5 results about "Physical metallurgy" patented technology

The invention relates to a noble metal and refractory multi-principal component substrate combined high-entropy alloy catalyst, a preparation method and acidic OER application. The catalyst is a high-entropy alloy formed by a refractory metal component A and a noble metal active component B, the component expression is AxBy, A is selected from multiple of Ta, Nb, Hf, Zr, Ti, W and Mo, and B is selected from at least one of Ir, Os and Ru. The structure of a precursor is regulated and controlled through physical metallurgy alloying, a unique structure that a dendritic refractory metal component supports a granular active component is obtained through a dealloying technology, and the catalyst can be directly used for an acidic OER catalyst, has activity and stability under the working condition of high current density, has the characteristics of low precious metal consumption and capability of being prepared in a large scale, and is suitable for industrial production. The method has the practical application potential as a PEM electrolytic cell catalyst.

The invention discloses a hot rolled steel CCT curve prediction method fusing a physical metallurgy principle and machine learning, and relates to the technical field of CCT curve prediction. The method comprises the steps that CCT data of steel are collected and preprocessed, and an initial small sample CCT data set is established; steel heating and deformation process parameters in the initial small sample CCT data set are converted into key microscopic structure information before phase change directly influencing the phase change temperature through a physical metallurgy theoretical model, and a high-quality small sample CCT data set is constructed; based on the constructed high-quality small sample CCT data set, a CCT curve prediction model is established in combination with a physical metallurgical theory and a support vector machine algorithm; and performing steel CCT curve prediction by using the CCT curve prediction model. According to the method, on the premise that the physical metallurgical law is met, high precision and applicability are achieved at the same time, and formulating of the cooling technological process in the actual steel production process can be guided.

This invention provides a laser cladding wear-resistant coating design method guided by a physical metallurgical knowledge graph, relating to the fields of nickel-based alloy wear-resistant coating design and machine learning applications. First, data is collected, and the data is divided into training and test sets using a multiple hold-out method. A graph neural network model guided by a physical metallurgical knowledge graph is established based on the training set. The graph neural network model with a squared correlation coefficient greater than 90% is used as the objective function in the genetic algorithm. The optimized composition, process, and material with the best target performance are obtained. This method introduces physical metallurgical mechanisms into a statistical graph neural network algorithm in the form of a knowledge graph, further improving the prediction accuracy of the machine learning model. Simultaneously, the combination with optimization algorithms makes the alloy design process more efficient, and the design results more consistent with the principles of physical metallurgy.

The application discloses a kind of mechanical properties prediction system after hot-rolled steel bar heat treatment, the system includes database communication module, process control module, machine learning algorithm module, physical metallurgy model module.The system real-time monitoring collection field production data, and according to the production data of different steel rolling process, it is not under the condition of heat treatment to predict its mechanical properties after heat treatment according to national standard heat treatment process, including tensile yield strength, tensile tensile strength, tensile elongation after fracture, tensile yield ratio test, surface shrinkage.The application realizes the on-line prediction of the mechanical properties of 42CrMo steel bar after heat treatment by using deep convolutional neural network, and the relevant prediction results can be used to replace the actual heat treatment inspection process to reduce production cost.

The invention relates to the technical field of intelligent manufacturing in the metallurgical industry, in particular to a high-speed wire rod after-rolling air cooling process temperature field prediction method which comprises the steps that a multi-steel-type hot-rolled wire rod cooling data set is obtained, and the air cooling heat exchange coefficient is reversely calculated based on the air cooling starting temperature, the air cooling ending temperature and a temperature field model; constructing and preprocessing a heat exchange coefficient prediction data set; establishing a heat exchange coefficient prediction model by adopting a random forest algorithm, and screening data by combining SHAP analysis and a physical metallurgy principle; and reconstructing a model by using the screened data, and realizing high-precision prediction of the air cooling ending temperature and the cooling speed based on the predicted heat exchange coefficient and the temperature field model. The method has the advantages that the heat exchange rule of multi-factor coupling is effectively captured in a data driving mode, the prediction precision and industrial applicability are remarkably improved, and reliable support is provided for optimizing the cooling process.