Online learning using information fusion for equipment predictive maintenance in railway operations

• US 9,187,104 B2
• Filed: 04/30/2013
• Issued: 11/17/2015
• Est. Priority Date: 01/11/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Fang, Dongping, Hampapur, Arun, He, Qing, Li, Hongfei, Li, Zhiguo, Parikh, Dhaivat P., Qian, Buyue
• Primary Examiner(s): ALHIJA, SAIF A
• Application Number:
  US13/873,851
• Publication Number:
  US 20140200872A1
• Time in Patent Office: 931 Days
• Field of Search: 703/8
• US Class Current: 1/1
• 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 an online learning system includes collecting data, via a computer processing device, from a plurality of data sources including multiple disparate detectors, the data including at least one of historical alarm data, failures, maintenance records, and environment observations. The data is stored in tables each corresponding to a subject of measurement. The online learning system also includes identifying common fields shared across the tables, merging at least a portion of the data across the tables having the common fields, and creating an integrated data model based on results of the merging.

Claims

1. A system, comprising:

a plurality of data sources configured to capture data related to components of an asset that is deployed at an operation site, the data sources comprising instrumentation that physically reside at the operation site and measure qualitative aspects of the components during operation of the asset and ambient conditions surrounding the asset at the operation site;

a computer processing device communicatively coupled to the plurality of data sources over a network; and

logic executable by the computer processing device, the logic configured to implement;

receiving the data from the plurality of data sources over the network;

storing the data in tables each corresponding to a respective component and one of a plurality of subjects of measurement, wherein a type of the instrumentation used is a function of the subject of measurement;

identifying common fields shared across the tables of each respective component; and

merging at least a portion of the data across the tables having the common fields into a final table for each respective component to produce

an integrated data model based on results of the merging.

2. The system of claim 1, wherein the tables include a first table and a second table, the first table storing information about a first subject of the plurality of subjects of measurement, the information collected over a first period of time, and the second table storing information about a second subject of the plurality of subjects of measurement that is different than the first subject of measurement, the information about the second subject of measurement collected over a second period of time that partially overlaps with the first period of time;

wherein the merging includes merging only the data that shares an overlapping period of time between the first period of time and the second period of time.

3. The system of claim 1, wherein the tables include a first table and a second table, the first table storing information about a first subject of the plurality of subjects of measurement, the information collected by a first detection device of the plurality of data sources, and the second table storing information about a second subject of the plurality of subjects of measurement that is different than the first subject of measurement, the information about the second subject of measurement including a measurement of a physical parameter that is common to the first subject of measurement and the second subject of measurement;

wherein the merging includes merging data that share the physical parameter that is common to the first subject of measurement and the second subject of measurement.

4. The system of claim 1, further comprising logic configured to implement:

applying the model to new data received from the plurality of data sources and performing failure pattern analysis and failure causal analysis on the new data.

5. The system of claim 1, wherein the plurality of data sources physically reside in a railroad environment and physical parameters associated with train wheels and tracks as the components include at least one of:

weight;

flange thickness;

flange height; and

rim thickness.

6. The system of claim 1, wherein the plurality of data sources physically reside in a railroad environment and operational parameters associated with the subject of measurement include at least one of:

speed;

dynamic load; and

bearing temperature.

7. The system of claim 1, wherein the plurality of data sources physically reside in a railroad environment and external factors associated with the subject of measurement include at least one of:

weather; and

usage history.