We propose a novel fault detection and classification approach via non-negative matrix factorisation with sparseness constraints (NMFSC) and Structural Support Vector Machines (Structural SVMs). The NMFSC method can n...
详细信息
We propose a novel fault detection and classification approach via non-negative matrix factorisation with sparseness constraints (NMFSC) and Structural Support Vector Machines (Structural SVMs). The NMFSC method can not only reduce data dimension, but also better describe the local feature of the process because of non-negative and sparsenessconstraints. The function of Structural SVMs is to identify multiple kinds of faults using only one uniform discriminative model instead of multiple ones. Tennessee Eastman Process (TEP), a benchmark chemical engineering problem, is used to generate datasets to evaluate the performance of the proposed approach. The results from the experiment show the superiority of the new method compared with the state-of-the-art approaches.
暂无评论