Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021249617 - SORTING SYSTEM FOR SORTING OBJECTS BELONGING TO AT LEAST TWO CLASSES OF OBJECTS HAVING DIFFERENT ACOUSTIC SIGNATURES WHEN IMPACTING AN IMPACT BODY AND ASSOCIATED METHODS

Publication Number WO/2021/249617
Publication Date 16.12.2021
International Application No. PCT/EP2020/065866
International Filing Date 08.06.2020
IPC
B07C 5/34 2006.1
BPERFORMING OPERATIONS; TRANSPORTING
07SEPARATING SOLIDS FROM SOLIDS; SORTING
CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
5Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
34Sorting according to other particular properties
CPC
B07C 2501/0027
BPERFORMING OPERATIONS; TRANSPORTING
07SEPARATING SOLIDS FROM SOLIDS; SORTING
CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
2501Sorting according to a characteristic or feature of the articles or material to be sorted
0027Sorting the articles according to a sound
B07C 5/34
BPERFORMING OPERATIONS; TRANSPORTING
07SEPARATING SOLIDS FROM SOLIDS; SORTING
CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
5Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
34Sorting according to other particular properties
G06N 20/10
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
10using kernel methods, e.g. support vector machines [SVM]
G06N 20/20
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
20Ensemble learning
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 5/003
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
003Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
Applicants
  • COMMISSARIAT À L'ÉNERGIE ATOMIQUE ET AUX ÉNERGIES ALTERNATIVES [FR]/[FR]
  • NANYANG TECHNOLOGICAL UNIVERSITY [SG]/[SG]
Inventors
  • GABRIEL, Jean-Christophe
  • MAURICE, Ange
  • BRAMBILLA, Andreas
Agents
  • TANTY, François
Priority Data
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) SORTING SYSTEM FOR SORTING OBJECTS BELONGING TO AT LEAST TWO CLASSES OF OBJECTS HAVING DIFFERENT ACOUSTIC SIGNATURES WHEN IMPACTING AN IMPACT BODY AND ASSOCIATED METHODS
(FR) SYSTÈME DE TRI POUR TRIER DES OBJETS APPARTENANT À AU MOINS DEUX CATÉGORIES D'OBJETS PRÉSENTANT DES SIGNATURES ACOUSTIQUES DIFFÉRENTES LORS DE L'IMPACT AVEC UN CORPS D'IMPACT ET PROCÉDÉS ASSOCIÉS
Abstract
(EN) The present invention relates to a sorting system for sorting objects (100) belonging to at least two classes of objects having different acoustic signatures when impacting an impact body (50, 104), the system comprising: - at least one acoustic detector (60) configured to capture acoustic data corresponding to the impact of a candidate object (100) to sort on the impact body (50, 104), - a processor (66) for processing acoustic data to identify the class of the candidate object (100) executing a machine learning algorithm trained to identify the class to which a candidate object (100) belongs based on acoustic data of objects previously captured by the acoustic detector (60) and additional information describing said objects, and to generate a sorting information based on the identified class for the candidate object, - feedback means (80, 120) for providing to the processor (66) an additional information on the candidate object depending on the sorting information generated by the processor (66).
(FR) La présente invention concerne un système de tri pour trier des objets (100) appartenant à au moins deux catégories d'objets présentant des signatures acoustiques différentes lors de l'impact avec un corps d'impact (50, 104), le système comprenant : - au moins un détecteur acoustique (60) conçu pour capturer des données acoustiques correspondant à l'impact d'un objet candidat (100) à trier sur le corps d'impact (50, 104) ; - un processeur (66) pour traiter les données acoustiques afin d'identifier la catégorie de l'objet candidat (100) grâce à l'exécution d'un algorithme d'apprentissage automatique entraîné pour identifier la catégorie à laquelle appartient un objet candidat (100) sur la base de données acoustiques d'objets précédemment capturées par le détecteur acoustique (60) et d'informations supplémentaires décrivant lesdits objets, et pour générer des informations de tri sur la base de la catégorie identifiée pour l'objet candidat ; - des moyens de retour d'information (80, 120) pour fournir au processeur (66) des informations supplémentaires sur l'objet candidat en fonction des informations de tri générées par le processeur (66).
Latest bibliographic data on file with the International Bureau