Tractor manufacturers need to know how farmers use their agricultural tractors for an optimal machine design. Tractor usage is not easy to assess due to the large variability of field operations. However, modern tractors embed sensors integrated into the CAN-BUS network and their data is accessible through the ISO 11,783 protocol. Even though this technology has been available for a long time, the use of CAN-BUS data for outlining the tractor usage is still limited, because a proper post-processing method is lacking. This study aimed to present a novel classification scheme of CAN-BUS data which permits to outline the tractor usage. On a tractor, a CAN-BUS data logger and a GNSS receiver were installed, and real-world data were recorded for 579 h. Thus, data was obtained in the most realistic condition. Tractor positions were classified using GIS layers while operating conditions were classified depending on the usage of the tractor's subsystems. The method highlights that showed to be able to detect the 97% of the logged data and that the tractor operated on the field in working, on idle, and moving duties for 65%, 18% and 16% of the time, respectively. The method allows a far more precise outline of tractor usage opening opportunities to obtain large benefits from massively collected CAN-BUS data.

Outlining the mission profile of agricultural tractors through CAN-BUS data analytics

Mattetti M.
Writing – Original Draft Preparation
;
Maraldi M.
Writing – Review & Editing
;
Molari G.
Writing – Original Draft Preparation
2021

Abstract

Tractor manufacturers need to know how farmers use their agricultural tractors for an optimal machine design. Tractor usage is not easy to assess due to the large variability of field operations. However, modern tractors embed sensors integrated into the CAN-BUS network and their data is accessible through the ISO 11,783 protocol. Even though this technology has been available for a long time, the use of CAN-BUS data for outlining the tractor usage is still limited, because a proper post-processing method is lacking. This study aimed to present a novel classification scheme of CAN-BUS data which permits to outline the tractor usage. On a tractor, a CAN-BUS data logger and a GNSS receiver were installed, and real-world data were recorded for 579 h. Thus, data was obtained in the most realistic condition. Tractor positions were classified using GIS layers while operating conditions were classified depending on the usage of the tractor's subsystems. The method highlights that showed to be able to detect the 97% of the logged data and that the tractor operated on the field in working, on idle, and moving duties for 65%, 18% and 16% of the time, respectively. The method allows a far more precise outline of tractor usage opening opportunities to obtain large benefits from massively collected CAN-BUS data.
2021
Mattetti M.; Maraldi M.; Lenzini N.; Fiorati S.; Sereni E.; Molari G.
File in questo prodotto:
File Dimensione Formato  
Outlining the mission profile of agricultural tractors through CAN-BUS data analytics.pdf

accesso riservato

Tipo: Versione (PDF) editoriale
Licenza: Licenza per accesso riservato
Dimensione 3.83 MB
Formato Adobe PDF
3.83 MB Adobe PDF   Visualizza/Apri   Contatta l'autore
postprint 832181.pdf

Open Access dal 22/03/2023

Tipo: Postprint
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale - Non opere derivate (CCBYNCND)
Dimensione 1.44 MB
Formato Adobe PDF
1.44 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/832181
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 23
  • ???jsp.display-item.citation.isi??? 15
social impact