为了克服神经网络以及单输出支持向量回归算法在有限元模型修正中的不足，提出了基于多输出支持向量回归算法的有限元模型修正方法。根据5-折交叉验证法选择支持向量回归机的参数，用均匀试验设计法构造样本，联合结构的动力和静力响应数据作为输入，多个设计参数作为输出，以支持向量回归机逼近输入输出二者之间的非线性映射关系，然后利用支持向量回归机的泛化推广能力，求解设计参数的目标值。空间网格结构数值模型的分析结果表明，该方法能同时修正多个设计参数，在少量样本的情况下具有较高的修正精度，为有限元模型修正提供了一种新的探索。

In order to overcome the shortcomings in finite element model updating of traditional neural networks and single-output support vector regression, a new method based on multiple-output support regression algorithm is proposed in this paper. The selection of parameters of support vector regression according to 5-fold cross validation, use the uniform design method to construct the samples, put the static and dynamic response data as the inputs and a number of design parameters as the outputs, use the support vector regression machine to approximation the mapping relationship between the inputs and outputs, then use the generalization ability of the support vector regression machine to get the target value of the design parameters value. The result of numerical application to a space grid structure shows that: this method proposed in this paper could update a number of design parameters with high precision in the case of a small number of samples. The method proposed in this paper provides a new exploration for finite element model updating.