Abstract: A system and a method of managing a manufacturing process includes receiving production data relating to the manufacturing process and determining an operational mode associated with the manufacturing process using historical, multivariate senor data. The method may further determine a recommended action to affect production based on the determined operational mode. The operational mode may be based on at least one of: a level of operation in a continuous flow process relating to a joint set of process variables, a representation of a joint dynamic of the set of process variables over a predefined length, and a joint configuration of an uptime/downtime of a plurality of units comprising a process flow.

Abstract: One or more systems, computer-implemented methods and/or computer program products to facilitate a process to monitor and/or facilitate a modification to a manufacturing process. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that identifies values of inflow data of one or more inflows of a set of inflows to a manufacturing process as control variables, and a computation optimization component that optimizes one or more intermediate flows, outflows or flow qualities of the manufacturing process using, for mode-specific regression models, decision variables that are based on a set of joint-levels of the control variables. An operation mode determination component can determine operation modes of the manufacturing process that are together defined by a set of joint-levels of the control variables.

Abstract: A computer system, computer program product, and computer-implemented method are provided that includes learning a tree ordered graphical event model from an event dataset. Temporal relationships between one or more events in received temporal event data is modeled, and an ordered graphical event model (OGEM) graph is learned. The learned OGEM graph is configured to capture ordinal historical dependence. Leveraging the learned OGEM graph, a parameter sharing architecture is learned, including order dependent statistical and causal co-occurrence relationships among event types. A control signal to an operatively coupled event device that is associated with at least one event type reflected in the learned parameter sharing environment is dynamically issued. The control signal is configured to selectively control an event injection.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can, identify a plurality of data variables within a multivariate event dataset. Embodiments of the present invention can then formalize a causal inference between at least two identified data variables within the multivariate event dataset and generate a structural framework of an average effect value for the multivariate event dataset based on the formalization of the causal inference of the identified data variables. Embodiments of the present invention can then calculate an inverse propensity score for the generated structural framework of the average effect based on a type of identified variable, a predetermined time associated with the identified variable, and a causal connection strength between the identified variables.

Abstract: A classifying neural network (CNN) obtains a mixed data set of a priori information and outcomes information for treated units and untreated units. Classify units as treated or untreated, by running the CNN on the a priori information. Deliver a latent representation of the classified units from an intermediate layer of the CNN to a self-organizing map (SOM) engine. Generate an SOM based on the latent representation. Train the CNN to optimize a combined total loss of the classification and of the SOM. Estimate average treatment effect on the treated units by comparing the outcome information of the treated units to outcome information for untreated units that are nearest-neighbors of the treated units on the SOM.

Abstract: Methods and systems for generating an environment include training transformer models from tabular data and relationship information about the training data. A directed acyclic graph is generated, that includes the transformer models as nodes. The directed acyclic graph is traversed to identify a subset of transformers that are combined in order. An environment is generated using the subset of transformers.

Abstract: A system and method for determining parameters for a system. Selectable questions with associated goal are presented. Operational goals are different from configurable parameters of the system. A question is selected and a goal indication is received. First values for each goal are determined by an optimization engine adjusting parameters of mathematical models for the system to improve a value of the goal associated with the selected question in a direction of the goal indication. Selectable questions and the first values are presented and selection of a second question and a second goal indication is received. An optimization engine determines second updated values by adjusting parameters of the mathematical model to improve a value of a goal associated with the second selected question in the direction of the second goal indication. Second updated values of the goals, and differences from the first updated values. are presented.

Abstract: A computer-implemented method of discovering a composite durational event structure through temporal logic includes identifying a plurality of temporally related atomic events from temporal data trajectories of a multivariate dataset according to a definition of an atomic event predicate. At least one composite event having a durational event structure of at least some of the plurality of the temporally related atomic events is discovered by machine learning. An action is performed that is selected from a predetermined list associated with the composite event.

Abstract: A hybrid sensor can be generated by training a machine learning model, such as a neural network, based on a training data set. The training data set can include a first time series of upstream sensor data having forward dependence to a target variable, a second time series of downstream sensor data having backward dependence to the target variable and a time series of measured target variable data associated with the target variable. The target variable has measuring frequency which is lower than the measuring frequencies associated with the upstream sensor data and the downstream sensor data. The hybrid sensor can estimate a value of the target variable at a given time, for example, during which no actual measured target variable value is available.

Abstract: Embodiments of the invention are directed to collecting, by a computer system, sensor data of a manufacturing system, the sensor data being measured at intervals smaller than a time interval of a target measurement of the manufacturing system. The sensor data is determined to have a relationship to the target measurement. A synthetic target measurement is generated at an interval smaller than the time interval based on the relationship. An advance warning is automatically generated for the target measurement based on the synthetic target measurement within the interval smaller than the time interval.

Abstract: A method of using a computing device to train a neural network to recognize features in variate time series data that includes receiving, by a computing device, variate time series data. The computing device further receives results associated with the variate time series data. The computing device determines an anchor of the variate time series data. The computing device additionally determines one or more portions of the variate time series data which lead to a positive result. The computing device further determines one or more portions of the variate time series data which lead to a negative result. The computing device trains a neural network to interpret results of future variate time series data based upon the anchor, the one or more portions of the variate time series data which lead to the positive result, and the one or more portions of the variate time series data which lead to the negative result.

Abstract: A method of using a computing device to determine a window size in variate time series data that includes receiving, by a computing device, variate time series data associated with a machine learning model. The computing device sets a moving window size and a standard deviation for the variate time series data. The computing device further calculates a moving window average for the variate time series data. The computing device additionally calculates a standard deviation across all variate time series data. The computing device sorts the standard deviations calculated in descending order. The computing device further iterates indices for the standard deviations until the indices have been visited by at least one anchor. The computing device iteratively expands each anchor to cover neighbors' anchors which have been visited by previous anchors. The computing device determines a window size based upon the expanded anchors.

Abstract: In an approach for real-time opportunity discovery for productivity enhancement of a production process, a processor extracts a set of features from time series data, through autoencoding using a neural network, based on non-control variables for the time series data. A processor identifies one or more operational modes based on the extracted features including a dimensional reduction with a representation learning from the time series data. A processor identifies a neighborhood of a current operational state based on the extracted features. A processor compares the current operational state to historical operational states based on the time series data at the same operational mode. A processor discovers an operational opportunity based on the comparison of the current operational state to the historical operational states using the neighborhood. A processor identifies control variables in the same mode which variables are relevant to the current operational state.

Abstract: A graphical event model method, system, and computer program product, include learning statistical and causal co-occurrence relationships among multiple event-types of data, requiring no complex input, and generating a representation that explains a mutual dynamic of the multiple event-types in a form of a graphical event model.

Abstract: A method, computer program product, and/or computer system improves a future efficiency of a specific system. One or more processors receive multiple historical data snapshots that describe past operational states of a specific system. The processor(s) identify a time series pattern for the time series of data in the multiple historical snapshots and calculate their variability. The processor(s) then determine that the variability in a first sub-set of the time series pattern is larger than a predefined value, and determine that future values of the first set of the time series pattern are a set of non-forecastable future values. The processor(s) also determine that the variability in a second sub-set of the time series pattern for the data is smaller than the predefined value, and utilizes this second sub-set to modify the specific system at a current time.

Abstract: Analyzing complex systems by receiving labeled event data describing events occurring in association with a complex system, generating a first machine learning model according to the distribution of labeled event data, receiving state variable transition data describing state variable transitions occurring in association with a complex system, training a second machine learning model according to a combination of a distribution of state variable transitions and the first machine learning model, and using the second machine learning model to predict the effects of events upon state variables within the complex system according to new state variable transition and new labeled event data.

Abstract: Techniques for model fidelity monitoring and regeneration for manufacturing process decision support are described herein. Aspects of the invention include determining that an output of a regression model corresponding to a current time period of decision support for a manufacturing process is not within a predefined range of a historical process dataset, wherein the regression model was constructed based on the historical process dataset, and performing an accuracy and fidelity analysis on the regression model based on process data from the manufacturing process corresponding to a previous time period. Based on a result of the accuracy and fidelity analysis being below a threshold, a mismatch of the regression model as compared to the manufacturing process is determined. Based on determining the mismatch, a temporary regression model corresponding to the manufacturing process is generated, and decision support for the manufacturing process is performed based on the temporary regression model.

Abstract: A hybrid sensor can be generated by training a machine learning model, such as a neural network, based on a training data set. The training data set can include a first time series of upstream sensor data having forward dependence to a target variable, a second time series of downstream sensor data having backward dependence to the target variable and a time series of measured target variable data associated with the target variable. The target variable has measuring frequency which is lower than the measuring frequencies associated with the upstream sensor data and the downstream sensor data. The hybrid sensor can estimate a value of the target variable at a given time, for example, during which no actual measured target variable value is available.

Abstract: A computer-implemented method is presented for learning relationships between multiple event types by employing a multi-channel neural graphical event model (MCN-GEM). The method includes receiving, by a computing device, time-stamped, asynchronous, irregularly spaced event epochs, generating, by the computing device, at least one fake epoch between each inter-event interval, wherein fake epochs represent negative evidence, feeding the event epochs and the at least one fake epoch into long short term memory (LSTM) cells, computing hidden states for each of the event epochs and the at least one fake epoch, feeding the hidden states into spatial and temporal attention models, and employing an average attention across all event epochs to generate causal graphs representing causal relationships between all the event epochs.

Abstract: A system and a method of managing a manufacturing process includes receiving production data relating to the manufacturing process and determining an operational mode associated with the manufacturing process using historical, multivariate senor data. The method may further determine a recommended action to affect production based on the determined operational mode. The operational mode may be based on at least one of: a level of operation in a continuous flow process relating to a joint set of process variables, a representation of a joint dynamic of the set of process variables over a predefined length, and a joint configuration of an uptime/downtime of a plurality of units comprising a process flow.