# US 2025/0112819 A1 · Monitoring an industrial facilty employing industrial internet of things (iiot) sensors using a tactical compute application

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0112819 A1
- Document ID: US20250112819A1
- Status: Published application
- Kind: A1
- Application number: 18/904,125
- Filed: 2024-10-02
- Published: 2025-04-03
- Earliest claimed: 2023-10-02
- Assignees: Schlumberger Technology Corporation
- Applicants: Schlumberger Technology Corporation
- Inventors: Michael John Williams; Derek Long; Peter Gregory
- Web page: https://patentgrep.com/patent/US20250112819A1

## CPC

- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- H04L 41/069: using logs of notifications; Post-processing of notifications
- H04L 41/142: using statistical or mathematical methods
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 41/16: using machine learning or artificial intelligence
- G05B 2219/31461: Use risk analysis to identify process parts that should be specially monitored
- G05B 2219/45129: Boring, drilling
- H04L 67/12: specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods are provided for monitoring operations of an industrial facility. A gateway device is located at the industrial facility and operably coupled to sensors disposed at the industrial facility. The gateway device executes tasks configured to i) monitor alarms or triggers or other events related to operating conditions of the industrial facility, ii) identify a particular alarm or trigger or other event that is activated or set, iii) identify at least one risk associated with the particular alarm or trigger or other event that is activated or set, and iv) dynamically construct a causal network to evaluate the at least one risk. The tasks can be implemented by a behavior tree (BT) that combines automated causal network generation and risk analysis. The BT performs real-time analysis of the sensor data to generate actions or indicators from the sensor data for input to the casual network for risk analysis.

## Claims

### Claim 1

A system for monitoring operations of an industrial facility, the system comprising:
a gateway device disposed at the industrial facility and operably coupled to sensors disposed at the industrial facility, wherein gateway device executes tasks configured to i) monitor alarms or triggers or other events related to operating conditions of the industrial facility, ii) identify a particular alarm or trigger or other event that is activated or set, iii) identify at least one risk associated with the particular alarm or trigger or other event that is activated or set, and iv) dynamically construct a causal network to evaluate the at least one risk.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the tasks are further configured to v) evaluate the causal network and generate a list of questions to evaluate the at least one risk.

### Claim 3 (depends on 2)

The system of claim 2, wherein:
the tasks are further configured to vi) generate or receive a list of actions or indicators corresponding to the questions that can be computed by scarce computational resources of the gateway device based on automated analysis of sensor data generated from the sensors disposed at the industrial facility, vii) compute the actions or indicators based on automated analysis of sensor data by the scarce computational resources of the gateway device, and viii) use the actions or indicators as input to the casual network to evaluate the at least one risk.

### Claim 4 (depends on 3)

The system of claim 3, wherein:
the tasks are further configured to ix) communicate a questionnaire to at least one human expert to obtain additional actions or indicators corresponding to the questions, wherein the additional actions or indicators are provided by the at least one human expert without the gateway device analyzing sensor data generated from the sensors disposed at the industrial facility, and x) use the additional actions or indicators as input to the casual network to evaluate the at least one risk.

### Claim 5 (depends on 1)

The system of claim 1, wherein:
the tasks are further configured to build and output a digital report that characterizes the risk based on output data generated by the casual network.

### Claim 6 (depends on 1)

The system of claim 1, wherein:
the tasks are implemented by a behavior tree.

### Claim 7 (depends on 1)

The system of claim 1, wherein:
the casual network comprises a causal Bayesian network or a casual Bayesian network stack.

### Claim 8 (depends on 1)

The system of claim 1, wherein:
the construction of the casual network involves querying and processing a domain-specific knowledge graph.

### Claim 9 (depends on 8)

The system of claim 8, wherein:
the processing of the domain-specific knowledge graph extracts a sub-network from a much larger causal network using do-calculus.

### Claim 10 (depends on 3)

The system of claim 3, wherein:
the list of actions or indicators is determined by an AI planner module that balances value of information that each action or indicator brings to a specific question, and the compute cost and/or time it takes to process each action or indicator.

### Claim 11 (depends on 10)

The system of claim 10, wherein:
the AI planner module is configured to create a plan that identifies the list of actions or indicators that are be calculated and input to the causal network for evaluating the at least one risk.

### Claim 12 (depends on 10)

The system of claim 10, further comprising:
a cloud-computing system or other computing resource disposed remotely from the industrial facility and operably coupled to the gateway device, wherein the cloud computing environment or other computing resource implement some or all of the functionality of the AI planner module.

### Claim 13

A method for monitoring operations of an industrial facility, the method comprising:
providing a gateway device disposed at the industrial facility and operably coupled to sensors disposed at the industrial facility, wherein the gateway device is configured to execute tasks that i) monitor alarms or triggers or other events related to operating conditions of the industrial facility, ii) identify a particular alarm or trigger or other event that is activated or set, iii) identify at least one risk associated with the particular alarm or trigger or other event that is activated or set, and iv) dynamically construct a causal network to evaluate the at least one risk.

### Claim 14 (depends on 13)

The method of claim 13, wherein:
the gateway device is further configured to execute tasks that v) evaluate the causal network and generate a list of questions to evaluate the at least one risk.

### Claim 15 (depends on 14)

The method of claim 14, wherein:
the gateway device is further configured to execute tasks that vi) generate or receive a list of actions or indicators corresponding to the questions that can be computed by scarce computational resources of the gateway device based on automated analysis of sensor data generated from the sensors disposed at the industrial facility, vii) compute the actions or indicators based on automated analysis of sensor data by the scarce computational resources of the gateway device, and viii) use the actions or indicators as input to the casual network to evaluate the at least one risk.

### Claim 16 (depends on 15)

The method of claim 15, wherein:
the gateway device is further configured to execute tasks that ix) communicate a questionnaire to at least one human expert to obtain additional actions or indicators corresponding to the questions, wherein the additional actions or indicators are provided by the at least one human expert without the gateway device analyzing sensor data generated from the sensors disposed at the industrial facility; and x) use the additional actions or indicators as input to the casual network to evaluate the at least one risk.

### Claim 17 (depends on 13)

The method of claim 13, wherein:
the gateway device is further configured to execute tasks that build and output a digital report that characterizes the risk based on output data generated by the casual network.

### Claim 18 (depends on 13)

The method of claim 13, wherein:
the tasks executed by the gateway device are implemented by a behavior tree.

### Claim 19 (depends on 13)

The method of claim 13, wherein:
the casual network comprises a causal Bayesian network or a casual Bayesian network stack.

### Claim 20 (depends on 13)

The method of claim 13, wherein:
the construction of the casual network involves querying and processing a domain-specific knowledge graph.

### Claim 21 (depends on 20)

The method of claim 20, wherein:
the processing the domain-specific knowledge graph extracts a sub-network from a much larger causal network using do-calculus.

### Claim 22 (depends on 15)

The method of claim 15, further comprising:
configuring an AI planer module to generate the list of actions or indicators that can be computed by scarce computational resources of the gateway device based on automated analysis of sensor data, wherein the AI planner module balances value of information that each action or indicator brings to a specific question, and the compute cost and/or time it takes to process each action or indicator.

### Claim 23 (depends on 22)

The method of claim 22, wherein:
the AI planner module is configured to create a plan that identifies the list of actions or indicators that are be calculated and input to the causal network for evaluating the at least one risk

### Claim 24 (depends on 22)

The method of claim 22, further comprising:
providing a cloud-computing system or other computing resource disposed remotely from the industrial facility and operably coupled to the gateway device, wherein the cloud computing environment or other computing resource implement some or all of the functionality of the AI planner module.
