Two-stage clustering algorithm for block aggregation in open pit mines

Abstract One of the main obstacles in using exact optimisation methods for open pit production scheduling is the size of real mining problems, which forms an intractable optimisation problem. The objective of this paper is to develop, implement, verify and validate a clustering algorithm for block aggregation for the purpose of production scheduling. The algorithm aggregates blocks into selective mining units based on a similarity index which is defined based on rock types, ore grades and distances between blocks. A two-stage clustering approach based on agglomerative hierarchical algorithm and tabu search is developed and tested. The algorithm is validated by a case study on an iron ore life of mine production schedule. The results illustrate that the size and shape of the aggregated blocks have 10–15% effect on the project’s net present value and also a significant impact on the practicality of long term production schedules genereated.

[1]  A. Mehrez,et al.  A Production Problem in Phosphate Mining , 1985 .

[2]  Leila Silva,et al.  Adaptive Mean-Linkage with Penalty : A new algorithm for cluster analysis , 2008 .

[3]  Zengyou He,et al.  G-ANMI: A mutual information based genetic clustering algorithm for categorical data , 2010, Knowl. Based Syst..

[4]  Natashia Boland,et al.  A strengthened formulation and cutting planes for the open pit mine production scheduling problem , 2010, Comput. Oper. Res..

[5]  Darwin Klingman,et al.  Integer Programming for Optimal Phosphate-Mining Strategies , 1988 .

[6]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[7]  Mark Gershon,et al.  Optimizing single hole mine cuts by dynamic programming , 1989 .

[8]  Rajive Ganguli,et al.  A genetic algorithms approach for grade control planning in a bauxite deposit , 2005 .

[9]  Alexandra M. Newman,et al.  A Review of Operations Research in Mine Planning , 2010, Interfaces.

[10]  Mark Gershon,et al.  Optimal mine production scheduling: evaluation of large scale mathematical programming approaches , 1983 .

[11]  Zengyou He,et al.  k-ANMI: A mutual information based clustering algorithm for categorical data , 2005, Inf. Fusion.

[12]  Kwame Awuah-Offei,et al.  Large-scale open pit production scheduling using Mixed Integer Linear Programming , 2010 .

[13]  S. C. Johnson.  Hierarchical clustering schemes , 1967, Psychometrika.

[14]  Joshua Zhexue Huang,et al.  A Fast Clustering Algorithm to Cluster Very Large Categorical Data Sets in Data Mining , 1997, DMKD.

[15]  Teofilo F. Gonzalez,et al.  On the computational complexity of clustering and related problems , 1982 .

[16]  Lou Caccetta,et al.  An Application of Branch and Cut to Open Pit Mine Scheduling , 2003, J. Glob. Optim..

[17]  Behrooz Karimi,et al.  Long-term open pit mine production planning: a review of models and algorithms , 2008 .

[18]  Joshua Zhexue Huang,et al.  Extensions to the k-Means Algorithm for Clustering Large Data Sets with Categorical Values , 1998, Data Mining and Knowledge Discovery.

[19]  Salih Ramazan,et al.  The new Fundamental Tree Algorithm for production scheduling of open pit mines , 2007, Eur. J. Oper. Res..

[20]  Meena Mahajan,et al.  The Planar k-means Problem is NP-hard I , 2009 .

[21]  M. Kumral,et al.  A simulated annealing approach to mine production scheduling , 2005, J. Oper. Res. Soc..

[22]  Asoo J. Vakharia,et al.  A comparative investigation of hierarchical clustering techniques and dissimilarity measures applied to the cell formation problem , 1995 .

[23]  Kai Liu,et al.  A fast divisive clustering algorithm using an improved discrete particle swarm optimizer , 2010, Pattern Recognit. Lett..