Title page for ETD etd-09222008-135734

Type of Document Dissertation
Author Baughman, D. Richard
URN etd-09222008-135734
Title Neural Networks in Bioprocessing and Chemical Engineering
Degree PhD
Department Chemical Engineering
Advisory Committee
Advisor Name Title
Liu, Y. A. Committee Chair
Conger, William L. Committee Member
Davis, Richey M. Committee Member
McGee, Henry A. Jr. Committee Member
Rony, Peter R. Committee Member
  • artificial intelligence
  • neural network
  • chemical engineering
  • bioprocessing
Date of Defense 1995-12-01
Availability unrestricted
This dissertation introduces the fundamental principles and practical aspects of neural networks, focusing on their applications in bioprocessing and chemical engineering. This study introduces neural networks and provides an overview oftheir structures, strengths, and limitations, together with a survey oftheir potential and commercial applications (Chapter 1). In addition to covering both the fundamental and practical aspects of neural computing (Chapter 2), this dissertation demonstrates, by numerous illustrative examples, practice problems, and detailed case studies, how to develop, train and apply neural networks in bioprocessing and chemical engineering. This study includes the neural network applications of interest to the biotechnologists and chemical engineers in four main groups: (1) fault classification and feature categorization (Chapter 3); (2) prediction and optimization (Chapter 4); (3) process forecasting, modeling, and control of time-dependent systems (Chapter 5); and (4) preliminary design of complex processes using a hybrid combination of expert systems and neural networks (Chapter 6).

This dissertation is also unique in that it includes the following ten detailed case studies of neural network applications in bioprocessing and chemical engineering: • Process fault-diagnosis of a chemical reactor. • Leonard-Kramer fault-classification problem. • Process fault-diagnosis for an unsteady-state continuous stirred-tank reactor system. • Classification of protein secondary-structure categories. • Quantitative prediction and regression analysis of complex chemical kinetics. • Software-based sensors for quantitative predictions ofproduct compositions from fluorescent spectra in bioprocessing. • Quality control and optimization of an autoclave curing process for manufacturing composite materials. • Predictive modeling of an experimental batch fermentation process. • Supervisory control of the Tennessee Eastman plantwide control problem • Predictive modeling and optimal design of extractive bioseparation in aqueous two-phase systems This dissertation also includes a glossary, which explains the terminology used in neural network applications in science and engineering.

  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  LD5655.V856_1995.B384.V1.pdf 13.28 Mb 01:01:28 00:31:37 00:27:39 00:13:49 00:01:10
  LD5655.V856_1995.B384.V2.pdf 11.37 Mb 00:52:37 00:27:03 00:23:40 00:11:50 00:01:00

Browse All Available ETDs by ( Author | Department )

dla home
etds imagebase journals news ereserve special collections
virgnia tech home contact dla university libraries

If you have questions or technical problems, please Contact DLA.