关键词: 过程监测;高斯混合模型;实例迁移;权重分配;全局概率指标

Abstract: Considering the shortage of industrial process data， process monitoring model based on data statistics is difficultly established， resulting in an adverse impact on the accuracy and timeliness of monitoring. Transfer learning provides an effective way for the above situation. In view of the fact that the coal mill process data in the target domain is less， on the basis of the source domain coal mill data， a target domain coal mill process monitoring model based on the instance-based transfer Gaussian mixture model(GMM)is established. The instance-based transfer learning is used to assign weight of source domain production process and target domain process data， using the modified algorithm of GMM to automatically optimize the number of Gaussian components and corresponding model parameters. The global probability index of the process monitoring is applied to realize the cross-domain monitoring of the coal mill process. The research results of the coal mill process verify the feasibility and effectiveness of the proposed method.

Key words: process monitoring; Gaussian mixture model; instance-based transfer learning; weight distribution; global probability index