Hello, this is the Users Conference secretariat.
We are pleased to announce the 27th JMAG Users Conference.
We are pleased to announce the 27th JMAG Users Conference.
JSOL Corporation would like the Users Conference each year to be an opportunity for users to communicate and share ideas.
A wealth of content will be provided to satisfy a range of skill levels including JMAG wizards and beginners, as well as those who have not yet participated in the Users Conference.
We have also prepared lecture sessions for our customers who have less than 3 years of experience since first using JMAG.
These presentations will be immensely helpful for those who are yet to have a long history of JMAG under their belts, as well as for those who will be looking to use JMAG in the foreseeable future. Discussions will touch on hurdles that users may encounter in their initial introductions to JMAG, which will also be accompanied by a number of analysis case studies.
For those who have not yet joined us, those who could not participate in the previous year, those who have not attended for several years, and those who join us every year – we welcome all of you.
We look forward to seeing new and familiar faces!
Schedules
| MON | TUE | WED | THU | FRI |
| 23 Nov | 24 | 25 | 26 | 27 |
| Loss 1V20 | Multi-Objective Optimization | Material (Magnet) | Material (Core)Loss 2 | |
| JMAG Seminar (Japanese only) | ||||
| 30 | 1 Dec | 2 | 3 | 4 |
| MBD | Topology optimization | Efficiency mapPresentations by JMAG developers | Multiphysics | MultiphysicsNoise/Vibration |
| JMAG Seminar (Japanese only) | ||||
| Academic Poster Session | ||||
| Exhibitors | ||||
Keynote Speech
AI technology with aid of data-driven method makes EM simulation and optimization more effective
Graduate School of Information Science and Technology, Hokkaido University
Prof. Igarashi, Hajime
This talk presents the various methods based on AI, in a broad sense, and data-driven methods that make EM simulations and optimizations more effective.
As a first topic, the speaker will introduce the motor design based on topology optimization and its acceleration using deep learning. Then, the speaker will focus on the surrogate models such as neural networks and response surface methods that can evaluate the machine properties much faster than the finite element method. Some case examples of the surrogate methods will be presented showing that they actually make the optimal computations much faster. Finally, the speaker will talk about the data-driven methods in which the big data obtained through EM simulations are effectively used to reduce the size of the finite element equations. This approach also makes it possible to effectively evaluate various motor properties such as loss and torque ripples through the behavior model.
As a first topic, the speaker will introduce the motor design based on topology optimization and its acceleration using deep learning. Then, the speaker will focus on the surrogate models such as neural networks and response surface methods that can evaluate the machine properties much faster than the finite element method. Some case examples of the surrogate methods will be presented showing that they actually make the optimal computations much faster. Finally, the speaker will talk about the data-driven methods in which the big data obtained through EM simulations are effectively used to reduce the size of the finite element equations. This approach also makes it possible to effectively evaluate various motor properties such as loss and torque ripples through the behavior model.
Overview
General Admission: ¥50,000 (without tax)