摘要
近年来,水火弯板加工自动化是船舶制造行业的研究热点和难点。由于影响钢板变形结果的参数之间复杂的非线性关系,导致水火弯板变形预测不能够快速准确的实现。支持向量机(SVM)具有良好的泛化能力,将其应用于水火弯板变形预测,可有效解决非线性、小样本、高维数等问题。支持向量机性能的好坏取决于其参数的选取,本文选用粒子群算法(PSO)来优化SVM的相关参数,并将预测结果和传统的支持向量机模型的预测结果进行对比分析。结果表明,PSO_SVM模型用于水火弯板变形预测可以较好地提高预测精度。
The line heating process automation has been the research hotspot and difficulty of shipbuilding industry in recent years. Because of the complicated nonlinear relationship between the results of the impact plate deformation parameters, resulting in the line heating deformation prediction will not be able to achieve fast and accurate. Support vector machine (SVM) can effectively solve the small sample, nonlinear, high dimension and other issues due to its excellent generalization ability, so it has been used in line heating deformation prediction. Since the performance of SVM results depends on the selection of parameters. In this paper, the particle swarm optimization (PSO) is used to optimize the parameters of SVM; and then the line heating deformation prediction based on PSO_SVM could be established. The predicted results are compared with the traditional SVM. The results show that the PSO_SVM deformation prediction model used in line heating can improve the prediction accuracy.
出处
《舰船科学技术》
北大核心
2015年第7期54-57,共4页
Ship Science and Technology
基金
江苏省科技厅资助项目(BY2011143)
关键词
水火弯板
支持向量机
粒子群优化算法
变形预测
line heating
support vector machine
particle swarm optimization
deformation prediction