23-06-2023 дата публикации
Номер: CN116312890A
Принадлежит:
The invention relates to a method for screening a high-hardness high-entropy alloy by using a particle swarm optimization algorithm to assist machine learning, which belongs to the technical field of metal materials, and comprises the following steps: acquiring hardness data and candidate features of a high-entropy alloy of an AlCoCrCuFeNi system, and establishing a component-hardness data set and a feature data set; the component-hardness data set is subjected to random oversampling, an SVM-rbf model is trained, PSO is used for optimizing the SVM-rbf model, and the high-entropy alloy component proportion with the high hardness value can be obtained; preliminarily screening candidate features of the feature data set by adopting GA (Genetic Algorithm); the screened features are analyzed, GA feature selection is used for an extended feature set, an optimized feature group is obtained, and the model prediction precision is improved; and establishing an RF hardness prediction model by utilizing ...
Подробнее