Unlike many other techniques used in process control, which are widely applied in practice and play significant roles, abnormal situation management (ASM) still relies heavily on human experience, not least because the problem of fault detection and diagnosis (FDD) has not been well addressed. In this paper, a process fault diagnosis method using multi-time scale dynamic feature extraction based on convolutional neural network (CNN) consisting of similarity measurement, variable ranking, and multi-time scale dynamic feature extraction is proposed. The CNN-based model containing the fixed multiple sampling (FMS) layer can extract dynamic characteristics of process data at different time scales. The benchmark Tennessee Eastman (TE) process is used to verify the performance of the proposed method. K E Y W O R D S convolutional neural network, dynamic feature extraction, fault diagnosis, TE process
Invariant features
characterize the essential nature
of things
behind the apparently rapid and noisy changes. Thus, learning invariances
become one of the key problems of machine learning. Slow-feature analysis
(SFA) is one such method. However, slowness in the original SFA, which
is used as the learning criterion, is defined based on the linear
temporal dependency assumption. To overcome this limitation, a new
learning principle is introduced in this paper to define slowness
that is suitable for nonlinear dynamic systems from an information
perspective. This new principle is called EVOLVE·INFOMAX as it
seeks to maximize the information preservation of system states during
dynamic evolution, while aligning each feature to having the same
uncertainty and constraining the features to be quasi-independent.
The theoretical properties of this new principle are rigorously justified,
which shows the characteristics of the model behavior, the optimality
of the induced estimator, and the relationship with maximum likelihood
estimation. The equivalence to the original definition of SFA is also
analyzed, and the existence of a solution is shown. Two case studies
show the potential capabilities and flexibility of the proposed method
in both slow-feature extraction and downstream tasks, such as process
monitoring.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.