%0 Journal Article
%T Research on Application of Regression Least Squares Support Vector Machine on Performance Prediction of Hydraulic Excavator
%A Zhan-bo Chen
%J Journal of Control Science and Engineering
%D 2014
%I Hindawi Publishing Corporation
%R 10.1155/2014/686130
%X In order to improve the performance prediction accuracy of hydraulic excavator, the regression least squares support vector machine is applied. First, the mathematical model of the regression least squares support vector machine is studied, and then the algorithm of the regression least squares support vector machine is designed. Finally, the performance prediction simulation of hydraulic excavator based on regression least squares support vector machine is carried out, and simulation results show that this method can predict the performance changing rules of hydraulic excavator correctly. 1. Introduction The hydraulic excavator belongs to the construction machinery, which has been applied in many fields successfully, such as transportation industry, mining industry, construction industry, and hydraulic engineering. The hydraulic excavator is made up of three parts, which are working equipment, upper turntable, and traveling gear. Normally working conditions of the hydraulic excavator are bad, and the loads being applied to the hydraulic excavator are big; therefore, the engine will deviate from operating mode with low fuel consumption, and then hydraulic excavator will exhibit poor performance. In addition, the energy consumption of the hydraulic pressure system is big, which can lead to the big energy wasting. Therefore, it is necessary to predict the performance of the hydraulic excavator correctly, and then the working efficiency of the hydraulic excavator can be improved [1]. The performance predicting procession is nonlinear, which is affected by many uncertain factors; therefore, an effective predicting technology should be chosen. At present, there are many performances prediction methods, such as artificial neural network technology, grey prediction technology, and extension technology [2]. However, the current prediction technologies have some disadvantages: the predicting precision is low, the predicting efficiency is low, and the operation is difficult [2]. Generally, the support vector machine has the nonlinear and uncertain characteristics. In recent years, the support vector machine was established by Vapnik, which has been concerned by many scientists, and the support vector has strong learning ability. Some scientists have improved the support vector machine. The least squares support vector machine is put forward by SukKens. The least squares support machine introduces the least squares system into the support vector, while the traditional support machine applies the two planning methods to deal with function estimation problem;
%U http://www.hindawi.com/journals/jcse/2014/686130/