WARRANTY COST ESTIMATION BASED ON COMPUTING A PROJECTED NUMBER OF FAILURES OF PRODUCTS

• US 20160019567A1
• Filed: 07/14/2015
• Published: 01/21/2016
• Est. Priority Date: 07/15/2014
• Status: Abandoned Application

• Current Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Original Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Inventors: Agarwal, Puneet, Shroff, Gautam, Singh, Karamjit
• Application Number:
  US14/798,892
• Publication Number:
  US 20160019567A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/012 Providing warranty services
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

Estimating warranty cost of products having multiple parts is described. In an implementation, part-failure data indicative of number of cycles at which each part fails in and after a first predefined time period is determined Sensor data and service records data are obtained to determine DTC occurrence data and DTC observance data. The DTC occurrence data and the DTC observance data are indicative of number of cycles at which each DTC associated with each part occurs and is observed for first time in the first predefined time period, respectively. Dependency parameters between the part-failure data, the DTC occurrence data and the DTC observance data are identified based on Bayesian Network that represents probabilistic relationships between the part-failure data, the DTC occurrence data and the DTC observance data. Number of failures of products in a second predefined time period is computed based on the dependency parameters for estimating the warranty cost.

Claims

1. A method for computing a projected number of failures of products having multiple parts, wherein the method comprises:

determining, by a processor, part-failure data, wherein the part-failure data is indicative of a number of cycles at which each part fails in and after a first predefined time period;

determining diagnosed trouble code (DTC) occurrence data from sensor data of the products, wherein the DTC occurrence data is indicative of a number of cycles at which each DTC associated with each part occurs for first time in the first predefined time period, and wherein functioning of each of the multiple parts is diagnosed using DTCs associated with a respective part, and wherein a DTC of the DTCs is associated for a trouble symptom for a part of the products;

determining DTC observance data from service records data of the products, wherein the DTC observance data is indicative of a number of cycles at which each DTC associated with each part is observed for first time in the first predefined time period;

identifying, by the processor, dependency parameters between the part-failure data, the DTC occurrence data and the DTC observance data, based on Bayesian Network, wherein the Bayesian Network represents probabilistic relationships between the part-failure data, the DTC occurrence data and the DTC observance data, and wherein the dependency parameters are associated with the probabilistic relationships; and

computing, by the processor, the projected number of failures of the products in a second predefined time period based on the dependency parameters, and wherein the second predefined time period is indicative of a time period after the first predefined time period.

2. The method as claimed in claim 1, wherein determining the part-failure data comprises:

identifying, for each part, a first set of products in which the respective part fails for a first time in the first predefined time period;

identifying, for each part and for each DTC associated with the respective part, a second set of products in which the respective part fails for a first time after the first predefined time period, and the associated DTC occurs and the associated DTC is observed for a first time in the first predefined time period; and

determining, for each part, a first part-failure set including a number of cycles at which the respective part fails for a first time for each product in the first set of products.

3. The method of claim 2, wherein determining the DTC occurrence data from the sensor data comprises:

determining, for each part and for each DTC associated with the respective part, a first DTC occurrence set including a number of cycles at which the respective DTC associated with the respective part occurs for the first time for each product in the first set of products; and

determining, for each part and for each DTC associated with the respective part, a second DTC occurrence set including a number of cycles at which the respective DTC associated with the respective part occurs for the first time for each product in the second set of products.

4. The method as claimed in claim 3, wherein determining the DTC observance data from the service records data comprises:

determining, for each part and for each DTC associated with the respective part, a first DTC observance set including number of cycles at which the respective DTC associated with the respective part is observed for the first time for each product in the first set of products; and

determining, for each part and for each DTC associated with the respective part, a second DTC observance set including a number of cycles at which the respective DTC associated with the respective part is observed for the first time for each product in the second set of products.

5. The method as claimed in claim 4, wherein identifying the dependency parameters comprises:

determining probability distribution functions that are respectively followed by the first part-failure set, the first DTC occurrence set, the second DTC occurrence set, the first DTC observance set, and the second DTC observance set, wherein

the first part-failure set follows Weibull distribution,

the first DTC occurrence set and the second DTC occurrence set respectively follows a Normal distribution with a mean dependent on the part-failure data, and

the first DTC observance set and the second DTC observance set respectively follows a Normalize distribution with a mean dependent on the part-failure data and the DTC occurrence data,

wherein the dependency parameters are based on;

a mean and variance of Normal distributions for the first DTC occurrence set and the second DTC occurrence set, and

a mean and variance of Normal distributions for the first DTC observance set and the second DTC observance set.

6. The method as claimed in claim 5, wherein computing the projected number of failures of the products comprises:

learning, for each part, the dependency parameters using the first part-failure set, the first DTC observance set and the probability distribution functions;

learning a second part-failure set for each part using the dependency parameters so learnt and the second DTC observance set, wherein the second part-failure set is indicative of a number of cycles at which the respective part fails for the first time after the first predefined time period;

determining a union set for each part based on a union of the first part-failure set and the second part-failure set for the respective part; and

learning, for each part, shape and scale parameters of a Weibull distribution based on the union set, wherein the projected number of failures of the products is based on the shape and the scale parameters for the each part.

7. The method as claimed in claim 5, wherein computing the number of failures of the products further comprises:

learning, for each part, the dependency parameters using the first part-failure set, the first DTC occurrence set, the first DTC observance set and the probability distribution functions;

learning a second part-failure set for each part using the dependency parameters so learnt, the second DTC occurrence set and the second DTC observance set, wherein the second part-failure set is indicative of a number of cycles at which the respective part fails for the first time after the first predefined time period;

determining a union set for each part based on union of the first part-failure set and the second part-failure set for the respective part; and

learning for each part, shape and scale parameters of Weibull distribution based on the union set, wherein the computing the number of failures of the products is based on the learnt shape and scale parameters for the each part.

8. The method as claimed in claim 1 further comprising:

estimating, by the processor, a warranty cost of the products based on the number of projected failures of the products and a part replacement cost of the products.

9. A system for computing a projected number of failures of products having multiple parts, wherein the system comprises:

a processor;

a memory coupled to the processor , wherein the processor executes computer-readable instructions stored in the memory to;

determine part-failure data, wherein the part-failure data is indicative of a number of cycles at which a part of a product fails in a first predefined time period;

determine diagnosed trouble code (DTC) occurrence data from sensor data of the products, wherein the DTC occurrence data is indicative of a number of cycles at which a DTC associated with a part of the products occurs for a first time in and after the first predefined time period, and wherein functioning of each of the multiple parts is diagnosed using DTCs associated with a respective part, and wherein the DTC is associated for a trouble symptom for the part of the product; and

determine DTC observance data from service records data of the products, wherein the DTC observance data is indicative of a number of cycles at which a DTC associated with a part of the products is observed for a first time in the first predefined time period; and

identify dependency parameters between the part-failure data, the DTC occurrence data and the DTC observance databased on a Bayesian Network, wherein the Bayesian Network represents probabilistic relationships between the part-failure data, the DTC occurrence data and the DTC observance data, and wherein the dependency parameters are associated with the probabilistic relationships; and

compute a number of projected failures of the products in a second predefined time period based on the dependency parameters, wherein the second predefined time period is indicative of a time period after the first predefined time period.

10. The system of claim 9, the processor executes the computer-readable instructions to:

identify, for each part, a first set of products in which the respective part fails for a first time in the first predefined time period;

identify, for each part and for each DTC associated with the respective part, a second set of products in which the respective part fails for a first time after the first predefined time period and the DTC occurs and the DTC is observed for a first time in the first predefined time period; and

determine, for each part, a first part-failure set including a number of cycles at which the respective part fails for a first time for each product in the first set of products.

11. The system of claim 10, wherein the processor executes the computer-readable instructions to:

determine, for each part and for each DTC associated with the respective part, a first DTC occurrence set including a number of cycles at which the respective DTC associated with the respective part occurs for the first time for each product in the first set of products; and

determine, for each part and for each DTC associated with the respective part, a second DTC occurrence set including a number of cycles at which the respective DTC associated with the respective part occurs for the first time for each product in the second set of products.

12. The system of claim 11, wherein the processor executes the computer-readable instructions to,

determine, for each part and for each DTC associated with the respective part, a first DTC observance set including a number of cycles at which the respective DTC associated with the respective part is observed for the first time for each product in the first set of products;

and

determine, for each part and for each DTC associated with the respective part, a second DTC observance set including a number of cycles at which the respective DTC associated with the respective part is observed for the first time for each product in the second set of products.

13. The system of claim 12, wherein the processor executes the computer-readable instructions to,

determine probability distribution functions that are respectively followed by the first part-failure set, the first DTC occurrence set, the second DTC occurrence set, the first DTC observance set, and the second DTC observance set, wherein

the first part-failure set follows a Weibull distribution,

the first DTC occurrence set and the second DTC occurrence set respectively follows a Normal distribution with a mean dependent on the part-failure data, and

the first DTC observance set and the second DTC observance set respectively follows a Normalize distribution with a mean dependent on the part-failure data and the DTC occurrence data,

wherein the dependency parameters are based on,

mean and variance of Normal distributions for the first DTC occurrence set and the second DTC occurrence set, and

mean and variance of Normal distributions for the first DTC observance set and the second DTC observance set.

14. The system of claim 13, wherein the processor executes the computer-readable instructions to,

learn, for each part, the dependency parameters using the first part-failure set, the first DTC observance set and the probability distribution functions;

learn a second part-failure set for each part using the dependency parameters so learnt and the second DTC observance set, wherein the second part-failure set is indicative of a number of cycles at which the respective part fails for the first time after the first predefined time period;

determine a union set for each part based on union of the first part-failure set and the second part-failure set for the respective part; and

learn for each part, shape and scale parameters of a Weibull distribution based on the union set, wherein computing the number of projected failures of the products is based on the shape and the scale parameters for each part.

15. The system as claimed in claim 13, wherein the processor executes the computer-readable instructions to,

learn, for each part, the dependency parameters using the first part-failure set, the first DTC occurrence set, the first DTC observance set and the probability distribution functions;

learn a second part-failure set for each part using the dependency parameters so learned, the second DTC occurrence set and the second DTC observance set, wherein the second part-failure set is indicative of a number of cycles at which the respective part fails for the first time after the first predefined time period;

determine a union set for each part based on union of the first part-failure set and the second part-failure set for the respective part; and

learn for each part, a shape and scale parameters of a Weibull distribution based on the union set, wherein the number of projected failures of the products is based on the shape and the scale parameters for each part.

16. The system of claim 9, wherein the processor executes the computer-readable instructions to estimate a warranty cost of the products based on the number of projected failures of the products and part replacement costs of the products.

17. A non-transitory computer-readable medium having embodied thereon a computer program for executing a method for computing a projected number of failures of products having multiple parts, the method comprising:

determining part-failure data, wherein the part-failure data is indicative of a number of cycles at which each part fails in and after a first predefined time period;

determine diagnosed trouble code (DTC) occurrence data from sensor data of the products, wherein the DTC occurrence data is indicative of a number of cycles at which each DTC associated with each part occurs for first time in the first predefined time period, and wherein functioning of each of the multiple parts is diagnosed using DTCs associated with a respective part, and wherein the DTC is associated for a trouble symptom for a part of the one or more products;

determine DTC observance data from service records data of the products, wherein the DTC observance data is indicative of a number of cycles at which each DTC associated with each part is observed for first time in the first predefined time period;

identifying dependency parameters between the part-failure data, the DTC occurrence data and the DTC observance databased on Bayesian Network that represents probabilistic relationships between the part-failure data, the DTC occurrence data and the DTC observance data, and wherein the dependency parameters are associated with the probabilistic relationships; and

computing, by the processor, a number of projected failures of the products in a second predefined time period based on the dependency parameters, wherein the second predefined time period is indicative of time after the first predefined time period.

18. The computer program of claim 17, wherein the method further comprises estimating a warranty cost of the products based on the number of projected failures of the products and part replacement costs of the products.