Abstract: A device receives first well data associated with first wells where plunger lift is installed, and receives second well data associated with a candidate well where plunger lift is not installed. The device processes the first well data to determine pre-plunger lift installation data associated with the first wells, and processes the first well data and the pre-plunger lift installation data to determine a set of performing wells and a set of underperforming wells, of the first wells. The device processes the second well data and data associated with the set of performing wells to determine a first metric associated with the candidate well, and processes the second well data and data associated with the set of underperforming wells to determine a second metric associated with the candidate well. The device determines whether to install plunger lift in the candidate well based on the first metric and the second metric.

Abstract: A method for predicting equipment failure includes receiving parameter sample values associated with parameters of benchmark equipment and operational status information associated with the benchmark equipment. The parameter sample values and operational status information are periodically acquired. A model is generated for relating one or more of the parameters to benchmark equipment failure. For each parameter, a threshold value at which an output of the model indicates benchmark equipment failure is determined. Next, parameters of an equipment under test having parameter sample values that match the determined threshold values are determined. For each determined parameter, benchmark equipment having parameter sample values that match the parameter sample values of the equipment under test that match the determine threshold values are determined. Survivability data for the equipment under test is generated based on survivability data associated with the determined benchmark equipment.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that leverage artificial intelligence and machine learning to analyze and categorize events associated with an equipment asset, such as industrial machinery, to determine a status (e.g., insight) associated with the equipment asset, and to determine maintenance actions to be performed with respect to the equipment asset to prevent, or reduce the likelihood or severity of, occurrence of a fault at the equipment asset. Machine learning (ML) models may be trained to categorize events that are detected based on operating characteristics data associated with the equipment asset, to determine a status of the equipment asset, and to recommend one or more maintenance actions (or other actions). Output that indicates the maintenance actions may be displayed to a user or used to automatically initiate performance of one or more of the maintenance actions.

Abstract: An AI-based asset maintenance system accesses a variety of data sources related to an entity to analyze data regarding one or more damage mechanisms corresponding to the entity thereby identifying and implementing corrective actions that mitigate the effects of the damage mechanisms within the entity. The accessed data is stored using a parameterized data model that represents the entity. A trained parameter model identifies the most significant operating parameters for a given component of the entity for the damage mechanism affecting the component. A projection model is used to perform ‘what-if’ analysis of the most significant operating parameters for determining the instances of minimum and maximum degradation due to the damage mechanism. Corrective actions for mitigating the degradation due to the damage mechanism can be determined based on analysis of the operating parameters and other attributes corresponding to the best and worst case degradation scenarios.

Abstract: A device receives first well data associated with first wells where plunger lift is installed, and receives second well data associated with a candidate well where plunger lift is not installed. The device processes the first well data to determine pre-plunger lift installation data associated with the first wells, and processes the first well data and the pre-plunger lift installation data to determine a set of performing wells and a set of underperforming wells, of the first wells. The device processes the second well data and data associated with the set of performing wells to determine a first metric associated with the candidate well, and processes the second well data and data associated with the set of underperforming wells to determine a second metric associated with the candidate well. The device determines whether to install plunger lift in the candidate well based on the first metric and the second metric.

Abstract: An AI-based asset maintenance system accesses a variety of data sources related to an entity to analyze data regarding one or more damage mechanisms corresponding to the entity thereby identifying and implementing corrective actions that mitigate the effects of the damage mechanisms within the entity. The accessed data is stored using a parameterized data model that represents the entity. A trained parameter model identifies the most significant operating parameters for a given component of the entity for the damage mechanism affecting the component. A projection model is used to perform ‘what-if’ analysis of the most significant operating parameters for determining the instances of minimum and maximum degradation due to the damage mechanism. Corrective actions for mitigating the degradation due to the damage mechanism can be determined based on analysis of the operating parameters and other attributes corresponding to the best and worst case degradation scenarios.

Abstract: A method for predicting equipment failure includes receiving parameter sample values associated with parameters of benchmark equipment and operational status information associated with the benchmark equipment. The parameter sample values and operational status information are periodically acquired. A model is generated for relating one or more of the parameters to benchmark equipment failure. For each parameter, a threshold value at which an output of the model indicates benchmark equipment failure is determined. Next, parameters of an equipment under test having parameter sample values that match the determined threshold values are determined. For each determined parameter, benchmark equipment having parameter sample values that match the parameter sample values of the equipment under test that match the determine threshold values are determined. Survivability data for the equipment under test is generated based on survivability data associated with the determined benchmark equipment.