Prediction of failure recovery timing in manufacturing process

Patent metadata

Field	Value
Publication number	US-2022036320-A1
Application number	US-202016944393-A
Country	US
Kind code	A1
Filing date	Jul 31, 2020
Priority date	Jul 31, 2020
Publication date	Feb 3, 2022
Grant date	—

Abstract

Methods, information handling systems and computer readable media are disclosed for formulating a proposed action involving a current repair process for a failed product in a manufacturing process. According to one embodiment, a method includes receiving identification of a current repair process and associating a first set of parameter values with the current repair process. The method further includes determining a likelihood of shipment delay resulting from the current repair process, where the determining includes applying a first machine learning model to the first set of parameter values. Based on the likelihood of shipment delay, the method further includes formulating a proposed action, including at least one of waiting for completion of the current repair process, replacing the failed product with an alternative product undergoing the manufacturing process, or initiating production of a new product to replace the failed product.

First claim

What is claimed is:

1 . A method, comprising:
receiving identification of a current repair process, within a manufacturing process, for a failed product associated with a first scheduled shipment; associating a first set of parameter values with the current repair process, wherein one or more of the parameter values within the first set are obtained using information characterizing previous repair processes for products similar to the failed product; predicting a degree of shipment delay, resulting from the current repair process, for the first scheduled shipment, wherein predicting the degree of shipment delay comprises applying a first machine learning model to the first set of parameter values; and based on the degree of shipment delay, formulating a proposed action, wherein the proposed action comprises at least one of waiting for completion of the current repair process,
replacing the failed product with an alternative product undergoing the manufacturing process, wherein the alternative product is associated with a second scheduled shipment, or
initiating production of a new product to replace the failed product.

2 . The method of claim 1 , wherein
formulating the proposed action comprises applying the first machine learning model to a second set of parameter values; and one or more of the parameter values within the second set are obtained using information characterizing a product undergoing the manufacturing process but not associated with the first scheduled shipment.

3 . The method of claim 1 , wherein the first machine learning model comprises a decision tree model.

4 . The method of claim 1 , wherein
one or more of the parameter values in the first set are obtained using a second machine learning model; and the second machine learning model is adapted to categorize the information characterizing previous repair processes.

5 . The method of claim 4 , wherein the second machine learning model comprises a support vector machine.

6 . The method of claim 1 , wherein
the first set of parameter values comprises one or more conditional parameter values; and the conditional parameter values are obtained using information characterizing the current repair process.

7 . The method of claim 6 , wherein the conditional parameter values are obtained using a conditional distribution model.

8 . The method of claim 1 , further comprising sending a description of the proposed action to a display screen of an information handling system.

9 . The method of claim 1 , further comprising sending a message describing the proposed action.

10 . An information handling system, comprising:
one or more processors; one or more non-transitory computer-readable storage media coupled to the one or more processors; and a plurality of instructions, encoded in the one or more computer-readable storage media and configured to cause the one or more processors to
receive identification of a current repair process, within a manufacturing process, for a failed product associated with a first scheduled shipment,
associate a first set of parameter values with the current repair process, wherein one or more of the parameter values within the first set are obtained using information characterizing previous repair processes for products similar to the failed product,
predict a degree of shipment delay, resulting from the current repair process, for the first scheduled shipment, wherein predicting the degree of shipment delay comprises applying a first machine learning model to the first set of parameter values, and
based on the degree of shipment delay, formulate a proposed action, wherein the proposed action comprises at least one of waiting for completion of the current repair process,
replacing the failed product with an alternative product undergoing the manufacturing process, wherein the alternative product is associated with a second scheduled shipment, or
initiating production of a new product to replace the failed product.

11 . The information handling system of claim 10 , wherein
the plurality of instructions is further configured to cause the one or more processors to apply the first machine learning model to a second set of parameter values, as a part of formulating the proposed action, and one or more of the parameter values within the second set are obtained using information characterizing a product undergoing the manufacturing process but not associated with the first scheduled shipment.

12 . The information handling system of claim 10 , wherein
one or more of the parameter values in the first set are obtained using a second machine learning model; and the second machine learning model is adapted to categorize the information characterizing previous repair processes.

13 . The information handling system of claim 10 , wherein
the first set of parameter values comprises one or more conditional parameter values; and the conditional parameter values are obtained using information characterizing the current repair process.

14 . The information handling system of claim 10 , further comprising a display screen coupled to the one or more processors, and wherein the plurality of instructions is further configured to cause the one or more processors to send a description of the proposed action to the display screen.

15 . The information handling system of claim 10 , wherein the plurality of instructions is further configured to cause the one or more processors to send a message describing the proposed action.

16 . A non-transitory computer readable storage medium having program instructions encoded therein, wherein the program instructions are executable to:
receive identification of a current repair process, within a manufacturing process, for a failed product associated with a first scheduled shipment, associate a first set of parameter values with the current repair process, wherein one or more of the parameter values within the first set are obtained using information characterizing previous repair processes for products similar to the failed product, predict a degree of shipment delay, resulting from the current repair process, for the first scheduled shipment, wherein predicting the degree of shipment delay comprises applying a first machine learning model to the first set of parameter values, and based on the degree of shipment delay, formulate a proposed action, wherein the proposed action comprises at least one of waiting for completion of the current repair process, replacing the failed product with an alternative product undergoing the manufacturing process, wherein the alternative product is associated with a second scheduled shipment, or initiating production of a new product to replace the failed product.

17 . The computer readable storage medium of claim 16 , wherein
the program instructions are further executable to apply the first machine learning model to a second set of parameter values, as a part of formulating the proposed action, and one or more of the parameter values within the second set are obtained using information characterizing a product undergoing the manufacturing process but not associated with the first scheduled shipment.

18 . The computer readable carrier medium of claim 16 , wherein
one or more of the parameter values in the first set are obtained using a second machine learning model; and the second machine learning model is adapted to categorize the information characterizing previous repair processes.

19 . The computer readable carr

Assignees

• Dell Products Lp

Inventors

• Anshul Shanir
• Panikkar Shibi

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title

• G06Q10/20 Primary

  Administration of product repair or maintenance · CPC title