Multivariate time series data classification has a wide range of applications in reality. With rapid development of deep learning, convolutional networks are widely used in this task and have achieved the current best performance. However, due to high difficulty and cost of collecting this type of data, labeled data is still scarce. In some tasks, the model shows overfitting, resulting in relatively poor classification performance. In order to improve the classification effect under such situation, this paper proposes a novel classification method based on transfer learning - similar domain knowledge transfer (call SDKT for short). Firstly, we designed a multivariate time series domain distance calulation method (call MTSDDC for short), which helped selecting the source domain that are most similar to target domain; Secondly, we used ResNet as a pre-trained classifier, transfered the parameters of the similar domain network to the target domain network and continued to fine-tune the parameters. To verify our method, we conducted experiments on several public datasets. Our study has also shown that the transfer effect from the source domain to the target domain is highly negatively correlated with the distance between them, with an average pearson coefficient of -0.78. For the transfer of most similar source domain, compared to the ResNet model without transfer and the current best model, the average accuracy improvement on the datasets we used is 4.01% and 1.46% respectively.