Construction resource leveling using neural networks

Daniela Savin, Sabah Alkass, Paul Fazio

Research output: Contribution to journalArticlepeer-review

42 Citations (Scopus)


A neural network model for construction resource leveling is developed and discussed. The model is derived by mapping an augmented Lagrangian multiplier optimization formulation of a resource leveling problem onto a discrete-time Hopfield net. The resulting neural network model consists of two main blocks. Specifically, it consists of a discrete-time Hopfield neural network block, and a control block for the adjustment of Lagrange multipliers in the augmented Lagrangian multiplier optimization, and for the computation of the new set of weights of the neural network block. An experimental verification of the proposed artificial neural network model is also provided.

Original languageEnglish
Pages (from-to)917-925
Number of pages9
JournalCanadian Journal of Civil Engineering
Issue number4
Publication statusPublished - Aug 1996
Externally publishedYes


  • Construction management
  • Neural networks in construction
  • Project management
  • Resource leveling

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • General Environmental Science


Dive into the research topics of 'Construction resource leveling using neural networks'. Together they form a unique fingerprint.

Cite this