Binary classification of items of interest in a repeatable process

摘要

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.

主权项

1. A system comprising:
a host machine and a learning machine, each having a respective processor, wherein the processors are in electrical communication with at least one sensor; and tangible, non-transitory memory on which is recorded instructions for predicting a binary quality status of an item of interest during a repeatable process, wherein the binary quality status includes a passing and a failing binary class, and wherein the learning machine is configured to execute the instructions via the processor of the learning machine to thereby:
receive signals from the at least one sensor;identify a set of candidate features as a function of the received signals;extract a plurality of features from the set of candidate features, each being more predictive of the binary quality status relative to other non-extracted features in the set of candidate features;map the extracted features to a dimensional space having a number of dimensions that is proportional to the number of extracted features, wherein the dimensional space includes most of the items of interest from the passing binary class and excludes at least 90 percent of the items of interest from the failing binary class; andrecord the dimensional space in the memory; wherein the host machine is programmed to compare the received signals for a subsequent item of interest to the boundaries of the recorded dimensional space during the repeatable process to thereby predict, in real time, the binary quality status of the subsequent item of interest.