Method, device, and apparatus for hard disk maintenance, and readable storage medium

A hard disk and preset technology, applied in the storage field, can solve the problems of low hard disk failure rate, difficult maintenance work for hard disk operation and maintenance personnel, and low single hard disk failure rate, so as to reduce workload, improve hard disk maintenance efficiency, and solve the problem of inconvenient maintenance Effect of comprehensive or redundant repairs

Inactive Publication Date: 2018-11-20
ZHENGZHOU YUNHAI INFORMATION TECH CO LTD
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the current manufacturing process has made rapid progress and the failure rate of a single hard disk is low, in large-scale storage devices, due to the large number of hard disks, hard disk failures are still frequent
The low failure rate of hard disks has brought great difficulties to the prediction of hard disk failures and the maintenance work of operation and maintenance personnel.
[0004] At present, the maintenance model for the hard disk in the storage system is to use the hard disk failure prediction method to predict the failure. After the hard disk failure prediction is completed, the operation and maintenance personnel are notified to carry out on-site maintenance, and the maintenance efficiency is low.
Moreover, most of the existing hard disk failure prediction methods use a single prediction model, and the accuracy of the prediction results is low, which undoubtedly further hinders the efficiency of hard disk maintenance.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device, and apparatus for hard disk maintenance, and readable storage medium
  • Method, device, and apparatus for hard disk maintenance, and readable storage medium
  • Method, device, and apparatus for hard disk maintenance, and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Please refer to figure 1 , figure 1 It is a flow chart of a hard disk maintenance method in an embodiment of the present invention, the method includes the following steps:

[0053] S101. Obtain the target index data of the hard disk and input them into different prediction sub-models to perform fault prediction, and obtain initial prediction results output by each prediction sub-model.

[0054]In the embodiment of the present invention, the target index data refers to various performance data of the hard disk, such as the underlying data read error rate, seek error rate, seek performance, and the like. Each prediction sub-model can be obtained by training with different machine learning methods, and the specific learning method corresponding to each prediction sub-model can be determined according to the actual operating environment and training effect, which is not limited here. It should be noted that different prediction sub-models mean that each prediction sub-mo...

Embodiment 2

[0064] Please refer to figure 2 , figure 2 It is a flowchart of another hard disk maintenance method in an embodiment of the present invention, and the method includes the following steps:

[0065] S201. Obtain the target index data of the hard disk and input them into different prediction sub-models for failure prediction, and obtain initial prediction results output by each prediction sub-model.

[0066] S202. Perform fault pre-analysis by using the fault prediction model in combination with the accuracy rates of each prediction sub-model and the corresponding initial prediction results, and obtain a fault prediction result including a fault occurrence rate.

[0067] When using each initial prediction result to determine the failure occurrence rate, the failure prediction model may be used in combination with the accuracy of each prediction sub-model and the corresponding initial prediction result for analysis. Specifically, it is assumed that there are j (j>=2) predicti...

Embodiment 3

[0073] Please refer to image 3 , image 3 It is a flow chart of a hard disk maintenance method in an embodiment of the present invention, the method includes the following steps:

[0074] S301. Obtain target index data of the hard disk.

[0075] S302. Input the target index data into different prediction sub-models including decision tree prediction sub-model, Bayesian network prediction sub-model, neural network prediction sub-model and support vector machine prediction sub-model to perform fault prediction, and obtain each Predict the initial prediction output by the submodel.

[0076] Among them, the decision tree prediction sub-model, the Bayesian network prediction sub-model, the neural network prediction sub-model and the support vector machine prediction sub-model use the principle of decision tree, Bayesian network, neural network and vector machine for fault prediction respectively. model. Decision tree, Bayesian network, neural network and vector machine are com...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a hard disk maintenance method. The method comprises the following steps: obtaining target index data of a hard disk and respectively inputting the target index data into different prediction submodels to carry out fault prediction, and obtaining initial prediction results output by each prediction submodel; inputting each initial prediction result to a preset fault prediction model for fault pre-analysis, to obtain fault prediction results; when the fault prediction result satisfies a preset fault correcting trigger condition, starting the preset fault correcting process to repair the hard disk. The hard disk maintenance method provided by the embodiment can improve hard disk maintenance efficiency and reduce workload of operation and maintenance personnel. The invention also discloses a device and an apparatus for hard disk maintenance and a readable storage medium, having corresponding technical effects.

Description

technical field [0001] The present invention relates to the field of storage technology, in particular to a hard disk maintenance method, device, equipment and readable storage medium. Background technique [0002] With the rapid development of Internet, cloud computing and other technologies, governments, enterprises and other institutions have generated massive amounts of data. These massive data require large-scale storage devices to store them. [0003] The core of mass storage devices is the hard disk. To ensure that stored data is not lost and protect data security, it is necessary to ensure that hard drives rarely fail. Although the current manufacturing process has made rapid progress and the failure rate of a single hard disk is low, in large-scale storage devices, due to the large number of hard disks, hard disk failures are still frequent. The low failure rate of hard disks has brought great difficulties to the prediction of hard disk failures and the maintenan...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F3/06
CPCG06F3/0604G06F3/0614G06F3/0629G06F3/0655G06F3/0689
Inventor 张贵勇
Owner ZHENGZHOU YUNHAI INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap