99 ی يبززاقت ف قيل ذـ تحل ض ؾيلثی ثوگي بعكي ه تقيي ای افطاظیK-means ثطاؾبؼ گكم ز ذغی هطتجبیض تب ( ضزی ه هغبلق: ثرتيبضی زثبضبی ض ؾسض ح) ىؿل قب ضؾ 1 * ، ی فلی آ 2 یقس یؾ ، ؾيس ؾقيس ه 3 هطيسی فلی 4  چىيس اظ ؾبيزطٸټي٪ طآيٷس ي زضب٦ ٷي٫ ټب ثب ټٳ٥لة، يٹٮيس ؾي ټبی س ٻ٣ ٲٷٻ٣طاٸاٶي ٲٷ ٵ ثطای سحٯي٭٫ ی ټٳي٭٧ ای ؾيلة ضا سك ٲي زټٷس. سحٯي٭ ذٹقٻٹٶٻ٪ ٷٹاٴ ای ای اظ ضٸـيطی آٲبضیحٯي٭ چٷس ٲش ټبی س طٸٺ٪ ثطای ؾطی زازٺ٥ ثٷسی يطٸٺ يب ذٹقٻ٪ ثٻ چٷسيٵ ټب اؾز. ايٵ ٻ٣طاٸاٶي ٲٷ ی ثطای سحٯي٭بضآٲس٦ ضٸـ، ضٸـ. زض ايٵ ای ؾيلة اؾز بزٺ اظ ظثبٴ ثطٶبٲٻعاضـ ثب اؾش٪ ؿي ٶٹيR ، سحٯي٭ ذٹقٻ ای ثط اؾب ؼ زازٺي ٲطسجٻ زٸكشبٸضټبی ذ٪ ٻظط ٮح٦ ټبی حسا ای34 بٺ٫ ايؿش سٸزٺ حٹيٻ ؾسټبی ضٸزثبض ٸ زض اؾشبٴ ٮطؾشبٴ ٸ زض ٲح٢ ټيسضٸٲشطی ٸا ساز ثرشيبضی ثطای س2 سب6 . زض سحٯي٭ ذٹقٻشٻ اؾزط٪ ذٹقٻ نٹضر ای، ٹضيشٱ٫ اظ اٮK-means ذٹقٻٻ زض ٶٹ٦ طاظی زؾشٻ ثٷسی ا ثٷسی ٲي قٹز، ثطٸٺ٪ .شٻ قسٺ اؾزط٪ ٽطٺبٺ٫ قسٺ اظ ايؿشب ټبی ازي٭ قسٺ ٸ٧ ټب سك طٸٺ٪ ٷي٫ آظٲٹٴ ټٳ ؾذؽ ثب اٶؼبٵ حٹيٻ ؾسټبی ضٸزثبض ٸ٫ ټبی ټٳ ييٵ قسٺ ثرشيبضی س اٶس. بت وليسیلو و: ٻ٣ ٲٷی، سحٯي٭ ذٹقٻ ثٷسي،كشبٸضټبی ذ٪ ، ای K-means ، ؾسټبی ضٸزثبض ٸ ثرشيبضی. بٮٻ:٣ز ٲ سبضيد زضيب13 يجٽكز اضز1392 سبضيد دصيطـبٮٻ٣ ٲ: 13 آثبٴ1393 1 - زاٶف آٲٹذشٻ قٽيسٷي ٸ ٲٽٷسؾي ضٸزذبٶٻ، دطزيؽبضقٷبؾي اضقس ٲٽٷسؾي٦ ی ثٽكشي، سٽطاٴبٺ قٽيس٫جبؾذٹض، زاٶك 2 - زاٶف آٲٹذشٻبضقٷبؾي اضقس ؾبظٺ٦ یشي قبټطٸزبٺ نٷ٫ ټبی آثي، زاٶك 3 - ثٽكشي، سٽطاٴبٺ قٽيس٫جبؾذٹض، زاٶك قٽيسٷي ٸ ٲٽٷسؾي اؾشبزيبض دطزيؽ 4 - ثٽكشي، سٽطاٴبٺ قٽيس٫جبؾذٹض، زاٶك قٽيسٷي ٸ ٲٽٷسؾي اؾشبزيبض دطزيؽ * - ٬ ٶٹيؿٷسٺ ٲؿئٹ Technical Note Recognition of Homogeneous Regions Using K-means Partitional Cluster Analysis Method Based on Second-order L-moment (Case Study: Roodbar Dam and Bakhtiari Dam Basins) R. Shahsavan  * 2 , A. Ahani 2 , SS. Mousavi Nadoushani 3 and A. Moridi 4 Abstract A group of sites with sufficient homogeneity in producing flood mechanisms form a homogeneous region for regional flood frequency analysis. Cluster analysis is the generic name of a variety of multivariate statistical procedures that are used to classify given data into similar groups or clusters. This procedure is an efficient method for regional flood frequency analysis. In this article, cluster analysis of annual maximum flow data of 34 gauging stations located in Lorestan province in Roodbar Dam and Bakhtiari Dam basins for 2 to 6 clusters has been performed using R programming language. K-means algorithm that is a type of partitional clustering has been used for cluster analysis. Merged groups of sites have been formed and homogeneous groups of Roodbar and Bakhtiari dam basins has then been identified by performing homogeneity test. Keywords: Regionalization, Cluster Analysis, L-moments, K-means, Roodbar and Bakhtiari Dams. Received: May 3, 2014 Accepted: October 5, 2014 1- M.Sc. of River Engineering, Shahid Abbaspour Campus, ShahidBeheshti University, Tehran, Iran. Email: shahsavanrasoul@yahoo.com 2 M.Sc. of Agricultural Engineering – Water Structures, School of Agricultural Engineering, Shahrood University of Technology, Shahrood, Iran 2 Assistant Professor, Faculty of Water and Environmental Engineering, Shahid Abbaspour Campus, Shahid Beheshti University, Tehran, Iran. 2 Assistant Professor, Faculty of Water and Environmental Engineering, Shahid Abbaspour Campus, Shahid Beheshti University, Tehran, Iran. *- Corresponding Author حميمبت ه تبثـ آة ايطاى Iran-Water Resources Research ن، قوبض ؾبل ز3 ، ظهؿتبى1393 Volume 10, No. 3, Winter 2015 (IR-WRR) 103 - 99