摘要
数控机床状态预测对于及时发觉数控机床健康状况有着非常重要的作用。为了实现数控机床状态的准确预测,提出采用粒子群算法优化支持向量机(PSO-SVM)进行数控机床状态预测方法,其中粒子群算法用于确定支持向量机(SVM)中的训练参数,以得到优化的SVM预测模型。试验结果表明,用PSO-SVM对数控机床状态进行预测,不仅所需样本少,而且具有很好的预测精度。
Prediction of CNC machine is significant to find out the health state of CNC machine.To forecast CNC machine exactly,Support Vector Machine optimized by Particle Swarm Optimization algorithm(PSO-SVM)is proposed to forecast the health state of CNC machine.Particle swarm optimization algorithm is used to determine the training parameters of support vector machine in this model,which can gain optimized SVM forecasting model.The experimental results indicate that the proposed PSO-SVM model not only requires small training data,but also can achieve great accuracy.
出处
《现代制造工程》
CSCD
北大核心
2011年第7期46-49,共4页
Modern Manufacturing Engineering
关键词
支持向量机
参数优化
数控机床
预测模型
Support Vector Machine(SVM)
parameter optimization
CNC machine
forecasting model