Online process monitoring based on incremental LPP

Process monitoring by manifold learning has become an important research area. This paper proposes an online process monitoring scheme based on incremental locality preserving projection (LPP). As new data sample arrives, the algorithm makes use of the previous computation results to update the neighbor structure; and also by using the eigenvectors at last time step as the initial vector of the Raleigh quotient iteration, thus achieves higher efficiency. The incremental LPP is then used to construct process monitoring model for blast furnace ironmaking process. Application results show that the proposed method can efficiently track the time-varying characteristics of the process, discover faults of the process and reduce false alarms.