Slow time-varying industrial process monitoring technology with recursive concurrent projection to latent Structures

In the time-varying industrial process, the quality of the product is crucial. The existing batch partial least squares (PLS) monitoring model can effectively monitor quality-related faults. In process monitoring, in order to overcome time-varying disturbances, the monitoring model needs to update regularly. How to update the monitoring model efficiently is a serious problem. This paper proposes a recursive concurrent projection to latent structures (RCPLS) algorithm, which can update models more efficiently with historical model parameters and new data, and can also provide better quality-related fault monitoring results than static concurrent projection to latent structures (CPLS). The updated computational quantities of the RCPLS model and the CPLS model are compared through the Tennessee Eastman Process (TEP). The effectiveness of the RCPLS algorithm is verified, and a comprehensive comparison of the quality-related fault detection capabilities of RCPLS and CPLS is performed. The results show that RCPLS can significantly reduce the computational burden and increase monitoring effectiveness.