Abstract: A computer-implemented failure predictor has a module arrangement (373) with first and second sub-ordinated modules (313, 323) that are sub-ordinated to an output module (363). The first and a second sub-oriented modules process data from an industrial machine to determine first and second intermediate status indicators. A third sub-oriented module (333) determines an operation mode indicator, and the output module (363) processes the status indicators and the operation mode indicator to predict a failure of the industrial machine. The module arrangement has been trained by cascaded training to comprises to train the sub-ordinated modules (312, 322, 332), to subsequently operate the trained sub-ordinated modules, and to subsequently train the output module.

Abstract: An industrial machine (123) may not have a sensor for a particular parameter, so that a computer uses a neural network (473) to virtualize the missing sensor. The computer trains the neural network (373) to provide a parameter indicator (Z?) of a further process parameter (173, z) for the industrial machine (123) with steps that comprise receiving measurement time-series with historical measurement data from reference machines, obtaining transformation rules by processing the time-series to feature series that are invariant to domain differences of the reference machines, transforming time-series by using the transformation rules, receiving a uni-variate time-series of the further process parameter (z), and training the neural network with features series at the input, and with the uni-variate time-series at the output.

Abstract: 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 fir

Abstract: A method and system for real-time motion artifact handling and noise removal for time-of-flight (ToF) sensor images. The method includes: calculating values of a cross correlation function c(?) at a plurality of temporally spaced positions or phases from sent (s(t)) and received (r(t)) signals, thereby deriving a plurality of respective cross correlation values [c(?0), c(?1), c(?2), c(?3)]; deriving, from the plurality of cross correlation values [c(?0), c(?1), c(?2), c(?3)], a depth map D having values representing, for each pixel, distance to a portion of an object upon which the sent signals (s(t)) are incident; deriving, from the plurality of cross correlation values [c(?0), c(?1), c(?2), c(?3)], a guidance image (I; I?); and generating an output image D? based on the depth map D and the guidance image (I; I?), the output image D? comprising an edge-preserving and smoothed version of depth map D, the edge-preserving being from guidance image (I; I?).

Abstract: A method and system for real-time noise removal and image enhancement of high-dynamic range (HDR) images. The method includes receiving an HDR input image I and operating processing circuitry for (i) applying a first edge-preserving filter (e.g. guided filter) to the input image I, thereby generating a first image component B1 and a first set of linear coefficients ?i,1; (ii) applying a second edge-preserving filter (e.g. guided filter) to the input image I, thereby generating a second image component B2 and a second set of linear coefficients ?i,2; (iii) generating a plausibility mask P from a combination of the first set of linear coefficients ?i,1 and the second set of linear coefficients ?i,2, the plausibility mask P indicating spatial detail within the input image I; and (iv) generating an output image O based on first image component B1, the second image component B2 and the plausibility mask P.

Abstract: A method and system for real-time motion artifact handling and noise removal for time-of-flight (ToF) sensor images. The method includes: calculating values of a cross correlation function c(?) at a plurality of temporally spaced positions or phases from sent (s(t)) and received (r(t)) signals, thereby deriving a plurality of respective cross correlation values [c(?0), c(?1), c(?2), c(?3)]; deriving, from the plurality of cross correlation values [c(?0), c(?1), c(?2), c(?3)], a depth map D having values representing, for each pixel, distance to a portion of an object upon which the sent signals (s(t)) are incident; deriving, from the plurality of cross correlation values [c(?0), c(?2), c(?3)], a guidance image (I; I?); and generating an output image D? based on the depth map D and the guidance image (I; I?), the output image D? comprising an edge-preserving and smoothed version of depth map D, the edge-preserving being from guidance image (I; I?).

Abstract: A method and system for real-time noise removal and image enhancement of high-dynamic range (HDR) images. The method includes receiving an HDR input image I and operating processing circuitry for (i) applying a first edge-preserving filter (e.g. guided filter) to the input image I, thereby generating a first image component B1 and a first set of linear coefficients ?i,1; (ii) applying a second edge-preserving filter (e.g. guided filter) to the input image I, thereby generating a second image component B2 and a second set of linear coefficients ?i,2; (iii) generating a plausibility mask P from a combination of the first set of linear coefficients ?i,1 and the second set of linear coefficients ?i,2, the plausibility mask P indicating spatial detail within the input image I; and (iv) generating an output image O based on first image component B1, the second image component B2 and the plausibility mask P.