SCALABLE RULE LOGICALIZATION FOR ASSET HEALTH PREDICTION

• US 20140200952A1
• Filed: 08/08/2013
• Published: 07/17/2014
• Est. Priority Date: 01/11/2013
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hampapur, Arun, Li, Hongfei, Parikh, Dhaivat P., Qian, Buyue
• Application Number:
  US13/962,203
• Publication Number:
  US 20140200952A1
• Time in Patent Office: Days
• US Class Current: 705/7.28
• CPC Class Codes: B61K 9/08 Measuring installations for surveying permanent way applications of measuring apparatus or devices for track building purposes E01B35/00; measuring techniques G01
• CPC Class Codes: B61L 23/042 Track changes detection
• CPC Class Codes: B61L 23/044 Broken rails
• CPC Class Codes: B61L 23/045 Rail wear
• CPC Class Codes: B61L 23/047 Track or rail movements
• CPC Class Codes: B61L 27/53 for trackside elements or systems, e.g. trackside supervision of trackside control system conditions
• CPC Class Codes: B61L 27/60 Testing or simulation
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities

Abstract

An aspect of scalable rule logicalization for asset health management includes aggregating data, via a computer processing device, from data sources, extracting a set of features from the data, projecting the features to a lower dimensional space, generating a prediction based on the projecting, logicalizing a decision boundary for the prediction, and estimating a confidence level of the prediction based on the decision boundary.

Claims

1. A method, comprising:

aggregating data, via a computer processing device, from data sources;

extracting a set of features from the data;

projecting the features to a lower dimensional space;

generating a prediction based on the projecting;

logicalizing a decision boundary for the prediction; and

estimating a confidence level of the prediction based on the decision boundary.

2. The method of claim 1, wherein data sources reside within a railroad environment.

3. The method of claim 2, wherein the data sources include detectors operating within the railroad environment, the detectors comprising at least one of:

a machine vision detector;

a wheel impact load detector;

an optical geometry detector;

a truck performance detector;

an acoustic bay detector;

a hot box detector;

a warm bearing detector;

a hot wheel detector; and

a cold wheel detector.

4. The method of claim 1, wherein the prediction is for a failure, the prediction generated by machine learning techniques, performing a grid search and extracting human interpretable rules using Support Vector Machine classification results.

5. The method of claim 4, wherein the confidence is estimated based on a relative position to support vectors associated with the prediction.

6. The method of claim 1, wherein the features are extracted using quantiles.

7. A computer program product comprising a storage medium embodied with machine-readable program instructions, which when executed by a computer, causes the computer to implement a method, the method comprising:

aggregating data from data sources;

extracting a set of features from the data;

projecting the features to a lower dimensional space;

generating a prediction based on the projecting;

logicalizing a decision boundary for the prediction; and

estimating a confidence level of the prediction based on the decision boundary.

8. The computer program product of claim 7, wherein data sources reside within a railroad environment.

9. The computer program product of claim 8, wherein the data sources include detectors operating within the railroad environment, the detectors comprising at least one of:

a machine vision detector;

a wheel impact load detector;

an optical geometry detector;

a truck performance detector;

an acoustic bay detector;

a hot box detector;

a warm bearing detector;

a hot wheel detector; and

a cold wheel detector.

10. The computer program product of claim 7, wherein the prediction is for a failure, the prediction generated by machine learning techniques, performing a grid search and extracting human interpretable rules using Support Vector Machine classification results.

11. The computer program product of claim 10, wherein the confidence is estimated based on a relative position to support vectors associated with the prediction.

12. The computer program product of claim 7, wherein the features are extracted using quantiles.