Methods and devices for reducing device test time

1. A method for testing a group of electronic devices, the method comprising:

receiving a first set of testing data associated with a first group of electronic devices, wherein the first set of testing data is generated during a tuning test applying a first range of testing parameters;

receiving a second set of testing data associated with the first group of electronic devices;

determining, based on the first set of testing data and the second set of testing data, a second range of testing parameters that is less than the first range of testing parameters; and

subjecting a second group of electronic devices through a tuning test applying the second range of testing parameters.

2. The method of claim 1 , wherein the second set of testing data is generated prior to the tuning test.

3. The method of claim 1 , wherein the first group of electronic devices has fewer electronic devices than the second group of electronic devices.

4. The method of claim 1 , wherein the second range of testing parameters is determined using an artificial neural network.

5. The method of claim 4 , wherein determining the second range of testing parameters further comprises:

training the artificial neural network by inputting the first set of testing data and the second set of testing data associated with the first group of electronics devices into the artificial neural network; and

using the trained artificial neural network to determine the second range of testing parameters.

6. The method of claim 1 , wherein the electronics devices are hard disc drives.

7. The method of claim 6 , wherein the tuning test is one of a write current test, adjustable fly height test, channel optimization test, and variable bit aspect ratio test.

8. The method of claim 6 , wherein the tuning test is a write current test, and wherein the first range of testing parameters and the second range of testing parameters are write current values.

9. The method of claim 8 , wherein the second set of testing data includes at least one of resistance values of magneto-resistive elements, heater current values, cylinder numbers, servo data eccentricity, writer width, and reader bias current.

10. A method comprising:

subjecting a first group of electronic devices through a screening test to generate a first set of testing data associated with the first group of electronic devices;

subjecting the first group of electronic devices through a series of tests separate from the screening test to generate a second set of testing data, wherein the second set of testing data is associated with the first group of electronic devices and comprises data from predetermined categories of data;

subjecting a second group of electronic devices through the series of tests to generate a third set of testing data, wherein the third set of testing data is associated with the second group of electronic devices and comprises data from the predetermined categories of data; and

in response to the first, second, and third sets of testing data, predicting whether an electronic device from the second group of electronic devices passes or fails the screening test.

11. The method of claim 10 , wherein the second set of testing data is generated prior to the screening test.

12. The method of claim 10 , wherein the first group of electronic devices has fewer devices than the second group of electronic devices.

13. The method of claim 10 , wherein predicting whether the electronic device from the second group of electronic devices passes or fails the screening test is performed using an artificial neural network.

14. The method of claim 13 , wherein predicting whether the electronic device from the second group of electronic devices passes or fails the screening test further comprises:

training the artificial neural network by inputting the first set of testing data and the second set of testing data associated with the first group of electronics devices into the artificial neural network; and

using the trained artificial neural network to predict whether the electronic device from the second group of electronic devices passes or fails the screening test.

15. The method of claim 10 , wherein the electronics devices are hard disc drives.

16. The method of claim 15 , wherein the screening test is an adjacent-track interference test.

17. The method of claim 16 , wherein the first set of testing data comprises bit-error rates.

18. The method of claim 16 , wherein the second set of testing data includes at least one of a width of a hard disc drive's writer, repeatable runout, non-repeatable runout, read-after-write error rate, writer overwrite capability, tracks-per-inch margin, and bits-per-inch margin.

19. A method for using an artificial neural network to improve a testing process for electronic devices, the method comprising:

training an artificial neural network to generate a screening test computational model by:

inputting to the artificial neural network a first set of testing data generated as a result of subjecting a first group of electronics devices to a series of tests, wherein the first set of testing data comprises data from predetermined categories of data,

inputting to the artificial neural network a second set of testing data generated as a result of a screening test subjected to the first group of electronic devices, and

generating the screening test computational model by determining, via the artificial neural network and by processing the first set of testing data and the second set of testing data, a weighting factor for each of the predetermined categories of data,

wherein the screening test computational model comprises the determined weighting factors;

subjecting a third set of testing data to the screening test computational model, the third set of testing data generated as a result of a series of tests subjected to a second group of electronic devices, wherein the third set of testing data comprises data from the predetermined categories of data associated with the second group of electronic devices; and

predicting whether electronic devices from the second group of electronic devices pass or fail the screening test, in response to subjecting the third set of testing data to the screening test computational model.

20. The method of claim 19 , wherein the screening test computational model is generated by recursively computing errors between the second set of testing data and a current prediction.