一种基于机器学习的高温高速润滑脂设计方法,包括以下步骤:收集润滑脂成品的组成成分和性能参数构建润滑脂库,建立基于润滑脂库的机器学习模型并用润滑脂库训练和测试,修正或者更换机器学习模型,用训练好的模型预测和优选出高温高速工况下具有优异摩擦学性能的润滑脂的组成成分;本发明利用已知润滑脂产品的配方参数,采用机器学习方法,寻找未知空间中可能的满足高温高速工况下具有优异摩擦学性能的润滑脂的组成成分,相比以往润滑脂的设计方法,具有更明确的目的性,更高的研发效率，极大地缩短了润滑脂研发的时间。

A machine learning based high temperature and high speed grease design method, comprising the steps of: collecting the composition and performance parameters of the finished grease product to build a grease library, building a machine learning model based on the grease library and training and testing the grease library, modifying or replacing the machine learning model, using the trained model to predict and preferably select the composition of the grease with excellent tribological performance under high temperature and high speed conditions The present invention uses the known formulation parameters of grease products and uses machine learning methods to find the composition of grease with excellent tribological properties under high temperature and high speed conditions in an unknown space, which is more purposeful and efficient than the previous grease design methods and greatly reduces the time of grease development.