Computer-Implemented System for Detecting Anomaly Conditions in a Fleet of Assets and Method of Using the Same

• US 20140188778A1
• Filed: 12/27/2012
• Published: 07/03/2014
• Est. Priority Date: 12/27/2012
• Status: Abandoned Application

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Garvey, Dustin Ross, Xue, Feng
• Application Number:
  US13/728,721
• Publication Number:
  US 20140188778A1
• Time in Patent Office: Days
• US Class Current: 706/50
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management

Abstract

A system for determining anomaly conditions within a fleet of physical assets includes a central system having at least one computing device, the computing device including a processor and a memory device coupled to the processor and a database associated with the central system. The system includes a plurality of databases and a plurality of client devices associated with the fleet of physical assets. The system is configured to receive a first set of fleet data. The system is further configured to generate one or more computer-executable steps for detection of predicted anomalies. The system is configured to receive a first set of fleet asset data. The system is configured to detect at least one physical asset from the fleet of physical assets predicted to have at least one anomaly using the one or more computer-executable steps for detection of predicted anomalies and the first set of fleet asset data.

Claims

1. A network-based system for determining anomaly conditions within a fleet of physical assets, said system comprising:

a central system having at least one computing device, said computing device including a processor and a memory device coupled to said processor;

a database associated with said central system;

a plurality of databases associated with the fleet of physical assets; and

a plurality of client devices associated with the fleet of physical assets, said network-based system configured to;

receive, at the central system, a first set of fleet data from at least one data repository, the first set of fleet data substantially representative of fleet asset condition signals that are substantially representative of conditions associated with the fleet of physical assets;

generate, at the central system, using the first set of fleet data, one or more computer-executable steps for detection of predicted anomalies for each asset of the fleet of physical assets;

receive, at the central system, a first set of fleet asset data from the at least one data repository, the first set of fleet asset data substantially representative of individual asset condition signals associated with a particular asset associated with the fleet of physical assets; and

detect, at the central system, using the one or more computer-executable steps for detection of predicted anomalies and the first set of fleet asset data, at least one physical asset from the fleet of physical assets predicted to have at least one anomaly.

2. A network-based system in accordance with claim 1, wherein said fleet asset condition signals are substantially representative of at least one of a plurality of signal states associated with detecting an anomaly in the fleet of physical assets.

3. A network-based system in accordance with claim 1, wherein said system is further configured such that receiving a first set of fleet data comprises:

receiving a first set of fleet data at the central system from the at least one data repository wherein the received first set of fleet data is one of incomplete or partially complete;

generating estimated fleet data comprises estimating the fleet data not received based upon previously received fleet data; and

incorporating the estimated fleet data with the received fleet data.

4. A network-based system in accordance with claim 1, wherein said system is further configured such that generating one or more computer-executable steps for detection of predicted anomalies comprises:

selecting, at the central system, a plurality of categories of state signals associated with an anomaly associated with a physical asset;

creating, at the central system, a trained predictor, the trained predictor substantially representative of a method of determining a future set of state signals based upon a present set of state signals for each asset in the fleet of physical assets; and

generating, at the central system, using the trained predictor and the first set of fleet data, the future set of state signals based upon the present set of state signals for a physical asset.

5. A network-based system in accordance with claim 1, wherein said system is further configured such that generating a method for detection of predicted anomalies further comprises:

creating, at the central system, a detector, the detector substantially representative of a method of identifying, based upon the future set of state signals, assets predicted to be anomalous, normal, or indeterminate; and

configuring the detector, at the central system, configuring the detector substantially representative of processing present set of state signals and future set of state signals for each asset of the fleet of assets using the detector.

6. A network-based system in accordance with claim 1, wherein said system is further configured such that detecting physical assets predicted to have anomalies comprises:

processing the first set of fleet asset data, at the central system, with the one or more computer-executable steps for detection of predicted anomalies;

generating, at the central system, with the one or more computer-executable steps for detection of predicted anomalies, hypotheses regarding the condition of the assets;

testing, at the central system, with the first set of fleet asset data and a plurality of tests for the fleet of physical assets, the hypotheses; and

determining, at the central system, whether the physical asset is predicted to be anomalous, normal, or indeterminate.

7. A network-based system in accordance with claim 6, wherein said system is further configured such that detecting physical assets predicted to have anomalies further comprises:

generating, at the central system, a plurality of methods to test the hypotheses, the plurality of methods includes at least one of;

machine learning, and

creating an expert data model; and

applying, at the central system, the plurality of methods to test the hypotheses.

8. A computer-implemented method for determining anomaly conditions within a fleet of physical assets, said method performed by a central system having at least one computing device, the computing device including a processor and a memory device coupled to the processor, said method comprising:

receiving, at the central system, a first set of fleet data from at least one data repository, the first set of fleet data substantially representative of fleet asset condition signals that are substantially representative of conditions associated with the fleet of physical assets;

generating, at the central system, using the first set of fleet data, one or more computer-executable steps for detection of predicted anomalies for each asset of the fleet of physical assets;

receiving, at the central system, a first set of fleet asset data from the at least one data repository, the first set of fleet asset data substantially representative of individual asset condition signals associated with a particular asset associated with the fleet of physical assets; and

detecting, at the central system, using the one or more computer-executable steps for detection of predicted anomalies and the first set of fleet asset data, at least one physical asset from the fleet of physical assets predicted to have at least one anomaly.

9. The method of claim 8, wherein said fleet asset condition signals are substantially representative of at least one of a plurality of signal states associated with detecting an anomaly in the fleet of physical assets.

10. The method of claim 8, wherein said receiving a first set of fleet data comprises:

receiving a first set of fleet data at the central system from the at least one data repository wherein the received first set of fleet data is one of incomplete or partially complete;

generating estimated fleet data comprises estimating the fleet data not received based upon previously received fleet data; and

incorporating the estimated fleet data with the received fleet data.

11. The method of claim 8, wherein said generating one or more computer-executable steps for detection of predicted anomalies comprises:

selecting, at the central system, a plurality of categories of state signals associated with an anomaly associated with a physical asset;

creating, at the central system, a trained predictor, the trained predictor substantially representative of a method of determining a future set of state signals based upon a present set of state signals for each asset in the fleet of physical assets; and

generating, at the central system, using the trained predictor and the first set of fleet data, the future set of state signals based upon the present set of state signals for a physical asset.

12. The method of claim 8, wherein said generating a method for detection of predicted anomalies further comprises:

creating, at the central system, a detector, the detector substantially representative of a method of identifying, based upon the future set of state signals, assets predicted to be anomalous, normal, or indeterminate; and

configuring the detector, at the central system, configuring the detector substantially representative of processing present set of state signals and future set of state signals for each asset of the fleet of assets using the detector.

13. The method of claim 8, wherein said detecting physical assets predicted to have anomalies comprises:

processing the first set of fleet asset data, at the central system, with the one or more computer-executable steps for detection of predicted anomalies;

generating, at the central system, with the one or more computer-executable steps for detection of predicted anomalies, hypotheses regarding the condition of the assets;

testing, at the central system, with the first set of fleet asset data and a plurality of tests for the fleet of physical assets, the hypotheses; and

determining, at the central system, whether the physical asset is predicted to be anomalous, normal, or indeterminate.

14. The method of claim 13, wherein detecting physical assets predicted to have anomalies further comprises:

generating, at the central system, a plurality of methods to test the hypotheses, the plurality of methods includes at least one of;

machine learning, and

creating an expert data model; and

applying, at the central system, the plurality of methods to test the hypotheses.

15. A computer for determining anomaly conditions within a fleet of physical assets, said computer associated with a database, said computer comprising a processor and a memory device coupled to the processor, said processor programmed to:

receive a first set of fleet data from at least one data repository, the first set of fleet data substantially representative of fleet asset condition signals substantially representative of conditions associated with the fleet of physical assets;

generate, using the first set of fleet data, one or more computer-executable steps for detection of predicted anomalies for each asset of the fleet of physical assets;

receive a first set of fleet asset data from at least one data repository, the first set of fleet asset data substantially representative of state signals associated with a particular asset associated with the fleet of physical assets; and

detect, using the one or more computer-executable steps for detection of predicted anomalies and the first set of fleet asset data, at least one physical asset from the fleet of physical assets predicted to have at least one anomaly.

16. The computer of claim 15, wherein said fleet asset condition signals are substantially representative of at least one of a plurality of signal states associated with detecting an anomaly in the fleet of physical assets.

17. The computer of claim 15, wherein said computer is further configured such that receiving a first set of fleet data comprises:

receiving a first set of fleet data at the central system from the at least one data repository wherein the received first set of fleet data is one of incomplete or partially complete;

generating estimated fleet data comprises estimating the fleet data not received based upon previously received fleet data; and

incorporating the estimated fleet data with the received fleet data.

18. The computer of claim 15, wherein said computer is further configured such that generating one or more computer-executable steps for detection of predicted anomalies comprises:

selecting, at the central system, a plurality of categories of state signals associated with an anomaly associated with a physical asset;

creating, at the central system, a trained predictor, the trained predictor substantially representative of a method of determining a future set of state signals based upon a present set of state signals for each asset in the fleet of physical assets; and

generating, at the central system, using the trained predictor and the first set of fleet data, the future set of state signals based upon the present set of state signals for a physical asset.

19. The computer of claim 15, wherein said computer is further configured such that generating a method for detection of predicted anomalies further comprises:

creating, at the central system, a detector, the detector substantially representative of a method of identifying, based upon the future set of state signals, assets predicted to be anomalous, normal, or indeterminate; and

configuring the detector, at the central system, configuring the detector substantially representative of processing present set of state signals and future set of state signals for each asset of the fleet of assets using the detector.

20. The computer of claim 15, wherein said computer is further configured such that detecting physical assets predicted to have anomalies comprises:

processing the first set of fleet asset data, at the central system, with the one or more computer-executable steps for detection of predicted anomalies;

generating, at the central system, with the one or more computer-executable steps for detection of predicted anomalies, hypotheses regarding the condition of the assets;

testing, at the central system, with the first set of fleet asset data and a plurality of tests for the fleet of physical assets, the hypotheses; and

determining, at the central system, whether the physical asset is predicted to be anomalous, normal, or indeterminate.