System and method for automatic change management for multi-disciplinary engineering projects

Abstract

A method for automated change management across multiple engineering disciplines is disclosed. The method involves detecting a change in an engineering project within a first discipline by monitoring a project database (118) using at least one processor (202). Upon detection, the processor (202) generates a first prompt for an artificial intelligence (AI) model to reconstruct project data in a second discipline, thereby creating a new version aligned with the detected change. The processor (202) then generates a second prompt for the Artificial intelligence model (116) to summarize a plurality of proposed adjustments for the project data in the second discipline. The processor (202) receives the summary of the proposed adjustments from the Artificial intelligence model (116), which is generated using the first and second prompts. Finally, the method includes displaying the summary of the proposed adjustments to a user via a user interface.

Description

[0001] Siemens Aktiengesellschaft

[0002] 1

[0003] SYSTEM AND METHOD FOR AUTOMATIC CHANGE MANAGEMENT FOR MULTI-DISCIPLINARY ENGINEERING PROJECTS

[0004] The present invention relates to the field of industrial automation and engineering project management. More specifically, the invention pertains to automated systems and methods for managing changes across multiple engineering disciplines, including mechanical, electrical, and automation engineering.

[0005] In the realm of industrial automation, engineering projects often encompass a multitude of disciplines, including mechanical, electrical, and automation engineering. Each discipline contributes specialized knowledge and tools to ensure the successful completion of complex engineering projects, such as the development, construction, and commissioning of industrial plants and factories. The collaborative effort of these diverse engineering disciplines is critical to achieving project objectives and ensuring efficient operation of the final system.

[0006] Traditionally, managing changes across these interconnected disciplines has been a significant challenge. Changes in one discipline frequently necessitate corresponding updates in the other disciplines to maintain coherence and functionality. For example, a modification to a mechanical component may require updates to electrical schematics and automation control logic. Similarly, changes in electrical wiring diagrams might necessitate adjustments to mechanical layouts and PLC programming. The interdependence of project data across these disciplines demands a robust change management system to track, coordinate, and integrate changes effectively.

[0007] Despite the critical need for efficient change management, existing systems often rely on manual processes that are prone to errors and inconsistencies. Engineers from different disciplines may use disparate tools and databases, leading to communication gaps and delays in synchronizing project data. Manual updates are time-consuming and increase the risk of overlooking critical dependencies, which can result in costly rework, project delays, and potential safety issues.

[0008] To address these challenges, there is a need for an automated method and system that can manage changes across multiple engineering disciplines seamlessly. Such a system would need to track changes in project data, determine intra- disciplinary and cross -disciplinary dependencies, and ensure that all modifications are accurately reflected and integrated across the project. By leveraging advanced computational algorithms and artificial intelligence, the system should facilitateSiemens Aktiengesellschaft

[0009] 2

[0010] real-time collaboration among engineers, enhance data consistency, and streamline project management processes.

[0011] The object of the invention is achieved by a method for automated change management across multiple engineering disciplines. In one example, the method is executed in at least one processor in an industrial automation network. The at least one processor refers to a computing unit that executes one or more computation algorithms and manages the data processing tasks required for running an industrial automation system. In some cases, the at least one processor can be part of a cloud-based infrastructure. For example, cloud services can providing scalable and robust processing power to handle large volumes of project data from various engineering disciplines.

[0012] The automated change management tracks and maintains changes occurring inside project data associated with an engineering project in a project database. The engineering project encompasses a comprehensive set of tasks, designs, and configurations required to develop, construct, and commission a plant or factory. The engineering project comprises project data in a plurality of engineering disciplines, including mechanical, electrical, and automation engineering, each contributing specialized knowledge and tools to ensure successful completion of the engineering project. Collaborative effort of the plurality of disciplines, coordinated through effective change management and communication, ensures the engineering project meets objectives and operates efficiently.

[0013] Project data in the mechanical engineering discipline comprises information necessary for designing and modeling mechanical components in a Mechanical Computer-Assisted Drawing (MCAD) file. The MCAD file includes detailed models and layouts of mechanical components and systems generated through tools such as Siemens NX. Mechanical engineers extensively interact with the project database to upload new designs and update existing ones as project specifications evolve. For example, if mechanical engineers decide to alter the dimensions of a mechanical component to improve efficiency, they must update the MCAD file accordingly. This change in the mechanical engineering discipline can necessitate corresponding updates in the electrical and automation engineering disciplines to ensure compatibility and integration.

[0014] Similarly, project data in the electrical engineering discipline comprises an EPLAN file containing detailed electrical schematics. The EPLAN file includes comprehensive information on component configurations, electrical symbols, voltageSiemens Aktiengesellschaft

[0015] 3

[0016] specifications, and wiring diagrams typically managed through electrical CAD systems like EPLAN. Electrical engineers rely on the project database to ensure that all electrical schematics are current and accurately reflect the necessary specifications for safe and efficient plant operations. For instance, if electrical engineers introduce new wiring configurations to accommodate additional sensors, they must update the EPLAN file. This update in the electrical engineering discipline may require mechanical engineers to adjust the physical layout of mechanical components in the MCAD file to provide space for the new wiring routes. Additionally, automation engineers might need to modify the PLC programming in TIA Portal to integrate the new sensors into the control system.

[0017] The project data in the automation engineering discipline utilizes TIA Portal for PLC programming and hardware configuration. In such a case, the project data covers hardware configurations, PLC programming, and HMI designs that are crucial for the automation and commissioning of an industrial plant. Automation engineers frequently interact with the project database to ensure that the control logic and hardware configurations are up-to-date and aligned with the overall project requirements. For example, if automation engineers decide to enhance the PLC programming to introduce new control sequences, the TIA Portal data must be updated. This change in the automation engineering discipline can necessitate updates in the electrical engineering discipline, requiring electrical engineers to revise wiring diagrams in the EPLAN file to reflect new connections. Furthermore, mechanical engineers may need to adjust the mechanical layout in the MCAD file to accommodate additional hardware components introduced by the updated PLC programming.

[0018] The interdependence of project data across mechanical, electrical, and automation engineering disciplines ensures that changes in one discipline are accurately reflected and integrated into the other disciplines. Mechanical, electrical, and automation engineers must collaborate closely and continuously update the project database to maintain coherence and consistency in project data. For example, if mechanical engineers decide to change the position of a mechanical component to improve accessibility, electrical engineers must update the EPLAN file to adjust the wiring routes accordingly. Automation engineers may also need to update the PLC programming in the TIA Portal to ensure that the control logic aligns with the new component positions. This collaborative effort across engineering disciplines ensures that the project meets objectives and operates efficiently.Siemens Aktiengesellschaft

[0019] 4

[0020] A project database enables seamless access and synchronization of data across the plurality of disciplines, fostering an integrated approach to plant and factory setup. It serves as the foundational backbone of the project, ensuring that mechanical, electrical, and automation engineers can collaborate effectively, each discipline drawing from and contributing to a unified pool of up-to-date and accurate project data.

[0021] The method includes processing the project data to determine a plurality of intra- disciplinary and cross -disciplinary dependencies which are stored as a knowledge graph. The project database enables seamless access and synchronization of data across the plurality of disciplines, fostering an integrated approach to plant and factory setup. The project database serves as the foundational backbone of the project, ensuring that mechanical, electrical, and automation engineers can collaborate effectively, each discipline drawing from and contributing to a unified pool of up-to-date and accurate project data.

[0022] When the method processes the project data, it identifies various intra- disciplinary dependencies within each engineering discipline. For example, within the mechanical engineering discipline, dependencies may include the relationship between the dimensions of a mechanical component and performance characteristics. If mechanical engineers decide to change the dimensions of a gear within an MCAD file, the method would recognize dependencies such as the impact on the gear's strength and compatibility with other mechanical components.

[0023] Similarly, the method identifies intra- disciplinary dependencies within the electrical engineering discipline. For example, in the electrical engineering discipline, dependencies might involve the connections between different electrical components within an EPLAN file. If electrical engineers modify a wiring diagram to add a new sensor, the method processes the project data to determine how this addition affects the existing circuitry and voltage specifications, ensuring that the new sensor is properly integrated into the electrical system.

[0024] In addition to intra- disciplinary dependencies, the method also determines cross- disciplinary dependencies that exist between different engineering disciplines. For example, when mechanical engineers update the dimensions of a mechanical component in the MCAD file, the method identifies cross -disciplinary dependencies by analyzing how this change affects the electrical and automation engineering disciplines. If the new dimensions require a different physical layout, electricalSiemens Aktiengesellschaft

[0025] 5

[0026] engineers may need to update the wiring diagrams in the EPLAN file to accommodate the new component placement.

[0027] By processing the project data and determining these intra- disciplinary and cross- disciplinary dependencies, the at least one processor constructs a knowledge graph. The knowledge graph serves as a comprehensive representation of the relationships and dependencies within and across the mechanical, electrical, and automation engineering disciplines. This knowledge graph is stored and continuously updated within the project database, enabling seamless access and synchronization of data. The project database ensures that all engineering disciplines can collaborate effectively, drawing from and contributing to a unified pool of up-to-date and accurate project data. This integrated approach facilitates efficient plant and factory setup, ensuring that the project meets objectives and operates efficiently.

[0028] The method further comprises detecting, by at least one processor, a change in the engineering project within a first discipline by monitoring the project database. In one example, the first discipline may be an electrical engineering discipline, and the change may be detected in an ECAD file. The change in context of the engineering project refers to any modification or update made to the project data, design parameters, configurations, or specifications. For example, the change may involve revising a wiring diagram in an ECAD system when new electrical components are added or when existing components need to be reconfigured. Another instance of the change could be altering a mechanical layout in an MCAD system to accommodate new machinery or to enhance an efficiency of the industrial plant. Additionally, the change could involve modifying the PLC programming in an automation system to improve process control or integrate new functionalities.

[0029] The detection of the change occurs because of the at least one processor, actively monitoring the project database for changes in the first discipline. For example, the at least one processor may detect the change when an engineer updates a PLC code or when new hardware is configured within an engineering system.

[0030] The at least one processor is further configured to extract information associated with the detected change by analyzing the project data. The information associated with the detected change comprises details such as a type of modification, a list of components affected, an extent of the change, and one or more potential implications for other engineering disciplines of the plurality of disciplines. For example, if the detected change involves an update to the PLC code, the at least one processor identifies specific fines of code that were modified, a logic implemented,Siemens Aktiengesellschaft

[0031] 6

[0032] and one or more hardware components impacted by the change. The at least one processor then compiles a list of all components that are affected by the change, such as sensors, actuators, and communication modules.

[0033] The at least one processor is further configured to evaluate a scope and a scale of modifications. For instance, if the change involves adding one or more new functions to a PLC code, the at least one processor assesses how extensive the one or more new functions are and how the one or more new functions integrate with the engineering project. In one example, the at least one processor uses a dependency analysis algorithm, to determine the extent of the modifications. For example, the dependency analysis algorithm examines the PLC code to identify all interrelated components and processes that the new functions will impact. The at least one processor then quantifies the scope of the modifications by analyzing a number of affected lines of code, a complexity of the new functions, and one or more integration points within the existing PLC code. In one example, the dependency analysis algorithm is applied on a knowledge graph comprising the dependencies between a plurality of components of the engineering project.

[0034] The at least one processor employs a cross-disciplinary impact assessment algorithm to perform evaluation to identify potential implications for other engineering disciplines. For instance, when the new functions in the PLC code introduce additional control sequences, the cross -disciplinary impact assessment algorithm identifies corresponding changes required in electrical schematics. The cross -disciplinary impact assessment algorithm analyzes new control sequences to determine if new wiring paths are necessary or if existing electrical components need to be reconfigured. The at least one processor then updates the electrical CAD (ECAD) files to reflect these changes accurately. For example, if a new control sequence necessitates additional sensors, the cross -disciplinary impact assessment algorithm uses the knowledge graph to identify all related components and systems that interact with these sensors. The cross -disciplinary impact assessment algorithm examines the dependencies and determines how the wiring diagrams in the ECAD files must be updated to integrate the new sensors seamlessly.

[0035] Moreover, the at least one processor evaluates the impact of the PLC code changes on the mechanical aspects of the engineering project using the cross -disciplinary impact assessment algorithm. For example, if the new PLC functions necessitate the addition of new sensors or actuators, the algorithm identifies the mechanical components that must be adjusted to accommodate these new devices. The at least one processor updates the Mechanical Computer- Assisted Drawing (MCAD) files toSiemens Aktiengesellschaft

[0036] 7

[0037] ensure that the mechanical layouts include new sensors or actuators and that their positions align with the overall project design. For instance, when the PLC code changes introduce a new actuator, the cross-disciplinary impact assessment algorithm uses the knowledge graph to pinpoint the mechanical components that need modification to support the new actuator. The algorithm ensures that the mechanical layouts are updated in the MCAD files, detailing the precise placement and necessary structural adjustments for the new actuator.

[0038] By using the knowledge graph as input, the cross -disciplinary impact assessment algorithm comprehensively evaluates the interconnected relationships and dependencies within the project data. The knowledge graph provides a detailed representation of how various components and systems interact across the mechanical, electrical, and automation engineering disciplines. This enables the cross-disciplinary impact assessment algorithm to identify potential implications of changes accurately and ensure that all necessary updates are made to maintain coherence and functionality within the project.

[0039] The method further comprises compiling information associated with the detected change into a first prompt template to generate the first prompt. A prompt template is a structured format that guides an artificial intelligence (Al) model by providing a specific arrangement of data, ensuring that the Artificial intelligence model processes information correctly and generates accurate outputs. The information associated with the detected change comprises details such as a type of modification, a list of components affected, an extent of the change, and an potential implications for other engineering disciplines. For instance, if the detected change involves updating a PLC program in an automation system, information would include new logic implemented, the hardware components impacted, and any changes to the HMI screens.

[0040] In one example, the at least one processor selects the first prompt template from a plurality of prompt templates based on a nature and a context of a detected change. Selecting the first prompt template from a plurality of prompt templates involves analyzing a nature and context of the detected change. For example, if the detected change pertains to a modification in the electrical component configuration within an ECAD system, the at least one processor selects a prompt template specifically tailored for electrical changes. Conversely, if the change involves a mechanical component design in an MCAD system, the at least one processor selects a different prompt template suited for mechanical changes.Siemens Aktiengesellschaft

[0041] 8

[0042] The first prompt is an initial instruction generated using the selected prompt template, which directs an Artificial intelligence model to reconstruct the project data in another engineering discipline. For example, if the detected change is a new wiring diagram in the ECAD system, the first prompt would instruct the Artificial intelligence model to align the wiring information with the corresponding mechanical layout in the MCAD system. By using the selected prompt template, the first prompt ensures that the Artificial intelligence model accurately interprets the detected change and reconstructs the project data accordingly. The Artificial intelligence model is a computational framework designed to perform specific tasks by learning patterns from data. An instance when the Artificial intelligence model is a generative Artificial intelligence model involves using advanced algorithms to create new content based on the input data.

[0043] The Artificial intelligence model is trained using historical project data from various engineering disciplines. During the training process, the Artificial intelligence model learns to identify patterns, relationships, and dependencies within the data. For example, the Artificial intelligence model is fed with numerous examples of changes in PLC code, wiring diagrams, and mechanical layouts, along with the corresponding adjustments made in other engineering systems. By analyzing these examples, the Artificial intelligence model learns to predict the necessary modifications when similar changes are detected in the future.

[0044] The method further comprises applying the first prompt on the Artificial intelligence model to cause the Artificial intelligence model to reconstruct the project data to generate the new version of the project data. The first prompt is applied by feeding structured instruction into the Artificial intelligence model, which uses trained algorithms to analyze and interpret the data. The new version of the project data is aligned to the detected change by ensuring that all relevant updates are accurately reflected across different engineering disciplines. For example, if the detected change involves updating the wiring configuration in the ECAD system, the Artificial intelligence model reconstructs the mechanical layout in the MCAD system to accommodate the new wiring paths and connections. By applying the first prompt, the Artificial intelligence model ensures that the new version of the project data in the second discipline is consistent with the detected change, maintaining coherence and integration across the engineering project.

[0045] In another example, if the detected change in the automation system involves reprogramming the PLC to improve efficiency, the first prompt guides the ArtificialSiemens Aktiengesellschaft

[0046] 9

[0047] intelligence model to update the human-machine interface (HMI) screens and control logic in the ECAD system. The Artificial intelhgence model reconstructs the project data to generate a new version that includes the revised electrical schematics and component configurations. This new version is then aligned to the detected change, ensuring that all engineering disciplines are synchronized and the project data is up-to-date.

[0048] By applying the first prompt, the Artificial intelligence model effectively reconstructs the project data, creating a new version that accurately reflects the detected change and aligns with the modifications made in the engineering project. This process ensures seamless integration and consistency across multiple engineering disciplines, enhancing collaboration and efficiency in project management.

[0049] In other words, the method further comprises generating, by the at least one processor, the first prompt for the Artificial intelligence model to reconstruct project data in a second discipline, thereby creating a new version of project data which is aligned with the detected change. Reconstruction of project data involves the Artificial intelhgence model interpreting the detected change and generating a coherent representation of the updated information in the context of the second discipline. For instance, if the detected change occurs in the automation system, the Artificial intelligence model reconstructs the corresponding electrical and mechanical data to reflect the modification. The second discipline refers to another area of engineering that is affected by the change, such as ECAD or MCAD. For example, if the first discipline is the automation system, the second discipline could be the electrical design system (ECAD) or the mechanical design system (MCAD).

[0050] The new version is the updated representation of the project data in the second discipline, which incorporates the detected change from the first discipline. For example, if the detected change involves updating the PLC code in the automation system, the new version of the project data in the electrical design system may include revised wiring diagrams and updated component configurations. The new version ensures that all engineering disciplines are aligned and consistent with the detected change, facilitating seamless integration and collaboration across different areas of the project.

[0051] In other words, an old version refers to the state of the project data after the change was detected but before reconstruction by the Artificial intelhgence model. For instance, if the project data in the ECAD system included a specific wiring diagramSiemens Aktiengesellschaft

[0052] 10

[0053] after the initial change detection, the specific wiring diagram represents the old version. The new version, on the other hand, is the updated project data that has been reconstructed by the Artificial intelligence model to incorporate and align with the detected change. For example, after the change detected in the specific wiring diagram, the new version of the project data would comprise changes in PLC code to align with the change in the specific wiring diagram. For instance, if the electrical engineers modify the wiring diagram to add a new sensor, the Artificial intelligence model would update the PLC code to include the logic necessary to process signals from the new sensor. The Artificial intelligence model would adjust the existing control sequences in the PLC program to ensure that the new sensor data is accurately integrated into the automation system. Additionally, the Artificial intelligence model would update any relevant HMI (Human-Machine Interface) screens to display the new sensor data, ensuring operators have real-time visibility of the updated system state. This comprehensive update across the PLC code and HMI screens ensures that the new version of the project data is fully aligned with the detected change in the specific wiring diagram.

[0054] The method further comprises determining, by the at least one processor, the plurality of differences between the old version of the project data and the new version of the project data in the second discipline, by comparison of the new version with the old version. The plurality of differences is determined by analyzing the changes made to the project data after the detected change has been incorporated. For example, if an update is made to the PLC code in the automation system, the Artificial intelligence model reconstructs the new version of the project data in the ECAD system, which might include updated wiring diagrams and component configurations.

[0055] The at least one processor is configured to determine the plurality of differences by using an algorithm such as a comparison algorithm designed to identify discrepancies between two datasets. One common algorithm for such tasks is the "difF algorithm, which is used to compare different versions of files and highlight differences. In one example, the comparison algorithm analyzes the attributes, structures, and relationships within the project data to identify any modifications.

[0056] Another example involves mechanical design changes in the MCAD system. If the old version of the project data includes a specific layout of mechanical components after the change detection, and the new version modifies the placement or dimensions of certain components to align with the detected change, the comparisonSiemens Aktiengesellschaft

[0057] 11

[0058] algorithm identifies one or more differences between the old version and the new version.

[0059] The method further comprises compiling information associated with the plurality of differences into a second prompt template to generate the second prompt. A selection of the second prompt template from the plurality of prompt templates is based on the specific nature of the differences identified between the old version and the new version of the project data. For example, if the plurality of differences includes changes in wiring connections within an ECAD system, the method selects a prompt template that is tailored to address electrical design modifications.

[0060] In one example, the at least one processor selects the second prompt template from the plurality of prompts by analyzing characteristics of the plurality of differences and matching the plurality of differences to most appropriate prompt template. For instance, if the plurality of differences involve addition of new components and reconfiguration of existing ones, the at least one processor selects the second prompt template such that the second prompt template is designed to handle component management and configuration updates. The selected second prompt template ensures that the second prompt generated is relevant and specific to the detected change that need to be communicated and implemented in the engineering project.

[0061] In one example, if the plurality of differences includes modifications to mechanical layouts in an MCAD system, such as changes in component positions and dimensions, the at least one processor is configured to select a prompt template that focuses on mechanical design adjustments. The selected second prompt template provides a structured format to compile the information associated with the plurality of differences, ensuring that the second prompt is accurate and comprehensive.

[0062] In other words, the method further comprises generating, by the at least one processor, the second prompt for the Artificial intelligence model to summarize a plurality of proposed adjustments for the project data in the second discipline. The second prompt is generated based on differences between an old version and the new version of the project data. The plurality of proposed adjustments refers to the specific modifications identified as necessary to align the project data with the detected changes.

[0063] The generated summary may provide a concise overview of the proposed adjustments, ensuring that they are directly related to the detected change. For instance, if the detected change necessitates relocating a component for betterSiemens Aktiengesellschaft

[0064] 12

[0065] accessibility, the summary might outline the new component location, the revised wiring paths, and any necessary changes to mounting brackets or supports. Thus the generated summary ensures that all proposed adjustments are coherent and directly address the implications of the detected change.

[0066] The method ensures that the plurality of proposed adjustments is aligned with the detected change by continuously validating the adjustments against the updated project data. For instance, if the detected change involves a new compliance requirement for safety standards, the plurality of proposed adjustments includes updating safety circuits, adding new safety components, and revising the documentation to reflect the new compliance criteria. The Artificial intelligence model ensures that all proposed adjustments are consistent with the detected change and that they fully address the new requirements.

[0067] The method further comprises applying the second prompt on the Artificial intelligence model to cause the Artificial intelligence model to propose the plurality of adjustments to the old version of the project data, to align the project data in accordance with the detected change in the engineering project. Transmission of the second prompt to the Artificial intelligence model involves sending the structured information, which includes the identified differences and the relevant context, to the Artificial intelligence model through a predefined communication interface. For example, if the project data resides in a centralized database, the second prompt is transmitted via an Application program Interface call or a direct data pipeline to the Artificial intelligence model.

[0068] The Artificial intelligence model receives the second prompt and processes information contained within the second prompt to generate the summary of the plurality of proposed adjustments. The Artificial intelligence model transmits the summary to the at least one processor by sending the summarized information back through the same communication interface used for the initial transmission of the second prompt. The at least one processor receives the summary and integrates it into the project management workflow, ensuring that all relevant stakeholders are informed of the proposed adjustments.

[0069] The method further comprises receiving, by the at least one processor, the summary of the plurality of proposed adjustments from the Artificial intelligence model. In other words, the summary is generated by using the generated first prompt and the second prompt on the GenArtificial intelligence model. The summary of the plurality of proposed adjustments generated by the Artificial intelligence modelSiemens Aktiengesellschaft

[0070] 13

[0071] includes contextual information about the detected change. The contextual information refers to the background details, circumstances, and specific factors surrounding the detected change that provide a deeper understanding of why the change is necessary and how it impacts the project data. For example, if the detected change involves updating the PLC code to incorporate new safety protocols, the contextual information might include details about the new safety regulations that prompted the update, the specific risks addressed by the new protocols, and any previous incidents that highlighted the need for enhanced safety measures.

[0072] The method further comprises displaying, by a user interface, the summary of the plurality of proposed adjustments to a user, thereby proposing project modifications to align the project data in the second discipline with the detected change in the first discipline. A user interface refers to the medium through which users interact with the system, typically involving graphical elements such as screens, buttons, menus, and forms. The user interface facilitates the communication between the user and the underlying system processes, making complex data and operations accessible and understandable.

[0073] The summary of the plurality of proposed adjustments is displayed on the user interface in a clear and organized manner, allowing the user to easily review and understand the proposed changes. For example, the user interface might present the summary in a dashboard format, with sections dedicated to different types of adjustments, such as wiring updates, component placements, and control logic modifications. Each section provides detailed descriptions of the proposed adjustments, along with contextual information about the detected change, ensuring that the user has all the necessary information to make informed decisions.

[0074] The advantages of proposing project modifications to align the project data in the second discipline with the detected change in the first discipline are numerous. The at least one processor ensures consistency and coherence across different engineering domains, reducing the risk of errors and discrepancies. For example, if a new safety protocol is introduced in the engineering project, corresponding modifications in the electrical design ensure that all safety components are correctly integrated and configured, enhancing the overall safety of the project.

[0075] The at least one processor facilitates better communication and collaboration among the engineering team. The clear and detailed display of the summary helps team members from different disciplines understand the rationale behind the proposedSiemens Aktiengesellschaft

[0076] 14

[0077] adjustments and their impact on the project. For instance, if a mechanical component is redesigned to improve performance, the corresponding updates in the electrical and control systems are clearly outlined, ensuring that all team members are on the same page and can work together effectively to implement the changes.

[0078] The at least one processor further enhances the efficiency and effectiveness of project management. By providing a comprehensive summary of the proposed adjustments and displaying them through an intuitive user interface, the method enables quicker decision-making and reduces the time required to implement the changes. For example, if a new component is added to the system, the user can quickly review the proposed wiring updates and approve them, streamlining the implementation process and minimizing project delays.

[0079] The at least one processor further ensures that all project modifications are aligned with the detected change, maintaining the integrity and accuracy of the project data. For instance, if a new compliance requirement is introduced, the proposed modifications ensure that all relevant components and systems are updated to meet the new standards, preventing potential compliance issues and ensuring the project meets all regulatory requirements.

[0080] The method further comprises receiving user feedback indicating one of an acceptance or a rejection of one or more of the plurality of proposed adjustments. The method further comprises retraining the Artificial intelligence model based on the received user feedback to improve reconstruction of the project data. The received user feedback is utilized to refine and enhance the Artificial intelligence model by incorporating the user's evaluations of the plurality of proposed adjustments. For example, when the user provides feedback accepting certain proposed adjustments, the Artificial intelligence model records these adjustments as validated and correct. Conversely, when the user rejects certain proposed adjustments, the Artificial intelligence model analyzes the reasons for rejection to understand any inaccuracies or shortcomings in the initial proposals. This feedback loop allows the Artificial intelligence model to learn from the user's expertise and improve future performance.

[0081] Retraining the Artificial intelligence model involves updating the model's algorithms and decision-making processes based on the received user feedback. For instance, if the user consistently rejects adjustments related to component placements due to spatial constraints not considered by the Artificial intelligence model, the retraining process will incorporate rules and patterns to better accountSiemens Aktiengesellschaft

[0082] 15

[0083] for spatial considerations in future proposals. The Artificial intelligence model uses feedback to adjust parameters, refine training data, and enhance predictive accuracy.

[0084] Improvement in reconstruction refers to the enhanced ability of the Artificial intelligence model to accurately rebuild and update the project data in alignment with detected changes. For example, if the Artificial intelligence model initially proposes adjustments that do not fully comply with updated safety regulations, the user feedback indicating rejection of these adjustments will trigger a retraining process. This process will incorporate the correct safety standards into the Artificial intelligence model's knowledge base, leading to improved reconstruction in future iterations. The Artificial intelligence model becomes more adept at generating adjustments that meet the required safety standards, ensuring that the reconstructed project data is both accurate and compliant.

[0085] In another instance, if the Artificial intelligence model proposes wiring updates that are repeatedly rejected due to practical implementation issues, the retraining process will involve understanding these practical constraints and incorporating them into the model's decision-making framework. As a result, the Artificial intelligence model improves in generating wiring updates that are not only theoretically sound but also practically feasible, leading to more accurate and useful reconstruction of the project data.

[0086] The method further comprises adjusting the project data within the second discipline based on the plurality of proposed adjustments to align the project data to the detected change in the engineering project. The project data is automatically adjusted by applying the proposed adjustments generated by the Artificial intelligence model directly to the relevant data sets and documents within the second discipline. For example, if the detected change involves updating the electrical control system, the Artificial intelligence model proposes adjustments such as new wiring diagrams, updated component layouts, and revised control logic. The at least one processor then automatically updates the electrical CAD drawings, control schematics, and related documentation to reflect these adjustments, ensuring that the project data is accurately aligned with the detected change.

[0087] The method further comprises notifying a change management system about the acceptance or rejection of the proposed adjustments. The change management system is a structured framework that manages and tracks changes within a project or organization. The change management system ensures that all changes areSiemens Aktiengesellschaft

[0088] 16

[0089] documented, evaluated, approved, and implemented in a controlled and systematic manner. In the context of the engineering project, the change management system monitors the acceptance or rejection of proposed adjustments, maintains records of the changes, and coordinates the implementation of approved modifications. For example, the change management system might include tools for version control, workflow management, and audit trails to track the progress and impact of changes throughout the project hfecycle.

[0090] The notification includes details of the detected change and the corresponding user feedback for tracking and reporting purposes. The notification ensures that the change management system has up-to-date information on the status of the proposed adjustments and the reasons for their acceptance or rejection. For example, if a proposed adjustment to the wiring diagram is accepted, the notification will include the details of the wiring update and the user feedback indicating acceptance. The change management system uses this information to update records, track the implementation of the change, and generate reports on the change management process.

[0091] The object of the invention is achieved by a system for automated change management across multiple engineering disciplines. The system comprises a project database configured to store project data for multiple engineering disciplines and a processor configured to detect a change in an engineering project within a first discipline by monitoring the project database. The processor is further configured to generate a first prompt for an artificial intelligence (Al) model to reconstruct project data in a second discipline, thereby creating a new version aligned with the detected change. The processor is also configured to generate a second prompt for the Artificial intelligence model to summarize a plurality of proposed adjustments for the project data in the second discipline. The second prompt is based on differences between an old version and the new version of the project data. The system receives the summary of the plurality of proposed adjustments from the Artificial intelligence model. The summary is generated using the first prompt and the second prompt on the Artificial intelligence model. A user interface is configured to display the summary of the plurality of proposed adjustments to a user, thereby proposing project modifications to align the project data in the second discipline with the detected change in the first discipline.

[0092] Additionally, the processor is further configured to adjust the project data within the second discipline based on the plurality of proposed adjustments to align the project data with the detected change in the engineering project. The processor isSiemens Aktiengesellschaft

[0093] 17

[0094] further configured to compile information associated with the detected change into a first prompt template to generate the first prompt. Moreover, the processor is configured to determine the plurahty of differences between the old version of the project data and the new version of the project data in the second discipline by comparison of the new version with the old version. The processor then compiles information associated with the plurality of differences into a second prompt template to generate the second prompt.

[0095] The above-mentioned and other features of the invention will now be addressed with reference to the accompanying drawings of the present invention. The illustrated embodiments are intended to illustrate, but not limit the invention.

[0096] The present invention is further described hereinafter with reference to illustrated embodiments shown in the accompanying drawings, in which:

[0097] FIG 1 is a block diagram of an industrial environment 100 capable of automatic change management for a multidisciplinary engineering project, according to an embodiment of the pre-sent invention!

[0098] FIG 2 is a block diagram of a system, such as those shown in FIG. 1, in which an embodiment of the present invention can be implemented! and

[0099] FIG 3 is a process flowchart illustrating an exemplary computer implemented method of automatic change management on an engineering project, according to an embodiment of the present invention.

[0100] Various embodiments are described with reference to the drawings, wherein like reference numerals are used to re-fer the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following de¬ scription, for the purpose of explanation, numerous specific details are set forth in order to provide thorough understanding of one or more embodiments. It may be evident that such embodiments may be practiced without these specific details.

[0101] FIG 1 is a block diagram of an industrial environment 100 capable of automatic change management for a multidisciplinary engineering project, according to an embodiment of the pre-sent invention. In FIG 1, the industrial environment 100 includes a system 102, the industrial plant 106 and one or more client devices 120A-N. As used herein, “industrial environment” refers to a processing environment comprising configurable computing physical and logical resources, for example,Siemens Aktiengesellschaft

[0102] 18

[0103] networks, servers, storage, applications, services, etc., and data distributed over a platform, such as cloud computing platform. The industrial environment 100 provides on- demand network access to a shared pool of the configurable computing physical and logical resources. The system 102 is communicatively connected to a industrial plant via the network 104 (such as Local Area Network (LAN), Wide Area Network (WAN), Wi-Fi, Internet, any short range or wide range communication). The system 102 is also connected to the one or more client devices 120A-N via the network 104. The system 102 is configured to perform automatic change management on an engineering project 106. The engineering project 102 comprises project data in a plurality of disciplines 108A-N. The plurality of disciplines 108A-N comprises at least a first discipline 108A and a second discipline 108B. The industrial environment 100 further comprises a project database 118, a application program interface (an artificial intelligence model 116, and a server 114. The industrial environment 100 further comprises a plurality of interfaces 122A-N. The system 102 may further comprise a platform 110 (such as a cloud computing platform), and an automation module 112.

[0104] The industrial environment 100 is a comprehensive processing environment that integrates various configurable computing physical and logical resources. These resources include networks, servers, storage, applications, and services, which are distributed over platforms such as cloud computing platforms. The industrial environment 100 provides on-demand network access to a shared pool of these resources, enabling scalable and efficient data management and processing within an industrial automation context. The industrial environment 100 is designed to support the complex requirements of multidisciplinary engineering projects by facilitating seamless communication and data exchange among different components and systems.

[0105] The system 102 is a core component within the industrial environment 100, responsible for executing automatic change management on multidisciplinary engineering projects. The system 102 interfaces with various other elements, including the industrial plant 106 and multiple client devices 120A-N, via the network 104. By leveraging advanced computational algorithms and artificial intelligence, the system 102 monitors, detects, and manages changes across different engineering disciplines, ensuring that project data remains coherent and up-to-date. The system 102 plays a crucial role in synchronizing modifications and maintaining the integrity of the overall project data.Siemens Aktiengesellschaft

[0106] 19

[0107] The industrial plant 106 represents the physical infrastructure where various industrial processes and operations are carried out. Within the context of the industrial environment 100, the industrial plant 106 is integrated with the system 102 to facilitate automatic change management. The plant 106 comprises various mechanical, electrical, and automation systems that contribute to the overall engineering project. By being communicatively connected to the system 102 via the network 104, the industrial plant 106 ensures that any changes in project data are accurately reflected in the physical operations, thereby enhancing efficiency and reducing the risk of errors.

[0108] The client devices 120A-N refer to the range of devices used by engineers and other stakeholders to interact with the system 102. These devices can include computers, tablets, smartphones, and other digital interfaces that allow users to access project data, review proposed changes, and provide feedback. The client devices 120A-N are connected to the system 102 via the network 104, ensuring real-time communication and data exchange. By facilitating user interaction, the client devices 120A-N play a vital role in the collaborative efforts required for multidisciplinary engineering projects.

[0109] The network 104 serves as the communication backbone within the industrial environment 100, connecting the system 102 with the industrial plant 106 and the client devices 120A-N. The network 104 can encompass various types of communication technologies, including Local Area Networks (LAN), Wide Area Networks (WAN), Wi-Fi, the Internet, and both short-range and wide-range communication protocols. By providing reliable and secure data transmission, the network 104 ensures that all components within the industrial environment 100 can seamlessly exchange information and coordinate their activities.

[0110] The engineering project 106 encompasses all tasks, designs, configurations, and data associated with developing, constructing, and commissioning an industrial plant or factory. This project involves contributions from multiple engineering disciplines, each bringing specialized knowledge and tools to ensure successful project completion. The system 102 manages the engineering project 106 by tracking changes, integrating updates, and maintaining consistency across the various disciplines involved. The project data within the engineering project 106 is stored in a project database and is continuously monitored and updated to reflect the latest modifications.

[0111] The plurality of disciplines 108A-N refers to the various engineering domains thatSiemens Aktiengesellschaft

[0112] 20

[0113] contribute to the engineering project 106. These disciplines include mechanical engineering (108A), electrical engineering (108B), and other specialized fields that may be involved in the project. Each discipline has project data, tools, and methodologies, which are integrated and synchronized by the system 102. By managing changes across the plurality of disciplines 108A-N, the system 102 ensures that the engineering project 106 remains coherent and that all modifications are accurately reflected in the project data.

[0114] The project database 118 is a centralized repository designed to store and manage all the project data associated with multiple engineering disciplines. The project database 118 facilitates seamless access and synchronization of data among different engineering teams, ensuring that all modifications and updates are accurately reflected across the project. The project database 118 serves as the foundational backbone of the engineering project 106, enabling efficient data management and fostering real-time collaboration among mechanical, electrical, and automation engineers. By maintaining a unified pool of up-to-date project information, the project database 118 enhances the consistency and coherence of the overall project workflow.

[0115] The Artificial intelligence model 116 is a computational framework designed to perform specific tasks by learning patterns from data. An instance when the Artificial intelligence model 116 is a generative Artificial intelligence model involves using advanced algorithms to create new content based on the input data. Engineers train the Artificial intelligence model 116 using historical project data from various engineering disciplines. During the training process, the Artificial intelligence model 116 learns to identify patterns, relationships, and dependencies within the data.

[0116] The Artificial intelligence model 116 can manifest in several technical forms depending on the specific requirements and tasks it is designed to perform. One technical manifestation of the Artificial intelligence model 116 is a generative adversarial network (GAN). In this configuration, the model comprises two neural networks: a generator and a discriminator. The generator creates new data samples based on input data, while the discriminator evaluates the authenticity of the generated samples. Engineers train both networks simultaneously, with the generator improving ability to create realistic data and the discriminator enhancing capability to distinguish between real and generated data. This type of model is particularly useful in scenarios where the Artificial intelligence model 116 needs to create new design elements or configurations in response to detected changes inSiemens Aktiengesellschaft

[0117] 21

[0118] project data.

[0119] Another technical manifestation of the Artificial intelligence model 116 is a recurrent neural network (RNN). RNNs are well-suited for tasks involving sequential data, such as time-series analysis or natural language processing. The RNN architecture allows the model to maintain an internal state that captures information from previous inputs, making it ideal for analyzing dependencies and relationships over time. Engineers can implement long short-term memory (LSTM) units within the RNN to address issues of long-term dependencies and improve the model's abihty to learn from sequences of data. This manifestation is particularly effective for tasks that require the Artificial intelligence model 116 to predict future trends or generate sequences of actions based on historical project data.

[0120] Engineers can also implement the Artificial intelligence model 116 as a convolutional neural network (CNN). CNNs are highly effective for tasks involving spatial data, such as image recognition or pattern detection within two-dimensional matrices. The architecture of CNNs includes convolutional layers that apply filters to the input data, extracting relevant features and reducing dimensionality. Pooling layers further downsample the data, enhancing the model's ability to recognize hierarchical patterns. This manifestation of the Artificial intelligence model 116 is advantageous for analyzing visual data, such as mechanical component layouts or electrical schematics, and for identifying specific features or anomalies within the project data.

[0121] In some cases, engineers may implement the Artificial intelligence model 116 using a hybrid architecture that combines elements of different neural network types. For example, a hybrid model could integrate CNNs for spatial data analysis and RNNs for sequential data processing. This approach leverages the strengths of both architectures, enabling the Artificial intelligence model 116 to handle complex tasks that involve multiple types of data. Engineers can design the hybrid model to process visual data from mechanical designs while simultaneously analyzing time¬ series data from automation system logs, providing a comprehensive solution for multidisciplinary engineering projects.

[0122] The Artificial intelligence model 116 can also be implemented using ensemble learning techniques. Ensemble learning involves combining multiple models to improve overall performance and robustness. Engineers can employ techniques such as bagging, boosting, or stacking to create an ensemble of models, each trained on different subsets of data or different aspects of the task. The ensemble approachSiemens Aktiengesellschaft

[0123] 22

[0124] enhances the model's ability to generalize from data and reduces the risk of overfitting. This manifestation is particularly useful for ensuring the reliability and accuracy of the Artificial intelligence model 116 in managing complex engineering changes and dependencies.

[0125] In all technical manifestations, engineers ensure that the Artificial intelligence model 116 is integrated with the project database 118 and other system components via an application program interface (API). The API facilitates seamless interaction between the model and the system, enabling real-time data processing and decisionmaking. The integration allows the Artificial intelligence model 116 to continuously monitor project data, detect changes, generate prompts, and propose adjustments, thereby enhancing the efficiency and accuracy of change management across multiple engineering disciplines.

[0126] The server 114 plays a crucial role in the industrial environment 100 by providing the necessary computational power and resources to execute various tasks associated with the engineering project. The server 114 hosts critical applications, processes data, and manages network communications, ensuring that all system components can operate smoothly and efficiently. By leveraging robust processing capabilities, the server 114 supports the automation module 112, project database 118, and other essential functions, enabling the effective management of multi¬ disciplinary engineering projects. It acts as the central hub for processing and storing project data, facilitating real-time access and updates across the network.

[0127] The plurality of interfaces 122A-N refers to the various user interfaces and system interfaces that facilitate interaction between the users and the system components within the industrial environment 100. These interfaces include graphical user interfaces (GUIs) for engineers to access and manage project data, as well as system interfaces that enable seamless data exchange between different software applications and hardware components. By providing intuitive and user-friendly interaction points, the plurality of interfaces 122A-N enhances the usability and accessibility of the system, allowing engineers from different disciplines to collaborate effectively and ensure that all project modifications are accurately implemented and reflected in the project data.

[0128] The platform 110 takes a form of a cloud computing platform. The cloud computing platform provides a robust and scalable infrastructure that allows for the storage, management, and processing of vast amounts of data over the internet. By leveraging cloud services, the platform 110 can offer on-demand access to a sharedSiemens Aktiengesellschaft

[0129] 23

[0130] pool of configurable computing resources, such as servers, storage, applications, and services. This flexibility is crucial for handling the complex data requirements of multidisciplinary engineering projects. The cloud computing platform ensures that the system 102 can scale its resources dynamically to meet the demands of large- scale industrial automation projects, enabling real-time data processing and seamless collaboration across different engineering disciplines. Additionally, the platform 110 supports enhanced data security, reliability, and disaster recovery capabilities, making it an integral component of the overall system architecture.

[0131] The automation module 112 is configured to streamline and automate a process of change management within multidisciplinary engineering projects. The automation module 112 is responsible for executing a series of complex tasks, including the detection of changes in project data, the generation of prompts for artificial intelligence models, and the evaluation of proposed adjustments across different engineering disciplines. By integrating advanced computational algorithms and artificial intelligence, the automation module 112 facilitates real-time synchronization and collaboration among mechanical, electrical, and automation engineers. It ensures that all modifications are accurately reflected and integrated across the project, maintaining data coherence and consistency. The automation module 112 significantly reduces the reliance on manual processes, thereby minimizing errors, reducing project delays, and enhancing overall project efficiency. Its role is pivotal in managing the interdependencies of project data, ensuring that the engineering project meets its objectives and operates efficiently.

[0132] FIG 2 is a block diagram of a system 102, such as those shown in FIG 1, in which an embodiment of the present invention can be implemented. In FIG 2, the system 102 includes a processing unit 202, an accessible memory 204, a storage unit 206, a communication interface 208, an input-output unit 210, a network inter-face 212 and a bus 214.

[0133] The processing unit 202, as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor unit, microcontroller, complex instruction set computing microprocessor unit, reduced instruction set computing microprocessor unit, very long instruction word microprocessor unit, explicitly parallel instruction computing microprocessor unit, graphics processing unit, digital signal processing unit, or any other type of processing circuit. The processing unit 202 may also include embedded controllers, such as generic or programmable logic devices or arrays, application specific integrated circuits, single-chip computers, and the like.Siemens Aktiengesellschaft

[0134] 24

[0135] The memory 204 may be non-transitory volatile memory and non-volatile memory. The memory 204 may be coupled for communication with the processing unit 202, such as being a computer-readable storage medium. The processing unit 202 may execute machine-readable instructions and / or source code stored in the memory 204. A variety of ma-chine-readable instructions may be stored in and accessed from the memory 204. The memory 204 may include any suitable elements for storing data and machine-readable instructions, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, a hard drive, a removable media drive for handling compact disks, digital video disks, diskettes, magnetic tape cartridges, memory cards, and the like. In the present embodiment, the memory 204 includes an integrated development environment (IDE) 216. The IDE 216 includes the automation module 112 stored in the form of machine-readable instructions on any of the above-mentioned storage media and may be in communication with and executed by the processor(s) 202.

[0136] The automation module 112 is configured to perform automatic change management in the engineering project 106. The automation module 112 is a sophisticated software component designed to streamline an entire process of generating the engineering project for the industrial plant 106. The computer-readable code within the module is meticulously crafted to perform a series of complex tasks, including the analysis of technical commissioning documents, identification of engineering objects, determination of metadata tags, and selection and application of appropriate Lowcode models on metadata tags.

[0137] The automated change management tracks and maintains changes occurring inside project data associated with the engineering project 106 in the project database 118. The engineering project 106 encompasses a comprehensive set of tasks, designs, and configurations required to develop, construct, and commission an industrial plant 106. The engineering project 106 comprises project data in the plurality of disciplines 108A-N, including mechanical, electrical, and automation engineering, each contributing specialized knowledge and tools to ensure successful completion of the engineering project 106. Collaborative effort of the plurality of disciplines 108A-N, coordinated through effective change management and communication, ensures the engineering project 106 meets objectives and operates efficiently.

[0138] The automation module 112 is configured to cause the processing unit 202 to process project data in the mechanical engineering discipline, which comprisesSiemens Aktiengesellschaft

[0139] 25

[0140] information necessary for designing and modeling mechanical components in a Mechanical Computer-Assisted Drawing (MCAD) file. The MCAD file includes detailed models and layouts of mechanical components and systems generated through tools such as Siemens NX. Mechanical engineers extensively interact with the project database 118 to upload new designs and update existing ones as project specifications evolve. For example, if mechanical engineers decide to alter the dimensions of a mechanical component to improve efficiency, they must update the MCAD file accordingly. This change in the mechanical engineering discipline can necessitate corresponding updates in the electrical and automation engineering disciplines to ensure compatibility and integration.

[0141] The automation module 112 is configured to cause the processing unit 202 to process project data in the electrical engineering discipline, which comprises an EPLAN file containing detailed electrical schematics. The EPLAN file includes comprehensive information on component configurations, electrical symbols, voltage specifications, and wiring diagrams typically managed through electrical CAD systems like EPLAN. Electrical engineers rely on the project database 118 to ensure that all electrical schematics are current and accurately reflect the necessary specifications for safe and efficient plant operations. For instance, if electrical engineers introduce new wiring configurations to accommodate additional sensors, they must update the EPLAN file. This update in the electrical engineering discipline may require mechanical engineers to adjust the physical layout of mechanical components in the MCAD file to provide space for the new wiring routes. Additionally, automation engineers might need to modify the PLC programming in TIA Portal to integrate the new sensors into the control system.

[0142] The automation module 112 is configured to cause the processing unit 202 to process project data in the automation engineering discipline, which utilizes TIA Portal for PLC programming and hardware configuration. In such a case, the project data covers hardware configurations, PLC programming, and HMI designs that are crucial for the automation and commissioning of an industrial plant 106. Automation engineers frequently interact with the project database 118 to ensure that the control logic and hardware configurations are up-to-date and aligned with the overall project requirements. For example, if automation engineers decide to enhance the PLC programming to introduce new control sequences, the TIA Portal data must be updated. This change in the automation engineering discipline can necessitate updates in the electrical engineering discipline, requiring electrical engineers to revise wiring diagrams in the EPLAN file to reflect new connections. Furthermore, mechanical engineers may need to adjust the mechanical layout inSiemens Aktiengesellschaft

[0143] 26

[0144] the MCAD file to accommodate additional hardware components introduced by the updated PLC programming. The interdependence of project data across mechanical, electrical, and automation engineering disciplines ensures that changes in one discipline are accurately reflected and integrated into the other disciplines.

[0145] Mechanical, electrical, and automation engineers must collaborate closely and continuously update the project database 118 to maintain coherence and consistency in project data. For example, if mechanical engineers decide to change the position of a mechanical component to improve accessibility, electrical engineers must update the EPLAN file to adjust the wiring routes accordingly. Automation engineers may also need to update the PLC programming in the TIA Portal to ensure that the control logic aligns with the new component positions. This collaborative effort across engineering disciplines ensures that the project meets objectives and operates efficiently. The project database 118 enables seamless access and synchronization of data across the plurality of disciplines 108A-N, fostering an integrated approach to plant and factory setup. It serves as the foundational backbone of the project, ensuring that mechanical, electrical, and automation engineers can collaborate effectively, each discipline drawing from and contributing to a unified pool of up-to-date and accurate project data.

[0146] The automation module 112 is configured to cause the processing unit 202 to process the project data to determine a plurality of intra- disciplinary and cross-disciplinary dependencies which are stored as a knowledge graph. The project database 118 enables seamless access and synchronization of data across the plurality of disciplines 108A-N, fostering an integrated approach to plant and factory setup. The project database 118 serves as the foundational backbone of the project, ensuring that mechanical, electrical, and automation engineers can collaborate effectively, each discipline drawing from and contributing to a unified pool of up-to-date and accurate project data. When the automation module 112 is configured to cause the processing unit 202 to process the project data, it identifies various intra- disciplinary dependencies within each engineering discipline. For example, within the mechanical engineering discipline 108A, dependencies may include the relationship between the dimensions of a mechanical component and performance characteristics. If mechanical engineers decide to change the dimensions of a gear within an MCAD file, the automation module 112 would recognize dependencies such as the impact on the gear's strength and compatibility with other mechanical components. Similarly, the automation module 112 identifies intra- disciplinary dependencies within the electrical engineering discipline 108B. For example, in the electrical engineering discipline 108B, dependencies might involve the connections between different electrical components within an EPLANSiemens Aktiengesellschaft

[0147] 27

[0148] file. If electrical engineers modify a wiring diagram to add a new sensor, the automation module 112 processes the project data to determine how this addition affects the existing circuitry and voltage specifications, ensuring that the new sensor is properly integrated into the electrical system.

[0149] In addition to intra- disciplinary dependencies, the automation module 112 is configured to cause the processing unit 202 to determine cross-disciplinary dependencies that exist between different engineering disciplines. For example, when mechanical engineers update the dimensions of a mechanical component in the MCAD file, the automation module 112 identifies cross -disciplinary dependencies by analyzing how this change affects the electrical and automation engineering disciplines. If the new dimensions require a different physical layout, electrical engineers may need to update the wiring diagrams in the EPLAN file to accommodate the new component placement. By processing the project data and determining these intra- disciplinary and cross-disciplinary dependencies, the automation module 112 constructs a knowledge graph. The knowledge graph serves as a comprehensive representation of the relationships and dependencies within and across the mechanical, electrical, and automation engineering disciplines. The knowledge graph is stored and continuously updated within the 118, enabling seamless access and synchronization of data. The project database ensures that all engineering disciplines can collaborate effectively, drawing from and contributing to a unified pool of up-to-date and accurate project data. This integrated approach facilitates efficient plant and factory setup, ensuring that the project meets objectives and operates efficiently.

[0150] The automation module 112 is configured to cause the processing unit 202 to detect a change in the engineering project 106 within a first discipline 108A by monitoring the project database 118. In one example, the first discipline 108A may be an electrical engineering discipline 108B, and the change may be detected in an ECAD file. The change in the context of the engineering project 106 refers to any modification or update made to the project data, design parameters, configurations, or specifications. For example, the change may involve revising a wiring diagram in an ECAD system when new electrical components are added or when existing components need to be reconfigured. Another instance of the change could be altering a mechanical layout in an MCAD system to accommodate new machinery or to enhance the efficiency of the industrial plant 106. Additionally, the change could involve modifying the PLC programming in an automation system to improve process control or integrate new functionalities.Siemens Aktiengesellschaft

[0151] 28

[0152] The detection of the change occurs because of the at least one processor, actively monitoring the project database 118 for changes in the first discipline 108A. For example, the at least one processor may detect the change when an engineer updates a PLC code or when new hardware is configured within an engineering system. The automation module 112 is configured to cause the processing unit 202 to extract information associated with the detected change by analyzing the project data. The information associated with the detected change comprises details such as the type of modification, a list of components affected, the extent of the change, and one or more potential implications for other disciplines of the plurality of disciplines 108A-N. For example, if the detected change involves an update to the PLC code, the automation module 112 identifies specific lines of code that were modified, the logic implemented, and one or more hardware components impacted by the change. The automation module 112 then compiles a list of all components that are affected by the change, such as sensors, actuators, and communication modules.

[0153] The automation module 112 is configured to cause the processing unit 202 to evaluate the scope and scale of modifications. For instance, if the change involves adding one or more new functions to a PLC code, the automation module 112 assesses how extensive the one or more new functions are and how the one or more new functions integrate with the engineering project 106. In one example, the automation module 112 uses a dependency analysis algorithm to determine the extent of the modifications. For example, the dependency analysis algorithm examines the PLC code to identify all interrelated components and processes that the new functions will impact. The automation module 112 then quantifies the scope of the modifications by analyzing the number of affected lines of code, the complexity of the new functions, and one or more integration points within the existing PLC code. In one example, the dependency analysis algorithm is applied to a knowledge graph comprising the dependencies between a plurality of components of the engineering project 106.

[0154] The automation module 112 is configured to cause the processing unit 202 to employ a cross -disciplinary impact assessment algorithm to perform an evaluation to identify potential implications for other disciplines 108A-N. For instance, when the new functions in the PLC code introduce additional control sequences, the cross- disciplinary impact assessment algorithm identifies corresponding changes required in electrical schematics. The cross -disciplinary impact assessment algorithm analyzes new control sequences to determine if new wiring paths are necessary or if existing electrical components need to be reconfigured. The automation module 112Siemens Aktiengesellschaft

[0155] 29

[0156] then updates the electrical CAD (ECAD) files to reflect these changes accurately. For example, if a new control sequence necessitates additional sensors, the cross-disciplinary impact assessment algorithm uses the knowledge graph to identify all related components and systems that interact with these sensors. The cross-disciplinary impact assessment algorithm examines the dependencies and determines how the wiring diagrams in the ECAD files must be updated to integrate the new sensors seamlessly.

[0157] Moreover, the automation module 112 is configured to cause the processing unit 202 to evaluate the impact of the PLC code changes on the mechanical aspects of the engineering project 106 using the cross -disciplinary impact assessment algorithm. For example, if the new PLC functions necessitate the addition of new sensors or actuators, the algorithm identifies the mechanical components that must be adjusted to accommodate these new devices. The automation module 112 updates the Mechanical Computer-Assisted Drawing (MCAD) files to ensure that the mechanical layouts include new sensors or actuators and that their positions align with the overall project design. For instance, when the PLC code changes introduce a new actuator, the cross -disciplinary impact assessment algorithm uses the knowledge graph to pinpoint the mechanical components that need modification to support the new actuator. The algorithm ensures that the mechanical layouts are updated in the MCAD files, detailing the precise placement and necessary structural adjustments for the new actuator.

[0158] By using the knowledge graph as input, the cross -disciplinary impact assessment algorithm comprehensively evaluates the interconnected relationships and dependencies within the project data. The knowledge graph provides a detailed representation of how various components and systems interact across the mechanical, electrical, and automation engineering disciplines. This enables the cross-disciplinary impact assessment algorithm to identify potential implications of changes accurately and ensure that all necessary updates are made to maintain coherence and functionality within the project.

[0159] The automation module 112 is configured to cause the processing unit 202 to compile information associated with the detected change into a first prompt template to generate the first prompt. A prompt template is a structured format that guides an artificial intelligence (Al) model by providing a specific arrangement of data, ensuring that the Artificial intelligence model 116 processes information correctly and generates accurate outputs. The information associated with the detected change comprises details such as the type of modification, a list ofSiemens Aktiengesellschaft

[0160] 30

[0161] components affected, the extent of the change, and potential implications for other disciplines 108A-N. For instance, if the detected change involves updating a PLC program in an automation system, the information would include new logic implemented, the hardware components impacted, and any changes to the HMI screens.

[0162] The automation module 112 is configured to cause the processing unit 202 to select the first prompt template from a plurality of prompt templates based on the nature and context of a detected change. Selecting the first prompt template from a plurality of prompt templates involves analyzing the nature and context of the detected change. For example, if the detected change pertains to a modification in the electrical component configuration within an ECAD system, the processing unit 202 selects a prompt template specifically tailored for electrical changes.

[0163] Conversely, if the change involves a mechanical component design in an MCAD system, the processing unit 202 selects a different prompt template suited for mechanical changes.

[0164] The first prompt is an initial instruction generated using the selected prompt template, which directs an Artificial intelligence model 116 to reconstruct the project data in another engineering discipline. For example, if the detected change is a new wiring diagram in the ECAD system, the first prompt would instruct the Artificial intelligence model 116 to align the wiring information with the corresponding mechanical layout in the MCAD system. By using the selected prompt template, the first prompt ensures that the Artificial intelligence model 116 accurately interprets the detected change and reconstructs the project data accordingly. The Artificial intelligence model 116 is a computational framework designed to perform specific tasks by learning patterns from data. An instance when the Artificial intelligence model 116 is a generative Artificial intelligence model 116 involves using advanced algorithms to create new content based on the input data. The Artificial intelligence model 116 is trained using historical project data from various engineering disciplines. During the training process, the Artificial intelligence model 116 learns to identify patterns, relationships, and dependencies within the data. For example, the Artificial intelligence model 116 is fed with numerous examples of changes in PLC code, wiring diagrams, and mechanical layouts, along with the corresponding adjustments made in other engineering systems. By analyzing these examples, the Artificial intelligence model 116 learns to predict the necessary modifications when similar changes are detected in the future.Siemens Aktiengesellschaft

[0165] 31

[0166] The automation module 112 is configured to cause the processing unit 202 to apply the first prompt on the Artificial intelligence model 116 to reconstruct the project data to generate the new version of the project data. The first prompt is applied by feeding structured instruction into the Artificial intelligence model 116, which uses trained algorithms to analyze and interpret the data. The new version of the project data is aligned to the detected change by ensuring that all relevant updates are accurately reflected across different engineering disciplines. For example, if the detected change involves updating the wiring configuration in the ECAD system, the Artificial intelligence model 116 reconstructs the mechanical layout in the MCAD system to accommodate the new wiring paths and connections. By applying the first prompt, the Artificial intelligence model 116 ensures that the new version of the project data in the second discipline is consistent with the detected change, maintaining coherence and integration across the engineering project.

[0167] In another example, if the detected change in the automation system involves reprogramming the PLC to improve efficiency, the first prompt guides the Artificial intelligence model 116 to update the human-machine interface (HMI) screens and control logic in the ECAD system. The Artificial intelligence model 116 reconstructs the project data to generate a new version that includes the revised electrical schematics and component configurations. This new version is then aligned to the detected change, ensuring that all engineering disciplines are synchronized and the project data is up-to-date.

[0168] By applying the first prompt, the Artificial intelligence model 116 effectively reconstructs the project data, creating a new version that accurately reflects the detected change and aligns with the modifications made in the engineering project. This process ensures seamless integration and consistency across multiple engineering disciplines, enhancing collaboration and efficiency in project management.

[0169] The automation module 112 is configured to cause the processing unit 202 to generate the first prompt for the Artificial intelligence model 116 to reconstruct project data in a second discipline, thereby creating a new version of project data which is aligned with the detected change. Reconstruction of project data involves the Artificial intelligence model 116 interpreting the detected change and generating a coherent representation of the updated information in the context of the second discipline. For instance, if the detected change occurs in the automation system, the Artificial intelligence model 116 reconstructs the corresponding electrical and mechanical data to reflect the modification. The second disciplineSiemens Aktiengesellschaft

[0170] 32

[0171] refers to another area of engineering that is affected by the change, such as ECAD or MCAD. For example, if the first discipline is the automation system, the second discipline could be the electrical design system (ECAD) or the mechanical design system (MCAD).

[0172] The new version is the updated representation of the project data in the second discipline, which incorporates the detected change from the first discipline. For example, if the detected change involves updating the PLC code in the automation system, the new version of the project data in the electrical design system may include revised wiring diagrams and updated component configurations. The new version ensures that all engineering disciplines are aligned and consistent with the detected change, facilitating seamless integration and collaboration across different areas of the project.

[0173] The automation module 112 is configured to cause the processing unit 202 to determine the plurality of differences between the old version of the project data and the new version of the project data in the second discipline, by comparison of the new version with the old version. The plurality of differences is determined by analyzing the changes made to the project data after the detected change has been incorporated. For example, if an update is made to the PLC code in the automation system, the Artificial intelligence model 116 reconstructs the new version of the project data in the ECAD system, which might include updated wiring diagrams and component configurations.

[0174] The processing unit 202 determines the plurality of differences by using an algorithm such as a comparison algorithm designed to identify discrepancies between two datasets. One common algorithm for such tasks is the "diff ' algorithm, which is used to compare different versions of files and highlight differences. In one example, the comparison algorithm analyzes the attributes, structures, and relationships within the project data to identify any modifications.

[0175] Another example involves mechanical design changes in the MCAD system. If the old version of the project data includes a specific layout of mechanical components after the change detection, and the new version modifies the placement or dimensions of certain components to align with the detected change, the comparison algorithm identifies one or more differences between the old version and the new version.

[0176] The automation module 112 is configured to cause the processing unit 202 toSiemens Aktiengesellschaft

[0177] 33

[0178] compile information associated with the plurahty of differences into a second prompt template to generate the second prompt. A selection of the second prompt template from the plurahty of prompt templates is based on the specific nature of the differences identified between the old version and the new version of the project data. For example, if the plurahty of differences includes changes in wiring connections within an ECAD system, the processing unit 202 selects a prompt template that is tailored to address electrical design modifications. The processing unit 202 selects the second prompt template from the plurality of prompts by analyzing characteristics of the plurality of differences and matching the plurality of differences to the most appropriate prompt template. For instance, if the plurality of differences involve the addition of new components and the reconfiguration of existing ones, the processing unit 202 selects the second prompt template designed to handle component management and configuration updates. The selected second prompt template ensures that the second prompt generated is relevant and specific to the detected change that needs to be communicated and implemented in the engineering project 106.

[0179] In one example, if the plurality of differences includes modifications to mechanical layouts in an MCAD system, such as changes in component positions and dimensions, the processing unit 202 selects a prompt template that focuses on mechanical design adjustments. The selected second prompt template provides a structured format to compile the information associated with the plurality of differences, ensuring that the second prompt is accurate and comprehensive.

[0180] The automation module 112 is configured to cause the processing unit 202 to generate the second prompt for the Artificial intelligence model 116 to summarize a plurality of proposed adjustments for the project data in the second discipline. The second prompt is generated based on differences between an old version and the new version of the project data. The plurality of proposed adjustments refers to the specific modifications identified as necessary to align the project data with the detected changes.

[0181] The generated summary may provide a concise overview of the proposed adjustments, ensuring that they are directly related to the detected change. For instance, if the detected change necessitates relocating a component for better accessibility, the summary might outline the new component location, the revised wiring paths, and any necessary changes to mounting brackets or supports. The generated summary ensures that all proposed adjustments are coherent and directly address the implications of the detected change.Siemens Aktiengesellschaft

[0182] 34

[0183] The automation module 112 is configured to cause the processing unit 202 to ensure that the plurality of proposed adjustments is aligned with the detected change by continuously validating the adjustments against the updated project data. For instance, if the detected change involves a new compliance requirement for safety standards, the plurality of proposed adjustments includes updating safety circuits, adding new safety components, and revising the documentation to reflect the new compliance criteria. The Artificial intelligence model 116 ensures that all proposed adjustments are consistent with the detected change and that they fully address the new requirements.

[0184] The automation module 112 is configured to cause the processing unit 202 to apply the second prompt on the Artificial intelligence model 116 to propose the plurality of adjustments to the old version of the project data, to align the project data in accordance with the detected change in the engineering project 106. Transmission of the second prompt to the Artificial intelligence model 116 involves sending the structured information, which includes the identified differences and the relevant context, to the Artificial intelligence model 116 through a predefined communication interface. For example, if the project data resides in a centralized database, the second prompt is transmitted via an Application Program Interface (API) call or a direct data pipeline to the Artificial intelligence model 116.

[0185] The Artificial intelligence model 116 receives the second prompt and processes the information contained within the second prompt to generate the summary of the plurality of proposed adjustments. The Artificial intelligence model 116 transmits the summary to the processing unit 202 by sending the summarized information back through the same communication interface used for the initial transmission of the second prompt. The processing unit 202 receives the summary and integrates it into the project management workflow, ensuring that all relevant stakeholders are informed of the proposed adjustments.

[0186] The automation module 112 is configured to cause the processing unit 202 to receive the summary of the plurality of proposed adjustments from the Artificial intelligence model 116. In other words, the summary is generated by using the generated first prompt and the second prompt on the Artificial intelligence model 116. The summary of the plurality of proposed adjustments generated by the Artificial intelligence model 116 includes contextual information about the detected change. The contextual information refers to the background details, circumstances, and specific factors surrounding the detected change that provide a deeperSiemens Aktiengesellschaft

[0187] 35

[0188] understanding of why the change is necessary and how it impacts the project data. For example, if the detected change involves updating the PLC code to incorporate new safety protocols, the contextual information might include details about the new safety regulations that prompted the update, the specific risks addressed by the new protocols, and any previous incidents that highlighted the need for enhanced safety measures.

[0189] The automation module 112 is configured to cause the processing unit 202 to display the summary of the plurality of proposed adjustments to a user, thereby proposing project modifications to align the project data in the second discipline with the detected change in the first discipline. A user interface refers to the medium through which users interact with the system, typically involving graphical elements such as screens, buttons, menus, and forms. The user interface facilitates the communication between the user and the underlying system processes, making complex data and operations accessible and understandable.

[0190] The summary of the plurality of proposed adjustments is displayed on the user interface in a clear and organized manner, allowing the user to easily review and understand the proposed changes. For example, the user interface might present the summary in a dashboard format, with sections dedicated to different types of adjustments, such as wiring updates, component placements, and control logic modifications. Each section provides detailed descriptions of the proposed adjustments, along with contextual information about the detected change, ensuring that the user has all the necessary information to make informed decisions.

[0191] The advantages of proposing project modifications to align the project data in the second discipline with the detected change in the first discipline are numerous. The processing unit 202 ensures consistency and coherence across different engineering domains, reducing the risk of errors and discrepancies. For example, if a new safety protocol is introduced in the engineering project 106, corresponding modifications in the electrical design ensure that all safety components are correctly integrated and configured, enhancing the overall safety of the project.

[0192] The processing unit 202 facilitates better communication and collaboration among the engineering team. The clear and detailed display of the summary helps team members from different disciplines understand the rationale behind the proposed adjustments and their impact on the project. For instance, if a mechanical component is redesigned to improve performance, the corresponding updates in theSiemens Aktiengesellschaft

[0193] 36

[0194] electrical and control systems are clearly outlined, ensuring that all team members are on the same page and can work together effectively to implement the changes.

[0195] The processing unit 202 further enhances the efficiency and effectiveness of project management. By providing a comprehensive summary of the proposed adjustments and displaying them through an intuitive user interface, the automation module 112 enables quicker decision-making and reduces the time required to implement the changes. For example, if a new component is added to the system, the user can quickly review the proposed wiring updates and approve them, streamlining the implementation process and minimizing project delays.

[0196] The processing unit 202 further ensures that all project modifications are aligned with the detected change, maintaining the integrity and accuracy of the project data. For instance, if a new compliance requirement is introduced, the proposed modifications ensure that all relevant components and systems are updated to meet the new standards, preventing potential compliance issues and ensuring the project meets all regulatory requirements.

[0197] The automation module 112 is configured to cause the processing unit 202 to receive user feedback indicating one of an acceptance or a rejection of one or more of the plurality of proposed adjustments. The automation module 112 is configured to cause the processing unit 202 to retrain the Artificial intelligence model 116 based on the received user feedback to improve reconstruction of the project data. The received user feedback is utilized to refine and enhance the Artificial intelligence model 116 by incorporating the user's evaluations of the plurality of proposed adjustments. For example, when the user provides feedback accepting certain proposed adjustments, the Artificial intelligence model 116 records these adjustments as validated and correct. Conversely, when the user rejects certain proposed adjustments, the Artificial intelligence model 116 analyzes the reasons for rejection to understand any inaccuracies or shortcomings in the initial proposals. This feedback loop allows the Artificial intelligence model 116 to learn from the user's expertise and improve future performance.

[0198] Retraining the Artificial intelligence model 116 involves updating the model's algorithms and decision-making processes based on the received user feedback. For instance, if the user consistently rejects adjustments related to component placements due to spatial constraints not considered by the Artificial intelligence model 116, the retraining process will incorporate rules and patterns to better account for spatial considerations in future proposals. The Artificial intelligenceSiemens Aktiengesellschaft

[0199] 37

[0200] model 116 uses this feedback to adjust parameters, refine training data, and enhance predictive accuracy.

[0201] Improvement in reconstruction refers to the enhanced ability of the Artificial intelligence model 116 to accurately rebuild and update the project data in alignment with detected changes. For example, if the Artificial intelligence model 116 initially proposes adjustments that do not fully comply with updated safety regulations, the user feedback indicating rejection of these adjustments will trigger a retraining process. This process will incorporate the correct safety standards into the Artificial intelligence model 116's knowledge base, leading to improved reconstruction in future iterations. The Artificial intelligence model 116 becomes more adept at generating adjustments that meet the required safety standards, ensuring that the reconstructed project data is both accurate and compliant.

[0202] In another instance, if the Artificial intelligence model 116 proposes wiring updates that are repeatedly rejected due to practical implementation issues, the retraining process will involve understanding these practical constraints and incorporating them into the model's decision-making framework. As a result, the Artificial intelligence model 116 improves in generating wiring updates that are not only theoretically sound but also practically feasible, leading to more accurate and useful reconstruction of the project data.

[0203] The automation module 112 is configured to cause the processing unit 202 to adjust the project data within the second discipline based on the plurality of proposed adjustments to align the project data to the detected change in the engineering project 106. The project data is automatically adjusted by applying the proposed adjustments generated by the Artificial intelligence model 116 directly to the relevant data sets and documents within the second discipline. For example, if the detected change involves updating the electrical control system, the Artificial intelligence model 116 proposes adjustments such as new wiring diagrams, updated component layouts, and revised control logic. The processing unit 202 then automatically updates the electrical CAD drawings, control schematics, and related documentation to reflect these adjustments, ensuring that the project data is accurately aligned with the detected change.

[0204] The automation module 112 is configured to cause the processing unit 202 to notify a change management system about the acceptance or rejection of the proposed adjustments. The change management system is a structured framework that manages and tracks changes within a project or organization. The changeSiemens Aktiengesellschaft

[0205] 38

[0206] management system ensures that all changes are documented, evaluated, approved, and implemented in a controlled and systematic manner. In the context of the engineering project 106, the change management system monitors the acceptance or rejection of proposed adjustments, maintains records of the changes, and coordinates the implementation of approved modifications. For example, the change management system might include tools for version control, workflow management, and audit trails to track the progress and impact of changes throughout the project lifecycle.

[0207] The notification includes details of the detected change and the corresponding user feedback for tracking and reporting purposes. The notification ensures that the change management system has up-to-date information on the status of the proposed adjustments and the reasons for their acceptance or rejection. For example, if a proposed adjustment to the wiring diagram is accepted, the notification will include the details of the wiring update and the user feedback indicating acceptance. The change management system uses this information to update records, track the implementation of the change, and generate reports on the change management process.

[0208] FIG 3 is a process flowchart illustrating an exemplary computer implemented method of automatic change management on an engineering project, according to an embodiment of the present invention. FIG 3 is described in conjunction with FIG 1, and 2.

[0209] At step 302, the automation module 112 is configured to cause the processing unit 202 to detect a change in an engineering project 106 within a first discipline 108A by monitoring a project database 118. This step involves continuously observing the project database 118 for any modifications or updates in the project data related to the first discipline 108A.

[0210] At step 304, the automation module 112 is configured to cause the processing unit 202 to generate a first prompt for an artificial intelligence (Al) model to reconstruct project data in a second discipline 108B, thereby creating a new version which is aligned with the detected change. This step ensures that the Artificial intelligence model 116 receives structured instructions to interpret the detected change and update the corresponding project data in the second discipline 108B accordingly.

[0211] At step 306, the automation module 112 is configured to cause the processing unit 202 to generate a second prompt for the Artificial intelligence model 116 toSiemens Aktiengesellschaft

[0212] 39

[0213] summarize a plurality of proposed adjustments for the project data in the second discipline 108B. The second prompt is generated based on differences between an old version and the new version of the project data. This step involves identifying the necessary adjustments required to align the project data in the second discipline 108B with the detected change.

[0214] At step 308, the automation module 112 is configured to cause the processing unit 202 to receive the summary of the plurality of proposed adjustments from the Artificial intelligence model 116. The summary is generated by using the generated first prompt and the second prompt on the Artificial intelligence model 116. This step involves compiling the Artificial intelligence model 116's analysis and proposed modifications into a coherent summary for review.

[0215] At step 310, the automation module 112 is configured to cause the processing unit 202 to display the summary of the plurality of proposed adjustments by a user interface to a user, thereby proposing project modifications to align the project data in the second discipline 108B with the detected change in the first discipline 108A. This step ensures that the user can review and understand the proposed changes, facilitating informed decision-making and effective project management.

[0216] The present invention can take a form of a computer program product comprising program modules accessible from computer-usable or computer-readable medium storing pro-gram code for use by or in connection with one or more computers, processors, or instruction execution system. For the purpose of this description, a computer-usable or computer-readable medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation mediums in and of themselves as signal carriers are not included in the definition of physical computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, random access memory (RAM), a read only memory (ROM), a rigid magnetic disk and optical disk such as compact disk read-only memory (CD-ROM), compact disk read / write, and DVD. Both processors and program code for implementing each aspect of the technology can be centralized or distributed (or a combination thereof) as known to those skilled in the art.

[0217] While the present invention has been described in detail with reference to certain embodiments, it should be appreciated that the present invention is not limited toSiemens Aktiengesellschaft

[0218] 40

[0219] those embodiments. In view of the present disclosure, many modifications and variations would be present themselves, to those skilled in the art without departing from the scope of the various embodiments of the present invention, as described herein. The scope of the present invention is, therefore, indicated by the following claims rather than by the foregoing description. All changes, modifications, and variations coming within the meaning and range of equivalency of the claims are to be considered within their scope. All advantageous embodiments claimed in meth-od claims may also be apply to system / apparatus claims.Siemens Aktiengesellschaft

[0220] 41

[0221] List of reference^

[0222] 100 Industrial Environment

[0223] 102 System for Automatic Change Management

[0224] 104 Network

[0225] 106 Industrial Plant

[0226] 108A First Discipline (e.g., Mechanical Engineering)

[0227] 108B Second Discipline (e.g., Electrical Engineering)

[0228] 108C-N Additional Disciplines (e.g., Automation Engineering, Civil Engineering, etc.)

[0229] 110 Platform (e.g., Cloud Computing Platform)

[0230] 112 Automation Module

[0231] 114 Server

[0232] 116 Artificial Intelligence Model

[0233] 118 Project Database

[0234] 120A-N Client Devices

[0235] 122A-N Interfaces

[0236] 202 Processing Unit (Processor)

[0237] 204 Memory

[0238] 206 Storage Unit

[0239] 208 Communication Interface

[0240] 210 Input-Output Unit

[0241] 212 Network Interface

[0242] 214 Bus

[0243] 216 Integrated Development Environment (IDE)

[0244] 302 Step for Detecting Change

[0245] 304 Step for Generating First Prompt

[0246] 306 Step for Generating Second Prompt

[0247] 308 Step for Receiving Summary of Proposed Adjustments 310 Step for Displaying Summary to User

Claims

1. Siemens Aktiengesellschaft42CLAIMS1. A method for automated change management across multiple engineering disciplines, comprising the steps of:detecting, by at least one processor (202), a change in an engineering project (106) within a first discipline (108A) by monitoring a project database (118);generating, by the at least one processor (202), a first prompt for an artificial intelligence (Al) model to reconstruct project data in a second discipline (108B), thereby creating a new version which is aligned with the detected change;generating, by the at least one processor (202) a second prompt for the Artificial intelligence model (116) to summarize a plurality of proposed adjustments for the project data in the second discipline, wherein the second prompt is generated based on differences between an old version and the new version of the project data;receiving, by the at least one processor (202), the summary of the plurality of proposed adjustments from the Artificial intelligence model (116), wherein the summary is generated by using the generated first prompt and the second prompt on the Artificial intelligence model (116); anddisplaying, by a user interface (120A), the summary of the plurality of proposed adjustments to a user, thereby proposing project modifications to align the project data in the second discipline with the detected change in the first discipline.

2. The method of claim 1, further comprising adjusting the project data within the second discipline (108B) based on the plurality of proposed adjustments to align the project data to the detected change in the engineering project (106).

3. The method of claim 1, generating the first prompt comprises compiling information associated with the detected change into a first prompt template to generate the first prompt.

4. The method of claim 1, generating the second prompt comprises:determining the plurality of differences between the old version of the project data and the new version of the project data in the second discipline (108B), by comparison of the new version with the old version; andcompiling information associated with the plurality of differences into a second prompt template to generate the second prompt.

5. The method of claim 1, wherein the artificial intelligence model (116) is trained on historical project data to reconstruct the project data within the second discipline (108B).Siemens Aktiengesellschaft436. The method of claim 1, wherein the first discipline (108A) is different from the second discipline (108B) and one of the first discipline (108A) and the second discipline (108B) is at least one of mechanical computer-aided design (MCAD), electrical computer-aided design (ECAD), and automation engineering systems.

7. The method of claim 1, further comprising the steps of:receiving user feedback indicating one of an acceptance or a rejection of one or more of the plurality of proposed adjustments!retraining the Artificial intelligence model (116) based on the received user feedback to improve reconstruction of the project data of the engineering project (106).

8. The method of claim 1, further comprising notifying a change management system about the acceptance or rejection of the plurality of proposed adjustments, wherein the notification includes details of the detected change and the corresponding user feedback.

9. The method of claim 1, wherein the summary of the plurality of proposed adjustments generated by the Artificial intelligence model (116) includes contextual information about the detected change.

10. A system (102) for automated change management across multiple engineering disciplines, comprising:a project database (118) configured to store project data for multiple engineering disciplines!a processor (202) configured to:detect a change in an engineering project within a first discipline (108A) by monitoring the project database (118);generate a first prompt for an artificial intelligence (Al) model (116) to reconstruct project data in a second discipline (108B), thereby creating a new version aligned with the detected change!generate a second prompt for the Artificial intelligence model (116) to summarize a plurality of proposed adjustments for the project data in the second discipline (108B), wherein the second prompt is based on differences between an old version and the new version of the project data!receive the summary of the plurality of proposed adjustments from the Artificial intelligence model (116), wherein the summary is generated usingSiemens Aktiengesellschaft44the first prompt and the second prompt on the Artificial intelligence model (116); anda user interface configured to display the summary of the plurality of proposed adjustments to a user, thereby proposing project modifications to align the project data in the second discipline with the detected change in the first discipline.

11. The system of claim 1, wherein the processor (202) is further configured to adjust the project data within the second discipline based on the plurality of proposed adjustments to align the project data with the detected change in the engineering project (106).

12. The system of claim 1, wherein the processor (202) is further configured to compile information associated with the detected change into a first prompt template to generate the first prompt.

13. The system of claim 1, wherein the processor (202) is further configured to:determine the plurality of differences between the old version of the project data and the new version of the project data in the second discipline (108B), by comparison of the new version with the old version; andcompile information associated with the plurality of differences into a second prompt template to generate the second prompt.

Images