Big-data computer system fault detection method based on deep recursion network

A computer system and fault detection technology, applied in the detection of faulty computer hardware, the use of neural networks to detect faulty hardware, biological neural network models, etc., can solve problems such as failure, complex structure, rapidity and accuracy to be improved, etc. Achieve the effects of preventing system failures, accurately finding failures, and predicting excellent results

Active Publication Date: 2018-08-28
哈尔滨工创智能科技有限公司
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the existing fault detection and processing methods mainly rely on the experience knowledge of domain experts, which puts forward higher requirements on the experience level of experts. Negligence can also lead to failure
At the same time, in the fault prediction process, it is necessary to manually extract and select fault features. Using the method of artificial neural network and relying on a large amount of historical data, the rapidity and accuracy of prediction also need to be improved.
With the development of big data computing systems, their structures are becoming more and more complex, and people cannot quickly detect the cause of failures, let alone predict failures

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
  • Big-data computer system fault detection method based on deep recursion network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Such as figure 1 As shown, the deep recursive network-based big data computer system fault detection method provided by the embodiment of the present invention includes the following steps:

[0023] The first step is to establish a mathematical model for the system according to its input-output relationship. By periodically sampling the operating state of the measurement system, the input-output data that changes dynamically over time is obtained, and the time series data that exists before and after the measurement points are dependent.

[0024] Define the time of the system as t, the input information of the system at the current moment is x(t), and the output data of the system is y(t). In order to judge the output y(t) of the system at time t, the input data x(t) at time t and all historical input data of the system before time t-1 are used as input.

[0025] Step 2, create mapping f: Make Infinitely approximates y(t). The specific method is: build a five-lay...

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 relates to a computer system fault detection method, in particular to a big-data computer system fault detection method based on a deep recursion network. The big-data computer system fault detection method has the advantages that the deep recursion network is introduced to a fault detection step, training and learning are conducted according to historical data, and manual feature extraction is replaced; fault features are extracted automatically via the network, weights can be updated in real time, and the difficulty in manual section of the fault features is eliminated; throughreal-time data learning and feature extraction, faults are discovered quickly and accurately, the types of the faults are predicated, and system performance is improved.

Description

technical field [0001] The invention relates to a computer system fault detection method, in particular to a large data computer system fault detection method based on a deep recursive network. Background technique [0002] At present, with the increasing scale and structural complexity of big data computing systems, their overall system performance has been affected in many ways. If a state node fails, other nodes connected to it will also be affected and cannot operate normally. At the same time, if the fault cannot be detected in time, it will continue to spread and even lead to the paralysis of the entire system. [0003] In the existing big data storage system, the use of fault detection technology can detect the possibility of system failure in advance according to the detection results, and make corresponding rescue preparations. The system state data is a typical time series data, which is the key to establish the system fault model. Establishing a system fault mo...

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): G06F11/22G06N3/04
CPCG06F11/2263G06N3/045
Inventor 王宏志赵志强
Owner 哈尔滨工创智能科技有限公司
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