Quality controlling device and control method thereof

Patent metadata

Field	Value
Publication number	US-10095225-B2
Application number	US-201514854719-A
Country	US
Kind code	B2
Filing date	Sep 15, 2015
Priority date	Sep 17, 2014
Publication date	Oct 9, 2018
Grant date	Oct 9, 2018

Abstract

According to one embodiment, there is provided a quality controlling device including: a predictor, a frequency calculator, and an implementing signal creator. The predictor employs a prediction model that associates an inspection result value of a first inspection with a predicted value being a value relating to a possibility of pass or failure in a second inspection and calculates the predicted value from an inspection result value that is obtained for an inspection target in the first inspection. The frequency calculator calculates, for the inspection target, an implementation frequency to implement the second inspection in accordance with the predicted value calculated by the predictor. The implementing signal creator creates a signal that indicates, for the inspection target, necessity of implementing the second inspection in accordance with the implementation frequency.

First claim

The invention claimed is:

1. A quality controlling device comprising:
a hardware storage to store a prediction model associating an inspection result value of a first inspection with a predicted value of a possibility by which a second inspection passes or fails; and
processing circuitry:
to calculate a predicted value of a possibility by which the second inspection passes or fails on an inspection target by calculating the prediction model based on the inspection result value of the first inspection on the inspection target to obtain the predicted value of the prediction model;
to calculate an implementation frequency to implement the second inspection on the inspection target based on the calculated predicted value and a function associating between an implementation frequency and a predicted value; and
to create a signal indicating whether to implement the second inspection, based on the implementation frequency.

2. The device according to claim 1 , wherein
the calculated predicted value represents a probability that the inspection target is passed or failed in the second inspection, and
the function returns a largest implementation frequency when the predicted value is a predetermined value and returns an implementation frequency that becomes smaller as an absolute value of a difference between the calculated predicted value and the predetermined value is larger.

3. The device according to claim 2 , wherein
the function returns an implementation frequency of a first probability greater than zero if the calculated predicted value is greater than or equal to a lower limit value and less than or equal to an upper limit value, and
the function returns an implementation frequency of a zero probability or an implementation frequency a second probability less than the first probability the predicted value is out of a range between the lower limit value and the upper limit value.

4. The device according to claim 1 , wherein
the hardware storage stores an evaluation value indicating pass or failure in the second inspection depending on an inspection result value of the second inspection and store the calculated predicted value,
the processing circuitry determines whether to update the prediction model in accordance with a number of times by which the signal indicating to implement the second inspection is generated for a plurality of the inspection targets, and
the processing circuitry updates the prediction model based on the evaluation value and the calculated predicted value that are stored in the storage, when the processing circuitry determines to update the prediction model.

5. The device according to claim 4 , wherein
the prediction model has a first prediction parameter,
the processing circuitry determines a prediction parameter included in a function associating between a predicted value and an evaluation value, on the basis of the evaluation value and the calculated predicted value that are stored in the storage, and
the processing circuitry updates the first prediction parameter in the prediction model by the determined prediction parameter.

6. The device according to claim 4 , wherein
the hardware storage stores a second prediction model associating the inspection result value of the first inspection with a predicted value of a possibility by which the second inspection passes or fails, and
the processing circuitry
calculates a predicted value of a possibility by the second inspection passes or fails on a second inspection target by calculating the second prediction model based on the inspection result value of the first inspection on the second inspection target to obtain the predicted value of the second prediction model, and
calculates the implementation frequency based on the calculated predicted value of the prediction model and the calculated predicted value of the second prediction model.

7. The device according to claim 6 ,
wherein
the hardware storage stores, for second inspection targets, an evaluation value indicating pass or failure in the second inspection depending on an inspection result value of the second inspection and store the calculated predicted value of the second prediction model,
the processing circuitry determines whether to update the second prediction model in accordance with a number of times by which the signal indicating to implement the second inspection is generated for second inspection targets, and
the processing circuitry updates the second prediction model based on the evaluation value and the calculated predicted value for second inspection targets, that are stored in the storage when the processing circuitry determines to update the second prediction model.

8. The device according to claim 6 , wherein
the second prediction model has a second prediction parameter,
the processing circuitry determines a prediction parameter included in a function associating between a predicted value and an evaluation value, on the basis of the evaluation value and the calculated predicted value on the second inspection targets that are stored in the hardware storage, and
the processing circuitry updates the second prediction parameter in the second prediction model by the determined prediction parameter.

9. The device according to claim 1 , wherein the processing circuitry creates, as the signal indicating whether to implement the second inspection, a signal indicating whether to implement either of the second inspection or a third inspection, a cost of the third inspection being lower than a cost of the second inspection.

10. The device according to claim 9 , further comprising a process switcher to output a signal to instruct an implementer that implements the second inspection to implement the second inspection when the signal indicating to implement the second inspection is created, and output a signal to instruct an implementer that implements the third inspection to implement the third inspection when the indicating to implement the third inspection is created.

11. A quality controlling method comprising:
providing a prediction model associating an inspection result value of a first inspection with a predicted value of a possibility by which a second inspection passes or fails;
calculating a predicted value of a possibility by which the second inspection passes or fails on an inspection target by calculating the prediction model based on the inspection result value of the first inspection on the inspection target to obtain the predicted value of the prediction model;
calculating an implementation frequency to implement the second inspection on the inspection target based on the calculated predicted value and a function associating between an implementation frequency and a predicted value; and
creating a signal indicating whether to implement the second inspection, based on the implementation frequency.

Assignees

• Toshiba Kk

Inventors

• Ohgushi Toshiaki
• Nishikawa Takeichiro

Classifications

• G05B19/41875 Primary

  characterised by quality surveillance of production · CPC title

• G05B2219/32194

  Quality prediction · CPC title

• Y02P90/22

  Cross-Sectional Technologies · mapped topic

• Y02P90/86

  Cross-Sectional Technologies · mapped topic

• Y02P90/80

  Management or planning · CPC title