer; Werner Jara; Carlos Madariaga; Juan A. Tapia

A Machine Learning Based Method to Efficiently Analyze the Cogging Torque Under Manufacturing Tolerances

Gerd Bramerdorfer, Werner Jara, Carlos Madariaga, Juan A. Tapia

Institute of Electrical Drives and Power Electronics

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

This paper addresses a new technique based on machine learning which reduces the number of evaluations required to perform robustness analysis of permanent magnet synchronous machines. This methodology is based on the logical behavior of possible faulty magnet combinations produced by manufacturing tolerances. Groups of faulty combinations with a similar structure and cogging output are identified by means of a fuzzy-logic algorithm. Subsequently, only a single faulty combination of each group needs to be evaluated through the finite element method, which severely decreases the computational burden of the tolerance analysis. A 6-slot 4-pole and a 9-slot 6-pole machine were subject to tolerance analysis considering the displacement of the magnets. Both machines were evaluated through the proposed method and the results were validated by means of the finite element method (FEM).

Original language	English
Title of host publication	IEEE ECCE2021, Energy Conversion Congress and Expo, Vancouver, Canada
Number of pages	5
Publication status	Published - Oct 2021

Fields of science

202 Electrical Engineering, Electronics, Information Engineering
202009 Electrical drive engineering
202011 Electrical machines
202025 Power electronics
202027 Mechatronics

JKU Focus areas

Digital Transformation
Sustainable Development: Responsible Technologies and Management

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

@inproceedings{416d5712eef04834834697d1ceb54685,

title = "A Machine Learning Based Method to Efficiently Analyze the Cogging Torque Under Manufacturing Tolerances",

abstract = "This paper addresses a new technique based on machine learning which reduces the number of evaluations required to perform robustness analysis of permanent magnet synchronous machines. This methodology is based on the logical behavior of possible faulty magnet combinations produced by manufacturing tolerances. Groups of faulty combinations with a similar structure and cogging output are identified by means of a fuzzy-logic algorithm. Subsequently, only a single faulty combination of each group needs to be evaluated through the finite element method, which severely decreases the computational burden of the tolerance analysis. A 6-slot 4-pole and a 9-slot 6-pole machine were subject to tolerance analysis considering the displacement of the magnets. Both machines were evaluated through the proposed method and the results were validated by means of the finite element method (FEM).",

author = "Gerd Bramerdorfer and Werner Jara and Carlos Madariaga and Tapia, \{Juan A.\}",

year = "2021",

month = oct,

language = "English",

booktitle = "IEEE ECCE2021, Energy Conversion Congress and Expo, Vancouver, Canada",

}

TY - GEN

T1 - A Machine Learning Based Method to Efficiently Analyze the Cogging Torque Under Manufacturing Tolerances

AU - Bramerdorfer, Gerd

AU - Jara, Werner

AU - Madariaga, Carlos

AU - Tapia, Juan A.

PY - 2021/10

Y1 - 2021/10

N2 - This paper addresses a new technique based on machine learning which reduces the number of evaluations required to perform robustness analysis of permanent magnet synchronous machines. This methodology is based on the logical behavior of possible faulty magnet combinations produced by manufacturing tolerances. Groups of faulty combinations with a similar structure and cogging output are identified by means of a fuzzy-logic algorithm. Subsequently, only a single faulty combination of each group needs to be evaluated through the finite element method, which severely decreases the computational burden of the tolerance analysis. A 6-slot 4-pole and a 9-slot 6-pole machine were subject to tolerance analysis considering the displacement of the magnets. Both machines were evaluated through the proposed method and the results were validated by means of the finite element method (FEM).

AB - This paper addresses a new technique based on machine learning which reduces the number of evaluations required to perform robustness analysis of permanent magnet synchronous machines. This methodology is based on the logical behavior of possible faulty magnet combinations produced by manufacturing tolerances. Groups of faulty combinations with a similar structure and cogging output are identified by means of a fuzzy-logic algorithm. Subsequently, only a single faulty combination of each group needs to be evaluated through the finite element method, which severely decreases the computational burden of the tolerance analysis. A 6-slot 4-pole and a 9-slot 6-pole machine were subject to tolerance analysis considering the displacement of the magnets. Both machines were evaluated through the proposed method and the results were validated by means of the finite element method (FEM).

M3 - Conference proceedings

BT - IEEE ECCE2021, Energy Conversion Congress and Expo, Vancouver, Canada

ER -