PAUL WURTH S.A.

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.

A system and method for monitoring the condition of a travelling grate machine including univocally identifying each pallet car; collecting a plurality of condition indicating parameters for the wheels, the grate bars, the car body and/or the side walls of the pellet car; attributing the collected condition indicating parameters to an individual pallet car; storing the collected condition indicating parameters for each pallet car in a database; evaluating the condition of the travelling grate machine; comparing the different condition indicating parameters collected by the different sensor means of each pallet car to reference parameters and/or to previously collected condition indicating parameters of that same pallet car; identifying the faults in each pallet car based on this comparison; classifying each pallet car according to its need of maintenance based on the severity of different identified faults; and determining the pallet car in most need of maintenance based on this classification.

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.

A system and method for monitoring the condition of a travelling grate machine including univocally identifying each pallet car; collecting a plurality of condition indicating parameters for the wheels, the grate bars, the car body and/or the side walls of the pellet car; attributing the collected condition indicating parameters to an individual pallet car; storing the collected condition indicating parameters for each pallet car in a database; evaluating the condition of the travelling grate machine; comparing the different condition indicating parameters collected by the different sensor means of each pallet car to reference parameters and/or to previously collected condition indicating parameters of that same pallet car; identifying the faults in each pallet car based on this comparison; classifying each pallet car according to its need of maintenance based on the severity of different identified faults; and determining the pallet car in most need of maintenance based on this classification.