
Elisa Cascina
Data-Driven Optimization of Vehicle Systems Enabled by a Centralized CAN Protocol Management.
Rel. Paolo Garza. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2025
Abstract: |
The increasing complexity of modern vehicles demands robust data management and analytical frameworks to enhance performance and efficiency. The first part of this work focuses on developing a comprehensive and centralized CAN Database, designed to efficiently store and decode vehicle communication data. The CAN protocol enables real-time data exchange between Electronic Control Units (ECUs), ensuring seamless vehicle operation. Beyond improving data traceability, consistency, and accessibility across all divisions, this resource enhances vehicle system analysis, supports compliance with industry standards, and facilitates future innovations. The second part of the thesis supports Toyota Motor Corporation’s (TMC Japan) data analysis efforts by comprehensively examining European driving conditions. Extensive coding pipelines were developed to process and analyze large volumes of data, addressing four specific use cases. Three of these focus on various aspects of braking system performance, including the interaction between regenerative braking and conventional friction brakes, as well as the assessment of current brake specifications and their compatibility with small vehicles and next-generation regenerative braking technologies. The goal is to maximize energy recovery during braking phases, enhance overall system efficiency, set new performance targets, and ensure safety and reliability across diverse driving scenarios. Furthermore, the study on road sign distribution investigates the spatial distribution and recognition of traffic signs, which has direct implications for improving the effectiveness of Road Sign Assistance (RSA) systems. By integrating structured data management with advanced analytics, this thesis bridges the gap between vehicle communication and braking system optimization. The findings contribute to improving regenerative braking strategies, refining CAN data interpretation, and enhancing the interaction between vehicles and their surrounding infrastructure. |
---|---|
Relatori: | Paolo Garza |
Anno accademico: | 2024/25 |
Tipo di pubblicazione: | Elettronica |
Numero di pagine: | 100 |
Informazioni aggiuntive: | Tesi secretata. Fulltext non presente |
Soggetti: | |
Corso di laurea: | Corso di laurea magistrale in Data Science And Engineering |
Classe di laurea: | Nuovo ordinamento > Laurea magistrale > LM-32 - INGEGNERIA INFORMATICA |
Aziende collaboratrici: | Toyota Motor Europe |
URI: | http://webthesis.biblio.polito.it/id/eprint/35365 |
![]() |
Modifica (riservato agli operatori) |