Application of the recurrent multilayer perceptron in modeling complex process dynamics

1994 ◽  
Vol 5 (2) ◽  
pp. 255-266 ◽  
Author(s):  
A.G. Parlos ◽  
K.T. Chong ◽  
A.F. Atiya
Mathematics ◽  
2018 ◽  
Vol 6 (11) ◽  
pp. 242 ◽  
Author(s):  
Wee Wong ◽  
Ewan Chee ◽  
Jiali Li ◽  
Xiaonan Wang

The pharmaceutical industry has witnessed exponential growth in transforming operations towards continuous manufacturing to increase profitability, reduce waste and extend product ranges. Model predictive control (MPC) can be applied to enable this vision by providing superior regulation of critical quality attributes (CQAs). For MPC, obtaining a workable system model is of fundamental importance, especially if complex process dynamics and reaction kinetics are present. Whilst physics-based models are desirable, obtaining models that are effective and fit-for-purpose may not always be practical, and industries have often relied on data-driven approaches for system identification instead. In this work, we demonstrate the applicability of recurrent neural networks (RNNs) in MPC applications in continuous pharmaceutical manufacturing. RNNs were shown to be especially well-suited for modelling dynamical systems due to their mathematical structure, and their use in system identification has enabled satisfactory closed-loop performance for MPC of a complex reaction in a single continuous-stirred tank reactor (CSTR) for pharmaceutical manufacturing.


2014 ◽  
Vol 43 (5) ◽  
pp. 1388-1420 ◽  
Author(s):  
Andreas Wihler ◽  
Gerhard Blickle ◽  
B. Parker Ellen ◽  
Wayne A. Hochwarter ◽  
Gerald R. Ferris

In recent years, personal initiative has been found to predict job performance. However, implicit in this direct initiative–performance relationship are more complex process dynamics that can be better understood when contextual antecedents, moderators, and mediators are considered. Drawing from perspectives of proactive behavior as a goal-directed process, a research model of personal initiative was tested in a three-study investigation intended to build upon and advance prior work. Specifically, the model indicates that climate for initiative interacts with the social astuteness dimension of political skill (i.e., opportunity recognition) to influence the demonstration of personal initiative, and this first part of the model is tested and supported in Study 1. Then, personal initiative is hypothesized to interact with the interpersonal influence dimension of political skill (i.e., opportunity capitalization) to predict supervisor assessments of job performance, and this part of the model is tested and supported in Study 2. Study 3 provided a test of the entire model and demonstrated support for moderated mediation, thus adding increased confidence in the validity of the theory and findings through constructive replication.


Author(s):  
Rick L. Vaughn ◽  
Shailendra K. Saxena ◽  
John G. Sharp

We have developed an intestinal wound model that includes surgical construction of an ileo-cecal patch to study the complex process of intestinal wound healing. This allows approximation of ileal mucosa to the cecal serosa and facilitates regeneration of ileal mucosa onto the serosal surface of the cecum. The regeneration of ileal mucosa can then be evaluated at different times. The wound model also allows us to determine the rate of intestinal regeneration for a known size of intestinal wound and can be compared in different situations (e.g. with and without EGF and Peyer’s patches).At the light microscopic level it appeared that epithelial cells involved in regeneration of ileal mucosa originated from the enlarged crypts adjacent to the intestinal wound and migrated in an orderly fashion onto the serosal surface of the cecum. The migrating epithelial cells later formed crypts and villi by the process of invagination and evagination respectively. There were also signs of proliferation of smooth muscles underneath the migratory epithelial cells.


Sign in / Sign up

Export Citation Format

Share Document