Fuzzy C-Means Cluster Analysis Based on Variable Length String Genetic Algorithm for the Grouping of Rock Discontinuity
- PDF / 1,220,612 Bytes
- 10 Pages / 595 x 786 pts Page_size
- 39 Downloads / 198 Views
pISSN 1226-7988, eISSN 1976-3808 www.springer.com/12205
DOI 10.1007/s12205-020-2188-2
Geotechnical Engineering TECHNICAL NOTE
Fuzzy C-Means Cluster Analysis Based on Variable Length String Genetic Algorithm for the Grouping of Rock Discontinuity Sets Xuejie Cuia and E-chuan Yana Faculty of Engineering, China University of Geosciences, Wuhan 430074, China
a
ARTICLE HISTORY
ABSTRACT
Received 31 December 2019 Revised 3 May 2020 Accepted 14 June 2020 Published Online 4 September 2020
Discontinuities have huge impact on civil and mining engineering. To understand the spatial features of discontinuities, it is common to group them into different sets based on orientation. In this paper, a new algorithm is introduced for the identification of discontinuity sets. The new algorithm is developed by combined fuzzy C-means algorithm with variable length string genetic algorithm. In the new method, the number of discontinuity sets is not the necessary input parameter any more. This method is robust, global optimal and totally automatic. To verify its validity, the new method was firstly applied to an artificial data as well as a published data. For artificial data set, the assignment error rate is only 7.4%. For published data set, only 2 discontinuities are assigned to wrong sets. The results indicate that the new algorithm is better than fuzzy C-means algorithm and comparable with other common methods. Afterwards, the new method was utilized to analyze the orientation data sampled at an underground storage cavern site. The new method determines that the ideal number of sets is 3. The new method provided satisfactory results, which confirm its effectiveness and convenience.
KEYWORDS Rock discontinuity Fuzzy C-means algorithm Variable length string genetic algorithm Orientation analysis Underground storage cavern
1. Introduction Discontinuities play a major role in determining the mechanical and hydrological behavior of rock masses (Kulatilake et al., 1993; Duncan and Christopher, 2004; Salimzadeh and Khalili, 2015; Lei et al., 2017). The understanding of discontinuities will help a lot to civil engineering and mining applications. Generally, discontinuities occur in sets and tend to have a pattern (Hammah and Curran, 1998). It is a fundamental issue to identify discontinuity sets based on orientation when analyzing discontinuity data. Commonly, this work is done by taking stock of contoured stereographic projections of discontinuity poles. Although intuitive, this method has been found to be heavily dependent on personal experience (Hammah and Curran, 1998; Jimenez, 2008; Xu et al., 2013). The defect of the method prompts the search for alternative techniques. In 1976, Shanley and Mahtab developed a density-based clustering algorithm for identifying discontinuity sets (Shanley and Mahtab, 1976). This method was enhanced by Mahtab and Yegulalp by modifying the way in which non-core
CORRESPONDENCE E-chuan Yan
[email protected]
ⓒ 2020 Korean Society of Civil Engineers
points are assigned (Mahtab and Yegulalp, 1982)
Data Loading...
