A comprehensive multi-objective optimization study was conducted to mitigate tool wear,decrease energy consumption,and enhance efficiency in the milling of titanium alloy TC4,taking the combined bending moment,machining energy consumption,and machining efficiency as the optimization objective.The effect laws of cutting parameters were analyzed through single-factor experiments and a radial basis neural network prediction model was established by using response surface experiments.Subsequently,the entire prediction model was integrated into a particle swarm algorithm to resolve the Pareto frontier,yielding several reasonable cutting parameter combinations.The results of the test show that:the neural network prediction model achieves a prediction accuracy exceeding 95%.Moreover,the optimization results of multi-objective optimization model can reduce the combined bending moment in the titanium alloy milling process by 28.98%,enhance machining efficiency by 25.93%,and lower machining energy consumption by 13.08%.These results can provide support for the selection of cutting parameters in titanium alloy milling processes and the coordination of multiple production goals.