Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electronic component fault diagnosis model based on data analysis and prediction

A fault diagnosis model and technology of electronic components, applied in database models, relational databases, structured data retrieval, etc., can solve problems such as relying on manual processing, inability to mine business value, and time-consuming task cycles, reducing manual repetition. Inspect work, tap the potential of production quality control, ensure the effect of reliability and stability

Pending Publication Date: 2019-10-15
SHANGHAI PRECISION METROLOGY & TEST RES INST
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current new environment of parallel development of multi-model tasks and high-intensity launches, traditional test and test technology methods are under increasing pressure on efficiency and cost, such as time-consuming, labor-intensive, and material-intensive task cycles, which cannot keep up with the fast pace Research and development requirements; test data is not centrally stored and utilized, and business value cannot be mined; business processes rely heavily on manual processing, data quality is inconvenient to quote, process traceability is difficult, and processing efficiency is low, etc.

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
  • Electronic component fault diagnosis model based on data analysis and prediction
  • Electronic component fault diagnosis model based on data analysis and prediction
  • Electronic component fault diagnosis model based on data analysis and prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] like figure 2 As shown, the implementation case includes: data acquisition module, data preprocessing module, fault diagnosis model building module, storage module, prediction module and prediction result output module.

[0038] The data acquisition module obtains the original batch of electronic component test data files, and each file contains a batch of component data, including the batch number, date, serial number, nominal voltage, and nominal capacitance of the batch of components , size, test voltage, evaluation, electrical performance parameters and tolerances of electrical performance parameters and other metadata.

[0039] The data preprocessing module preprocesses the received batch electronic component test data files, and performs data cleaning on the batch component data according to the tolerance range of the nominal value of each electrical performance parameter of the batch component, that is, each electronic component The performance parameters must be...

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 provides an electronic component fault diagnosis model based on data analysis and prediction. The electronic component fault diagnosis model comprises a data acquisition module, a data preprocessing module, a fault diagnosis model construction module, a prediction module and a prediction result output module. The fault diagnosis model construction module receives the 'clean' structured data set and then performs clustering to obtain a plurality of clusters. For each cluster, fractal geometry is applied to quantify the fractal dimension value of the cluster, the fractal dimensionvalue of each cluster is the fault feature of the cluster, and the value is used for judging the fault type existing in the batch components. Input data is stored in a storage module in a classified mode according to fault types. According to the method, the manual repetitive detection work is reduced, the music detection period is shortened, the screening cost is reduced, the production quality control potential of electronic components of manufacturers is excavated, the continuous improvement of the music ability and benefits is realized, high-quality and high-reliability electronic components are provided for models, and the reliability and stability of aerospace model products are ensured.

Description

technical field [0001] The invention relates to the field of electronic components, in particular to a fault diagnosis model of electronic components based on data analysis and prediction. Background technique [0002] Electronic components are important components of aerospace weapons and equipment, and the reliability and stability of their quality may determine the success or failure of aerospace product missions. According to statistics, 80% of aerospace quality problems are related to the quality of components. [0003] At present, the component quality and reliability assurance business mainly relies on the traditional test and detection technology, that is, the "one case, one discussion" small sample test and identification technology. Through the test and test of each type of component, each specification, and each production batch, Such as appearance inspection, pre-screening test, temperature shock, sealing inspection, X-ray inspection, vibration, impact, stress, ...

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): G06F11/07G06F16/215G06F16/25G06F16/28G06K9/62
CPCG06F11/079G06F16/215G06F16/258G06F16/285G06F18/23213
Inventor 陈闪闪蔡滨妮张运洪张亚军杨积东李春陈继勋
Owner SHANGHAI PRECISION METROLOGY & TEST RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products