A prediction method for crankshaft fatigue life based on genetic nerve network

A fatigue life prediction and fatigue life technology, applied in the direction of biological neural network model, gene model, etc., can solve the problems of crankshaft test damage and long test time.

Inactive Publication Date: 2012-09-26
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF2 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a crankshaft fatigue life prediction method based on genetic neural network, using the historical data tested by the crankshaft bending fatigue testing machine as a training sample set, training the genetic neural network model,

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 prediction method for crankshaft fatigue life based on genetic nerve network
  • A prediction method for crankshaft fatigue life based on genetic nerve network
  • A prediction method for crankshaft fatigue life based on genetic nerve network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] Below in conjunction with embodiment the method of the present invention is described in detail. The present invention is not limited to the following examples, and any design idea utilizing the present invention falls within the protection scope of the present invention.

[0066] First, the original test data of 100 DC resonant crankshaft fatigue life testing machines, where p1-p10 is the crankshaft natural frequency unit (Hz) collected every 6 seconds within 1 minute, and the fatigue life is the test cycle number unit (times), See Table 1.

[0067] Table 1 The original data of the DC resonance crankshaft fatigue life testing machine in the first half of 2011

[0068]

[0069] Normalize the original data in Table 1 to build a training sample set (a 1 ...a 100 ), where each training sample a i (1≤i≤100) contains 10 inputs and 1 crankshaft fatigue life history test value, such as Figure 4 shown. For example, the first training sample a in the training sample se...

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 prediction method for crankshaft fatigue life based on a genetic nerve network, belongs to the field of crankshaft fatigue life testing of an internal combustion engine. The purpose of the method is to solve the deficiency of a DC resonant-type crankshaft fatigue life testing machine for possessing destructiveness to the crankshaft testing and having long testing time. The principle of the method is to normalize the historical data of the crankshaft testing by utilizing the conventional DC resonant-type crankshaft fatigue life testing machine to obtain a training sample set; to optimize a BP artificial nerve network model through genetic algorithm; to carry out iteration training to the genetic algorithm-based and optimized BP artificial nerve network by utilizing the training sample set to obtain a trained BP artificial nerve network prediction model; to use the prediction model to carry out rapid prediction for the crankshaft fatigue life. The method optimizes the BP artificial nerve network based on the genetic algorithm, avoids the "over fitting" problem of the single BP nerve network, improves the training speed and prediction precision effectively; rapidly predicts the crankshaft fatigue life in a short time without destroying the crankshaft quality, is capable of carrying out a batch testing for the crankshafts of a whole production batch.

Description

technical field [0001] The invention relates to a method for predicting crankshaft fatigue life based on a genetic neural network, which belongs to the field of fatigue life testing of internal combustion engine crankshafts. Background technique [0002] The safety and reliability of mechanical products are important indicators of the technical level. The reliability and failure issues within the product design life have an important impact on human production and life, so they have been widely concerned by people. The crankshaft is a key bearing part of the internal combustion engine, and one of the main contents of its reliability is its fatigue life under the action of high cycle fatigue stress. [0003] On the one hand, due to the complexity of the crankshaft fatigue life problem, there are still many limitations in the current technical level through purely mathematical derivation and calculation analysis of the reliability of the crankshaft in actual work. For example,...

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
IPC IPC(8): G06N3/02G06N3/12
Inventor 孙福振廖乐健李艳李业刚刘彦臣李国强杜建光
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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