Cluster analysis system and method to improve sorting performance
AssigneeIllinois Tool Works Inc.
InventorLucas R. Miller
Life of this patent
Estimating the term…
Abstract
A method for classifying an unknown part includes acquiring a broadband frequency response for a plurality of parts in a training set of parts, the training set of parts including a plurality of non-flawed parts and a plurality of flawed parts, performing a statistical analysis on the broadband frequency responses to form a plurality of part subsets, the plurality of part subsets including at least one subset of non-flawed parts and at least one subset of flawed parts, and utilizing the plurality of part subsets to form a blended subset of parts, the blended subset of parts being used to classify an unknown part as either a defective part or a non-defective part. A tool for implementing the method is also described.
Claims20
A method for classifying an unknown part, said method comprising:
- acquiring a broadband frequency response for a plurality of parts in a training set of parts, the training set of parts including a plurality of non-flawed parts and a plurality of flawed parts;
- performing a statistical analysis on the broadband frequency responses to form a plurality of part subsets, the plurality of part subsets including at least one subset of non-flawed parts and at least one subset of flawed parts;
- and
- utilizing the plurality of part subsets to form a blended subset of parts, the blended subset of parts being used to classify an unknown part as either a defective part or a non-defective part.
A method of determining whether an unknown part is a flawed part or a non-flawed part, said method comprising:
- acquiring a broadband frequency response for each part in a training set of parts, the training set of parts including a plurality of non-flawed parts and a plurality of flawed parts to;
- identifying columns that represent frequency responses that are common among the plurality of broadband signatures;
- performing a statistical analysis on the identified columns to form a plurality of part subsets;
- and
- utilizing the plurality of part subsets to classify an unknown part as either a defective part or a non-defective part.
A cluster analysis tool for determining whether an unknown part is a flawed part or a non-flawed part, said tool comprising:
- a ultrasound probe for scanning a training set of parts, the training set of parts including a plurality of non-flawed parts and a plurality of flawed parts to;
- and
- a cluster analysis module coupled to the ultrasound probe, the cluster analysis module configured to:
- acquire a broadband frequency response from the ultrasound probe for a plurality of parts in a training set of parts, the training set of parts including a plurality of non-flawed parts and a plurality of flawed parts;
- perform a statistical analysis on the broadband frequency responses to form a plurality of part subsets, the plurality of part subsets including at least one subset of non-flawed parts and at least one subset of flawed parts;
- and
- transmit the plurality of part subsets to a statistical analysis tool, the statistical analysis tool forming a blended subset of parts, the blended subset of parts being used to classify an unknown part as either a defective part or a non-defective part.
Dependencies are inferred from the claim text.