# US 2022/0043435 A1 · AI-Based Determination of Action Plan for Manufacturing Component Carriers

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0043435 A1
- Document ID: US20220043435A1
- Status: Published application
- Kind: A1
- Application number: 17/443,927
- Filed: 2021-07-28
- Published: 2022-02-10
- Earliest claimed: 2020-08-07
- Assignees: AT&S Austria Technologie & Systemtechnik Aktiengesellschaft
- Applicants: AT&S Austria Technologie & Systemtechnik Aktiengesellschaft
- Inventors: Tim Lu; Peter Wang
- Web page: https://patentgrep.com/patent/US20220043435A1

## CPC

- G05B 19/41865: {characterised by job scheduling, process planning, material flow}
- G05B 19/41875: {characterised by quality surveillance of production}
- G05B 13/027: {using neural networks only}
- G06N 3/0499: Feedforward networks
- G06N 3/09: Supervised learning
- H10P 72/0612: {Production flow monitoring, e.g. for increasing throughput}
- G05B 2219/31053: Planning, generate assembly plans
- G05B 2219/32188: Teaching relation between controlling parameters and quality parameters
- G05B 2219/32193: Ann, neural base quality management
- G05B 2219/45035: Printed circuit boards, also holes to be drilled in a plate
- G06N 3/08: Learning methods
- H05K 3/4638: {Aligning and fixing the circuit boards before lamination; Detecting or measuring the misalignment after lamination; Aligning external circuit patterns or via connections relative to internal circuits}
- Y02P 90/02: Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
- H05K: PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

A method of planning the manufacture of component carriers includes defining a set of final product parameters as a target for component carriers to be manufactured, ranking the process parameters concerning their impact on the final product parameters, selecting a subset of higher ranked process parameters, inputting the selected subset of process parameters for processing by an artificial intelligence module, and determining an action plan for the manufacturing based on an output of the artificial intelligence module, where the product parameters are influenceable by a set of process parameters settable during the manufacturing method.

## Claims

### Claim 1

A method of planning a manufacture of component carriers, comprising:
defining a set of final product parameters as a target for component carriers to be manufactured, wherein the product parameters are influenceable by a set of process parameters being settable during the manufacturing method;
ranking the process parameters concerning their impact on the final product parameters;
selecting a subset of higher ranked process parameters;
inputting the selected subset of process parameters for processing by an artificial intelligence module; and
determining an action plan for the manufacturing method based on an output of the artificial intelligence module.

### Claim 2 (depends on 1)

The method according to claim 1, further comprising:
categorizing the process parameters into multiple categories, each category relating to an assigned manufacturing stage of the manufacturing method.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the ranking is based on the categorized process parameters.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the categorizing is based on at least one of the group consisting of expert knowledge, modelling, empirical data, and theoretical calculations.

### Claim 5 (depends on 1)

The method according to claim 1, further comprising:
validating the output of the artificial intelligence module and determining the action plan based on the validated output.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the validating comprises determining whether an output of the artificial intelligence module meets at least one predefined compliance criterion, and if not, modifying the output of the artificial intelligence module for meeting the at least one predefined compliance criterion.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the ranking is based on at least one of the group consisting of a regression, a correlation, and process knowledge.

### Claim 8 (depends on 1)

The method according to claim 1, wherein processing by the artificial intelligence module comprises processing by deep learning.

### Claim 9 (depends on 1)

The method according to claim 1, wherein processing by the artificial intelligence module comprises processing using a neural network.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the final product parameters describe physical properties of the manufactured component carrier.

### Claim 11 (depends on 1)

The method according to claim 1, wherein the final product parameters are not directly adjustable during the manufacturing method.

### Claim 12 (depends on 1)

The method according to claim 1, wherein the process parameters are directly adjustable during the manufacturing method.

### Claim 13 (depends on 1)

The method according to claim 1, further comprising:
discarding another subset of lower ranked process parameters.

### Claim 14 (depends on 1)

The method according to claim 1, further comprising:
storing data obtained during carrying out the method in a database for training the artificial intelligence module.

### Claim 15 (depends on 1)

The method according to claim 1, comprising at least one of the following features:
wherein the process parameters comprise at least one of the group consisting of a trace thickness, a trace width, an insulator thickness, a pad diameter, a via diameter, a temperature, a pressure, a processing time, an etch rate, and a concentration;
wherein the final product parameters comprise at least one of the group consisting of a shrinkage, a coefficient of thermal expansion, an impedance, a resistance, a thickness of the component carrier, an alignment, and a land coplanarity;
wherein the action plan is indicative of how to carry out the manufacturing method to achieve compliance with the defined set of final product parameters;
wherein the method comprises analyzing, in particular adjusting, the input selected subset of process parameters by the artificial intelligence module so that the output of the artificial intelligence module provides instructions relating to the manufacturing method for obtaining component carriers complying with the defined set of final product parameters;
wherein the method comprises manufacturing the component carriers based on the determined action plan.

### Claim 16

An apparatus for determining an action plan for manufacturing component carriers, the apparatus comprising:
a receiving unit configured for receiving a defined set of final product parameters as a target for component carriers to be manufactured and for receiving a set of process parameters, wherein the product parameters are influenceable by the set of process parameters being settable during the manufacturing method;
a ranking unit configured for ranking the process parameters concerning their impact on the final product parameters;
a selection unit configured for selecting a subset of higher ranked process parameters;
an artificial intelligence module configured for processing the selected subset of process parameters using artificial intelligence; and
a determining unit configured for determining the action plan for the manufacturing method based on an output of the artificial intelligence processing.

### Claim 17 (depends on 16)

The apparatus according to claim 16, wherein the apparatus comprises a manufacturing device configured for manufacturing the component carriers based on the determined action plan.

### Claim 18 (depends on 16)

The apparatus according to claim 16, wherein the apparatus is configured to carry out and/or control a method including:
defining a set of final product parameters as a target for component carriers to be manufactured, wherein the product parameters are influenceable by a set of process parameters being settable during the manufacturing method;
ranking the process parameters concerning their impact on the final product parameters;
selecting a subset of higher ranked process parameters;
inputting the selected subset of process parameters for processing by an artificial intelligence module; and
determining an action plan for the manufacturing method based on an output of the artificial intelligence module.

### Claim 19

A non-transitory computer-readable medium, in which a computer program of planning a manufacture of component carriers is stored, which computer program, when being executed by one or a plurality of processors, is adapted to carry out and/or control a method including:
defining a set of final product parameters as a target for component carriers to be manufactured, wherein the product parameters are influenceable by a set of process parameters being settable during the manufacturing method;
ranking the process parameters concerning their impact on the final product parameters;
selecting a subset of higher ranked process parameters;
inputting the selected subset of process parameters for processing by an artificial intelligence module; and
determining an action plan for the manufacturing method based on an output of the artificial intelligence module.
