T
Thomas J. McAvoy
Researcher at University of Maryland, College Park
Publications - 146
Citations - 7575
Thomas J. McAvoy is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Artificial neural network & Process control. The author has an hindex of 43, co-authored 145 publications receiving 7333 citations. Previous affiliations of Thomas J. McAvoy include University of Maryland, Baltimore.
Papers
More filters
Journal ArticleDOI
Use of neural nets for dynamic modeling and control of chemical process systems
N. Bhat,Thomas J. McAvoy +1 more
TL;DR: The backpropagation algorithm is applied to model the dynamic response of pH in a CSTR and is shown to be able to pick up more of the nonlinear characteristics of the CSTR.
Journal ArticleDOI
Nonlinear principal component analysis—Based on principal curves and neural networks
Dong Dong,Thomas J. McAvoy +1 more
TL;DR: In this paper, a nonlinear principal component analysis (NLPCA) method which integrates the principal curve algorithm and neural networks is presented. But when applied to data sets the algorithm does not yield an NLPCA model in the sense of principal loadings.
Journal ArticleDOI
Identification of faulty sensors using principal component analysis
TL;DR: In this article, a sensor validity index (SVI) is proposed to determine the status of each sensor and the way the index is filtered represents an important tuning parameter for sensor fault identification.
Journal ArticleDOI
Nonlinear PLS Modeling Using Neural Networks
S.J. Qin,Thomas J. McAvoy +1 more
TL;DR: The proposed neural net PLS method gives better prediction results than the PLS modeling method and the direct neural network approach and is shown that, by analysing the NN PLS algorithm, the global NNPLS model is equivalent to a multilayer feedforward network.
Journal ArticleDOI
Base control for the Tennessee Eastman problem
Thomas J. McAvoy,N. Ye +1 more
TL;DR: An approach to configure a basic PID control system for the recently published Tennessee Eastman testbed process control problem using a combination of steady-state screening tools, followed by dynamic simulation of the most promising candidates.