EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3977. A Digital Twin-driven approach for the mixed load palletizing problem.
Invited abstract in session MC-7: Cutting and Packing 3 - 3D loading, stream Cutting and Packing (ESICUP).
Monday, 12:30-14:00Room: 1019 (building: 202)
Authors (first author is the speaker)
1. | António Ramos
|
INESC TEC, ISEP, Polytechnic of Porto | |
2. | Pedro Rocha
|
INESCTEC and School of Engineering, Polytechnic of Porto | |
3. | Fábio Moreira
|
INESC TEC, INEGI, Faculty of Engineering, University of Porto | |
4. | Manuel Lopes
|
INESC TEC and School of Engineering, Polytechnic of Porto |
Abstract
The problem of preparing mixed pallets is one of the main challenges in automating tasks in distribution centers. Whether it's the intrinsic complexity of packaging problems or the need to incorporate physical constraints such as stability and interference between cargo and robots in solving methods, traditional approaches to the problem tend to fall short of real-world needs.
In this work we propose an approach based on Digital Twins. A Digital Twin is a dynamic virtual representation of a physical object or system that uses real-world data, simulation models and/or machine learning.
The framework of our Digital Twin is based on three main components: classic optimization tools; physics engines; and machine learning.
A physics engine is a software system that simulates Newtonian physics in a simulated environment, including collision detection, rigid body dynamics and soft body dynamics.
In our Digital Twin framework, packing solutions are generated using classical optimization tools, the physical behavior of which is then simulated in the physics engine. Both results feed the machine learning model so that it acquires the knowledge needed to build solutions that can be used in the real world.
Keywords
- Logistics
- Industrial Optimization
- Simulation
Status: accepted
Back to the list of papers