.png){kind=icon}
.png){kind=icon}
Return
Preconditioning Water Distribution Network Optimization with Head Loss-Based Design Method
.png){kind=icon}
PRE
AI
DOI：10.1061/(ASCE)WR.1943-5452.0001299.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper develops a new domain knowledge-based initial design method for the optimization of water distribution network design. The new initial water distribution network design method, termed as head loss-based design preconditioner (HDP), is based on head loss analysis in the supplying path from source to user. The new HDP-preconditioned search is compared with two algorithms: one preconditioned on a velocity-based initial design method and a simple genetic algorithm without preconditioning. Results show the HDP head loss-based method outperforms the prescreened heuristic sampling method (PHSM) in terms of the quality of the initial solutions and computational efficiency on all three cases. HDP also outperforms stochastic initialization on two of the three cases. The results obtained imply that the proposed domain knowledge-based design method HDP also would be able to provide effective starting conditions for other optimization algorithms, besides genetic algorithm for large water distribution systems, since most optimization methods are greatly assisted by a good starting condition.
Keywords:
Water distribution network
Preconditioning
Optimization
Design
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.7
Papers:
8.1K
Citations:
1.6W
View more organizations