System to improve predictive maintenance and warranty cost/price estimation

• US 8,275,642 B2
• Filed: 01/19/2007
• Issued: 09/25/2012
• Est. Priority Date: 01/19/2007
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chan, Hoi Yeung, Chieu, Trieu Can, Mok, Lawrence Shungwei
• Primary Examiner(s): Jasmin, Lynda
• Assistant Examiner(s): Padot, Timothy
• Application Number:
  US11/625,129
• Publication Number:
  US 20080177613A1
• Time in Patent Office: 2,076 Days
• Field of Search: 705/7.11, 705/7.12, 705/302, 705/400, 702/181, 702/184
• US Class Current: 705/7.11
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/0639 Performance analysis of employees; Performance analysis of enterprise or organisation operations

Abstract

A method and system of predicting a maintenance schedule and estimating a cost for warranty service of systems, for example, hardware systems, is provided. The method and system in one aspect may collect component usage data and obtain component reliability data for each of the plurality of components. A component life distribution module (CLDM) may be constructed based on the real time component usage data and the component reliability data, and from CLDM a mean time to fail data may be obtained. A system life distribution model (SLDM) may be selected and the mean time to fail data input into the SLDM to obtain an operating environment index that represents the effect of environment conditions on the lifetime and reliability. A maintenance schedule may be predicted and an adjusted cost of warranty service may be calculated based on the operating environment index for each of the plurality of components.

Claims

1. A computer-implemented method of predicting a maintenance schedule for a system comprising a plurality of components and estimating a cost for warranty service of the system, the method comprising the steps performed by a computer of:

collecting real-time component usage data for each of the plurality of components;

obtaining component reliability data for each of the plurality of components;

constructing, by a processor, a component life distribution module (CLDM) for each of the plurality of components based on the real time component usage data and the component reliability data for each of the plurality of components;

obtaining from each CLDM a mean time to fail for each of the plurality of components;

selecting a system life distribution model (SLDM);

inputting the mean time to fail for each of the plurality of components into the SLDM to obtain an operating environment index for each of the plurality of components that represents the effect of environment conditions on the lifetime and reliability of each of the plurality of components; and

predicting a maintenance schedule and calculating an adjusted cost of warranty service based on the operating environment index for each of the plurality of components,

wherein the calculating further includes determining an instantaneous operating environment index (IOEl) representing current cycle of measurement for each of the plurality of components, determining a cumulative operating environment index (COEl) representing a cumulative effect of environmental conditions on each of the plurality of components using COEl=(IOEl₁+IOEl₂+ . . . IOEl_n)/n, where n represents a cycle of measurement, and determining a system cumulative operating environment index (SCOEl) representing an overall system'"'"'s cumulative operating environment index using SCOEl=(W_{component 1}*COEl_{component 1}+W_{component 2}*COEl_{component 2} . . . +W_{component n}*COEl_{component n})/m, where m is number of system components and W represents a weight value associated with each of the system components, and the adjusted cost is determined using Cost_adj=C_base*(1+F(SCOEl)), where Cost_adj is the adjusted cost, C_base is a cost of maintenance and/or warranty services based on laboratory generated reliability data, and F(SCOEl) is a user defined function for adjustment.

2. The method of claim 1, wherein component reliability data comprises at least one of accelerated test data, component current usage profiles, and current component reliability projections.

3. The method of claim 1, wherein selecting a system life distribution model comprises selecting a Bayesian network, a neural network, or a Markov chain predictive model.

4. The method of claim 1, further comprising calculating a System Cumulative Operating Environment Index representing an overall system'"'"'s instantaneous operating environment index for a current cycle of measurement.

5. The method of claim 1, wherein calculating an adjusted cost of warranty service comprises multiplying a base cost of warranty service by a System Cumulative Operating Environmental Index.

6. The method claim 1, wherein the plurality of components include components of a hardware system.

7. The method of claim 1, wherein the step of inputting further includes producing a component dependency matrix from the SLDM and the inputted mean time to fail.

8. The method of claim 7, further including presenting the component dependency matrix in a dashboard view.

9. The method of claim 8, wherein the dashboard view includes repair and maintenance schedules.

10. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for predicting a maintenance schedule for a system comprising a plurality of components and estimating a cost for warranty service of the system, the method steps comprising:

collecting real-time component usage data for each of the plurality of components;

obtaining component reliability data for each of the plurality of components;

constructing a component life distribution module (CLDM) for each of the plurality of components based on the real time component usage data and the component reliability data for each of the plurality of components;

obtaining from each CLDM a mean time to fail for each of the plurality of components;

selecting a system life distribution model (SLDM);

inputting the mean time to fail for each of the plurality of components into the SLDM to obtain an operating environment index for each of the plurality of components that represents the effect of environment conditions on the lifetime and reliability of each of the plurality of components; and

predicting a maintenance schedule and calculating an adjusted cost of warranty service based on the operating environment index for each of the plurality of components,

wherein the calculating further includes determining an instantaneous operating environment index (IOEl) representing current cycle of measurement for each of the plurality of components, determining a cumulative operating environment index (COEl) representing a cumulative effect of environmental conditions on each of the plurality of components using COEl=(IOEl₁+IOEl₂+ . . . IOEl_n)/n, where n represents a cycle of measurement, and determining a system cumulative operating environment index (SCOEl) representing an overall system'"'"'s cumulative operating environment index using SCOEl=(W_{component 1}*COEl_{component 1}+W_{component 2}*COEl_{component 2} . . . +W_{component n}*COEl_{component n})/m, where m is number of system components and W represents a weight value associated with each of the system components, and the adjusted cost is determined using Cost_adj=C_base*(1+F(SCOEl)), where Cost_adj is the adjusted cost, C_base is a cost of maintenance and/or warranty services based on laboratory generated reliability data, and F(SCOEl) is a user defined function for adjustment.

11. The program storage device of claim 10, wherein component reliability data comprises at least one of accelerated test data, component current usage profiles, and current component reliability projections.

12. The program storage device of claim 10, wherein selecting a system life distribution model comprises selecting a Bayesian network, a neural network, or a Markov chain predictive model.

13. The program storage device of claim 10, further comprising calculating a System Cumulative Operating Environment Index representing an overall system'"'"'s instantaneous operating environment index for a current cycle of measurement.

14. The program storage device of claim 10, wherein calculating an adjusted cost of warranty service comprises multiplying a base cost of warranty service by a System Cumulative Operating Environmental Index.

15. The program storage device of claim 10, wherein the plurality of components include components of a hardware system.

16. The program storage device of claim 10, wherein the step of inputting further includes producing a component dependency matrix from the SLDM and the inputted mean time to fail.

17. The program storage device of claim 16, further including presenting the component dependency matrix in a dashboard view.

18. A computer system for predicting a maintenance schedule for a system comprising a plurality of components and estimating a cost for warranty service of the system, the computer system comprising:

a processor;

a service agent module for collecting real-time component usage data for each of the plurality of components;

a first module for obtaining component reliability data for each of the plurality of components;

the first module further for constructing a component life distribution module (CLDM) for each of the plurality of components based on the real time component usage data and the component reliability data for each of the plurality of components;

the first module further for obtaining from each CLDM a mean time to fail for each of the plurality of components;

the first module further for selecting a system life distribution model (SLDM);

the first module further for inputting the mean time to fail for each of the plurality of components into the SLDM to obtain an operating environment index for each of the plurality of components that represents the effect of environment conditions on the lifetime and reliability of each of the plurality of components; and

a second module for predicting a maintenance schedule and calculating an adjusted cost of warranty service based on the operating environment index for each of the plurality of components,

wherein the calculating further includes determining an instantaneous operating environment index (IOEl) representing current cycle of measurement for each of the plurality of components, determining a cumulative operating environment index (COEl) representing a cumulative effect of environmental conditions on each of the plurality of components using COEl=(IOEl₁+IOEl₂+ . . . IOEl_n)/n, where n represents a cycle of measurement, and determining a system cumulative operating environment index (SCOEl) representing an overall system'"'"'s cumulative operating environment index using SCOEl=(W_{component 1}*COEl_{component 1}+W_{component 2}*COEl_{component 2} . . . +W_{component n}*COEl_{component n})/m, where m is number of system components and W represents a weight value associated with each of the system components, and the adjusted cost is determined using Cost_adj=C_base*(1+F(SCOEl)), where Cost_adj is the adjusted cost, C_base is a cost of maintenance and/or warranty services based on laboratory generated reliability data, and F(SCOEl) is a user defined function for adjustment.

19. The system of claim 18, wherein the means for collecting real-time component usage data comprises a plurality of sensors for monitoring the plurality of components.