Abstract: A computer-implemented method includes identifying a repository of equipment documents in an unstructured format for oil and gas equipment, generating text-based equipment documents in a computer-readable text format, and generating a vector index of vector embeddings from the text-based equipment documents. The method includes, in response to receiving an equipment content request, providing the vector index and an equipment content prompt to a generative AI model for instructing the generative AI model to generate an equipment content response using the vector embeddings from the vector index. Based on receiving the equipment content response from the generative AI model, the method includes providing the equipment content response to a client device.

Abstract: The present disclosure relates to systems and methods for using generative artificial intelligence in facilities. The systems and methods receive sensor data from sensors within a facility and use the sensor data to determine a context of the facility. The systems and methods generate an action in response to the context.

Abstract: A method of operation of an unmanned autonomous vehicle includes autonomously maneuvering the unmanned autonomous vehicle about a facility, collecting gas concentration data using one or more sensors carried on or integrated with the unmanned autonomous vehicle, and monitoring the collected gas concentration data to detect a high concentration due to a gas leak. The method further includes, if a high concentration is detected, estimating a location of the gas leak and maneuvering the unmanned autonomous vehicle toward the estimated location of the gas leak.

Abstract: A system may include a processor, a memory, and instructions stored on the memory and executable by the processor to receive, from a fiber optic cable extending along a fluid conduit, an indication of a leak event, and receive, from one or more sensors, measured pressure values of a fluid flow along the conduit. Additionally, the processor may determine one or more estimated time stamps associated with one or more expected pressure changes at one or more locations along the fluid conduit based on the indication of the leak event and a rarefaction wave model, compare the measured pressure values from the one or more sensors to expected pressure values at the one or more locations along the fluid conduit to verify the one or more estimated time stamps, and generate a notification based on the comparison of the measured pressure values and the expected pressure values.

Abstract: A system for inspecting one or more gas plumes in a facility, including a processor and a memory having instructions executable by the processor, wherein the instructions are configured to obtain one or more images from one or more cameras, wherein the one or more images include a gas plume. The instructions are further configured to focus the one or more images on an area of interest with an object detection model to generate a boundary box around the gas plume, and focus the one or more images on the area of interest with a segmentation model to generate a mask around the gas plume based on the boundary box. The instructions are further configured to obtain one or more masked images from the segmentation model, and analyze the one or more masked images to obtain an image analysis of one or more parameters of the gas plume.

Abstract: Methods, systems, and computer program products are provided for defect detection in industrial inspections. In one embodiment, captured images are ingested from a robotic platform equipped with imaging sensors. The ingested images are analyzed using an image analysis pipeline and a plurality of labeled images to generate a plurality of segmentation masks. In an environment shown in at least a subset of the plurality of ingested images, a plurality of environmental conditions are simulated to create an augmented plurality of labeled images. A defect analysis model is then trained with the augmented plurality of labeled images and the plurality of segmentation masks.

Abstract: The disclosed techniques are directed to using unmanned autonomous vehicles to perform inspections of, for example, gas sensors or other assets located within a processing facility. For example, the unmanned autonomous vehicles may autonomously navigate through a processing facility to perform the inspections. In addition, one or more properties of data captured by the unmanned autonomous vehicles may be controlled based on real-time conditions to optimize the inspection of the assets of the processing facility. Furthermore, the unmanned autonomous vehicles may be configured to perform calibration of the assets when anomalies readings are collected. In addition, the unmanned autonomous vehicles may be self-learning autonomous devices configured to learning from data collected during previous inspections of assets.

Abstract: A method for creating a domain-specific benchmarking dataset for a domain-specific task in an oil and/or gas domain includes receiving input data. The method also includes receiving the domain-specific task that is related to the oil and/or gas domain. The method also includes receiving a prompt from a user. The prompt is received by a text or multimodal large language model (LLM). The method also includes generating a plurality of synthetic instruction-response pairs in response to the prompt based upon the input data and the domain-specific task. The synthetic instruction-response pairs are created by the text or multimodal LLM. The synthetic instruction-response pairs form at least part of the domain-specific benchmarking dataset.

Abstract: A method for producing multi-dimensional spectral models of a production system. Input data is received from a plurality of spectral markers that are disposed in the production system, the spectral markers providing reference points for multiple readings taken by mobile or stationary sensors to be matched. Each of the spectral markers within the three-dimensional space are read to determine a unique spectral signature corresponding to each one of the spectral markers, the spectral signature having a pattern of spectral values that is unique to each one of the corresponding spectral markers. The determined spectral signatures of each of the plurality of spectral markers are associated with a unique identification which are then provided to a robot within the three-dimensional space. The multi-dimensional spectral model is then reconstructed using the assigned locations. The spectral markers also double as sensors and can transmit readings along with their unique spectral signatures.

Abstract: Methods, computing devices, and computer-readable storage media are provided. A computing device receives an image of a respective area of a facility, detects signage within the image, and maps the detected signage to the respective area represented in a map to produce a map of signs that is stored in a spatial data structure. Natural language processing with references to well-known symbols semantically understands information included on the signage, which is then stored. When one or more anomalies are determined to exist in the signage, information regarding the one or more anomalies is presented. An impact area of the signage is determined, if any. The received image is compared with a previously received image of the respective area to determine a difference. The computing device presents an indication of the difference.

Abstract: The present disclosure relates to systems and methods for remote operations of a facility using an extended reality device. The systems and methods receive a video feed of the facility and present on a display of the extended reality device the video feed. The systems and methods provide real-time data visualization of the facility using the extended reality device. The systems and methods cause an action to be performed at the facility in response to the video feed.

Abstract: Systems and methods presented herein generally relate to greenhouse gas emission management and, more particularly, to greenhouse gas emission management systems and methods for performing greenhouse gas detection sensor placement planning, leakage source tracing, and quantification of leakage source detections for oil and gas production facilities.

Abstract: A system includes one or more sensors to obtain three-dimensional (3D) data in a facility and a processor communicatively coupled to the one or more sensors. The processor is configured to execute instruction to generate a 3D model of the facility based on a first 3D data received from the one or more sensors at a first time and receive a second 3D data from the one or more sensors at a second time after the first time. The processor is further configured to execute instructions to determine an event based on the second 3D data and the 3D model and output a notification via an electronic device based on the event.

Abstract: A system for inspecting one or more gas plumes in a facility, including a processor and a memory having instructions executable by the processor, wherein the instructions are configured to obtain one or more images from one or more cameras, wherein the one or more images include a gas plume. The instructions are further configured to focus the one or more images on an area of interest with an object detection model to generate a boundary box around the gas plume, and focus the one or more images on the area of interest with a segmentation model to generate a mask around the gas plume based on the boundary box. The instructions are further configured to obtain one or more masked images from the segmentation model, and analyze the one or more masked images to obtain an image analysis of one or more parameters of the gas plume.

Abstract: This disclosure generally relates to systems and methods for inspecting one or more equipment of a facility. The system may be configured to obtain one or more images including an equipment from one or more cameras, wherein the one or more cameras are fixed within the facility or are attached to an unmanned autonomous vehicle; focus the one or more images on an area of interest with an object detection model to generate a boundary box around the equipment; focus the one or more images on the area of interest with a segmentation model to generate a mask around the equipment based on the boundary box; obtain one or more masked images from the segmentation model; and analyze the one or more masked images to obtain an image analysis of one or more parameters of the equipment.

Abstract: A method of operation of an unmanned autonomous vehicle includes autonomously maneuvering the unmanned autonomous vehicle about a facility, collecting gas concentration data using one or more sensors carried on or integrated with the unmanned autonomous vehicle, and monitoring the collected gas concentration data to detect a high concentration due to a gas leak. The method further includes, if a high concentration is detected, estimating a location of the gas leak and maneuvering the unmanned autonomous vehicle toward the estimated location of the gas leak.

Abstract: A system includes a fiber optic cable configured to detect one or more first parameters of a leak event along a fluid conduit, and one or more sensors configured to measure one or more second parameters of a fluid flow along the fluid conduit. The system also includes a controller including a processor, a memory, and instructions stored on the memory and executable by the processor to: detect the one or more first parameters of the leak event via the fiber optic cable, measure the one or more second parameters of the fluid flow via the one or more sensors, input the one or more first parameters and the one or more second parameters into a model configured to simulate operation with the fluid conduit, and output leak information corresponding to the leak event via execution of the model.

Abstract: Methods, systems, and computer program products are provided for defect detection in industrial inspections. In one embodiment, captured images are ingested from a robotic platform equipped with imaging sensors. The ingested images are analyzed using an image analysis pipeline and a plurality of labeled images. to generate a plurality of segmentation masks. In an environment shown in at least a subset of the plurality of ingested images, a plurality of environmental conditions are simulated to create an augmented plurality of labeled images. A defect analysis model is then trained with the augmented plurality of labeled images and the plurality of segmentation masks.

Abstract: Nano-sized mixed metal oxide carriers capable of delivering a well treatment additive for a sustained or extended period of time in the environment of use, methods of making the nanoparticles, and uses thereof are described herein. The nanoparticles can have a formula of: A/[Mx1My2Mz3]OnHm where x is 0.03 to 3, y is 0.01 to 0.4, z is 0.01 to 0.4 and n and m are determined by the oxidation states of the other elements, and M1 can be aluminum (Al), gallium (Ga), indium (In), or thallium (Tl). M2 and M3 are not the same and can be a Column 2 metal, Column 14 metal, or a transition metal. A is can be a treatment additive.

Abstract: Nano-sized mixed metal oxide carriers capable of delivering a well treatment additive for a sustained or extended period of time in the environment of use, methods of making the nanoparticles, and uses thereof are described herein. The nanoparticles can have a formula of: A/[Mx1My2Mz3]OnHm where x is 0.03 to 3, y is 0.01 to 0.4, z is 0.01 to 0.4 and n and m are determined by the oxidation states of the other elements, and M1 can be aluminum (Al), gallium (Ga), indium (In), or thallium (Tl). M2 and M3 are not the same and can be a Column 2 metal, Column 14 metal, or a transition metal. A is can be a treatment additive.