Lahiri, S. K.

National Institute of Technology, Durgapur, India

Development of support vector regression-based soft sensor

Khalfe, N., Lahiri, S. K., National Institute of Technology

Application was used in a commercial ethylene glycol plant

A support vector classification method for regime identification of slurry transport in pipelines

Ghanta, K. C., Lahiri, S. K., National Institute of Technology

Statistical analysis showed the proposed solution has an average misclassification error of only 1.5%

Computational fluid dynamics simulation of solid–liquid slurry flow

Ghanta, K. C., Lahiri, S. K., National Institute of Technology

The resulting model's predictions showed reasonably good agreement with the experimental data

Genetic algorithm tuning improves artificial neural network models

Ghanta, K. C., Lahiri, S. K., National Institute of Technology

The technique is illustrated by predicting hold-up of slurry flow in pipelines

Minimize power consumption in slurry transport

Ghanta, K. C., Lahiri, S. K., National Institute of Technology

Accurately predict critical velocity

Process modeling and optimization strategies integrating neural networks and differential evolution

Garawi, M. A., Khalfe, N., Lahiri, S. K., National Institute of Technology

The technology was applied to an ethylene oxide reactor

Novel approach for process plant monitoring

Al-Baiyaa, M., Lenka, C., Jubail United Petrochemical Co., Sabic; Khalfe, N., Lahiri, S. K., National Institute of Technology

Using statistical data compression important process changes can be quickly detected and identified