Abstract: The present technology relates to artificial intelligence assisted device troubleshooting. In an implementation, an interface service of a human machine interface application trains a machine learning model on the content of an embeddings database. The interface service then receives an input comprising a context of an automation system design. The interface service generates a prompt that includes an instruction for the ML model to identify an anomaly type associated with the context of the automation system design and to generate a solution that addresses the anomaly type. The interface service transmits the prompt to the ML model and receives a response from the ML model that includes the anomaly type and the requested solution. After receiving a response, the interface service may modify the automation system design based on the content of the response and surface a graphical user interface that includes the modified design.

Abstract: Dynamic connection and communication services in container orchestration systems. A connection broker is leveraged to overcome a mismatch between stateless connections to data access services and stateful connections to industrial automation devices (IAD) by acting as an intermediary between the stateless and stateful connections. The broker maintains stateless connections between itself and data access services and establishes stateful connections between itself and IADs. The broker manages stateful connections such that any data access service can communicate with the IADs via stateful connections, despite the stateless nature of the connections between the broker and the data access services. The broker receives data requests along the stateless connections, facilitates communication between data access services and IADs, and receives data responses from IADs along the stateful connections.

Abstract: Dynamic attribute-based edge-deployed security in an industrial automation environment is described. A policy engine receives a command executable relevant to operational technology of an industrial automation environment via an access account. The policy engine classifies the command as approved or denied based on identifying a security policy based on the access account and operational technology, determining a set of parameter values based on the security policy, determining an intent of the command based on the set of parameter values, and classifying the command by evaluating the intent against the security policy. In response to command approval, the policy engine identifies a first communication channel coupling the operational technology and a policy enforcement point, connects a second communication channel coupling the policy enforcement point and the policy engine, and transmits the command and an indication of the first channel to the policy enforcement point via the second channel.

Abstract: Systems and methods are disclosed for performing a local update from a global catalog of device and system attributes. In certain embodiments, a system may comprise an edge server of an industrial automation environment, configured to update a local catalog from a cloud-based global catalog. The edge server may perform a device discovery operation to identify an industrial device connected to a local network on premises with the edge server, access the global catalog to obtain data about the industrial device, store the data about the industrial device to the local catalog, and respond to a query about the industrial device based on the data about the industrial device from the local catalog.

Abstract: A computer readable medium stores instructions that cause a processor to receive an indication of a request for analysis of a simulation model associated with an industrial automation system, wherein the industrial automation system includes a plurality of devices, wherein each of the plurality of devices includes a respective compute surface configured to perform one or more software tasks, identify a first device of the plurality of devices having sufficient resources to perform the analysis, and deploy a container to the first device. The container is configured to collect data from one or more sensors disposed in or around the industrial automation system, update the simulation model based on the collected data, and provide the updated simulation model for distribution to one or more other devices of the plurality devices.

Abstract: A non-transitory computer readable medium stores instructions that cause a processor to receive an indication of an event associated with an industrial automation system, wherein the industrial automation system includes a plurality of devices configured to perform a plurality of operations within the industrial automation system, and wherein each of the plurality of devices includes a compute surface configured to perform one or more software tasks, determine a plurality of data processing tasks to perform based on the event, identify a portion of the plurality of devices to perform the plurality of data processing tasks based on the compute surface available for each of the plurality of devices, and deploy a container to each of the portion of the plurality of devices, wherein each container of each of the portion of the plurality of devices is configured to perform at least one of the plurality of data processing tasks.

Abstract: Described systems and methods may enable a cloud-computing system to use data model-based analysis to manage maintenance of an industrial automation system based on life stage predictions and real-time evaluations. Based on the data model-based analyses, the cloud-computing system may instruct an industrial control system of the industrial automation system to implement recommended adjustments and/or to confirm a part replacement occurred in situ. The recommended adjustment may include a part replacement. The cloud-computing system may generate instructions to cause shipment of the part to be installed as part of the part replacement to the industrial automation system.

Abstract: Systems and methods described herein may enable a cloud-computing system to use data model-based analysis to manage maintenance of an industrial automation system based on life stage predictions and real-time evaluations. Based on the data model-based analyses, the cloud-computing system may instruct an industrial control system of the industrial automation system to implement recommended adjustments and/or to confirm a part replacement occurred in situ. After confirming a part replacement, the cloud-computing system may reset, in a memory corresponding to the replaced part, an indication of total operating time of that replaced part to reflect the part replacement, thereby bypassing an input also able to be used to reset the indication of total operating time in the memory.

Abstract: Disclosed herein are methods and systems for automated anomaly detection and resolution for industrial device function. Where anomalies are detected, anomaly information is collected, including an anomaly description, an anomaly context, and a code block source of the anomaly. Anomaly information is used in generating prompts to be sent to a generative large language model (LLM) trained on anomaly data. The LLM is configured to accept a prompt containing anomaly information and return a reference anomaly solution selected for its similarity to the target anomaly. The reference anomaly solution, containing control logic that governs industrial device function, is tailored for the target anomaly. The tailored reference anomaly solution, now acting as the target anomaly solution, is deployed to the industrial controller associated with the industrial device experiencing anomalous function. The control logic of the target anomaly solution replaces existing control logic, thereby eliminating the anomaly.

Abstract: A method includes receiving a work order associated with a problem experienced by an industrial automation system configured to perform an industrial automation process, receiving, from an industrial automation device within the industrial automation system, supplemental data including one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, or any combination thereof, generating, via processing circuitry, using one or more large language models (LLMs), service content based on the work order and the supplemental data, wherein the service content includes a guided workflow for addressing the problem associated with the work order, and providing the service content to a mobile computing device for display via a user interface.

Abstract: Disclosed herein are methods and systems for an industrial automation device interface system that leverages generative artificial intelligence (GAI). The system receives a user request associated with an industrial device. The system processes the request to identify an intent and user interface functionality based at least on an industrial device context. When no existing user interface functionality is identified in the programming, the system generates a prompt designed to elicit a response from a generative artificial intelligence (GAI) model. The prompt contains industrial device context and a request to generate user interface functionality in the form of executable code for performing an action corresponding to the intent. The system submits the prompt to the GAI model and receives user interface functionality in return. The system executes the user interface functionality or provides it to the user device for execution.

Abstract: A system includes processing circuitry and a memory, accessible by the processing circuitry, storing instructions that, when executed by the processing circuitry, cause the processing circuitry to receive discovery data including one or more characteristics of an industrial automation device of an industrial automation system configured to perform an industrial automation process, wherein the industrial automation device is communicatively coupled to an operational technology (OT) network, request, from a database, catalog data for the industrial automation device, and generate, based on the discovery data and the catalog data, a device twin for the industrial automation device, wherein the device twin comprises an interface by which one or more applications may interact with the industrial automation device.

Abstract: A system includes processing circuitry and a memory, accessible by the processing circuitry, storing instructions that, when executed by the processing circuitry, cause the processing circuitry to receive data from a device twin representative of an industrial automation device of an industrial automation system configured to perform an industrial automation process, wherein the industrial automation device is communicatively coupled to an operational technology (OT) network, wherein the device twin includes an interface by which one or more applications may interact with the industrial automation device, determine that the industrial automation device is accessible via a plurality of edge devices, apply one or more policies to select a particular edge device of the plurality of edge devices, and transmit the data to the particular edge device for transmission to the industrial automation device.

Abstract: A system includes processing circuitry and a memory, accessible by the processing circuitry, storing instructions that, when executed by the processing circuitry, cause the processing circuitry to receive data collected during operation of an industrial automation device of an industrial automation system configured to perform an industrial automation process, process the received data, including applying one or more rules to filter the received data, prioritize the received data, or both, and transmit the processed received data to a device twin for the industrial automation device, wherein the device twin includes an interface by which one or more applications may interact with the industrial automation device, wherein the device twin runs in a cloud environment.

Abstract: A system includes processing circuitry and a memory, accessible by the processing circuitry, storing instructions that, when executed by the processing circuitry, cause the processing circuitry to deploy a first device twin in a first computing environment, wherein the first device twin includes a first interface by which a first application interacts with an industrial automation device of an industrial automation system configured to perform an industrial automation process wherein the industrial automation device is communicatively coupled to an operational technology (OT) network, deploy a second device twin in a second computing environment, wherein the second device twin includes a second interface by which a second application interacts with the industrial automation device, receive updated data corresponding to the industrial automation device, and update the first and second device twins based on the received updated data.

Abstract: Intelligent code block selection and codebase updating using generative AI is disclosed herein. A user may request a code block for performing a task based on a given quality parameter (e.g., most energy efficient, fastest, or the like). The system may select an AI model for evaluating code blocks to meet the quality parameter. The system may identify code blocks for evaluation and execute each code block in an isolated testing environment. The selected AI model evaluates each code block execution and selects a code block based on completing the task in a way that most adheres to the quality parameter. The selected code block is returned via a user interface. The selected code block may be stored in a configuration code building block library associated with the quality parameter and the task and used when developing and revising software for the industrial automation environment.

Abstract: Dynamic attribute-based edge-deployed security in an industrial automation environment is described. A policy engine receives a command executable relevant to operational technology of an industrial automation environment via an access account. The policy engine classifies the command as approved or denied based on identifying a security policy based on the access account and operational technology, determining a set of parameter values based on the security policy, determining an intent of the command based on the set of parameter values, and classifying the command by evaluating the intent against the security policy. In response to command approval, the policy engine identifies a first communication channel coupling the operational technology and a policy enforcement point, connects a second communication channel coupling the policy enforcement point and the policy engine, and transmits the command and an indication of the first channel to the policy enforcement point via the second channel.

Abstract: A method includes generating, via a containerized control application executing in a container running on computing infrastructure, a command that defines at least one characteristic of an operation of an industrial automation device in performance of an industrial automation process, transmitting the command from the containerized control application to an input/output (I/O) proxy, wherein the I/O proxy is configured to interface between the containerized control application and a physical I/O, transmitting the command from the I/O proxy to the physical I/O, wherein the physical I/O is configured to receive data from the industrial automation device and provide commands to the industrial automation device, transmitting the command from the physical I/O to the industrial automation device, and implementing, via the industrial automation device, the command.

Abstract: A method may include receiving an indication of an available updated container. The method may also involve identifying one or more compute surfaces comprising a first container and a second container that correspond to the available container, such that the first container may control one or more operations of an operational technology (OT) device. The method may also include scheduling a deployment of the updated container to replace the second container, receiving expected output data associated with a digital model associated with the OT device, and scheduling a switchover of control of the one or more operations to the second container based on the expected output data.

Abstract: In a container orchestration environment implemented in an industrial automation environment, a new industrial automation component (e.g., device or software) attaches to an industrial automation network, and a pod of the container orchestration environment detects the attachment. In response, the pod creates a new pod representing the new industrial automation component by determining a type of the new industrial automation component, identifying functionality specific to the industrial automation component based on the type, provisioning software to implement the functionality, and generating a pod with containers for the software. The pod couples interfaces in the software to interfaces of the new industrial automation component and exposes the pod in the container orchestration environment, allowing the industrial automation component to participate in the container orchestration system.