The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 19, 2026

Filed:

Dec. 15, 2021
Applicant:

Prima Industrie S.p.a., Collegno, IT;

Inventors:

Stefano Albrile, Collegno, IT;

Andrea Bertaldi, Collegno, IT;

Claudio Filippo Vitiello, Collegno, IT;

Luigi Nobile, Collegno, IT;

Valter Manuello, Collegno, IT;

Assignee:

PRIMA INDUSTRIE S.P.A., Collegno, IT;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G05B 19/406 (2006.01); G06T 7/00 (2017.01); G06T 11/00 (2006.01);
U.S. Cl.
CPC ...
G05B 19/406 (2013.01); G06T 7/0004 (2013.01); G06T 11/00 (2013.01); G05B 2219/31449 (2013.01); G06T 2207/20056 (2013.01); G06T 2207/20064 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01);
Abstract

A method of monitoring the state of industrial processing processes carried out by processing machines, in particular laser processing machines. The method comprises: sensing () a set of signals (R) representing parameters of the industrial process via a set of sensors (), wherein sensed signals (R1, R2, R3) of the set of signals (R) comprise signals indicative of said industrial process that vary in time; applying to one or more sensed signals (R1, R2, R3) of the set of sensed signals (R) a classification operation () to obtain as a result at least one classification signal (Q) indicative of a state of said industrial process; providing said at least one classification signal (Q) to an interface unit () to control the state of processing of said industrial process; and representing () signals among the sensed signals (R1, R2, R3) by applying a respective representation () of a set of representations () based on the membership of the signals among the sensed signals (R1, R2, R3) in a respective subset defined in said set of sensed signals (R) to produce corresponding digital images (Rhf, RIf, Rcf) that represent said sensed signals (R1, R2, R3). At least one first representation () of the set of representations () comprises representing signals of a subset (R1), which in particular comprises signals that vary in time, in an observation time window (K) via a map, in which one of the dimensions represented is time, and producing a corresponding first digital image (Rhf) of said set of digital images (Rhf, RIf, Rcf). The method comprises producing at least one composite image (Rf) via adding () to, in particular superimposition on, said first digital image (Rhf) one or more digital images (Rhf, Rcf, RIf) produced by signals of other subsets, and applying to said at least one composite image (Rf) said classification operation () to obtain at least one classification signal (Q) indicative of a state of said industrial process as a result of said classification operation ().


Find Patent Forward Citations

Loading…