| KEYWORD |
Area Engineering
Performance Comparison of Neural Network-Based Metamodels in Automated Storage and Retrieval Systems
keywords AUTOMATED TRANSPORT SYSTEMS; COMPARISON, INDUSTRIAL AUTOMATION, NEURAL NETWORKS, WAREHOUSE
Reference persons GIOVANNI ZENEZINI
External reference persons Andrea Ferrari
Research Groups www.reslog.polito.it
Thesis type RESEARCH, RESEARCH / EXPERIMENTAL
Description In the field of simulation and optimization techniques, there is a specialized area that involves the use of metamodels. A metamodel, in this context, is defined as a higher-level representation of an existing model. Building upon an existing discrete event simulation (DES) model for an automated storage and retrieval system (AS/RS) and a series of metamodels based on recurrent neural networks (RNNs), this thesis aims to extend the scope of these metamodels. The objective of the work is also to compare the performance of such metamodels.
Required skills • Proficiency in DES techniques and tools.
• Strong understanding of machine learning concepts, particularly artificial neural networks.
• Experience in languages like Python, especially for implementing and training neural networks using frameworks like TensorFlow or PyTorch.
• Skills in data analysis.
Deadline 07/10/2025
PROPONI LA TUA CANDIDATURA