# US 2020/0004219 A1 · Defect rate analytics to reduce defectiveness in manufacturing

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

- Number: US 2020/0004219 A1
- Document ID: US20200004219A1
- Status: Published application
- Kind: A1
- Application number: 16/025,865
- Filed: 2018-07-02
- Published: 2020-01-02
- Earliest claimed: 2018-07-02
- Assignees: Hitachi, Ltd.
- Applicants: Hitachi, Ltd.
- Inventors: Qiyao WANG; Susumu SERITA; Chetan GUPTA
- Web page: https://patentgrep.com/patent/US20200004219A1

## CPC

- G05B 19/406: characterised by monitoring or safety (G05B19/19 takes precedence)
- G06Q 50/04: Manufacturing
- G05B 2219/32222: Fault, defect detection of origin of fault, defect of product
- Y02P 90/30: Computing systems specially adapted for manufacturing
- 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)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

Example implementations described herein are directed to systems and methods for defect rate analytics to reduce defectiveness in manufacturing. In an example implementation, a method include determining, from data associated with each feature for a manufacturing process, the data feature indicative of process defects detected based on the feature, an estimated condition for the feature that reduces a defect rate of the process defects, the estimated condition indicating the data into a first group and second group; calculating the rate reduction of the defect rate based on a difference in defects between the first group and the second group; for the rate reduction meeting a target confidence level for a target defect rate, applying the estimated condition to the manufacturing process associated with each of the features. In example implementations, the defect rate analytics reduce defectiveness in manufacturing with independent processes and/or dependent processes.

## Claims

### Claim 1

A method comprising:
determining, from data associated with each data feature for a manufacturing process, the data feature indicative of process defects detected based on the feature, an estimated condition for the feature that reduces a defect rate of the process defects, the estimated condition indicating the data into a first group and second group;
calculating a rate reduction of the defect rate based on a difference in defects between the first group and the second group; and
for the rate reduction meeting a target confidence level for a target defect rate, applying the estimated condition to the manufacturing process associated with each of the features.

### Claim 2 (depends on 1)

The method of claim 1, wherein the determining the data feature indicative of process defects detected based on the data feature comprises, for the manufacturing process involving related processes, removing one or more accumulated effects of the process detects associated with the related processes.

### Claim 3 (depends on 2)

The method of claim 2, wherein the one or more accumulated effects are learned from a regression model configured to predict an effect of a process from the related processes, based on one or more prevision iterations of the process from the related processes; wherein the removing the one or accumulated effects comprises applying fitted data from the regression model to remove the one or more accumulated effects for the process from the related processes.

### Claim 4 (depends on 1)

The method of claim 1, wherein an application of estimated conditions is conducted for features that are ranked above a threshold.

### Claim 5 (depends on 1)

The method of claim 1, wherein the target confidence level is a statistical confidence indicative of a repeatability rate of the target defect rate.

### Claim 6 (depends on 1)

The method of claim 1, wherein the calculating the rate reduction of the defect rate based on the difference in defects between the first group and the second group comprises:
for a true unknown defect rate of the first group exceeding that of the second group: the calculating of the rate reduction is a ratio of a product of a robust estimate and total number of units of the first group, and a sum of total units of the first group and the second group; and
for the true unknown defect rate of the first group not exceeding that of the second group: the calculating of the rate reduction is a ratio of a product of a robust estimate and total number of units of the second group, and a sum of total units of the first group and the second group.

### Claim 7

A system comprising:
a memory;
a processing device configured to:
determine, from data associated with each data feature for a manufacturing process, the data feature indicative of process defects detected based on the feature, an estimated condition for the feature that reduces a defect rate of the process defects, the estimated condition indicating the data into a first group and second group;
calculate a rate reduction of the defect rate based on a difference in defects between the first group and the second group; and
for the rate reduction meeting a target confidence level for a target defect rate, apply the estimated condition to the manufacturing process associated with each of the features.

### Claim 8 (depends on 7)

The system of claim 7, wherein the processing device is configured to determine the data feature indicative of process defects detected based on the data feature by, for the manufacturing process involving related processes, removing one or more accumulated effects of the process detects associated with the related processes.

### Claim 9 (depends on 8)

The system of claim 8, wherein the one or more accumulated effects are learned from a regression model configured to predict an effect of a process from the related processes, based on one or more prevision iterations of the process from the related processes; wherein the removing the one or accumulated effects comprises applying fitted data from the regression model to remove the one or more accumulated effects for the process from the related processes.

### Claim 10 (depends on 7)

The system of claim 7, wherein an application of estimated conditions is conducted for features that are ranked above a threshold.

### Claim 11 (depends on 7)

The system of claim 7, wherein the target confidence level is a statistical confidence indicative of a repeatability rate of the target defect rate.

### Claim 12 (depends on 7)

The system of claim 7, wherein the calculating the rate reduction of the defect rate based on the difference in defects between the first group and the second group comprises:
for a true unknown defect rate of the first group exceeding that of the second group: the calculating of the rate reduction is a ratio of a product of a robust estimate and total number of units of the first group, and a sum of total units of the first group and the second group; and
for the true unknown defect rate of the first group not exceeding that of the second group: the calculating of the rate reduction is a ratio of a product of a robust estimate and total number of units of the second group, and a sum of total units of the first group and the second group.

### Claim 13

A non-transitory computer-readable medium storing instructions for a policy based network application management system, the instructions executed by a processing device, the instructions comprising:
determining, from data associated with each data feature for a manufacturing process, the data feature indicative of process defects detected based on the feature, an estimated condition for the feature that reduces a defect rate of the process defects, the estimated condition indicating the data into a first group and second group;
calculating a rate reduction of the defect rate based on a difference in defects between the first group and the second group; and
for the rate reduction meeting a target confidence level for a target defect rate, applying the estimated condition to the manufacturing process associated with each of the features.

### Claim 14 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein determining the data feature indicative of process defects detected based on the data feature comprises, for the manufacturing process involving related processes, removing one or more accumulated effects of the process detects associated with the related processes.

### Claim 15 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the one or more accumulated effects are learned from a regression model configured to predict an effect of a process from the related processes, based on one or more prevision iterations of the process from the related processes; wherein the removing the one or accumulated effects comprises applying fitted data from the regression model to remove the one or more accumulated effects for the process from the related processes.

### Claim 16 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein an application of estimated conditions is conducted for features that are ranked above a threshold.

### Claim 17 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the target confidence level is a statistical confidence indicative of a repeatability rate of the target defect rate.

### Claim 18 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the calculating the rate reduction of the defect rate based on the difference in defects between the first group and the second group comprises:
for a true unknown defect rate of the first group exceeding that of the second group: the calculating of the rate reduction is a ratio of a product of a robust estimate and total number of units of the first group, and a sum of total units of the first group and the second group; and
for the true unknown defect rate of the first group not exceeding that of the second group: the calculating of the rate reduction is a ratio of a product of a robust estimate and total number of units of the second group, and a sum of total units of the first group and the second group.
