Papers by Soundar Ramchandran
Minimize Trapped Components in Distillation Columns
Chemical Engineering, 2006
Minimize Trapped Components in Distillation Columns
Chemical Engineering, 2006
Control of a distillation column using virtual analyzer
Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251), 2000
Summary form only given. In many processes, especially distillation columns, feed composition cha... more Summary form only given. In many processes, especially distillation columns, feed composition changes can be a source of large disturbances that affect process operations. Feed composition changes affect the physical behavior of the process phenomenon, i.e., thermodynamics, vapor-liquid equilibrium, etc., and therefore, such disturbances tend to have a more pronounced impact on the operations, and typically, it takes more time to recover from such upsets. Often times, feed composition changes are not transient disturbances. They can be the result of changes made “on-purpose” to the front-end of the unit such as adjustments to reactor conditions, etc. Moreover, there is usually a significant deadtime associated with such disturbances. All of the above can pose a challenging control problem. The column operation can be adversely affected if the feed composition change is not anticipated properly and appropriate corrective action are not taken in a timely manner. The problem is complicated by the fact that online analyzers are rare in industrial practice partly due to analyzer reliability and maintenance issues, and partly due to the fact that online analysis of certain streams are difficult or cost prohibitive
Neural network control of distillation: an industrial application
Proceedings of the 1997 American Control Conference (Cat. No.97CH36041), 1997
ABSTRACT The use of models to improve control of chemical processes has been an active area for a... more ABSTRACT The use of models to improve control of chemical processes has been an active area for academic research for the past two decades. Neural networks is one such topic; research has shown neural networks possess the potential to model complicated process systems, and how these models could be used to improve control and operation of such processes. The paper discusses an application of a neural network model-based controller to an industrial distillation column
Do neural networks offer something for you?
The concept of neural network computation was inspired by the hope to artifically reproduce some ... more The concept of neural network computation was inspired by the hope to artifically reproduce some of the flexibility and power of the human brain. Human beings can recognize different patterns and voices even though these signals do not have a simple phenomenological understanding. Scientists have developed artificial neural networks (ANNs) for modeling processes that do not have a simple phenomenological explanation, such as voice recognition. Consequently, ANN jargon can be confusing to process and control engineers. In simple terms, ANNs take a nonlinear regression modeling approach. Like any regression curve-fitting approach, a least-squares optimization can generate model parameters. One advantage of ANNs is that they require neither a priori understanding of the process behavior nor phenomenological understanding of the process. ANNs use data describing the input/output relationship in a process to {open_quotes}learn{close_quotes} about the underlying process behavior. As a res...
Consider Steady-State Models for Process Control
Journal of Process Control, 1995
This paper presents a novel approach for process control that uses neural networks to model the s... more This paper presents a novel approach for process control that uses neural networks to model the steadystate inverse of a process which is then coupled with a simple reference system synthesis to generate a multivariable controller. The control strategy is applied to dynamic simulations of two methanol-water distillation columns that express distinctly different behaviour from each other (one simulates a lab column, while the second simulates an industrial-scale high-purity column). A steady-state process simulation package was used to generate all the neural network training data. An efficient training algorithm based on a nonlinear least-squares technique was used to train the networks. The neural network modelbased controllers show robust performance for both setpoints and disturbances, and performed better than conventional feedback proportional-integral (PI) controllers with feedforward features.
Uploads
Papers by Soundar Ramchandran