According to the characteristics of aircraft assembly, a new comprehensive evaluation method for aircraft assembling tech-nique based on support vector machine ( SVM) is proposed. To acquire the training sample and evaluation vector, in this method, the suitable evaluation indexes are chosen from the aspects of assembly efficiency, assembly costs, assembly precision and human factors to build the membership function with fuzzy mathematics. Then, in this method, those training samples previously acquired are used to train the SVM, so that prediction vectors can be imported into the well-trained SVM to obtain the final evaluation result. Because this new method has the advantages of balancing risk and accuracy of SVM, it can be used to obtain a more accurate and reliable evaluation result.%针对飞机装配的特点,提出了一种基于支持向量机的飞机装配工艺性综合评价方法.该方法从装配效率、装配成本、装配精度、人机工效学4个方面选取对应的评价指标,通过模糊数学建立这些指标的隶属度函数,从而获取训练样本和评价向量.并利用获取的训练样本对支持向量机进行训练,将获取的预测向量导入训练好的支持向量机中得出评价结果.该方法充分利用了支持向量机的均衡风险性和准确率的优点,可得到准确、可信的评价结果.
展开▼
