Optimization of Operation Modes of the Roasting Conveyor Machine Using the Coevolutionary Algorithm of Cuckoo Search

The article deals with an urgent scientific problem of optimizing the operation modes of a roasting conveyor machine used to produce phosphorite pellets from apatite-nepheline ore waste stored in tailing dumps of mining and processing plants. The specifics of this problem (in particular, the non-linearity, the large dimensionality, the computational complexity) significantly limits the possibilities of applying the deterministic search methods. This leads to the choice of stochastic methods, in particular, population algorithms, which are based on modeling the collective behavior of living organisms (bees, ants, wolves, etc.) and allow simultaneous processing of several solutions. The problem is proposed to be solved using the cuckoo search algorithm, which is distinguished by a small number of "free" parameters that affect its convergence. The coevolutionary approach was used to determine the optimal values of these parameters. Its essence lies in the parallel launch of several versions of the bioinspired algorithm with different "settings" for each subpopulation. The calculation of the penalty for subpopulations at each iteration is performed using the Takagi-Sugeno fuzzy inference algorithm. The use of optimization results to manage a chemical-technological system for processing apatite-nepheline ores waste should provide an energy-saving operation mode of the roasting conveyor machine.