Granted Patent B2

US 12,746,578 · App. 17/919,079 · Granted Sep 29, 2026

Inventor: Roeland Geurts (Mol, BE)

Assignee: VITO NV

B07C5/342B09B5/00G06V10/58G06V10/70G06V10/774G06V10/776G06V20/40

Abstract

Claims (30)

1 . A method for training a machine learning model configured to perform characterization of components in a heterogeneous material stream with a plurality of unknown components, the method comprising:

scanning the material stream by imaging of the material stream with the plurality of unknown components;

predicting one or more prediction labels and associated label prediction probabilities for each of the unknown components in the material stream by a machine learning model which is configured to receive as input the imaging of the material stream and/or one or more features of the unknown components extracted from the imaging of the material stream;

determining a training reward associated with each unknown component within the plurality of unknown components in the material stream;

determining a value associated with each unknown component that is indicative of a difficulty for performing physical isolation of the unknown component from the material stream by a separator unit;

selecting a top number of unknown components from the plurality of unknown components in the material stream based on the training reward associated with the unknown components;

selecting at least one unknown component from the top number of unknown components based at least partially on the value indicative of the difficulty for performing physical isolation, wherein the selected at least one unknown component is physically isolated from the material stream by the separator unit, wherein the separator unit is configured to move the selected at least one unknown component to a separate accessible compartment;

analyzing the isolated at least one unknown component by an analyzing unit automatically performing a characterization of the isolated at least one unknown component within the separate accessible compartment for determining a ground truth label thereof, wherein the determined ground truth label of the isolated at least one unknown component is added to a training database; and

training an incremental version of the machine learning model using the determined ground truth label of the physically isolated at least one unknown component;

wherein the analyzing unit performs the characterization by subjecting the isolated at least one unknown component to an automated chemical analysis for determining the ground truth label at least partially based thereon.

2 . The method according to claim 1 , wherein the machine learning model is configured to receive as input one or more user-defined features of the unknown components extracted from the imaging of the material stream, and wherein user-generated selection criteria for the selection of components are employed.

3 . The method according to claim 1 , wherein the separator unit has at least a first separation device and a second separation device, wherein one of the first or second separation device is selected for physical isolation of the selected at least one unknown component based on the one or more features of the unknown components extracted from the imaging of the material stream.

4 . The method according to claim 3 , wherein the first separation device is used for physical isolation of smaller and/or lighter components in the material stream, and the second separation device is used for physical isolation of larger and/or heavier components in the material stream.

5 . The method according to claim 3 , wherein the first separation device is configured to isolate components by directing a fluid jet towards the components in order to blow the components to the separate accessible compartment, and wherein the second separation device is configured to isolate components by a mechanical manipulation device.

6 . The method according to claim 5 , wherein a resulting force induced by the fluid jet is adjusted based on the mass of the selected at least one unknown component.

7 . The method according to claim 1 , wherein for each unknown component in the material stream data indicative of a mass is calculated.

8 . The method according to claim 1 , wherein the separate accessible compartment enables a manual removal of the isolated unknown component, wherein an indication of an internal reference of the machine learning model is provided for the isolated unknown component within the separate accessible compartment, wherein the analysis of the at least one selected unknown component is performed at least partially by human annotation.

9 . The method according to claim 1 , wherein the characterization is by destructive measurements on the isolated at least one unknown component for determining the ground truth label at least partially based thereon.

10 . The method according to claim 1 , wherein the one or more features relate to at least one of a volume, dimension, diameter, shape, texture, color, or eccentricity.

11 . A system for training a machine learning model which is configured to perform characterization of components in a heterogeneous material stream with a plurality of unknown components, the system including a processor, a computer readable storage medium, a sensory system, an analyzing unit and a separator unit, wherein the computer readable storage medium has instructions stored which, when executed by the processor, result in the processor performing operations comprising:

operating the sensory system to scan the material stream such as to perform imaging of the material stream with the plurality of unknown components;

predicting one or more labels and associated label probabilities for each of the unknown components in the material stream by a machine learning model which is configured to receive as input the imaging of the material stream and/or one or more features of the unknown components extracted from the imaging of the material stream;

determining a training reward associated with each unknown component within the plurality of unknown components in the material stream;

determining a value associated with each unknown component that is indicative of a difficulty for performing physical isolation of the unknown component from the material stream by-the separator unit;

selecting a top number of unknown components from the plurality of unknown components in the material stream based on the training reward associated with the unknown components;

selecting at least one unknown component from the top number of unknown components based at least partially on the value indicative of the difficulty for performing physical isolation;

operating the separator unit for physically isolating the selected at least one unknown component from the material stream, wherein the separator unit is configured to move the selected at least one unknown component to a separate accessible compartment;

receiving for the isolated at least one unknown component a ground truth label determined by the analyzing unit automatically performing an characterization of the isolated at least one unknown component within the separate accessible compartment, wherein the determined ground truth label of the isolated at least one unknown component is added to a training database; and

training an incremental version of the machine learning model using the determined ground truth label of the physically isolated at least one unknown component;

wherein the analyzing unit is configured to perform the characterization by subjecting the isolated at least one unknown component to an automated chemical analysis for determining the ground truth label at least partially based thereon.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (41)