Optimisation of Aluminium Electrolysis Current Efficiency Based on Multi-Strategy Improved Dung Beetle Optimisation Algorithm

Aluminum electrolysis is a complex production process, and current efficiency is crucial. This paper proposes a Multi-Strategy Improved Dung Beetle Optimization Algorithm (MSIDBO) to optimize the current efficiency of aluminum electrolysis, addressing the issues of low convergence accuracy and tendency to get trapped in local optima that are common with traditional algorithms. By initializing the population with chaotic mapping, introducing the Levy flight strategy, and dynamically adjusting the optimal solution, the algorithm's global optimization capability and convergence speed are enhanced. Experimental results show that MSIDBO outperforms other algorithms on the CEC2022 test functions and, combined with the AMFormer model, successfully optimizes the production parameters of aluminum electrolysis, significantly improving current efficiency and reducing energy consumption.