EP-4207002-B1 - KNOWLEDGE DRIVEN ARTIFICIAL INTELLIGENCE ENGINE FOR ENGINEERING AUTOMATION

EP4207002B1EP 4207002 B1EP4207002 B1EP 4207002B1EP-4207002-B1

Inventors

Gondhi, Dinesh
SINHA, BHASKAR
Patil, Ashish Bhaskarrao
MAHENDRAN, NIRANJANA
Namburu, Kalyana Srinivas
Gavande, Vinod Krushna

Dates

Publication Date: 20260513
Application Date: 20221201

Claims (14)

A method of automating engineering design performed by an automated engineering system, the method comprising: querying (902) a knowledge base (104) for a template to map with new control loop data of a new control loop that was identified in new digitized design data for a new engineering project, the query including the new control loop data, wherein the knowledge base (104) is trained to map past control loop data of past control loops that were identified in past digitized design data from one or more past engineering projects to respective templates based on past instantiation of the respective templates with the past control loops by the one or more past engineering projects; receiving (904) a selected template in response to the query, wherein the selected template is selected based on its mapping with past control loop data that matches the new control loop data; instantiating the selected template with the new control loop data; characterized by causing a control component of an engineering system (170) to be operated using the instantiated template for controlling a physical entity including a valve or a switch; wherein the method further comprises: collecting, before providing to the knowledge base (104) for training, pairings of past templates and past control loops having identifiers and past control loop data as used for respective past instantiations by the respective past engineering projects; submitting the pairings for a conflict review performed manually and/or automatically; receiving review data based on the conflict review; and updating the collection as a function of the conflict review data, wherein the knowledge base (104) is created and/or trained using the collection; wherein the conflict review comprises: identifying a conflict in which first and second control loop data for two different pairings are the same and are paired respectively with different templates; reviewing the past digitized design data to identify an additional attribute of the respective first and second control loops that is different for the first control loop relative to the second control loop; and including in the review data a new feature to be added to the control loop data in the collection for the first and second control loops that corresponds to the additional attribute so that the first and second control loops have different corresponding control loop data.
The method of claim 1, wherein the new control loop data and past control loop data are standardized and/or normalized.
The method of claim 1, further comprising adding the additional attribute to the control loop data of at least one of the first and second control loops.
The method of claim 1, further comprising: submitting a mapping of the selected template and the new control loop data for engineering review; receiving review data based on the engineering review; and updating the knowledge base (104) as a function of the review data.
The method of claim 1, further comprising: identifying (1002) the past control loop data in past digitized design data from a past engineering project; and pairing (1006) the past control loop data to a past template that was instantiated by the past engineering project using a control loop that corresponds to the past control loop data.
The method of claim 1, wherein the new digitized design data is digitized from data including pictorial data.
The method of claim 1, wherein machine learning is used for training (1008) the knowledge base (104) and for responding to queries submitted to the knowledge base (104).
The method of claim 1, wherein the past and new control loop data include control loop type, one or more tags, and/or attributes of the one or more tags, wherein the attributes of the one or more tags include system type, signal type, signal count, signal level, alarms, and/or signal and/or equipment description.
The method of claim 4, wherein each mapping in the knowledge base (104) has an associated confidence score, and updating the knowledge base (104) includes increasing the confidence score when the mapping was approved by the engineering review, and decreasing the confidence score when the mapping was disapproved and/or a modification to or replacement of the selected template was suggested by the engineering review.
An automated engineering system comprising: a memory (1128) configured to store instructions; and a processor (1116) in communication with the memory (1128), wherein the processor (1116) upon execution of the instructions is configured to: query a knowledge base (104) for a template to map with new control loop data of a new control loop that was identified in new digitized design data for a new engineering project, the query including the new control loop data, wherein the knowledge base (104) is trained to map past control loop data of past control loops that were identified in past digitized design data from one or more past engineering projects to respective templates based on past instantiation of the respective templates with the past control loops by the one or more past engineering projects; receive a selected template in response to the query, wherein the selected template is selected based on its mapping with past control loop data that matches the new control loop data; instantiate the selected template with the new control loop data; characterized by cause a control component of an engineering system (170) to be operated using the instantiated template for controlling a physical entity including a valve or a switch; wherein the processor upon execution of the instructions is further configured to: collect, before providing to the knowledge base (104) for training, pairings of past templates and past control loops having identifiers and past control loop data as used for respective past instantiations by the respective past engineering projects; submit the pairings for a conflict review performed manually and/or automatically; receive review data based on the conflict review; and update the collection as a function of the conflict review data, wherein the knowledge base (104) is created and/or trained using the collection; wherein the conflict review comprises: identifying a conflict in which first and second control loop data for two different pairings are the same and are paired respectively with different templates; reviewing the past digitized design data to identify an additional attribute of the respective first and second control loops that is different for the first control loop relative to the second control loop; and including in the review data a new feature to be added to the control loop data in the collection for the first and second control loops that corresponds to the additional attribute so that the first and second control loops have different corresponding control loop data.
The automated engineering system of claim 10, wherein the processor upon execution of the instructions is further configured to add the additional attribute to the control loop data of at least one of the first and second control loops.
The automated engineering system of claim 10, wherein the processor upon execution of the instructions is further configured to: submit a mapping of the selected template and the new control loop data for engineering review; receive review data based on the engineering review; and update the knowledge base (104) as a function of the review data.
The automated engineering system of claim 12, wherein each mapping in the knowledge base (104) has an associated confidence score, and updating the knowledge base includes increasing the confidence score when the mapping was approved by the engineering review, and decreasing the confidence score when the mapping was disapproved and/or a modification to or replacement of the selected template was suggested by the engineering review.
A non-transitory computer readable storage medium having one or more computer programs stored therein, the computer programs comprising instructions, which when executed by a processor of a computer system, cause the processor to: query a knowledge base (104) for a template to map with new control loop data of a new control loop that was identified in new digitized design data for a new engineering project, the query including the new control loop data, wherein the knowledge base (104) is trained to map past control loop data of past control loops that were identified in past digitized design data from one or more past engineering projects to respective templates based on past instantiation of the respective templates with the past control loops by the one or more past engineering projects; receive a selected template in response to the query, wherein the selected template is selected based on its mapping with past control loop data that matches the new control loop data; instantiate the selected template with the new control loop data; characterized by cause a control component of an engineering system (170) to be operated using the instantiated template for controlling a physical entity including a valve or a switch; wherein the instructions, when executed by the processor of the computer system, further cause the processor to: collect, before providing to the knowledge base (104) for training, pairings of past templates and past control loops having identifiers and past control loop data as used for respective past instantiations by the respective past engineering projects; submit the pairings for a conflict review performed manually and/or automatically; receive review data based on the conflict review; and update the collection as a function of the conflict review data, wherein the knowledge base (104) is created and/or trained using the collection; wherein the conflict review comprises: identifying a conflict in which first and second control loop data for two different pairings are the same and are paired respectively with different templates; reviewing the past digitized design data to identify an additional attribute of the respective first and second control loops that is different for the first control loop relative to the second control loop; and including in the review data a new feature to be added to the control loop data in the collection for the first and second control loops that corresponds to the additional attribute so that the first and second control loops have different corresponding control loop data.

Description

RELATED APPLICATIONS This application claims priority to U.S. Patent Application Serial No. 63/295,625 filed December 31, 2021. TECHNICAL FIELD The present disclosure relates to engineering automation, and more particularly, to knowledge driven artificial intelligence engine for engineering automation for industrial control and design applications. BACKGROUND The design of specifications for control applications, human machine interfaces (HMIs), and cabinet engineering for a particular process are performed manually. The effort utilizes significant time and resources to understand characteristics of the process from the overall design inputs and requirements. The overall design inputs can include, for example, a front-end engineering and design (FEED) that can include, e.g., piping and instrumentation diagrams (P&IDs) and a database of component identifiers (also referred to as TAGs)). When developing a new design, engineers rely on skill and can use significant amounts of time to determine if a new solution should be created of if a specific requirement has already been addressed by a previous team that can be leveraged by reusing associated existing artifacts. When this problem is approached by applying a strictly rules driven approach, there are constraints that limit use and a lack of scalability. The process still requires a high level of engineering skill and significant time resources to design the rules for every new project and each type of project. While conventional methods and systems for monitoring dangerous conditions in an operation unit have generally been considered satisfactory for their intended purpose, there remains a need for improvements. Related technology is known from WO 2019/164503 A1. SUMMARY The present invention is set out in the appended claims. The purpose and advantages of the below described illustrated embodiments will be set forth in and apparent from the description that follows. Additional advantages of the illustrated embodiments will be realized and attained by the devices, systems and methods particularly pointed out in the written description and claims hereof, as well as from the appended drawings. To achieve these and other advantages and in accordance with the purpose of the illustrated embodiments, in one aspect, disclosed is a method of automating engineering design. The method includes querying a knowledge base for a template to map with new control loop data of a new control loop that was identified in new digitized design data for a new engineering project, the query including the new control loop data. The knowledge base is trained to map past control loop data of past control loops that were identified in past digitized design data from one or more past engineering projects to respective templates based on past instantiation of the respective templates with the past control loops by the one or more past engineering projects. The method further includes receiving a selected template in response to the query, wherein the selected template is selected based on its mapping with past control loop data that matches the new control loop data. Configuration data, including an instantiation of the selected template with the new control loop data, is provided for implementation of the new control loop in an engineering system. In one or more embodiments, the method can further include instantiating the new control loop data with the selected template. In one or more embodiments, the new control loop data and past control loop data can be standardized and/or normalized. The methode further includes collecting, before providing to the knowledge base for training, pairings of past templates and past control loops having identifiers and past control loop data as used for respective past instantiations by the respective past engineering projects, submitting the pairings for a conflict review performed manually and/or automatically, receiving review data based on the conflict review, and updating the collection as a function of the conflict review data, wherein the knowledge base is created and/or trained using the collection. The conflict review includes identifying a conflict in which first and second control loop data for two different pairings are the same and are paired respectively with different templates, reviewing the digitized design data to identify an additional attribute of the respective first and second control loops that is different for the first control loop relative to the second control loop, and including in the review data a new feature to be added to the control loop data in the collection for the first and second control loops that corresponds to the additional attribute so that the first and second control loops have different corresponding control loop data. In one or more embodiments, the method can further include adding the additional attribute to the control loop data of at least one of the first and second control loops. In one or more embod