Single Phase Laminar & Turbulent Flow Classification via a Knowledge-Based Linear Model


Following the success of support vector machines (SVMs) and neural network (NNs) model for data classification, this study presents a knowledge-based linear classification model for single phase fluid flow in the annulus with the Reynolds number equations used as prior knowledge also for classification. This approach is achieved by simulating the experimental laminar & turbulent flow data and Reynolds number equation through a knowledge-based classification model. Classification of fluid flow patterns can be seen as a machine learning problem where the inputs are vectors of length 5 with attributes that represent the parameters which determine the fluid flow in the annulus or pipe. The classification weight includes information inherent to each flow type with respect to its critical Reynolds number, and it will be in the form of a polyhedral set. The algorithm constructs a separating hyperplane, where the weights of the hyperplane represent a scaled level of importance for each of the parameters.

  • Abstract
  • Introduction
  • Knowledge-Based Linear Classification Model
  • Flow Pattern Dataset
  • Discussion of Results
  • Conclusion
  • Reference
Topics: Turbulence

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In