IP Library › Granted Patent US 11,630,444
Granted Patent B2
US 11,630,444 · App. 17/107,738 · Granted Apr 18, 2023

Artificial Intelligence empowered industrial Internet of Things

Inventors: Xinlin Wang (Irvine, CA); Guo Qiang Hu (Shanghai, CN); Peng Ji (Nanjing, CN); Jun Zhu (Shanghai, CN)
Assignee: International Business Machines Corporation
G05B19/41835G05B13/0265G06N5/04G06N20/00G05B2219/31368
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 11,630,444
App. No.
17/107,738
Granted
Apr 18, 2023
Kind
B2
Abstract

In an approach to AI empowered factory automation using an industrial IoT, responsive to receiving a new production task, production requirements are input into an AI engine. Equipment and software containers are selected based on the AI model. An orchestration service is created, where the orchestration service collaborates the equipment and the software containers.

Claims (62)

1. A computer-implemented method for factory automation, the computer-implemented method comprising:

responsive to receiving a new production task, inputting, by one or more computer processors, one or more production requirements into an Artificial Intelligence (AI) engine;

selecting, by the one or more computer processors, one or more equipment and one or more software containers based on output data from the AI engine;

extracting, by the one or more computer processors, one or more AI models from one or more robot software functions controlled by one or more robots;

detaching, by the one or more computer processors, one or more sensor functions from the one or more robots;

deploying, by the one or more computer processors, the one or more robot software functions, the one or more AI models, and the one or more detached sensor functions in the selected one or more software containers on an edge cloud; and

creating, by the one or more computer processors, an orchestration service, wherein the orchestration service collaborates the one or more equipment and the one or more software containers.

2. The computer-implemented method of claim 1 , further comprising:

recording, by the one or more computer processors, a history usage of each container of the one or more containers; and

updating, by the one or more computer processors, each AI model of the one or more AI models based on the history usage.

3. The computer-implemented method of claim 1 , further comprising:

creating, by the one or more computer processors, a context service, wherein the context service maintains a spatial context and a temporal context for each equipment of the one or more equipment.

4. The computer-implemented method of claim 1 , further comprising:

extracting, by the one or more computer processors, a Quality of Service (QoS) requirement and a network traffic profile for each container of the one or more containers;

calculating, by the one or more computer processors, a required network bandwidth for each container of the one or more containers, wherein the required network bandwidth is based on the QoS requirement and the traffic profile; and

storing, by the one or more computer processors, the required network bandwidth as metadata in each container of the one or more containers.

5. The computer-implemented method of claim 1 , wherein selecting the one or more equipment and the one or more software containers based on the AI engine further comprises:

selecting, by the one or more computer processors, a specific equipment from the one or more equipment, wherein the specific equipment is selected based on the production requirements and one or more attached sensors; and

determining, by the one or more computer processors, a specific version of one software container of the one or more software containers, wherein the specific version of one software container is determined by a physical location of the specific equipment.

6. The computer-implemented method of claim 1 , further comprising an AI-based automatic calibration procedure, wherein the AI-based automatic calibration procedure calibrates a set of local spatial-temporal coordinates between a plurality of the one or more equipment.

7. A computer program product for factory automation, the computer program product comprising one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions including instructions to:

responsive to receiving a new production task, input one or more production requirements into an Artificial Intelligence (AI) engine;

select one or more equipment and one or more software containers based on output data from the AI engine;

extract, by the one or more computer processors, one or more AI models from one or more robot software functions controlled by one or more robots;

detach, by the one or more computer processors, one or more sensor functions from the one or more robots;

deploy, by the one or more computer processors, the one or more robot software functions, the one or more AI models, and the one or more detached sensor functions in the selected one or more software containers on an edge cloud; and

create an orchestration service, wherein the orchestration service collaborates the one or more equipment and the one or more software containers.

8. The computer program product of claim 7 , further comprising one or more of the following program instructions, stored on the one or more computer readable storage media, to:

record a history usage of each container of the one or more containers; and

update each AI model of the one or more AI models based on the history usage.

9. The computer program product of claim 7 , further comprising one or more of the following program instructions, stored on the one or more computer readable storage media, to:

create a context service, wherein the context service maintains a spatial context and a temporal context for each equipment of the one or more equipment.

10. The computer program product of claim 7 , further comprising one or more of the following program instructions, stored on the one or more computer readable storage media, to:

extract a Quality of Service (QoS) requirement and a network traffic profile for each container of the one or more containers;

calculate a required network bandwidth for each container of the one or more containers, wherein the required network bandwidth is based on the QoS requirement and the traffic profile; and

store the required network bandwidth as metadata in each container of the one or more containers.

11. The computer program product of claim 7 , wherein select the one or more equipment and the one or more software containers based on the AI engine further comprises one or more of the following program instructions, stored on the one or more computer readable storage media, to:

select a specific equipment from the one or more equipment, wherein the specific equipment is selected based on the production requirements and one or more attached sensors; and

determine a specific version of one software container of the one or more software containers, wherein the specific version of one software container is determined by a physical location of the specific equipment.

12. The computer program product of claim 7 , further comprising an AI-based automatic calibration procedure, wherein the AI-based automatic calibration procedure calibrates a set of local spatial-temporal coordinates between a plurality of the one or more equipment.

13. A computer system for factory automation, the computer system comprising:

one or more computer processors;

one or more computer readable storage media; and

program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the stored program instructions including instructions to:

responsive to receiving a new production task, input one or more production requirements into an Artificial Intelligence (AI) engine;

select one or more equipment and one or more software containers based on output data from the AI engine;

extract, by the one or more computer processors, one or more AI models from one or more robot software functions controlled by one or more robots;

detach, by the one or more computer processors, one or more sensor functions from the one or more robots;

deploy, by the one or more computer processors, the one or more robot software functions, the one or more AI models, and the one or more detached sensor functions in the selected one or more software containers on an edge cloud; and

create an orchestration service, wherein the orchestration service collaborates the one or more equipment and the one or more software containers.

14. The computer system of claim 13 , further comprising one or more of the following program instructions, stored on the one or more computer readable storage media, to:

record a history usage of each container of the one or more containers; and

update each AI model of the one or more AI models based on the history usage.

15. The computer system of claim 13 , further comprising one or more of the following program instructions, stored on the one or more computer readable storage media, to:

create a context service, wherein the context service maintains a spatial context and a temporal context for each equipment of the one or more equipment.

16. The computer system of claim 13 , further comprising one or more of the following program instructions, stored on the one or more computer readable storage media, to:

extract a Quality of Service (QoS) requirement and a network traffic profile for each container of the one or more containers;

calculate a required network bandwidth for each container of the one or more containers, wherein the required network bandwidth is based on the QoS requirement and the traffic profile; and

store the required network bandwidth as metadata in each container of the one or more containers.

17. The computer system of claim 13 , wherein select the one or more equipment and the one or more software containers based on the AI engine further comprises one or more of the following program instructions, stored on the one or more computer readable storage media, to:

select a specific equipment from the one or more equipment, wherein the specific equipment is selected based on the production requirements and one or more attached sensors; and

determine a specific version of one software container of the one or more software containers, wherein the specific version of one software container is determined by a physical location of the specific equipment.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 30, 2020
From: WANG, XINLIN; HU, GUO QIANG; JI, PENG; ZHU, JUN
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 054496/0227 →
Continuity (1)
Related Publication 20220171371A1 · Jun 2, 2022