Integrated production loss management

• US 8,510,151 B2
• Filed: 07/23/2008
• Issued: 08/13/2013
• Est. Priority Date: 07/23/2008
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Easo, Ajay Kurian, Kil, David H., Mei, Zhu-Song, Shah, Baiju
• Primary Examiner(s): Mansfiled, Jr., Thomas I
• Application Number:
  US12/178,466
• Publication Number:
  US 20100023359A1
• Time in Patent Office: 1,847 Days
• Field of Search: 705/7.36, 705/7.37, 705/7.38
• US Class Current: 705/7.36
• 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
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis

Abstract

Current monitoring systems often provide the operating condition of a specific component and do not consider the impact of a specific failure upon an entire system or a business. Nor do the current systems provide an avenue for the business to predict the loss, as well as its impact, and make an educated decision of mitigating the loss based upon economic, environmental, and health and safety considerations. Methods and systems are provided for predicting loss events, impacts of loss events, and providing potential corrective measures to reduce or eliminate the occurrence or impact of the loss events. One aspect relates to the use of system-wide information to predict variables that are directly linked to business impact, such as production loss. Extraneous and transactional data are also utilized according to other aspects of the invention.

Claims

1. A method comprising:

receiving, for a system that includes multiple subsystems, system-wide information comprising operational data from a plurality of sensors, wherein a first sensor measures a parameter related to operation of a first subsystem of the system and a second sensor measures a parameter related to operation of a second subsystem of the system, the first subsystem being distinct from the second subsystem;

receiving transactional data;

selecting at least a portion of the operational data included in the received system-wide information;

applying, by a computer system, at least one statistical model to the selected operational data, and the transactional data to determine a best-fit model in regards to correlation among the operational data and the transactional data for the first subsystem with respect to the operational data and the transactional data for the second subsystem; and

predicting, by a computer system and for the first subsystem, at least one of a loss event and impact of a loss event in terms of at least one of economic impact, environmental impact, and health and safety impact based on the best-fit model and operational data and transactional data received for the second subsystem that is distinct from the first subsystem,

wherein receiving transactional data comprises receiving maintenance data describing maintenance performed on the first subsystem and the second subsystem; and

wherein applying at least one statistical model to the selected operational data, and the transactional data comprises applying at least one statistical model to the selected operational data and the maintenance data describing maintenance performed on the first subsystem and the second subsystem.

2. The method of claim 1, further comprising:

utilizing the best-fit model to determine at least one intervention to reduce or eliminate predicted impact of a predicted loss event.

3. The method of claim 1, wherein the selection of at least a portion of the received system-wide information comprises the utilization of a threshold comprising at least one of a frequency threshold, an impact threshold, and combinations thereof.

4. The method of claim 3, wherein the impact threshold is selected from an impact group comprising environmental, economic, health and safety, and combinations thereof.

5. The method of claim 1, wherein the selection of at least a portion of the collected system-wide data considers whether to utilize at least a portion of extraneous data to limit the operational data applied to the at least one statistical model.

6. The method of claim 5:

wherein applying at least one statistical model to the selected operational data, and the transactional data comprises applying a plurality of statistical models to the selected operational data, extraneous data, and transactional data to determine a best-fit model in regards to correlation among the operational data and extraneous data with the transactional data to predict events and impacts of the predicted events;

wherein the application of the plurality of statistical models to the selected operational data, extraneous data, and transactional data to determine the best-fit model in regards to the correlation among the operational data and extraneous data with the transactional data to predict events and impacts of the predicted events further comprises investigation of any correlation of specific sensor data with other sensor data.

7. The method of claim 1, further comprising:

applying features to at least a portion of the selected data to amplify patterns before applying the data to the at least one statistical model.

8. The method of claim 7, wherein upon the application of the features, determining to alter the selection of the portion of the collected system-wide information that is utilized.

9. The method of claim 2, further comprising:

displaying on a display device at least one intervention.

10. The method of claim 9, wherein at least two interventions are displayed on the display device and wherein at least one intervention differs from another intervention in regards to at least one impact comprising environmental, economic, health and safety, and combinations thereof.

11. The method of claim 1, further comprising:

comparing at least one prediction determined by the best fit model with an actual outcome.

12. The method of claim 1, further comprising:

comparing an actual outcome with at least one statistical model that is not the best-fit model to determine if the at least one statistical model is more accurate than the best-fit model.

14. The method of claim 1, wherein selecting at least a portion of the operational data included in the received system-wide information comprises utilizing an impact threshold to remove a portion of the operational data included in the received system-wide information by, when repetitive occurrence routinely or consistently provides an impact below a significant amount, excluding data associated with the impact.

15. The method of claim 1, wherein selecting at least a portion of the operational data included in the received system-wide information comprises utilizing a frequency threshold to exclude a portion of the operational data included in the received system-wide information associated with an event that does not occur above a certain frequency.

16. The method of claim 1:

wherein predicting, for the first subsystem, at least one of a loss event and impact of a loss event comprises predicting, for the first subsystem, a loss event and impact of the predicted loss event, further comprising;

determining multiple, different preventive measures for reducing the impact of the predicted loss event;

determining a predicted impact and a predicted cost of using each of the multiple, different preventive measures; and

controlling display of the multiple, different preventive measures with the predicted impact and the predicted cost for each of the multiple, different preventive measures.

17. The method of claim 1, wherein predicting, for the first subsystem, at least one of a loss event and impact of a loss event comprises predicting, for the first subsystem, timing, location, severity, and cause of a loss event.

13. A method comprising:

receiving, for a system that includes multiple subsystems, system-wide information comprising operational data from a plurality of sensors, wherein a first sensor measures a parameter related to operation of a first subsystem of the system and a second sensor measures a parameter related to operation of a second subsystem of the system, the first subsystem being distinct from the second subsystem;

receiving transactional data;

selecting at least a portion of the operational data included in the received system-wide information;

applying, by a computer system, at least one statistical model to the selected operational data, and the transactional data to determine a best-fit model in regards to correlation among the operational data and the transactional data for the first subsystem with respect to the operational data and the transactional data for the second subsystem;

predicting, by a computer system and for the first subsystem, at least one of a loss event and impact of a loss event in terms of at least one of economic impact, environmental impact, and health and safety impact based on the best-fit model and operational data and transactional data received for the second subsystem that is distinct from the first subsystem; and

receiving extraneous data that comprises at least one of

     1) data originated outside the system and

     2) data originating inside the system regarding measurement of an external impact source upon the system, excluding any man-made intended input or output of the system or data regarding processing or manufacturing performed by the system,

wherein applying at least one statistical model to the selected operational data, and the transactional data comprises applying at least one statistical model to the operational data, the extraneous data, and the transactional data to determine a best-fit model in regards to correlation among the operational data and the extraneous data with the transactional data, and

wherein predicting, for the first subsystem, at least one of a loss event and impact of a loss event comprises predicting, for the first subsystem, at least one of a loss event and impact of a loss event based on the best-fit model, operational data and transactional data received for the second subsystem that is distinct from the first subsystem, and extraneous data comprising at least one of

     1) data originated outside the system and

     2) data originating inside the system regarding measurement of an external impact source upon the system, excluding any man-made intended input or output of the system or data regarding processing or manufacturing performed by the system.

18. A non-transitory computer-readable medium having computer-executable instructions that when executed, by a computer system, cause the computer system to perform operations comprising:

receiving, for a system that includes multiple subsystems, system-wide information comprising operational data from a plurality of sensors, wherein a first sensor measures a parameter related to operation of a first subsystem of the system and a second sensor measures a parameter related to operation of a second subsystem of the system, the first subsystem being distinct from the second subsystem;

receiving transactional data;

selecting at least a portion of the operational data included in the received system-wide information;

applying at least one statistical model to the selected operational data, and the transactional data to determine a best-fit model in regards to correlation among the operational data and the transactional data for the first subsystem with respect to the operational data and the transactional data for the second subsystem; and

predicting, for the first subsystem, at least one of a loss event and impact of a loss event in terms of at least one of economic impact, environmental impact, and health and safety impact based on the best-fit model and operational data and transactional data received for the second subsystem that is distinct from the first subsystem,

wherein receiving transactional data comprises receiving maintenance data describing maintenance performed on the first subsystem and the second subsystem; and

wherein applying at least one statistical model to the selected operational data, and the transactional data comprises applying at least one statistical model to the selected operational data and the maintenance data describing maintenance performed on the first subsystem and the second subsystem.

19. A computer system comprising:

at least one processing device; and

at least one computer-readable medium having computer-executable instructions that when executed, by the at least one processing device, cause the at least one processing device to perform operations comprising;

receiving, for a system that includes multiple subsystems, system-wide information comprising operational data from a plurality of sensors, wherein a first sensor measures a parameter related to operation of a first subsystem of the system and a second sensor measures a parameter related to operation of a second subsystem of the system, the first subsystem being distinct from the second subsystem;

receiving transactional data;

selecting at least a portion of the operational data included in the received system-wide information;

applying at least one statistical model to the selected operational data, and the transactional data to determine a best-fit model in regards to correlation among the operational data and the transactional data for the first subsystem with respect to the operational data and the transactional data for the second subsystem; and

predicting, for the first subsystem, at least one of a loss event and impact of a loss event in terms of at least one of economic impact, environmental impact, and health and safety impact based on the best-fit model and operational data and transactional data received for the second subsystem that is distinct from the first subsystem,

wherein receiving transactional data comprises receiving maintenance data describing maintenance performed on the first subsystem and the second subsystem; and

wherein applying at least one statistical model to the selected operational data, and the transactional data comprises applying at least one statistical model to the selected operational data and the maintenance data describing maintenance performed on the first subsystem and the second subsystem.

20. A computer system comprising:

at least one processing device; and

at least one computer-readable medium having computer-executable instructions that when executed, by the at least one processing device, cause the at least one processing device to perform operations comprising;

receiving, for a system that includes multiple subsystems, system-wide information comprising operational data from a plurality of sensors, wherein a first sensor measures a parameter related to operation of a first subsystem of the system and a second sensor measures a parameter related to operation of a second subsystem of the system, the first subsystem being distinct from the second subsystem;

receiving transactional data;

selecting at least a portion of the operational data included in the received system-wide information;

applying, by a computer system, at least one statistical model to the selected operational data, and the transactional data to determine a best-fit model in regards to correlation among the operational data and the transactional data for the first subsystem with respect to the operational data and the transactional data for the second subsystem;

predicting, by a computer system and for the first subsystem, at least one of a loss event and impact of a loss event in terms of at least one of economic impact, environmental impact, and health and safety impact based on the best-fit model and operational data and transactional data received for the second subsystem that is distinct from the first subsystem; and

receiving extraneous data that comprises at least one of

     1) data originated outside the system and

     2) data originating inside the system regarding measurement of an external impact source upon the system, excluding any man-made intended input or output of the system or data regarding processing or manufacturing performed by the system,

wherein applying at least one statistical model to the selected operational data, and the transactional data comprises applying at least one statistical model to the operational data, the extraneous data, and the transactional data to determine a best-fit model in regards to correlation among the operational data and the extraneous data with the transactional data, and

wherein predicting, for the first subsystem, at least one of a loss event and impact of a loss event comprises predicting, for the first subsystem, at least one of a loss event and impact of a loss event based on the best-fit model, operational data and transactional data received for the second subsystem that is distinct from the first subsystem, and extraneous data comprising at least one of

     1) data originated outside the system and

     2) data originating inside the system regarding measurement of an external impact source upon the system, excluding any man-made intended input or output of the system or data regarding processing or manufacturing performed by the system.