Abstract

In order to solve the problems of welding deformation in the process of calibrating the medium and small tonnage crane arm’s, method of LS-SVM was introduced in the paper. Using the deformation of the crane arm cylinder as the input of the LS-SVM, and using the pressure of the hydraulic system as the output of the LS-SVM. The model was trained, in the mean while the theory of the Genetic algorithm was adopted to optimize the parameters of Kernel function and the Penalty factor, in the process the Error function was defined as the evaluation index, in the end the parameters of Kernel function and the Penalty factor was confirm, σ=2.7 and c=37. Finally, in order to verify the feasibility and accuracy of the model, the intelligent hydraulic pressure calibration device which was based on the LS-SVM was used in the actual calibrating work. The result shows that the device for correction of the deformation has a good effect, the deformation of after calibrating was reduced apparently, and its maximum deformation was less than 2mm. The intelligent hydraulic pressure calibration device based on the LS-SVM could replace the traditional calibration methods, this method was an effective correction method at present.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call