Abstract: Examples techniques to manage performance of assets installed in an industrial facility are described. Operating parameters of a component from amongst one or more components of an asset are monitored. A range of values indicative of normal operational behavior of the asset is predefined for each operating parameter of the component. One or more operating parameters of the component are identified to deviate from corresponding predefined range of values. Deviation in an operating parameter is a symptom of a fault. A severity index is assigned to each symptom of a fault based on an amount of the deviation in the respective operating parameter from corresponding predefined range of values. Further, a fault severity indicator is assigned for the fault associated with the component based on severity indexes of each symptom of the fault. A corrective action is caused when the fault severity indicator is above a predetermined threshold.

Abstract: Techniques for risk management in a supply chain are described. In one aspect, to determine an overall impact of a fault associated with an equipment operating in a facility, multiple operational parameters of the equipment are monitored to detect an anomaly, based on which a fault in the equipment is identified. On identifying the fault, a first impact factor corresponding to an energy impact, a second impact factor corresponding to an emission impact, and a third impact factor corresponding to an economic impact are derived based on the multiple operational parameters. Further, an integrated risk indicator is computed from the impact factors to determine a current overall impact of the fault on the equipment. Accordingly, a risk profile including one or more remedial strategies is generated based on the integrated risk indicator and is issued to personnel of the facility for risk management.

Abstract: Systems, apparatuses, methods, and computer program products are provided herein. For example, a computer-implemented method may include receiving operational data representing operations of an asset. In some embodiments, the computer-implemented method may include processing the operational data to generate a fault anomaly score for the operational data. In some embodiments, determining, based at least in part on the fault anomaly score, whether the operational data is indicative of the asset being associated with at least one fault. In some embodiments, the computer-implemented method may include generating, based at least in part on applying the operational data to a fault classification model, fault data. In some embodiments, the computer-implemented method may include generating, based at least in part on applying the fault data to a fault impact model, fault impact data. In some embodiments, the computer-implemented method may include initiating performance of one or more fault optimization actions.

Abstract: Example techniques to control operations in an industrial facility is described. In an operation, operating parameters of an equipment from amongst a plurality of equipments installed in the industrial facility are monitored. A range of values is predefined for each of the operating parameters of the equipment. An operating parameter of the equipment that deviates from the corresponding predefined range of values is identified. A dataset is queried to identify past instances of deviation in the operating parameter that are within a specified range of deviation to the deviation in the operating parameter of the equipment. A corrective action is selected from amongst at least one corrective action in the dataset. The corrective action is implemented to correct the deviation in the operating parameter of the equipment.

Abstract: Techniques for evaluating performance of an industrial autonomous system are described. In an example, a corrective action initiated by the industrial autonomous system is identified, where the corrective action is initiated for responding to an alarm event associated with an equipment at an industrial facility. The alarm event is generated upon detection of a deviation beyond threshold, where the deviation is associated with at least one operation parameter of the equipment. Further, the industrial autonomous system is utilized for monitoring operation parameters of the equipment and initiating the corrective action by modifying a first set of operation parameters. The corrective action is then compared with a benchmark corrective action. A performance rating of the industrial autonomous system is then generated based on a difference between the corrective action and the benchmark corrective action.

Abstract: Examples techniques to select training data to train Artificial Intelligence models to monitor industrial processes are described. From historical data relating to an industrial process, a range of values exhibited by operating parameters of the industrial process under normal operation is estimated. One or more steady time windows are identified for the operating parameters. A steady time window of an operating parameter is a duration of time where values of the operating parameter are within the estimated range of values. Based on the identified steady time windows, a composite steady time window is determined. The composite steady time window is a duration of time where a maximum of the identified steady time windows overlap. The data corresponding to the composite steady time window is provided as training data to the AI model.

Abstract: A trained machine learning algorithm processes time series production data. The time series production data are representative of a control process within a facility control loop. The machine learning training algorithm is trained using positive training data that are representative of a normal operation of components within the facility control loop and negative training data that are representative of an abnormal operation of components within the facility control loop. Output of the trained machine learning algorithm identifies abnormalities in the facility control loop.

Abstract: Example methods, apparatuses, systems, and computer program products are provided. For example, an example computer-implemented method includes receiving a plurality of runtime facility process variable indicators and a plurality of runtime derived process metric indicators, receiving a facility state tree data object that comprises a plurality of facility state tree nodes corresponding to a plurality of facility state indicators; generating a runtime facility state indicator, generating a runtime facility score indicator associated with the runtime facility state indicator, and generating a remote operator assistance data object associated with the facility indicator.

Abstract: Example methods, apparatuses, systems, and computer program products are provided. For example, an example computer-implemented method includes receiving a battery manufacturing operation parameter indicator, determining whether the battery manufacturing operation parameter indicator satisfies a battery manufacturing parameter threshold indicator, and in response to determining that the battery manufacturing operation parameter indicator does not satisfy the battery manufacturing parameter threshold indicator, the example computer-implemented method comprises: generating a battery manufacturing deviation event data object, and generating a battery manufacturing adjustment data object based at least in part on inputting the battery manufacturing deviation event data object to one or more machine learning models.

Abstract: Example methods, apparatuses, systems, and computer program products are provided. For example, an example computer-implemented method includes receiving a plurality of runtime hydrogen production variable indicators from a hydrogen production control system associated with a hydrogen production facility, generating at least one predicted hydrogen production operation indicator. Further, in response to determining that the at least one predicted hydrogen production operation indicator does not satisfy the at least one corresponding hydrogen production operation threshold indicator, generating an adjusted hydrogen production variable indicator corresponding to a runtime hydrogen production variable indicator, and transmitting the adjusted hydrogen production variable indicator to the hydrogen production control system.

Abstract: A system processes historical facility data that relate to facility states and modes of operation. The historical facility data are clustered into groups representing the facility states and the modes of operation. The groups are used to determine a current state and mode of the facility. When the facility is in a normal state, the system determines whether an event in the facility is an abnormality. If an abnormality is identified, the system transmits a signal indicating the abnormality.

Abstract: Embodiments of the present disclosure provide for asset lifetime monitoring. Estimated values for factors representing root causes of operational anomalies of an asset may be generated utilizing one or more models. Estimated remaining lifetime values for one or more root cause variables may be generated that indicate a time until the value for a root cause variable is estimated to reach a particular limit threshold corresponding to the root cause variable, and/or an estimated second remaining lifetime value for an asset health index representing a combination of one or more root cause variables. The second remaining lifetime value for the asset health index may be provided to enable processing of the second remaining lifetime value as the remaining useful lifetime of the asset based on overall root cause variables.

Abstract: A trained machine learning algorithm processes time series production data. The time series production data are representative of a control process within a facility control loop. The machine learning training algorithm is trained using positive training data that are representative of a normal operation of components within the facility control loop and negative training data that are representative of an abnormal operation of components within the facility control loop. Output of the trained machine learning algorithm identifies abnormalities in the facility control loop.

Abstract: A system processes historical facility data that relate to facility states and modes of operation. The historical facility data are clustered into groups representing the facility states and the modes of operation. The groups are used to determine a current state and mode of the facility. When the facility is in a normal state, the system determines whether an event in the facility is an abnormality. If an abnormality is identified, the system transmits a signal indicating the abnormality.

Abstract: A system processes historical facility data that relate to facility states and modes of operation. The historical facility data are clustered into groups representing the facility states and the modes of operation. The groups are used to determine a current state and mode of the facility. When the facility is in a normal state, the system determines whether an event in the facility is an abnormality. If an abnormality is identified, the system transmits a signal indicating the abnormality.

Abstract: A method of alarm notification includes providing data for an industrial process including stored alarm event data and stored Key Performance Indicator (KPI) data, and an alarm event-KPI correlation and operator notification system. Patterns of relationships are discovered between the stored alarm event and KPI data to provide a reference pattern database that identifies KPI violation events in the KPI data as a function of the alarm event data or alarm events in the alarm event data as a function of the KPI data. Pattern matching uses a real-time alarm event and real-time KPI data to determine a pattern similarity by comparing a current sequence spanning a predetermined time of the real-time alarm event and KPI data to the patterns. When the pattern matching identifies a current alarm event or KPI violation event, an operator is notified and a predicted KPI value or feature or a predicted alarm event.

Abstract: An apparatus, method, and non-transitory machine-readable medium provide for accurate automatic determination of alarm-operator action linkage for operator assessment and alarm guidance using custom graphics and control charts. The apparatus includes a memory and a processor operably connected to the memory. The processor receives process control system data regarding a field device in an industrial process control and automation system; extracts information from the process control system data; generates a tuple based on the extracted information; and performs a rectifying operation in the industrial process control and automation system based on the generated tuple of the field device.

Abstract: A method includes receiving one or more operating conditions from one or more field devices of one or more industrial plants in response to receiving one or more alarm signals. The method also includes determining one or more industrial plant states based on the one or more operating conditions. The method further includes identifying one or more historical alarm episodes stored in one or more data stores based on the one or more industrial plant states. In addition, the method includes identifying one or more recommended historical alarm episodes of the one or more historical alarm episodes based on one or more benchmark metrics of the one or more historical alarm episodes. The method also includes generating the one or more recommended historical alarm episodes for display on a user interface.

Abstract: A method includes identifying changes in an alarm count for at least one alarm to be generated in an industrial process control and automation system. The changes in the alarm count are based on a plurality of different sets of alarm settings. The method also includes presenting the changes in the alarm count to a user and receiving a selection of one of the sets of alarm settings. The method further includes configuring the industrial process control and automation system with the selected set of alarm settings to enable the industrial process control and automation system to generate alarms using the selected set of alarm settings.

Abstract: An apparatus, method, and non-transitory machine-readable medium provide for accurate automatic determination of alarm-operator action linkage for operator assessment and alarm guidance using custom graphics and control charts. The apparatus includes a memory and a processor operably connected to the memory. The processor receives process control system data regarding a field device in an industrial process control and automation system; extracts information from the process control system data; generates a tuple based on the extracted information; and performs a rectifying operation in the industrial process control and automation system based on the generated tuple of the field device.