Circuit diagram identification using machine learning

Abstract

Disclosed is a method for producing a machine-readable representation of a circuit diagram document, as well as an associated data processing device and a computer program.

Description

[0001] MRR P2023124 - 1 -

[0002] Circuit diagram recognition using machine learning

[0003] TECHNICAL AREA

[0004] The present invention relates generally to the field of planning, installation and setup of electrical systems in automation technology and in particular to a method for generating a machine-readable representation of a circuit diagram document using machine learning.

[0005] BACKGROUND

[0006] Planning, installing, and setting up electrical automation technology is a complex task. This applies to centralized control cabinet architectures as well as to decentralized architectures where control modules are mounted directly on the equipment.

[0007] In modern industrial automation, electrical circuit diagrams are increasingly created using digital tools. While these tools enable efficient graphical representation of electrical components and their connections, they often offer only limited possibilities for semantic verification and automated processing of the diagrams. The circuit diagrams are essentially "drawn," with the electrician defining the components and connections according to their own discretion. Automated verification of logical consistency and compliance with standards and safety guidelines is generally not performed.

[0008] This can lead to various problems. Faulty or inconsistent circuit diagrams, for example, can cause malfunctions, production downtime, or even safety risks. Manually checking the diagrams is time-consuming and prone to errors, especially in complex systems with numerous components and interconnections.

[0009] It is therefore an objective of the present invention to improve the semantic analysis of electrical circuit diagrams in order to at least partially overcome the aforementioned limitations. MRR P2023124 - 2 -

[0010] SUMMARY OF THE INVENTION

[0011] This is achieved by the subject matter defined in the independent claims. Advantageous further developments of embodiments of the present disclosure are defined in the dependent claims, as well as in the description and the figures.

[0012] According to one aspect of the invention, a method for generating a machine-readable representation of a circuit diagram document is provided. The circuit diagram document can represent an electrical system, in particular a distributed electrical system. The method can be computer-implemented.

[0013] The electrical system can be designed as at least one of the following: an automation system, a production system, a logistics system, a production line, a machining center, an industrial robot, a manufacturing plant, a unit, an electrical device, or combinations thereof.

[0014] A "decentralized system" can be designed as a modular system or as a mobile or movable system, in which individual components are installed modularly at different locations. This installation is carried out, at least partially, manually by a user such as a worker. Unlike a centralized system, where electrical equipment is connected via a point-to-point connection (i.e., the start point, connection, and endpoint are clearly defined), electrical equipment in a decentralized system is typically connected via a module-switch-module-hub-point connection. This means that in decentralized systems, multiple connection modules are typically arranged between the start point and the endpoint of an electrical device to establish the connection via the local distribution system. Due to this increased complexity, the planning, design, and...Maintaining decentralized systems is significantly more demanding than maintaining centralized systems.

[0015] The process may include receiving the circuit diagram document. The circuit diagram document may contain graphical circuit diagram information.

[0016] The process can include generating the machine-readable representation. This can be done, at least partially, using machine learning based on the graphical circuit diagram information.

[0017] The machine-readable representation can include a graph that can be displayed on a graphical user interface. The graph can show at least one electrical device, MRR P2023124 - 3 - which is shown in the schematic document, and at least one electrical connection which is shown in the schematic document.

[0018] The resulting machine-readable representation provides a semantic understanding of a circuit diagram, enabling a software-supported method for the efficient planning, design, and operation of an electrical system. This is particularly relevant for decentralized systems, as their complexity is significantly higher compared to centralized systems, making their planning, design, and operation considerably more demanding.

[0019] However, the method according to the present disclosure can also be applied to centralized systems, since, in principle, methods for decentralized systems are also applicable to centralized systems, whereas methods for centralized systems are typically not directly applicable to methods for decentralized systems. The reason for this, as described above, is the greater complexity of decentralized systems. One application example is the redesign or conversion of a centralized system into a decentralized system. In this case, the method would first be applied to the circuit diagram of the centralized system to generate a machine-readable representation of the associated circuit diagram document. Using this machine-readable representation, the redesign of the centralized system into a decentralized system can then be carried out.

[0020] Although this document primarily describes circuit diagram documents, it should be emphasized that the methodologies disclosed here can also be applied to other types of installation documents. In general, virtually any technical drawing can be processed, such as architectural plans, process diagrams, fluid circuit diagrams, pneumatic circuit diagrams, or the like.

[0021] Graphical circuit diagram information can be understood as any graphical representation of objects within the circuit diagram document, such as circuit diagrams of electrical equipment as well as associated connections, terminals, links and the like.

[0022] It may be provided that generating the machine-readable representation includes the recognition of at least one electrical device. It may also be provided that the recognition of at least one electrical device includes the recognition of at least one graphical object in the circuit diagram document using an object recognition model. This allows the computer to perform a more accurate and precise identification of electrical devices such as cables, sockets, or components. This can lead to improved accuracy in the analysis and interpretation of circuit diagrams. Another advantage is the ability to automatically extract and store relevant information about electrical devices. This includes, for example, the identification of cable types, socket types, or component properties.Furthermore, this technique can also help minimize errors in the planning and installation of electrical systems. A more precise analysis of circuit diagrams allows electricians to better identify which components and cables are needed to ensure the system is installed correctly.

[0023] It may be provided that the recognition of at least one electrical device includes the recognition of at least one text string in the circuit diagram document using a text recognition model. It may also be provided that the recognition of at least one electrical device includes determining, at least partially based on the recognized text string, that the at least one graphic object is an electrical device. This allows the computer to perform even more accurate and precise identification of electrical devices, such as designations for cables, sockets, or components, which can lead to improved accuracy in the analysis and interpretation of circuit diagrams. Another advantage is the ability to automatically extract and store specific, relevant information about electrical devices. This includes, for example...This includes identifying cable types, socket types, or component properties, as well as analyzing designations such as "12V" for a battery or "AC 230V" for a power supply unit. Furthermore, this technique can also help to further minimize errors in the planning and installation of electrical systems.

[0024] It may be intended that the generation of the machine-readable representation includes the recognition of at least one electrical terminal using a terminal recognition model. This allows the computer to perform a more accurate and precise identification of electrical terminals, such as switch terminals, connection terminals, or safety terminals. This can lead to further improved accuracy in the analysis and interpretation of circuit diagrams. Another advantage is the ability to automatically extract and store relevant information about electrical terminals. This includes, for example, the identification of the terminal type, the number of terminal leads, or the terminal's position relative to other components. Furthermore, this technique can also help to further minimize errors in the design and installation of electrical systems.A more detailed analysis of wiring diagrams allows electricians to better identify which terminals are needed to ensure correct installation. For example, a plug of a specific type (e.g., 3-pin) can be connected correctly if a terminal is identified as a "plug terminal." This enables the electrician to make the correct connections and avoid errors.

[0025] It may be provided that generating the machine-readable representation further includes determining, at least partially based on the identified terminal and electrical device, at least one connection of the electrical device. This offers several advantages: By combining identified terminals and devices, an electrician can ensure that all connections are made correctly. This combination reduces the probability of connection errors. Correctly acquiring connections can increase the safety of the electrical system by preventing faults such as short circuits or overloads. Automatic connection identification can accelerate the planning and execution process.

[0026] It may be possible to include the generation of the machine-readable representation as well as the detection of at least one electrical connection using a connection detection model. This can increase the accuracy of connection creation, since, for example, an electrician can ensure that all connections are correctly made by recognizing at least one electrical connection in the circuit diagram.

[0027] It may be intended that generating the machine-readable representation further includes mapping the at least one electrical connection to the at least one piece of electrical equipment. Mapping connections can increase the accuracy of the electrical system, as all connections are correctly placed in the right locations, and errors in connection creation can be reduced. This allows for the rapid identification of problems in the system, which reduces repair time. Furthermore, mapping connections can lead to automated monitoring of the electrical system, which increases safety and can prevent faults such as short circuits or overloads. Finally, this can also lead to a simplification of complex systems, as all connections can be correctly established.

[0028] It may be provided that the detection of at least one electrical device further includes a comparison of the at least one graphical object with one or more reference objects. The reference object can correspond to an electrical device whose form, structure, and / or function substantially correspond to those of the graphical object within the circuit diagram document. Comparing the at least one graphical object with one or more reference objects offers technical advantages, such as more accurate identification and localization of electrical devices. This comparison can increase the accuracy of the detection, as the system is able to match the graphical object with the correct reference object. This leads to improved reliability and precision in the identification of electrical devices.Furthermore, matching can also help to exclude incorrect or related objects, which increases the security of the system.

[0029] It may be provided that, if the generated machine-readable representation incorrectly depicts and / or omits at least one electrical device within the schematic document, the procedure further includes receiving a corrective user input to accurately represent the incorrectly depicted electrical device and / or receiving a reference object to represent the omitted electrical device. This can further increase the accuracy of the generated machine-readable representation, as the system responds to corrections and corrects incorrect representations of electrical devices. This leads to improved reliability and precision of the system. Furthermore, the procedure can also help to eliminate erroneous or incomplete information, thus increasing the safety and quality of the representation.Furthermore, by receiving a reference object to represent the unrepresented electrical equipment, the system can also learn and improve in order to better respond to the specific needs of the application in similar situations in the future.

[0030] It may be provided that the object recognition model, the text recognition model, the terminal recognition model, and / or the connection recognition model can be trained separately. Separate, individual training allows each model to address specific requirements and challenges, leading to improved MRR (Mean Rate of Success).

[0031] This leads to improved performance in each area. It also prevents errors in one model from being propagated to other models. Furthermore, separate training allows each model to be better tailored to the specific requirements of its task. This results in greater accuracy and reliability of the system, as each component has been trained for its own unique challenges. Additionally, separating the models can improve the modeling of complex systems such as circuit diagrams or terminal connection scenarios. Each model can be specifically trained for its own level of complexity, leading to greater scalability and adaptability of the system.

[0032] According to another aspect, a data structure is provided which includes a machine-readable representation of a circuit diagram document generated by any of the methods disclosed herein.

[0033] According to another aspect, a data processing device is provided, comprising means for carrying out any of the methods disclosed herein.

[0034] According to another aspect, a computer program and / or a computer-readable medium on which a computer program is stored is provided. The computer program comprises instructions which, when executed by a data processing device, cause the device to execute any of the methods disclosed herein.

[0035] BRIEF DESCRIPTION OF THE FIGURES

[0036] The invention can be better understood with the help of the following figures:

[0037] Fig. 1: A flowchart of a process for generating a machine-readable

[0038] Representation of a circuit diagram document according to an exemplary embodiment of the present invention.

[0039] Fig. 2: A data processing device according to an exemplary

[0040] embodiment of the present invention.

[0041] Fig. 3: A circuit diagram document according to an exemplary embodiment of the present invention.

[0042] Fig. 4: A machine-readable representation of a circuit diagram document according to an exemplary embodiment of the present invention. MRR P2023124 - 8 -

[0043] Fig. 5: A graph displayed on a graphical user interface according to an exemplary embodiment of the present invention.

[0044] Fig. 6: A system architecture for generating and processing machine-readable

[0045] Representations of circuit diagram documents according to an exemplary embodiment of the present invention.

[0046] DETAILED DESCRIPTION

[0047] The following section describes representative embodiments illustrated in the accompanying drawings. It should be understood that the illustrated embodiments and the following descriptions are examples and are not intended to limit the embodiments to a preferred embodiment.

[0048] Fig. 1 shows a flowchart of a method 100 for generating a machine-readable representation of a circuit diagram document 102a according to an exemplary embodiment. The circuit diagram document 102a represents a distributed electrical system. The circuit diagram document 102a includes graphical circuit diagram information 102b.

[0049] After receiving the schematic document, a machine-readable representation is generated, at least partially, based on the graphical schematic information 102b, for example, using machine learning. The schematic document 102a can, for example, be in the form of a PDF file. An image can be generated for each page of the PDF, each serving as the basis for generating the machine-readable representation. For example, the respective images can serve as input for a machine learning model. The model is configured to process the images, which can include object recognition and classification. Configuring the model can involve training it using appropriately labeled images. The model can either be trained from scratch (i.e., an untrained model is used) or a pre-trained model can be used.In the case of a pre-trained model, it can be further trained using labeled images of circuit diagrams ("fine-tuning").

[0050] During model training, the model is specifically sensitized to recognizing the edges of the electrical devices depicted in the circuit diagram and their associated electrical connections. This is possible because these typically have high-contrast edges or lines, which the model(s) use to identify an object (e.g., a device, a connection, etc.).

[0051] The machine-readable representation may include a graph that can be displayed on a graphical user interface and that shows at least one electrical device and at least one electrical connection shown in the circuit diagram document 102a.

[0052] Generating the machine-readable representation can include recognizing an electrical device (104c). Recognizing an electrical device (104c) can also include recognizing a graphical object (104a) and / or recognizing a text element in the schematic document (102a). An object recognition model or a text recognition model can be used for this purpose. For example, a Convolutional Neural Network (CNN) can be used as the object recognition model. This could be implemented based on the EffNet architecture, the U-Net architecture, or YOLO ("You Only Look Once") models. For example, an ABINet architecture can be used as the text recognition model. The output of the model(s) can be a list containing suggestions for recognized electrical devices.

[0053] In an embodiment where both a graphic object and a text string are recognized in the circuit diagram document 102a, it can be determined, at least partially, based on the recognized text string, that the graphic object is an electrical device. Furthermore, the type of electrical device can be determined, i.e., which electrical device it is. A corresponding device identifier (DIN) can be used for this purpose. This facilitates the recognition of relevant text strings, i.e., text strings to which corresponding electrical devices can be assigned. This can be particularly helpful if other, irrelevant text strings, i.e., text strings to which no electrical devices can be assigned, are present in the circuit diagram document. The DIN can use unambiguous indicators (e.g., special symbols such as "+" or "-" or number).This includes the IDs of the corresponding resources. Based on these indicators, the recognition of relevant text elements can be improved, and irrelevant text elements can be ignored or omitted.

[0054] The recognition of at least one electrical device (104c) can further include comparing the at least one graphical object with one or more reference objects. The reference object can correspond to an electrical device (MRR P2023124 - 10) whose form, structure, and / or function essentially correspond to those of the graphical object within the schematic document (102a). This comparison (also referred to as "template matching") can be useful for improving recognition efficiency. Electrical devices, which almost always have the same structure, frequently appear in schematic documents. For example, an optical sensor or an ultrasonic sensor almost always has the same standard circuit diagram. This can be stored as a reference object (e.g., in a database 604).When a graphical object is detected, it can first be compared with the existing reference objects to identify the corresponding electrical device. Only if such a comparison is unsuccessful is a classification result from the model used. However, if the comparison is successful, the result is not only highly likely to be correct, but it also eliminates the need to run the model. This allows for efficient use of computing resources, as retrieving the reference objects and comparing them is less computationally intensive than running the model.

[0055] Method 100 can further include the detection 106 of at least one electrical terminal. This can be done using a terminal detection model. This can, for example, be based on the YOLO approach.

[0056] In an embodiment in which an electrical device and an associated electrical terminal have been detected, at least one connection of the electrical device can be determined at least partially based on the detected at least one terminal and the detected at least one electrical device 108.

[0057] Method 100 can further include the detection 110 of an electrical connection. This can be done using a connection detection model. This model can, for example, be based on the YOLO approach. The model can also be configured to combine electrical connections across multiple pages. That is, it can detect a connection between two electrical devices located on different pages / images.

[0058] In an embodiment in which an electrical connection 110 has been detected, the method 110 may include assigning 112 the electrical connection to the electrical equipment.

[0059] Procedure 100 may also include any of the aspects mentioned above. MRR P2023124 - 11 -

[0060] Fig. 2 shows a data processing device 200 according to an exemplary embodiment of the invention. The data processing device can include means for carrying out the method according to the present disclosure (e.g., the method 100). The means can be a processor 202 and a memory 204. The processor 202 and the memory 204 can be operatively connected. A computer program 206 can be stored in the memory 204, wherein the computer program 206 comprises instructions which, when the computer program 206 is executed by a computer, cause the computer to execute the method according to any of the aspects mentioned (e.g., the method 100).

[0061] Fig. 3 shows a circuit diagram document 300 according to an exemplary embodiment of the invention. The circuit diagram document 300 comprises graphical circuit diagram information representing a plurality of electrical devices 302 and a plurality of electrical connections 304. Such a circuit diagram document 300 can serve as input for the method for generating a machine-readable representation of the circuit diagram document 300 according to aspects of the present disclosure, for example, for the method 100 in Fig. 1.

[0062] Fig. 4 shows a machine-readable representation 400 of a circuit diagram document according to an exemplary embodiment of the invention. The machine-readable representation 400 can be generated, for example, using the method according to aspects of the present disclosure, for example, using method 100 in Fig. 1. In the machine-readable representation 400, detected electrical devices 404 are delimited from other detected electrical devices 406 by means of bounding boxes. Associated detected electrical connections 402 are shown as lines.

[0063] Fig. 5 shows a graph 500 displayed on a graphical user interface according to an exemplary embodiment of the invention. The graph 500 shows a structured representation of a circuit diagram document 300 of a control cabinet. The graph 500 comprises a plurality of electrical devices 502, 506-510, associated electrical connections 512, and corresponding terminals 514. A device 508 can comprise one or more further electrical devices 516 (e.g., sensors such as ultrasonic or optical sensors or corresponding actuators).

[0064] Fig. 6 shows a system architecture of a system 600 for generating and processing machine-readable representations 400 of circuit diagram documents 300 according to an exemplary embodiment of the invention. This supports a user in the technical planning, design, and maintenance of an electrical system.

[0065] System 600 comprises an import module 602, a database 604, a presentation module 606, and an optimization module 608. One or more of these modules of System 600 can be implemented in hardware (e.g., by the data processing device 200) and / or software (e.g., by the computer program 206).

[0066] The import module 602 is configured to process an input comprising a circuit diagram document 300 (e.g., as a PDF) and to generate a machine-readable representation 400 from it. For this purpose, the import module 602 can be configured to perform the method according to the present disclosure (e.g., method 100 in Fig. 1). The circuit diagram document 300 and / or the associated machine-readable representation 400 is then stored in the database 604. The input can further include information on electrical equipment (e.g., device data) and / or Automation Markup Language (AML) information about the electrical system. The input can also include user input (e.g., a correction user input and / or a reference object).

[0067] The display module 606 is configured to read and display data (e.g., machine-readable representations 400 of circuit diagram documents 300) from the database 604 (e.g., on an electronic display device). This can be done, for example, using a graph 500 (see Fig. 5), thus providing a user (e.g., a plant engineer) with a better overview of the electrical system. This is important because electrical systems, especially distributed electrical systems, are highly complex, often resulting in inefficiencies in system design. The provided overview helps a user identify and correct inefficiencies or errors in a real-world system. An error might, for example, be a cause that renders the system unusable until the cause is resolved.

[0068] The provided overview also helps the user to efficiently plan an electrical system that is currently in the planning phase. In both cases, the visualization supports the user in the technical planning, construction, and maintenance of an electrical system (e.g., when converting a centralized system to a decentralized system). MRR P2023124 - 13 -

[0069] The optimization module 608 is configured to read data (e.g., machine-readable representations 400 of circuit diagram documents 300) from the database 604 and optimize it. For example, the optimization module 608 can optimize the topology of a machine-readable representation of a circuit diagram document 300 of an electrical system. This allows for more efficient system design. For instance, a user can first display the machine-readable representation 400 using the display module 608. If the user identifies an inefficiency, they can provide information about the inefficiency as additional input for the optimization module 608, which will then begin the optimization process. Alternatively, the user can also start the optimization without providing this additional information.This can be helpful if the user cannot detect any inefficiencies upon first viewing the machine-readable representation 400 of the circuit diagram document 300. Thus, they can use the optimization as a technical verification of the electrical system (i.e., as a plausibility check). If the optimization does not result in any further changes to the circuit diagram 300, the user can assume that the system is technically functional and efficient. If the optimization results in a change to the circuit diagram 300, the user can assume that the current state of the system is not optimally planned or designed, at least with regard to efficiency.

[0070] Once the optimization is complete, the user can have the now optimized machine-readable representation 400 displayed again using the display module 608. This process can be repeated iteratively until the user can no longer identify any inefficiencies and / or the optimization module 608 can no longer optimize the machine-readable representation 400 (i.e., the optimization converges).

[0071] This iteration cycle also enables the redesign of centralized systems into decentralized systems. For this purpose, a circuit diagram document 300 of a centralized system is converted into a machine-readable representation 400, and this is then iteratively optimized so that a functional and efficiently operating decentralized system can be created from it.

[0072] The term “and / or” used here includes all combinations of one or more of the listed aspects and can be abbreviated with “ / ”.

[0073] Although some aspects related to a device have been described, it is clear that these aspects also constitute a description of the corresponding process, MRR P2023124-14, where a block or device corresponds to a process step or a feature of a process step. Similarly, aspects described in connection with a process step also constitute a description of a corresponding block, element, or feature of a corresponding device.

[0074] Embodiments of the present disclosure can be implemented on a computer system. The computer system may be a local computing device (e.g., a personal computer, laptop, tablet computer, or mobile phone) with one or more processors and one or more memory devices, or a distributed computing system (e.g., a cloud computing system with one or more processors and one or more memory devices distributed across different locations, such as a local client and / or one or more remote server farms and / or data centers). The computer system may comprise any circuit or combination of circuits. In one embodiment, the computer system may comprise one or more processors, which may be of any type. The term "processor" as used herein can refer to any type of computing circuit, e.g.,a microprocessor, a microcontroller, a CISC (Complex Instruction Set Computing) microprocessor, a RISC (Reduced Instruction Set Computing) microprocessor, a VLIW (Very Long Instruction Word) microprocessor, a graphics processor, a digital signal processor (DSP), a multi-core processor, an FPGA (Field Programmable Gate Array), or any other type of processor or processing circuit. Other types of circuitry that may be included in the computer system could be a custom-designed circuit, an application-specific integrated circuit (ASIC), or similar, such as one or more circuits (e.g., a communications circuit) for use in wireless devices like mobile phones, tablet computers, laptop computers, two-way radios, and similar electronic systems.The computer system may include one or more storage devices, which may comprise one or more storage elements suitable for the application, such as main memory in the form of random-access memory (RAM), one or more hard disks, and / or one or more drives that handle removable media such as compact discs (CDs), flash memory cards, digital video discs (DVDs), and the like. The computer system may also include a display device, one or more speakers, and a keyboard and / or a control device, which may include a mouse, trackball, touchscreen, speech recognition device, or any other device that enables a system user to... MRR P2023124 - 15 -.

[0075] To enter information into the computer system and to receive information from it.

[0076] Some or all of the process steps can be performed by (or using) a hardware device, such as a processor, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, some or more of the key process steps can be performed by such a device.

[0077] Depending on specific implementation requirements, embodiments of the present disclosure can be implemented in hardware or in software. The implementation can be carried out using a non-transferable storage medium such as a digital storage medium, for example, a floppy disk, DVD, Blu-ray disc, CD, ROM, PROM, EPROM, EEPROM, or FLASH memory, on which electronically readable control signals are stored that interact (or can interact) with a programmable computer system to execute the respective method. Therefore, the digital storage medium can be computer-readable.

[0078] Some embodiments according to the present disclosure include a data carrier with electronically readable control signals that can interact with a programmable computer system to perform one of the methods described herein. In general, embodiments of the present disclosure can be implemented as a computer program product with program code, wherein the program code serves to execute one of the methods when the computer program product is running on a computer. The program code can, for example, be stored on a machine-readable medium.

[0079] Other embodiments include the computer program for carrying out one of the methods described herein, which is stored on a machine-readable medium.

[0080] In other words, an embodiment of the present disclosure is therefore a computer program with program code for carrying out one of the methods described herein when the computer program runs on a computer.

[0081] Another embodiment of the present disclosure is therefore a storage medium (or a data carrier or a computer-readable medium) on which the computer program for carrying out one of the methods described herein is stored when executed by a processor. The data carrier, digital storage medium, or recorded medium is typically tangible and / or non-transferable. Another embodiment of the present disclosure is a device as described herein, comprising a processor and the storage medium.

[0082] Another embodiment of the present disclosure is therefore a data stream or a sequence of signals that represents the computer program for carrying out one of the methods described herein. The data stream or sequence of signals can, for example, be configured to be transmitted via a data communication link, e.g., via the Internet.

[0083] Another embodiment comprises a processing means, e.g. a computer or a programmable logic device, configured or adapted to perform one of the methods described herein.

[0084] Another embodiment comprises a computer on which the computer program for carrying out one of the methods described herein is installed.

[0085] Another embodiment according to the present disclosure comprises a device or system configured to transmit a computer program for carrying out one of the methods described herein to a receiver (e.g., electronically or optically). The receiver may be, for example, a computer, a mobile device, a storage device, or the like. The device or system may, for example, include a file server for transmitting the computer program to the receiver.

[0086] In some embodiments, a programmable logic device (e.g., a field-programmable gate array) can be used to perform some or all of the functions of the methods described herein. In some embodiments, a field-programmable gate array can cooperate with a microprocessor to perform one of the methods described herein. In general, the methods are preferably performed by any hardware device.

Claims

MRR P2023124 - 17 - REQUIREMENTS 1. A method (100) for generating a machine-readable representation of a circuit diagram document (102a), wherein the circuit diagram document (102a) represents a decentralized electrical system, wherein the method comprises at least the following steps: Receiving the circuit diagram document (102a), wherein the circuit diagram document (102a) includes graphical circuit diagram information (102b); and Generating the machine-readable representation at least partially based on the graphical circuit diagram information (102b) using machine learning; wherein the machine-readable representation comprises a graph that can be displayed on a graphical user interface and that shows at least one electrical device and at least one electrical connection represented in the circuit diagram document (102a).

2. The method according to claim 1, wherein generating the machine-readable representation comprises: recognizing (104c) the at least one electrical device.

3. The method according to claim 2, wherein the detection (104c) of the at least one electrical device comprises: detection (104a) of at least one graphic object in the circuit diagram document (102a) by means of an object recognition model.

4. The method according to claim 2 or 3, wherein the recognition (104c) of the at least one electrical device comprises: recognition (104b) of at least one text string in the circuit diagram document by means of a text recognition model.

5. The method according to claims 3 and 4, wherein the detection (104c) of the at least one electrical device further comprises: determining, at least partially based on the detected at least one text string, that the at least one graphic object is an electrical device. MRR P2023124 - 18 - 6. The method according to any one of the preceding claims 1-5, wherein generating the machine-readable representation comprises: recognizing (106) at least one electrical terminal using a terminal recognition model.

7. The method according to any of the preceding claims 2-5 combined with claim 6, wherein generating the machine-readable representation further comprises: determining (108), at least partially based on the detected at least one terminal and the detected at least one electrical device, at least one connection of the electrical device.

8. The method according to any one of the preceding claims 1-7, wherein generating the machine-readable representation further comprises: detecting (110) the at least one electrical connection by means of a connection detection model.

9. The method according to any of the preceding claims 1-7 combined with claim 8, wherein generating the machine-readable representation further comprises: assigning (112) the at least one electrical connection to the at least one electrical device.

10. The method according to any one of the preceding claims 3-9, wherein the detection (104c) of the at least one electrical device further comprises: matching the at least one graphic object with one or more reference objects, wherein a reference object corresponds to an electrical device whose shape, structure and / or function substantially corresponds to those of the graphic object within the circuit diagram document (102a).

11. The method according to any one of the preceding claims 1-10, wherein the generated machine-readable representation incorrectly and / or not represents at least one electrical device within the circuit diagram document (102a), and wherein the method further comprises: Receiving a corrective user input to properly display the incorrectly displayed electrical equipment; and / or Receiving a reference object to represent the electrical equipment not shown. MRR P2023124 - 19 - 12. The method according to any one of the preceding claims 3-11, wherein the object recognition model, the text recognition model, the terminal recognition model and / or the connection recognition model can be trained separately.

13. A data structure comprising a machine-readable representation of a circuit diagram Document (102a) comprises which was produced by the method according to any of the preceding claims 1-12.

14. A data processing device comprising means for carrying out the method according to any one of the preceding claims 1-12.

15. A computer program or a computer-readable medium on which a a computer program is stored, wherein the computer program comprises instructions which, when the computer program is executed by a data processing device, cause the latter to execute the method according to any of the preceding claims 1-12.

Images