Under the strategic backdrop of the “dual carbon” goals, the low-carbon transformation of the coal mining industry is now urgent. Addressing the issues of energy waste and low coal production efficiency caused by the operation of coal cutters in fully mechanized mining faces, this paper proposes a method for the synergistic optimization of energy efficiency and operational effectiveness of coal cutters based on cutting resistance prediction, aiming to achieve efficient and energy-saving operation of coal cutters. First, to address the complex and variable operating conditions in fully mechanized mining faces, an optimized radial basis function neural network (SPSO-RBF) is employed to accurately predict the cutting resistance of coal cutters; second, by analyzing the resistance encountered by coal cutters during operation, an energy consumption model based on cut-ting resistance is established; furthermore, the non-dominated sorting genetic algorithm-II (NSGA-II+ARSBX) based on adaptive rotary simulated binary crossover is used to establish a multi-objective optimization model with the objectives of minimizing energy consumption, maximizing coal production efficiency, and maximizing block coal area, and the optimized traction speed and drum speed of the coal miner are obtained; finally, engineering case verification is conducted based on coal miner data from the Jinjie Coal Mine. The results show that under the one-cut process, energy consumption is reduced by 20.04%, coal mining productivity is increased by 45.71%, and the area of lump coal is increased by 41.56%, verifying the correctness and effectiveness of the proposed model and algorithm.