Stochastic-Optimization Annealing of an Intelligent Open Pit Mine Design

Optimized pit layouts are used to extract mineable reserves with minimum waste under geological, geotechnical and property boundary constraints and to develop strategic and tactical production plans for achieving corporate goals. Pit design and optimization algorithms are limited in dealing with the random field properties of these layouts resulting in sub-optimal results. Database changes require complete rerun of these algorithms resulting in long CPU times with no allowance for incorporating operating strategies. in this study, the authors develop an intelligent pit optimizer, IPOP, to solve these problems. It combines stochastic models of ore reserves and commodity prices to generate economic block and target values. the error backpropation algorithm is used to train the neural network for block pattern recognition and partitioning based on the target values. the PITSEARCH program is then used to search for the optimized layout under the pit slope constraints. Stochastic-optimization annealing is carried out to examine the random field properties of the optimized pit value. IPOP is used to optimize Section SBHP 860001 of the Sabi open pit in Zimbabwe, and the results are compared with that from the 2D Lerchs-Grossmann\u27s algorithm. the two algorithms yield the same value of ZS3.58 milliona for the optimized Section SBHP 860001. in addition, IPOP provides analysts with the risks associated with the optimized value of this section with a reduced CPU time