A fuzzy neural network approach to evaluation of slope failure potential

S. H. Ni, P. C. Lu, C. H. Juang

Research output: Contribution to journalReview articlepeer-review

37 Citations (Scopus)

Abstract

Stability of natural slopes depends highly on their existing geologic conditions and surrounding environment. However, the conditions of a natural slope and its environment usually cannot be described with precise numbers. Thus an approach that is capable of dealing with vagueness in the stability evaluation of natural slopes is essential. This paper presents a fuzzy neural network approach for evaluating the stability of natural slopes. In this approach, fuzzy sets are used to represent the parameters of the neural network. A total of 13 factors that are believed to be important to the stability of natural slopes are used as input parameters. A two-stage training method is used for establishing fuzzy parameters. A fuzzy artificial neural network is developed and tested. A number of hypothetical natural slopes are evaluated, and the results appear to be reasonable compared with those obtained by different approaches in a previous study.

Original languageEnglish
Pages (from-to)59-66
Number of pages8
JournalMicrocomputers in Civil Engineering
Volume11
Issue number1
Publication statusPublished - 1996 Jan 1

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Environmental Science(all)
  • Engineering(all)
  • Earth and Planetary Sciences(all)

Fingerprint Dive into the research topics of 'A fuzzy neural network approach to evaluation of slope failure potential'. Together they form a unique fingerprint.

Cite this