US-12627141-B2 - Systems and methods for facilitating the management of energy production or processing facilities

US12627141B2US 12627141 B2US12627141 B2US 12627141B2US-12627141-B2

Abstract

A method for facilitating the management of one or more energy production or processing facilities includes receiving an alert corresponding to an operational anomaly associated with the process equipment, interrogating a data structure linking together and organizing a plurality of distinct data sources, selecting a subset of data sources from the plurality of data sources identified as associated with a potential cause of the alert based on the interrogation of the data structure, statistically analyzing data sourced from the selected subset of data sources, identifying the potential cause of the alert based on the statistical analysis, and recommending a corrective action to resolve the identified potential cause of the alert using the plurality of distinct data sources.

Inventors

Jesus Pacheco-Rodriguez
Joshua Ellison
Greg Hickey
Adam Ballard
Martin R. Gonzalez

Assignees

BP CORPORATION NORTH AMERICA INC.
BP EXPLORATION OPERATING COMPANY LIMITED

Dates

Publication Date: 20260512
Application Date: 20220211

Claims (14)

1 . A method for facilitating the management of one or more energy production or processing facilities, comprising: (a) receiving by an application executing on a computer system an alert pertaining to process equipment of the one or more energy production or processing facilities, the alert corresponding to an operational anomaly associated with the process equipment; (b) interrogating by a data handler of the application a data structure linking together and organizing a plurality of distinct data sources, the plurality of distinct data sources having a sensor data class associated with sensor data sources of the process equipment, and a contextual data class associated with contextual data sources excluding the sensor data sources of the sensor data class; (c) selecting a subset of data sources from the plurality of data sources, including both contextual data sources and sensor data sources, identified by the data handler as associated with a potential cause of the alert based on the interrogation of the data structure; (d) statistically analyzing by the data handler data sourced from the selected subset of data sources; (e) identifying by the data handler the potential cause of the alert based on the contextual data sources within the subset of data sources and the statistical analysis performed at (d); (f) determining a severity of impact to the operation of the one or more energy production or processing facilities should failure occur to the process equipment; and (g) recommending by the data handler a particular corrective action from a plurality of distinct potential corrective actions to resolve the identified potential cause of the alert using the plurality of distinct data sources and based on the severity of impact to the operation of the one or more energy production or processing facilities should failure occur to the process equipment.
2 . The method of claim 1 , wherein (e) further comprises interrogating the data structure by the data handler to identify the potential cause of the alert.
3 . The method of claim 1 , wherein the statistical analysis in (d) identifies anomalous sensor data, and wherein interrogation of the data structure to select a subset of data sources at (c) is based on identifying, by the linking and organizing of the data structure, other data sources linked with the data source associated with the anomalous sensor data.
4 . The method of claim 1 , wherein (b) comprises forming by the data handler new associations between different data sources of the plurality of distinct data sources.
5 . The method of claim 1 , wherein the contextual data source class includes at least one of maintenance history data specific to the process equipment, maintenance history data of the one or more energy production or processing facilities, planned maintenance data, design data specific to the process equipment, current operating condition data associated with a current operational status of the process equipment and/or of the one or more energy production or processing facilities, alert data relating to equipment of the one or more energy production or processing facilities, failure mode data, and safety data.
6 . The method of claim 1 , wherein (e) comprises: (e1) identifying the potential cause of the alert by identifying a plurality of anomalous data streams of the plurality distinct data sources based on the statistical analysis performed at (d).
7 . The method of claim 6 , wherein (e) comprises: (e2) determining by the data handler an anomaly score for each of the identified anomalous data streams.
8 . The method of claim 6 , wherein (e) comprises: (e2) determining a likelihood of a failure for each of a plurality of sub-components of the process equipment based on the plurality of anomalous data streams.
9 . The method of claim 8 , wherein (e) comprises: (e3) identifying one or more potential failure modes for each of the plurality of sub-components based on the plurality of anomalous data streams.
10 . The method of claim 1 , wherein the data structure comprises a knowledge graph accessible by the data handler and comprising a plurality of nodes connected by a plurality of edges, and wherein at least one of the plurality of nodes comprises an equipment identifier node representing the process equipment.
11 . A system for facilitating the management of one or more energy production or processing facilities, comprising: a processor; a non-transitory memory; and an application stored in the non-transitory memory that, when executed by the processor: receives an alert pertaining to a process equipment of the one or more energy production or processing facilities, the alert corresponding to an operational anomaly in the operation of the process equipment; interrogates by a data handler of the application a data structure linking together and organizing a plurality of distinct data sources, the plurality of distinct data sources having a sensor data class associated with sensor data sources of the process equipment, and a contextual data class associated with contextual data sources excluding the sensor data sources of the sensor data class; selects a subset of data sources from the plurality of distinct data sources, including both contextual data sources and sensor data sources, identified by the data handler as associated with a potential cause of the alert based on the interrogation of the data structure; statistically analyzes by the data handler data sourced from the selected subset of data sources; identifies by the data handler the potential cause of the alert based on the contextual data sources within the subsea of data sources and the performed statistical analysis; determines a severity of impact to the operation of the one or more energy production or processing facilities should failure occur to the process equipment; and recommends by the data handler a particular corrective action from a plurality of distinct potential corrective actions to resolve the identified potential cause of the alert using the plurality of distinct data sources and based on the severity of impact to the operation of the one or more energy production or processing facilities should failure occur to the process equipment.
12 . The system of claim 11 , wherein the data source comprises a knowledge graph including a plurality of nodes connected by a plurality of edges, and wherein at least one of the plurality of nodes comprises an equipment identifier node representing the process equipment.
13 . The system of claim 11 , wherein the application stored in the non-transitory memory that, when executed by the processor: identifies the potential cause of the alert by identifying by the data handler a plurality of anomalous data streams of the plurality distinct data sources; determines a likelihood of a failure for each of a plurality of sub-components of the piece of equipment based on the plurality of anomalous data streams; and identifies one or more potential failure modes for each of the plurality of sub-components based on the plurality of anomalous data streams.
14 . The system of claim 11 , wherein the application stored in the non-transitory memory that, when executed by the processor: identifies anomalous sensor data based on the performed statistical analysis; and selects the subset of data sources based on identifying, by the linking and organizing of the data structure, other data sources linked with the data source associated with the anomalous sensor data.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application is a 35 U.S.C. § 371 national stage application of PCT/US2022/016165 filed Feb. 11, 2022, and entitled “Systems and Methods for Facilitating the Management of Energy Production or Processing Facilities,” which claims benefit of U.S. provisional patent application No. 63/148,340 filed Feb. 11, 2021, entitled “Systems and Methods for Facilitating the Management of Hydrocarbon Production and Operation Facilities,” each of which is incorporated herein by reference in its entirety for all purposes. STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT Not applicable. BACKGROUND Energy production and processing facilities are used to extract and process different sources of energy to be ultimately consumed by one or more end users. For example, energy production and processing facilities encompass photovoltaic systems which convert captured sunlight into electrical power distributed to, for example, an electrical grid, a wind farm which converts wind energy into electrical power, and hydrocarbon production and processing facilities which extract hydrocarbons from the earth and process the captured hydrocarbons into hydrocarbon products usable by end users Energy production and processing facilities may comprise a variety of process equipment for performing various functions including, for example, transmitting and/or processing different forms of energy (e.g., electrical energy, wind energy, chemical energy in the form of hydrocarbons, etc.), electromechanical equipment used to power equipment, and/or convert different types of energy (e.g., a generator which converts torque applied from wind power into electrical energy), and equipment used to handle and/or process various types of fluids such as, for example, process equipment of a hydrocarbon production or processing facility. As one example, hydrocarbon production and processing facilities may include process equipment in the form of stationary equipment (e.g., fluid conduits, valves, heat exchangers, vessels, separators, etc.), rotating equipment (e.g., compressors, pumps, turbines, etc.) as well as other types of process equipment. Personnel, including subject matter experts (SMEs), may be tasked with monitoring and assisting with the management of the stationary, rotating, and other types of equipment comprising one or more energy production or processing facilities. In an effort to assist with managing one or more energy production or processing facilities, SMEs may provide technical support should anomalies arise at the one or more energy production or processing facilities. For example, SMEs may process alerts received from an energy production or processing facility and pertaining to process equipment of the energy production or processing facility. Particularly, in at least some applications, SMEs may prioritize the alert with respect to other alerts received from the energy production or processing facility as well as other energy production or processing facilities, determine or identify the issue underlying the alert, determine a plan for addressing the underlying cause on information related to the piece of equipment pertaining to the alert as well as other information pertaining to the energy production or processing facility, and perform an action to resolve the underlying cause. SUMMARY An embodiment of a method for facilitating the management of one or more energy production or processing facilities comprises (a) receiving by an application executing on a computer system an alert pertaining to process equipment of the one or more energy production or processing facilities, the alert corresponding to an operational anomaly associated with the process equipment, (b) interrogating by a data handler of the application a data structure linking together and organizing a plurality of distinct data sources, the plurality of distinct data sources having a sensor data class associated with sensor data sources of the process equipment, and a contextual data class associated with contextual data sources excluding the sensor data sources of the sensor data class, (c) selecting a subset of data sources from the plurality of data sources, including both contextual data sources and sensor data sources, identified by the data handler as associated with a potential cause of the alert based on the interrogation of the data structure, (d) statistically analyzing by the data handler data sourced from the selected subset of data sources, (e) identifying by the data handler the potential cause of the alert based on the contextual data sources within the subset of data sources and the statistical analysis performed at (d), and (f) recommending by the data handler a corrective action to resolve the identified potential cause of the alert using the plurality of distinct data sources. In some embodiments, (f) includes determining a severity of impact to the operation of the one or more energy prod