Aiming at noise problem of two-stage gearbox, this paper uses the panel acoustic contribution analysis (PACA) and response surface methodology to conduct structural-borne acoustics analysis and multi-objective optimization of gearbox. Using this optimization, optimal layout and parameters of the added ribs can be determined. The dynamic model of a spur gear-shaft-bearing system is built in consideration of the time-varying mesh stiffness, the time-varying bearing stiffness, and the flexibility of the shaft, while dynamic load of the bearing is obtained through solving the model. The dynamic load of bearings is considered as excitation to analyze the vibration and noise radiation characteristics of housing. Furthermore, acoustic transfer vector, modal acoustic contribution and PACA are used to select the region with the most acoustic contribution. The variable ribs structure model (VRSM) is established in this region. Finally, the VRSM are adopted to optimize the housing. The optimization model based on the peak sound pressure level (PSPL) and the ribs mass (Rm) is established by using response surface method. Through multi-objective optimization, the variable in VRSM can be modified or deleted to reduce the radiated noise of the gearbox. The optimization results demonstrate that the PSPL after optimization is decreased by 4.88 dB at frequency of 3130 Hz. At the same mass, the noise reduction effect of VRSM is 12% higher than that of standard rib. Therefore, the optimization effect of the housing structure is obvious. PACA-VRSM-RSM- NSGA-II technology provides a new research scheme for reducing the vibration and noise of the gearbox.