Nonlinear process monitoring based on load weighted denoising autoencoder

Abstract

Traditional monitoring methods are trained with normal data and map the process variables into latent variables directly. However, for these methods, the process variables would become intertwined in the latent variables, which results in that the fluctuations of process variables would be submerged in noise or neutralized in latent variables space. In order to address the submergence and neutralization problems, a novel algorithm load weighted denoising autoencoder (LWDAE) is proposed. According to the direction and magnitude of online data, the loading matrix of LWDAE is weighted to highlight the useful information of both training data and online data in latent variables space. In addition, to reduce the effect of noise on weighting matrix, LWDAE modifies the loss function by adding two new regularizations and revises the calculation logic of weighting matrix to consider the successive samples. Case studies of continuous stirred tank reactor demonstrate the effectiveness of LWDAE.