China Nonferrous Metallurgy

To improve the utilization efficiency of electric energy and reduce the energy consumption of aluminium electrolysis,according to the real production data of an aluminium plant in Guizhou, the optimization model of aluminium electrolysis process parameters was constructed with the multi-objective of maximum current efficiency and minimum tonne of aluminium energy consumption by using the grey correlation analysis method to select the seven parameterswith significant impact, including cell voltage (U), electrolysis temperature (Tb), feed interval (tNB), aluminium level (hm), electrolyte level (hg), molecular ratio (rm) and out aluminum (q). The improved Non-dominated Sorting Genetic Algorithm (NSGA-II) was used to compare and analyse the differences between 60 sets of actual values and the theoretical values of the traditionaland improved NSGA-II algorithm, the performance of the algorithm was verified using 30 sets of actual production data, and the Pareto front was obtained by iterative calculations using MATLAB software. The results show that the optimal set of current efficiency of the improved NSGA-II algorithm is 95.66%, and the energy consumption of tonnes of aluminium is 12424.54kW·h; compared with the traditional NSGA-II algorithm, the current efficiency is improved by 0.31%, and the energy consumption of tonnes aluminium is reduced by 22.11kW·h, which achieves the effect of energy saving and consumption reduction, and verifies the effectiveness and applicability of the improved NSGA-II algorithm in improving the optimization of the process parameters of aluminium electrolysis. It verifies the effectiveness and applicability of the improved NSGA-II algorithm in improving the optimization of aluminium electrolysis process parameters, and can provide reference suggestions for the optimization of aluminium electrolysis energy saving and production design.