Abstract: A method for analysing process data related to a segment of a production process includes providing a process data sequence of the segment of the production process exhibiting a data pattern of at least one process variable to be analyzed; providing a set of metadata; determining process data sequences, which are stored in a first database; determining a start timestamp and end timestamp of each of the determined process data sequence, based on the first database; and calculating a similarity value for each of the determined process data sequences compared to the provided process data sequence, based on the data pattern of the at least one process variable, wherein the determined process data sequences for the calculation are provided, based on the related start timestamps and end timestamps, by accessing a second database comprising the process data sequences, for analysing the process data.

Abstract: A control module is adapted to control technical equipment by processing batch-run data from the technical equipment. The control module operates according to parameters that are obtained by a parameter module. The module receives a reference plurality of multi-variate reference time series with data values from sources that are related to the equipment. There are time series with measurement values and time series with data that describes particular manufacturing operations during a batch-run time interval. The module splits the time interval into phases by determining transitions between the particular manufacturing operations, and divides the time series into particular phase-specific partial series. For each phase separately, and for the phase-specific partial series in combination, the module differentiates phase-specific time series into relevant partial time series or non-relevant partial time series and set the parameters accordingly.

Abstract: A computer-implemented method of generating a training data set for training an artificial intelligence module includes providing first and second data sets, the first data set including first data elements indicative of a first operational condition, the second data set including second data elements indicative of a second operational condition that matches the first operational condition. The method further comprises determining a data transformation for transforming the first data elements into the second data elements; applying the data transformation to the first data elements and/or to further data elements of further data sets, thereby generating a transformed data set; and generating a training data set for training the AI module based on at least a part of the transformed data set.

Abstract: A method for generating a process model modeling a manual mode procedure instance of a plant process includes providing log events of operational actions; selecting related sequences of manual mode operational actions from the log events; filtering the related sequences according to an individual plant section; identifying a sequential order from the filtered related sequences; determining statistical properties of values of related process variables and/or statistical properties of values of related set point changes to each sequential ordered manual mode operational action from the filtered related sequences; generating the process model of the manual mode procedure instance by arranging related manual mode operational actions with the sequential order of each operational action assigned with the statistical properties of the values of related process variables and/or assigned with the statistical properties of the values of the related set point changes.

Abstract: A computer-implemented method to control technical equipment that performs a production batch-run of a production process, the technical equipment providing data in a form of time-series from a set of data sources, the data sources being related to the technical equipment, includes: accessing a reference time-series with data from a previously performed batch-run of the production process, the reference time-series being related to a parameter for the technical equipment; and while the technical equipment performs the production batch-run: receiving a production time-series with data, identifying a sub-series of the reference time-series, and comparing the received time-series and the sub-series of the reference time-series, to provide an indication of similarity or non-similarity, in case of similarity, controlling the technical equipment during a continuation of the production batch-run, by using the parameter as control parameter.

Abstract: A method of transfer learning for a specific production process of an industrial plant includes providing data templates defining expected data for a production process, and providing plant data, wherein the data templates define groupings for the expected data according to their relation in the industrial plant; determining a process instance and defining a mapping with the plant data; determining historic process data; determining training data using the determined process instance and the determined historic process data, wherein the training data comprises a structured data matrix, wherein columns of the data matrix represent the sensor data that are grouped in accordance with the data template and wherein rows of the data matrix represent timestamps of obtaining the sensor data; providing a pre-trained machine learning model using the determined process instance; and training a new machine learning model using the provided pre-trained model and the determined training data.

Abstract: A method of hierarchical machine learning includes receiving a topology model having information on hierarchical relations between components of the industrial plant, determining a representation hierarchy comprising a plurality of levels, wherein each representation on a higher level represents a group of representations on a lower level, wherein the representations comprise a machine learning model, and training an output machine learning model using the determined hierarchical representations.

Abstract: An industrial plant machine learning system includes a machine learning model, providing machine learning data, an industrial plant providing plant data and an abstraction layer, connecting the machine learning model and the industrial plant, wherein the abstraction layer is configured to provide standardized communication between the machine learning model and the industrial plant, using a machine learning markup language.

Abstract: A computer-implemented method for automating the development of industrial machine learning applications includes one or more sub-methods that, depending on the industrial machine learning problem, may be executed iteratively. These sub-methods include at least one of a method to automate the data cleaning in training and later application of machine learning models, a method to label time series (in particular signal data) with help of other timestamp records, feature engineering with the help of process mining, and automated hyper-parameter tuning for data segmentation and classification.

Abstract: A method includes training a first control model by utilizing a first set of input data as first input, resulting in a trained first control model; copying the trained first control model to a second control model, wherein, after copying, the second input layer and the plurality of second hidden layers is identical to the plurality of first hidden layers, and the first output layer is replaced by the second output layer; freezing the plurality of second hidden layers; training the second control model by utilizing the first set of input data as second input, resulting in a trained second control model; and running the trained second control model by utilizing a second set of input data as second input, wherein the second output outputs the quality measure of the first control model.

Abstract: A system for action determination includes an input unit, a processing unit, and an output unit. The input unit provides the processing unit with information relating to a plurality of past actions over a period of time associated with the operation of an industrial process. The input unit provides the processing unit with information relating to a plurality of past process events over the time period associated with the operation of the industrial process. The input unit provides the processing unit with information relating to a new process event. The processing unit determines a correlation between at least some of the plurality of past actions with at least some of the past process events. The processing unit determines at least one recommended action from the information relating to the new process event, the determination including utilization of the determined correlation. The output unit outputs the at least one recommended action.

Abstract: To determine a quality indicator of production batch-run of a production process, a computer compares time-series with multi-source data from a reference batch-run and time-series with multi-source data from the production batch-run. Before comparing, the computer converts multi-variate time-series to uni-variate time-series, by first multiplying data values of source-specific uni-variate time-series with source-specific factors from a conversion factor vector and second summing up the multiplied data values according to discrete time points. The source-specific factors of the conversion factor vector are obtained earlier by processing reference data, including the determination of characteristic portions of the time-series, converting, aligning by time-warping and evaluating displacement in time between characteristic portions before alignment and after alignment.

Abstract: A control module is adapted to control technical equipment by processing batch-run data from the technical equipment. The control module operates according to parameters that are obtained by a parameter module. The module receives a reference plurality of multi-variate reference time series with data values from sources that are related to the equipment. There are time series with measurement values and time series with data that describes particular manufacturing operations during a batch-run time interval. The module splits the time interval into phases by determining transitions between the particular manufacturing operations, and divides the time series into particular phase-specific partial series. For each phase separately, and for the phase-specific partial series in combination, the module differentiates phase-specific time series into relevant partial time series or non-relevant partial time series and set the parameters accordingly.

Abstract: A computer-implemented method for determining an abnormal technical status of a technical system includes: receiving, from the technical system, a plurality of signals, each signal being sampled over time and reflecting the technical status of at least one system component; computing, for each signal with associated high and low alarm thresholds obtained from an alarm management system, at every sampling time point, a univariate distance to its associated alarm thresholds as a maximum of the distances between a value of the respective signal and its associated alarm thresholds to quantify a degree of abnormality for the respective at least one system component; computing, at every sampling time point, based on the univariate distances at the respective sampling time points, an aggregate abnormality indicator reflecting the technical status of the technical system; and providing, to an operator, a comparison of the aggregate abnormality indicator with a predetermined abnormality threshold.

Abstract: An apparatus for alarm information determination includes: an input unit; a processing unit; and an output unit. The input unit provides the processing unit with historical process control data, the process control data including a plurality of data signals, a plurality of alarm data, and data relating to an event of interest. The processing unit determines a plurality of correlation scores for the plurality of data signals paired with the plurality of alarm data, a correlation score being determined for a data signal paired with an alarm data, a high correlation score indicating a higher degree of correlation than a low correlation score. The processing unit identifies at least one first alarm data from the plurality of alarm data, the identification including utilization of the data relating to the event of interest.

Abstract: An anomaly detection module is configured to apply a plurality of machine learning models to received technical status data to detect one or more indicators of an abnormal technical status prevailing in the industrial process system. The plurality of machine learning models are trained on historic raw or pre-processed sensor data and the anomaly detection module configured to generate the anomaly alert based on the one or more indicators. The received technical status data is assigned to signal groups and the generated anomaly alert is a vector with each vector element representing a group anomaly indicator for the respective signal group. Each vector element is determined by applying a respective group specific machine learning model.

Abstract: A computer system is configured to process alarm activations received from technical systems, where an alarm activation represents a deviation of the technical status of a technical system from normal. The system includes: a data storage interface for receiving alarm activations in data storage, where the recorded alarm activations correspond to alarms; a data processor for: determining, from the recorded alarm activations, time intervals for alarm analysis; and computing similarity measures between the time intervals that depend on the occurrence of the recorded alarm activations in the time intervals, and where the contribution of an alarm activation to the similarity of two time intervals is reduced with an increasing occurrence of the alarm in the time intervals; and a user interface configured to provide pairs of time intervals to an operator of the one or more technical systems that include time intervals with similarity measures indicating similar alarm.

Abstract: A method for sorting alarm-messages of a plant having at least one alarm-area each having at least two plant-devices connected by at least one connection, wherein the at least one alarm-area is defined so that the plant-devices and the respective connection provide a directed graph, involves: providing at least one database containing alarm-data and topology-data; wherein the topology-data describe a directed graph having at least one connection with a related flow direction between the respective plant-devices of the respective assigned alarm-area; generating at least one partly complete first alarm-order of the alarm-messages of the at least one alarm-area by sorting the alarm-messages according to the flow direction of the directed graph.

Abstract: An operation and observation system of a technical plant and/or a technical process and associated method are provided for operating components and for displaying measurement readings, process variables and/or status messages of the components of the plant and/or process. The system includes at least one large screen for displaying the components of the technical process and/or technical plant, and a plurality of operator workstations. A movement detection and movement control component is installed on the screen and on the operator workstations, which allows an operation and/or polling of the components, the measurement readings, the process variables and/or the status messages of the components of the technical plant or of the technical process by means of a body movement of an operator.

Abstract: An alarm handling system in plant process automation with a data processing device includes: at least one interface for accessing and/or processing one or more process signals and for determining corresponding process variables; an alarm configuration device for accessing and/or providing alarm configuration information including at least one setpoint for one or more determined process variables; and a prediction device for determining and processing a current rate of change of at least one process variable to predict how long it will take and/or a period until and/or predict at which date and/or time a provided setpoint and/or threshold is reached and/or crossed, and/or for determining whether and/or when at least one of the monitored and/or determined process variable values will cross the respective setpoint.