Generative AI for industrial automation design environment
An integrated development environment (IDE) for designing, programming, and configuring aspects of an industrial automation system uses a generative artificial intelligence (AI) model and associated neural networks to generate portions of an industrial automation project in accordance with functional requirements provided to the industrial IDE system in intuitive formats, such as spoken or written plain language text. The system uses generative AI to translate plain language requests or functional specifications into industrial control code, human-machine interface (HMI) applications, device configuration settings, or other aspects of an industrial control project.
1 . A system, comprising:
a memory that stores executable components and a generative artificial intelligence (AI) model that has been trained using training data comprising at least industrial safety standards and at least one of industrial control code samples, industrial standards data, or industrial protocol data; and
a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising:
a user interface component configured to render a chat interface configured to receive industrial design input data;
a project generation component configured to generate industrial control code based on the industrial design input data; and
a generative AI component configured to
generate, based on application of generative AI analysis to the industrial control code using the generative AI model, one or more plain language comments describing functionalities of respective sections of the industrial control code,
embed the one or more plain language comments into the control code at the respective sections, and
generate, based on the application of the generative AI analysis, safety documentation for an industrial control system for which the industrial control code is designed.
2 . The system of claim 1 , wherein the one or more comments comprise at least one comment assigned to a rung or line of the industrial control code.
3 . The system of claim 1 , wherein
the generative AI component is further configured to generate, based on the application of the generative AI analysis to the industrial control code using the generative AI model, one or more plain language labels for respective elements of the industrial control code, and to assign the one or more labels to the respective elements, and
the one or more elements comprise at least one of an output coil, an input contact, or a data tag.
4 . The system of claim 1 , wherein the generative AI component is configured to generate a comment, of the one or more plain language comments, based on a variable name extracted from a section of the industrial control code to which the comment is to be assigned.
5 . The system of claim 1 , wherein the generative AI component is configured to, infer a control function that a section of the industrial control code is designed to perform based on the application of the generative AI analysis, and generate, for the section, a plain language comment describing the control function.
6 . The system of claim 1 , wherein the generative AI component is further configured to generate, based on the application of the generative AI analysis on the industrial control code and the industrial design input data, development documentation for the industrial control system.
7 . The system of claim 1 , wherein the generative AI component is configured to generate the safety documentation based on at least one a determination of an industrial vertical for which the industrial control code was developed, a determination of a type of industrial application that the industrial control code is designed to perform, a determination of a control function that a portion of the industrial control code is designed to perform, or a determination of an industrial device of an automation system to be monitored and controlled by the industrial control code.
8 . The system of claim 1 , wherein the safety documentation defines validation tests to be performed on an automation system that the industrial control code is designed to monitor and control.
9 . The system of claim 6 , wherein the development documentation comprises at least one of control code development documentation or engineering drawings for an automation system being designed by the industrial design input data.
10 . The system of claim 1 , wherein the project generation component is configured to generate the industrial control code formatted as an industrial domain-specific language.
11 . A method, comprising:
rendering, by an industrial integrated development environment (IDE) system comprising a processor, a chat interface configured to receive industrial design input data;
generating, by the industrial IDE system, industrial control code based on the industrial design input data;
generating, by the industrial IDE system based on application of generative artificial intelligence (AI) analysis to the industrial control code using a generative AI model, one or more plain language comments describing functionalities of respective sections of the industrial control code, wherein the generative AI model is trained using training data comprising at least industrial safety standards and at least one of industrial control code samples, industrial standards data, or industrial protocol data;
embedding, by the industrial IDE system, the one or more plain language comments into the control code at the respective sections; and
generating, by the industrial IDE system based on the application of the generative AI analysis, safety documentation for an industrial control system for which the industrial control code is designed.
12 . The method of claim 11 , wherein the generating of the one or more plain language comments comprises generating at least one comment assigned to a rung or line of the industrial control code.
13 . The method of claim 11 , further comprising:
generating, by the industrial IDE system based on the application of the generative AI analysis, one or more plain language labels for respective elements of the industrial control code, and
assigning, by the industrial IDE system, the one or more labels to the respective elements,
wherein the one or more elements comprise at least one of an output coil, an input contact, or a data tag.
14 . The method of claim 11 , wherein the generating of the one or more plain language comments comprises generating a comment based on a variable name extracted from a section of the industrial control code to which the comment is to be assigned.
15 . The method of claim 11 , wherein the generating of the one or more plain language comments comprises
inferring a control function that a section of the industrial control code is designed to perform based on the application of the generative AI analysis, and
generating, for the section, a plain language comment describing the control function.
16 . The method of claim 11 , further comprising generating, by the industrial IDE system based on the application of the generative AI analysis, development documentation for the industrial control system.
17 . The method of claim 11 , wherein the generating of the safety documentation comprises generating the safety documentation based on at least one a determination of an industrial vertical for which the industrial control code was developed, a determination of a type of industrial application that the industrial control code is designed to perform, a determination of a control function that a portion of the industrial control code is designed to perform, or a determination of an industrial device of an automation system to be monitored and controlled by the industrial control code.
18 . A non-transitory computer-readable medium having stored thereon instructions that, in response to execution, cause an industrial integrated development environment (IDE) system comprising a processor to perform operations, the operations comprising:
rendering a chat interface configured to receive industrial design input data;
generating industrial control code based on the industrial design input data;
generating, based on application of generative artificial intelligence (AI) analysis to the industrial control code using a generative AI model, one or more plain language comments describing functionalities of respective sections of the industrial control code, wherein the generative AI model is trained using training data comprising at least industrial safety standards and at least one of industrial control code samples, industrial standards data, or industrial protocol data;
embedding the one or more plain language comments into the control code at the respective sections; and
generating, based on the application of the generative AI analysis, safety documentation for an industrial control system for which the industrial control code is designed.
19 . The non-transitory computer-readable medium of claim 18 , wherein the generating comprises generating at least one comment assigned to a rung or line of the industrial control code.
20 . The non-transitory computer-readable medium of claim 18 , wherein the operations further comprise:
generating, based on the application of the generative AI analysis, one or more plain language labels for respective elements of the industrial control code, and
assigning the one or more labels to the respective elements,
wherein the one or more elements comprise at least one of an output coil, an input contact, or a data tag.