The invention discloses an optimization method for energy conservation and emission reduction of aluminum electrolysis based on decision maker preference information. Firstly, a recursive neural network is used to model an aluminum electrolysis production process, and then a decision maker sets a desired target value, an R-dominance preference dominance method is introduced, a multi-objective quantum particle swarm algorithm is combined to optimize a production process model, and an optimal decision variable that best meets the expectation of the decision maker, and the corresponding current efficiency, cell voltage, perfluorinated compound emissions and the energy consumption per ton of aluminum are further obtained. The MQPSO algorithm does not need to perform crossover and mutation operations, and only requires the simplest location update step, so that the encoding process is simple, a strong global search capability is realized, the integrity of a preference optimal value in the process of population evolution can be easily implemented, and the needs of the decision maker can be met. By using the method to determine the optimal value of process parameters in the aluminum electrolysis production process, the current efficiency can be effectively improved, the cell voltage can be reduced, the greenhouse gas emissions and the energy consumption per ton of aluminum can be reduced, and the purpose of energy conservation and emission reduction can be achieved.