Binary classification of items of interest in a repeatable process
Abstract
A system includes host and learning machines. Each machine has a processor in electrical communication with at least one sensor. Instructions for predicting a binary quality status of an item of interest during a repeatable process are recorded in memory. The binary quality status includes passing and failing binary classes. The learning machine receives signals from the at least one sensor and identifies candidate features. Features are extracted from the candidate features, each more predictive of the binary quality status. The extracted features are mapped to a dimensional space having a number of dimensions proportional to the number of extracted features. The dimensional space includes most of the passing class and excludes at least 90 percent of the failing class. Received signals are compared to the boundaries of the recorded dimensional space to predict, in real time, the binary quality status of a subsequent item of interest.
- Inventors:
- Issue Date:
- Research Org.:
- GM Global Technology Operations LLC, Detroit, MI (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1167030
- Patent Number(s):
- 8925791
- Application Number:
- 14/264,113
- Assignee:
- GM Global Technology Operations LLC (Detroit, MI)
- Patent Classifications (CPCs):
-
G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
B - PERFORMING OPERATIONS B23 - MACHINE TOOLS B23K - SOLDERING OR UNSOLDERING
- DOE Contract Number:
- EE0002217
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 2014 Apr 29
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING
Citation Formats
Abell, Jeffrey A, Spicer, John Patrick, Wincek, Michael Anthony, Wang, Hui, and Chakraborty, Debejyo. Binary classification of items of interest in a repeatable process. United States: N. p., 2015.
Web.
Abell, Jeffrey A, Spicer, John Patrick, Wincek, Michael Anthony, Wang, Hui, & Chakraborty, Debejyo. Binary classification of items of interest in a repeatable process. United States.
Abell, Jeffrey A, Spicer, John Patrick, Wincek, Michael Anthony, Wang, Hui, and Chakraborty, Debejyo. Tue .
"Binary classification of items of interest in a repeatable process". United States. https://www.osti.gov/servlets/purl/1167030.
@article{osti_1167030,
title = {Binary classification of items of interest in a repeatable process},
author = {Abell, Jeffrey A and Spicer, John Patrick and Wincek, Michael Anthony and Wang, Hui and Chakraborty, Debejyo},
abstractNote = {A system includes host and learning machines. Each machine has a processor in electrical communication with at least one sensor. Instructions for predicting a binary quality status of an item of interest during a repeatable process are recorded in memory. The binary quality status includes passing and failing binary classes. The learning machine receives signals from the at least one sensor and identifies candidate features. Features are extracted from the candidate features, each more predictive of the binary quality status. The extracted features are mapped to a dimensional space having a number of dimensions proportional to the number of extracted features. The dimensional space includes most of the passing class and excludes at least 90 percent of the failing class. Received signals are compared to the boundaries of the recorded dimensional space to predict, in real time, the binary quality status of a subsequent item of interest.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2015},
month = {1}
}