Skip to main content
padlock icon - secure page this page is secure

Residual life prediction method for remanufacturing sucker rods based on magnetic memory testing and a support vector machine model

Buy Article:

$22.00 + tax (Refund Policy)

It is crucial for remanufacturability to be able to determine the residual life of remanufacturing cores. In the light of weaknesses in the available methods for fatigue damage evaluation and residual life prediction for remanufacturing sucker rods, a novel prediction approach using an optimised support vector machine (SVM) model based on metal magnetic memory (MMM) testing is proposed here. Firstly, tension-tension fatigue experiments on pre-cut groove sucker rod specimens are conducted to investigate the variations in the magnetic memory signals after different numbers of cycles and seven characteristic parameters are extracted to characterise the degree of fatigue damage. Then, a residual life prediction model for remanufacturing sucker rods based on a SVM model is established, where the SVM model parameters, including the radial basis function (RBF) kernel parameter and the penalty factor, are optimised in turn by a genetic algorithm (GA), partical swarm optimisation (PSO) and grid search optimisation (GSO). The results show that the proposed PSO-based approach significantly improves the prediction accuracy, compared with a basic SVM approach, and also yields more stable and accurate results when compared with the GA and the GSO method, providing a new and feasible approach for predicting remaining life.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Keywords: METAL MAGNETIC MEMORY TESTING; PARAMETER OPTIMISATION; REMANUFACTURING SUCKER RODS; RESIDUAL LIFE PREDICTION; SUPPORT VECTOR MACHINE

Document Type: Research Article

Publication date: January 1, 2019

More about this publication?
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more