ENBIS-21 Online Conference

Session

Process 2

PS62_C13

15 Sept 2021, 12:00

Online

Conveners

Process 2

• Chair: Christian Weiß (Helmut Schmidt University)

25. A novel fault detection and diagnosis approach based on orthogonal autoencoders

Davide Cacciarelli (Technical University of Denmark (DTU))

15/09/2021, 12:00

Process

The need to analyze complex nonlinear data coming from industrial production settings is fostering the use of deep learning algorithms in Statistical Process Control (SPC) schemes. In this work, a new SPC framework based on orthogonal autoencoders (OAEs) is proposed. A regularized loss function ensures the invertibility of the covariance matrix when computing the Hotelling $T^2$ statistic and...

38. Fault detection in continuous chemical processes using a PCA-based local approach

Ms Leticia Almada (Federal University of Minas Gerais)

15/09/2021, 12:20

Process

Early fault detection in the process industry is crucial to mitigate potential impacts. Despite being widely studied, fault detection remains a practical challenge. Principal components analysis (PCA) has been commonly used for this purpose. This work employs a PCA-based local approach to improve fault detection efficiency. This is done by adopting individual control limits for the principal...

81. A novel online PCA algorithm for large variable space dimensions

Philipp Froehlich (University of Wuerzburg), Rainer Göb

15/09/2021, 12:40

Process

Principal component analysis (PCA) is a basic tool for reducing the dimension of a space of variables. In modern industrial environments large variable space dimensions up to several thousands are common, where data are recorded live in high time resolution and have to be analysed without time delay. Classical batch PCA procedure start from the full covariance matrix and construct the exact...