The construction of underground engineering in urban areas involves a vast array and substantial quantity of construction machinery, which can pose a significant challenge of noise pollution during construction. To address this issue, a noise management method based on optimizing the configuration of construction machinery is presented. Firstly, the primary noise sources during construction are analyzed, and a noise source model is established. Secondly, the health effects induced by exposure to construction noise are analyzed, and the exposure-response formula is determined. Finally, a multi-objective optimization model for the configuration of construction machinery is developed, which takes into account the health damage cost caused by construction noise, as well as constraints on construction period, cost, and quality. To demonstrate the feasibility and practicality of the proposed method, a case study of deep excavation construction in a tunnel engineering project in Wuhan is presented, and a hybrid algorithm combining genetic algorithm and improved quantum particle swarm optimization algorithm is utilized to solve the optimization model. The results indicate that the proposed method can reduce construction noise while meeting the requirements for construction efficiency, and thus has significant potential for practical implications.