The traditional design optimization of vibration amplitude reduction mainly has the disadvantages of low modeling and prediction accuracy as well as low optimization efficiency. Therefore, this paper presents a design optimization method for vibration amplitude reduction based on virtual prototyping and machine learning, which combines the high accuracy of numerical calculations with the efficiency of machine learning, overcoming the shortcomings of traditional methods. Firstly, sample points are collected through the design of experiments and virtual prototype simulation. Then, based on the sampled data, a prediction model for the relationship between the design parameters and the amplitude of the product is established using Genetic Algorithm-Support Vector Regression (GA-SVR). On the basis of the GA-SVR prediction model, a multi-objective optimization model of product is established, and Multiple Objectives Particle Swarm Optimization -entropy weight- Technique for Order Preference by Similarity to Ideal Solution (MOPSO-entropy weight-TOPSIS) is used to solve for the optimal design parameters. Finally, the washing machine suspension system is used as an example to verify the effectiveness of the model. The results show that, compared with the original design scheme, the design scheme obtained by the model can reduce the amplitude of the washing machine suspension system by 12.68%, and reduce the total weight of the counterweight by 7.35%. This method is conducive to the intelligent and efficient design optimization of vibration amplitude reduction, and is of great significance to product life cycle design.