A fault identification method of analog circuit based on improved limit learning machine

A technology for simulating circuit faults and extreme learning machines, which can be used in analog circuit testing, neural learning methods, electronic circuit testing, etc., and can solve problems such as lack of modeling flexibility in diagnostic models.

Active Publication Date: 2019-01-04
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The selection of input variables and the construction of the diagnostic model constructed by the existing knowledge-based diagnostic methods are mostly fixed in advance, which not only makes the diagnostic model lack the flexibility of modeling, but also does not need to keep the nodes and input parameters in a certain range. To a certain extent, it affects the accuracy of modeling, and at the same time brings unnecessary computational complexity

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
  • A fault identification method of analog circuit based on improved limit learning machine
  • A fault identification method of analog circuit based on improved limit learning machine
  • A fault identification method of analog circuit based on improved limit learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0072] figure 1 It is a flow chart of the fault identification method for analog circuits based on the improved extreme learning machine of the present invention.

[0073] In this example, if figure 1 Shown, the present invention a kind of analog circuit fault identification method based on improved extreme learning machine, comprises the following steps:

[0074] S1. Collect voltage eigenvalues ​​at different corner frequencies

[0075] Such as figure 2 As shown, analyze the corner frequency of the analog circuit, and collect the voltage eigenvalues ​​of N groups of samples at different corner frequencies in the fault state and healthy state of the analog circuit, denoted as X={x 1 ,x 2 ,...,x i ,...,x N}, where the voltage eigenvalue x i ={x i,1, x i,2 ,...,x i,k ...,x i,T},x i,k Indicates the voltage value of the i-th sample collected at the k-th corner frequency, and T is the number of corner frequencies;

[0076] Construct the expected output vector Y={y for...

example

[0137] In order to illustrate the technical effects of the present invention, an analog circuit is taken as an example to verify the implementation of the present invention. Such as image 3 As shown, the circuit is composed of 4 second-order filters and an adder, and it is modeled and simulated using Pspice software. The tolerance of R1, R2, R3, R4, R5, R6, R7 and R8 is ±10%, the tolerance of C1, C2, C3, C4, C5, C6, C7 and C8 is ±5%, the gain of the amplifier is Av1 , the tolerance of Av2, Av3 and Av4 is ±1%, and the tolerance of R9, R10 and R11 is ±1%. Analysis shows that the circuit has 4 corner frequencies: 10Hz, 100Hz, 10kHz and 100kHz. The probability of a single fault in an analog circuit accounts for about 80%, so only the state monitoring and health management of a single fault is considered.

[0138] Set Av 1 ,Av 2 ,Av 3 and Av 4 In (1.1~1.5%)Xn, (1.6~2%)Xn, (2.1~2.5%)Xn, (2.6~3.0%)Xn, (3.1~3.5%)Xn, (3.6~4.0%)Xn, ( 4.1~4.5%)Xn, (4.6~5.0%)Xn, (5.1~5.5%)Xn, (5....

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 fault identification method of an analog circuit based on an improved extreme learning machine, wherein the method comprises steps: the voltage eigenvectors of analog circuits at different corner frequencies are used as inputs, and then input vectors corresponding to each hidden layer neuron are selected based on each entropy rate, and weights and offsets that reach the highest correlation degree are generated through the multi-dimensional particle swarm optimization algorithm, then the appropriate parameters are found by PSO algorithm and iterative operation, so as to construct an efficient hidden layer model; finally, the hidden layer model is trained to identify the fault of analog circuit, and the fault of analog circuit can be identified. The model has the characteristics of high fault identification accuracy and high speed.

Description

technical field [0001] The invention belongs to the technical field of circuit fault identification and machine learning, and more specifically relates to an analog circuit fault identification method based on an improved extreme learning machine. Background technique [0002] With the development of modern electronic technology, the integration of analog circuits is getting higher and higher, and the design of circuits is becoming more and more complex. How to effectively monitor the status of analog circuits accurately to ensure their reliable operation has become the current topic in the field of analog circuits. Research hotspots. [0003] Existing typical diagnostic methods for analog circuits mainly include diagnostic methods based on analytical models, diagnostic methods based on signal analysis and diagnostic methods based on knowledge. [0004] The diagnostic method based on the analytical model compares the measurable information of the diagnosed analog circuit wi...

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): G06F17/50G06N3/08G06N3/00G01R31/316
CPCG06N3/006G06N3/08G01R31/316G06F30/367
Inventor 刘震梅文娟杨成林周秀云田书林
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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