Ross E. Gough - Foothill Ranch CA, US Steven Neal Rivkin - Laguna Niguel CA, US
Assignee:
Western Digital Technologies, Inc. - Irvine CA
International Classification:
G06F 11/00
US Classification:
714 473, 706 21
Abstract:
A method of predicting disk drive failure at a central processing facility using an evolving drive failure prediction algorithm (DFPA) is disclosed. A set of quality metric values are transmitted from each of a plurality of remote disk drives to the central processing facility. The DFPA is executed at the central processing facility in response to the quality metric values to detect an impending failure of at least one of the remote disk drives. The DFPA is evolved at the central processing facility in response to a reference data base of quality metric values and a corresponding failure indicator. The processes is repeated so as to improve the accuracy of the DFPA over time.
Binning Disk Drives During Manufacturing By Evaluating Quality Metrics Prior To A Final Quality Audit
Ross E. Gough - Foothill Ranch CA, US Steven Neal Rivkin - Laguna Niguel CA, US Jan G. Abrahamsson - San Clemente CA, US Carl R. Messenger - Mission Viejo CA, US Arun Makhija - Fremont CA, US Gordon K. Rydquist - San Jose CA, US Michael J. Cullen - Discovery Bay CA, US
Assignee:
Western Digital Technologies, Inc. - Lake Forest CA
International Classification:
G06F 19/00
US Classification:
702 81, 702123
Abstract:
A method of binning disk drives by evaluating quality metrics prior to a final quality audit is disclosed. A number of disk drives are assembled, and a plurality of quality metrics are generated for each disk drive representing a plurality of operating characteristics. The quality metrics for each disk drive are evaluated for binning the disk drives into a plurality of lots including a first lot and a second lot. A final quality audit (FQA) is performed by executing a number of write and read operations for a plurality of the disk drives in each lot and classifying each disk drive as passing or failing the FQA. If the number of disk drives that fail the FQA out of the first lot falls below a first threshold, the first lot is classified as acceptable for a first tier customer. If the number of disk drives that fail the FQA out of the second lot falls below a second threshold, the second lot is classified as acceptable for a second tier customer.
Using A Genetic Algorithm To Select A Subset Of Quality Metrics As Input To A Disk Drive Failure Prediction Algorithm
Ross E. Gough - Foothill Ranch CA, US Steven Neal Rivkin - Laguna Niguel CA, US
Assignee:
Western Digital Technologies, Inc. - Lake Forest CA
International Classification:
G06F 11/30
US Classification:
702185, 360 75, 702123, 714 38
Abstract:
A subset of quality metrics as input to a disk drive failure prediction algorithm (DFPA) may be selected using a genetic algorithm. The DFPA is executed for an initially selected generation of subset quality metrics using quality metric values stored in a reference data base. At least one DFPA setting is adjusted and the DFPA executed again for the selected subset. After training the DFPA, the best DFPA setting is saved for the selected subset. A fitness score is generated for the selected subset, representing an accuracy of the DFPA relative to failure indicators stored in the reference data base. At least one genetic operator is applied in response to the fitness scores to generate a new generation of subsets. The process is repeated until a best subset of quality metrics and corresponding DFPA setting are found.
Methods And Systems For Optimizing Engine Selection Using Machine Learning Modeling
- Newport Beach CA, US Steven Neal Rivkin - Laguna Niguel CA, US
International Classification:
G10L 15/16 G06N 3/08 G10L 15/30
Abstract:
A system for optimizing selection of transcription engines using a combination of selected machine learning models. The system includes a plurality of preprocessors that generate a plurality of features from a media data set. The system further includes a deep learning neural network model, a gradient boosted machine model and a random forest model used in generating a ranked list of transcription engines. A transcription engine is selected from the ranked list of transcription engines to generate a transcript for the media dataset.
Isbn (Books And Publications)
Technology Unbound:Transferring Scientific and Engineering Resources from Defense to Civilian Purposes: Transferring Scientific and Engineering Resources from Defense to Civilian Purposes