Industrial process fault variable identification method based on support vector description

The invention discloses an industrial process fault variable identification method based on support vector description. The method comprises the following steps: step 1, data acquisition; 2, data preprocessing; step 3, offline training a support vector data description model; 4, calculating the hypersphere center of the support vector data description model; step 5, online data acquisition; 6, calculating the offset of the support vector center of each dimension; and 7, determining a fault related variable. The fault identification method based on the support vector theory has the advantages that the fault identification method based on the support vector theory is provided for the nonlinear variable identification problem in the industrial process and the nonlinear variable overall structure deviation, and compared with a traditional method, the fault variable identification rate is increased, and professionals can be effectively assisted in positioning a fault source. 本发明公开了一种基于支持向量描述的工业过程故障变量识别方法，包括如下步骤：步骤