IP Library › Granted Patent US 12,340,493
Granted Patent B2
US 12,340,493 · App. 17/297,572 · Granted Jun 24, 2025

Centralized analytics of multiple visual inspection appliances

Inventors: Yonatan Hyatt (Tel-Aviv, IL); Harel Boren (Givat Shmuel, IL)
Assignee: Siemens Aktiengesellschaft
G06T7/0004G05B19/41875G08B5/22G05B2219/32181G06T2207/30108H04N23/56H04N23/60
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,340,493
App. No.
17/297,572
Granted
Jun 24, 2025
Kind
B2
Abstract

A visual inspection data collection and analysis system comprising: a plurality of visual inspection appliances (VTA) configured to inspect and acquire visual inspection data relating to inspected items; and a data collection and analytics server (DCAS) configured to receive information comprising the visual inspection data from the multiple VIAs and to analyze the received information to form a big data analysis. The VIAs are adapted for detecting defects or gating or counting the inspected items without the involvement of the DCAS.

Claims (76)

1. A visual inspection data collection and analysis system, comprising:

a. a plurality of visual inspection appliances (VIA) configured to acquire visual inspection data relating to inspected items, each of the plurality of VIAs comprising a flexible mounting assembly, an inspection camera, a lighting source and a controller, the inspection camera and the lighting source being connected to and controlled by the controller; and

b. a data collection and analytics server (DCAS) in communication with the plurality of VIAS over a communications network and configured to:

receive the visual inspection data from at least one of said multiple VIAs;

automatically detect and register under a unique identifier a new VIA connecting to the network, based on a signal sent over the network from either one or both of the new VIA and DCAS;

receive visual inspection data from the new VIA; and

initiate an activity in the new VIA based on the unique identifier;

wherein defect free items are processed in a setup stage in which the controller learns parameters of the defect free items captured in images obtained by the inspection camera.

2. The system of claim 1 , wherein the activity comprises one or a combination of: collecting visual inspection data, timing collection of the visual inspection data, storing received data, analysis of the received data and issuing reports.

3. The system of claim 1 , wherein the activity is selected from the group consisting of one or a combination of:

a. DCAS checks operational status of the new VIA;

b. DCAS checks software version running on the new VIA;

c. DCAS checks security status of the new VIA;

d. DCAS accesses a real-time view of an inspected item from the new VIA;

e. DCAS requests specific data from the new VIA;

f. DCAS changes inspection or other settings of the new VIA

g. DCAS performs software upgrades to the new VIA;

h. DCAS initiates inspection to be performed by the new VIA;

i. DCAS changes a region of interest to be inspected by the new VIA;

j. DCAS initiates re-inspection of previously inspected items; and

k. DCAS initiates re-inspection of previously inspected items with changed inspection parameters.

4. The system of claim 1 , wherein the DCAS is configured to receive the visual inspection data from the plurality of VIAS and to analyze said received information to form a big data analysis.

5. The system of claim 4 , wherein the inspected items are different types of items.

6. The system of claim 5 , wherein the big data analysis comprises a combination of information related to the different types of items.

7. The system of claim 4 , further comprising:

a display;

wherein said DCAS outputs said analysis to said display.

8. The system of claim 4 , wherein said analysis is selected from the group consisting of:

a. root cause analysis of detected defects;

b. predictive maintenance analysis;

c. intensity of defects;

d. significance of defects;

e. analysis of product deviations from ideal that are not defects but indicate a trend towards decreasing quality;

f. analysis of defect shape, area and type of defect;

g. cost of defect;

h. product recall, latent product fault vs. defect or product deviation history analysis;

i. supplier analysis comparing product raw material suppliers vs defects; and

j. relationship analysis between different production stages of a same item.

9. The system of claim 4 , wherein said DCAS is configured to issue reports based on received inspection data; and

wherein said reports are selected from the group consisting of:

a. % defects detected per item;

b. defect report including images of item showing where defects were detected;

c. % defects detected per manufacturing area;

d. number of items inspected per period of time;

e. personnel vs item defect report;

f. % defects per shift;

g. % defects per manufacturing type;

h. % defects per defect type;

i. defect report per period of time and production area; and

j. a combination of the above.

10. The system of claim 4 ; wherein said DCAS is configured to store said received visual inspection data; and wherein the stored inspection data is searchable.

11. The system of claim 10 , wherein said DCAS is configured to execute third-party applications to produce analyses and reports based on said stored inspection data.

12. The system of claim 4 , wherein said DCAS is configured to issue alerts based on said analysis.

13. The system of claim 1 , wherein the visual inspection data from each of the plurality of VIAs is selected from the group consisting of:

a. images of an inspected item;

b. record of decision by VIA whether an item has a defect;

c. image of the defects;

d. number of defects;

e. records of deviations from good item samples which are not significant enough to be reported as defects but can imply issues in a production line;

f. item unique ID;

g. plant work/job order;

h. batch ID,

i. personnel in charge of a production line or station;

j. production tool ID;

k. part name;

l. part serial number;

m. production tool ID; and

n. a combination of the above.

14. The system of claim 1 , wherein said visual inspection data is communicated from a VIA to said DCAS in accordance with timing selected from the group consisting of:

a. after inspection of each item by each VIA;

b. after inspection of a configurable number of items per VIA;

c. after a configurable period of time per VIA;

d. based on a date schedule;

e. based on a time of day schedule; and

f. a combination of the above.

15. The system of claim 1 , wherein the controller utilizes machine learning/artificial intelligence (AI) and computer vision algorithms to analyze the images and to create a representation of the defect free items for at least one of defect detection, gating, sorting and other inspection tasks on a production line.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 9, 2024
From: INSPEKTO A.M.V. LTD.
To: SIEMENS AKTIENGESELLSCHAFT
Reel/Frame 067938/0517 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 11, 2023
From: HYATT, YONATAN; BOREN, HAREL
To: INSPEKTO A.M.V. LTD.
Reel/Frame 063608/0861 →
Priority Claims (1)
IL 263399 · Nov 29, 2018 · national
Continuity (2)
Provisional Application 62772758 · Nov 29, 2018
Related Publication 20210398267A1 · Dec 23, 2021
References Cited (30)
US 6661931B1 · Kawada · 2003 [cited by applicant]
US 9224070B1 · Sundareswara et al. · 2015 [cited by applicant]
US 20020180960A1 · Katz · 2002 [cited by applicant]
US 20030182251A1 · Kim et al. · 2003 [cited by applicant]
US 20060104788A1 · Ban · 2006 [cited by examiner]
US 20100215246A1 · Albeck et al. · 2010 [cited by applicant]
US 20110069179A1 · Bathiche · 2011 [cited by examiner]
US 20120128230A1 · Meada · 2012 [cited by applicant]
US 20120154607A1 · Moed et al. · 2012 [cited by applicant]
US 20120155741A1 · Shibuya · 2012 [cited by applicant]
US 20130202200A1 · Evan · 2013 [cited by applicant]
US 20150064813A1 · Ayotte · 2015 [cited by applicant]
US 20150131116A1 · Sochi · 2015 [cited by applicant]
US 20150138325A1 · Seo · 2015 [cited by examiner]
US 20170324933A1 · Alrod · 2017 [cited by examiner]
US 20180276811A1 · Wen et al. · 2018 [cited by applicant]
US 20180356804A1 · Oka · 2018 [cited by examiner]
US 20180374022A1 · Wang · 2018 [cited by examiner]
US 20180374207A1 · Niculescu-Mizil · 2018 [cited by examiner]
US 20190073760A1 · Wang · 2019 [cited by examiner]
US 20190360942A1 · Kano · 2019 [cited by examiner]
US 20190362480A1 · Diao · 2019 [cited by examiner]
US 20190362486A1 · Diao · 2019 [cited by examiner]
US 20200141908A1 · Bingham · 2020 [cited by examiner]
US 20210014308A1 · Larsson · 2021 [cited by examiner]
US 20210232126A1 · Feyo Gebhard · 2021 [cited by examiner]
KR 101688458 · 2016 [cited by applicant]
WO 2016083897A2 · 2016 [cited by applicant]
Park, et al., “Machine Learning-Based Imaging System for Surface Defect Inspection,” International Journal of Precision Engineering and Manufacturing—Green Technology, Jul. 10, 2016, pp. 303-310, vol. 3, No. 3, Springer… [cited by applicant]
Natsagdorj et al. Vision-based assembly and inspection system for golf club heads, Robotics and Integrated Manufacturing, Apr. 2015, pp. 83-92, vol. 32, Elsevier Ltd., Amsterdam, Netherlands. [cited by applicant]