基于支持向量机的钢淬透性预测研究

Study on support vector machine-based prediction of steel quenching degree

支持向量机是建立在统计学理论之上的强有力的机器学习技术。本文提出了基于支持向量机模型预测钢淬透性的方法,并分析了核函数的选择对支持向量机建模的影响。以江阴兴澄钢铁公司的实际数据进行实验,结果表明,支持向量机方法有着良好的泛化能力,优于人工神经网络建模方法。

Support vector machine （SVM） is a powerful machine learning technique based on statistical learning theory （SLT）. In this paper, an SVM-based approach applied to predict steel quenching degree is presented, and the effects of selecting kernel function on SVM modeling are also analyzed. With real data collected from Jiangyin Xingcheng Steel Work CO. LTD, experiments show that SVM-based method is effective and superior to ANN based method on generalization performance.