公开(公告)号：US20230359155A1

公开(公告)日：2023-11-09

申请号：US18027184

申请日：2021-09-28

申请人： PAUL WURTH S.A.

发明人： Cédric SCHOCKAERT ,  Fabrice HANSEN ,  Lionel HAUSEMER ,  Maryam BANIASADI ,  Philipp BERMES

IPC分类号： G05B13/02

CPC分类号： G05B13/027

摘要： Computer system, computer-implemented method and computer program product are provided for training a reinforcement learning model to provide operating instructions for thermal control of a blast furnace, where a domain adaptation machine learning model generates a first domain invariant dataset from historical operating data obtained as multivariate time series and reflecting thermal states of respective blast furnaces of multiple domains, a transient model of a generic blast furnace process is used to generate artificial operating data as multivariate time series reflecting a thermal state of a generic blast furnace for a particular thermal control action, a generative deep learning network generates a second domain invariant dataset by transferring the features learned from the historical operating data 21 to the artificial operating data, where the reinforcement learning model determines a reward for the particular thermal control action in view of a given objective function by processing the combined first and second domain invariant datasets, and dependent on the reward, the second domain invariant data set is regenerated based on modified parameters, and repeating the determining of the reward to learn optimized operating instructions for optimized thermal control actions to be applied for respective operating states of one or more blast furnaces.