Intelligent detection method and system of crankshaft thrust pieces

A technology of intelligent detection and thrust piece, which is used in measuring devices, optical testing of flaws/defects, and material analysis by optical means, etc. Production needs, reduce manual feature extraction process, and meet the effect of online product detection

Inactive Publication Date: 2019-04-05
SHAOXING UNIVERSITY
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the deficiencies of the prior art, the present invention provides an intelligent detection method and system for the crankshaft thrust piece that solves the problems of the existing detection method of the crankshaft thrust piece and the low degree of overall automation of the system, high labor intensity of workers, and poor measurement accuracy

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
  • Intelligent detection method and system of crankshaft thrust pieces
  • Intelligent detection method and system of crankshaft thrust pieces
  • Intelligent detection method and system of crankshaft thrust pieces

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be specifically introduced below in conjunction with the accompanying drawings and specific embodiments.

[0022] Such as figure 1 As shown, an intelligent detection method for the crankshaft thrust piece includes the following steps: S1 acquires images of different working surfaces of the crankshaft thrust piece, S2 performs denoising and normalized preprocessing on the obtained images, and S3 establishes deep learning based on the preprocessed images Network, and train the initial weight of the network and the feature mapping relationship between the sample and the non-defective template. S4 uses the features obtained by the deep learning network to detect and classify the crankshaft thrust plate to be tested.

[0023] For step S1, obtain images of different working surfaces of the crankshaft thrust plate:

[0024] The images of different working surfaces of the crankshaft thrust plate are acquired by the image acquisition device, and multi...

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 an intelligent detection method and system of crankshaft thrust pieces. The method comprises the following steps: acquiring images of different working surfaces of a crank thrust piece; performing denoising and normalizing preprocessing on the acquired images; establishing a deep learning network according to the preprocessed images, and training a mapping relationship between an initial weight of the network and features of a defect-free template; and detecting and classifying crankshaft thrust pieces to be detected by using the features acquired by the deep learning network. By adoption of the intelligent detection method of the crankshaft thrust pieces provided by the invention, the features in the images can be spontaneously learned under an unsupervised condition, thereby requiring no particular artificial marking or other special processing on the features of the trained images, so that the weight training can be quickly completed, and the quality detection time can be greatly shortened.

Description

technical field [0001] The invention relates to the technical field of intelligent detection, in particular to an intelligent detection method and system for a crankshaft thrust plate. Background technique [0002] As a kind of engine sliding bearing, the crankshaft thrust plate mainly plays the role of crankshaft axial support in the engine, and prevents the axial movement of the crankshaft while ensuring the axial rotation of the crankshaft. With the rapid development of the automobile industry and the internal combustion industry, my country has become a big consumer of crankshaft thrust plates, and its demand is growing rapidly. At the same time, the requirements for its quality are also getting higher and higher. In particular, the crankshaft thrust plate, as a wear-reducing gasket that participates in mechanical transmission and bears axial pressure, has requirements for its thickness, defect area of ​​the appearance working surface, and parameters such as holes, oil g...

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): G01N21/88
CPCG01N21/8851G01N2021/8854
Inventor 马海平朱敏杰金宝根
Owner SHAOXING UNIVERSITY
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