Design support system for electrical equipment storage panels

The design support system addresses the issue of human error and long design times by employing machine learning to prioritize specification items and generate efficient design proposals, enhancing the design process for electrical equipment storage panels.

JP2026035962APending Publication Date: 2026-03-05MITSUBISHI ELECTRIC CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024138439
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2026-03-05

AI Technical Summary

Technical Problem

Conventional design support systems for electrical equipment storage panels lack specification of priority for required items, leading to increased human error and prolonged design times due to complex processes and numerous setting items.

Method used

A design support system utilizing machine learning models to prioritize specification items and compare past design data with user inputs, generating edited design proposals that satisfy required specifications, thereby reducing human error and design time.

Benefits of technology

The system effectively suppresses human error and significantly reduces design time by using machine learning to generate highly similar design proposals based on past data, minimizing the need for rework.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026035962000001_ABST
    Figure 2026035962000001_ABST
Patent Text Reader

Abstract

To provide a design support system for electrical equipment storage panels that suppresses the occurrence of human error and significantly reduces design time. [Solution] In a design section (60) of the design support system for electrical equipment storage panels, required specification items and the priority of the required specification items in the specifications for the electrical equipment storage panel are input as required specification data, past design data for the electrical equipment storage panel stored in a database is compared with the input required specification data, and an edited design proposal for the electrical equipment storage panel that satisfies the required specification data is output as output data using a first machine learning model learned from the past design data for the electrical equipment storage panel.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present disclosure relates to a design support system for an electrical equipment storage panel. [Background technology]

[0002] A conventional design support system that supports the design of a new electrical equipment storage panel by reusing existing design data includes a database that stores the design data for the existing electrical equipment storage panel, source data selection means that is accessible to the database and selects source data, which is the design data for the electrical equipment storage panel to be reused, in response to a user's input, source data loading means that loads, from the selected source data, at least unit identification information that identifies the units that make up the electrical equipment storage panel, unit layout information regarding the layout of each of the units, and equipment information regarding the internal equipment that makes up each unit, source data modification means that allows the user to change at least any of the unit identification information, the unit layout information, and the equipment information in the source data in response to a user's input, and design data creation means that creates design data for the new electrical equipment storage panel based on the information modified by the source data modification means (see Patent Document 1 listed below). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-146640 Summary of the Invention [Problem to be solved by the invention]

[0004] In the design support system described in the patent document, there is no specification of the priority of the required specification items that are input to search for the source data. Therefore, if there are multiple required specification items, the first item specified has a higher priority (the priority cannot be changed), and there is a problem in that it is not possible to search for drawings that are close to the required specifications. Furthermore, since there are many setting items and work items and the work process is complicated, there are problems in that the frequency of human error increases and the design process takes a long time.

[0005] The present disclosure discloses technology for solving the above-mentioned problems, and aims to provide a design support system for electrical equipment storage panels that reduces the occurrence of human error and significantly reduces design time. [Means for solving the problem]

[0006] The design support system for an electrical equipment storage panel disclosed herein comprises: In the design section of the electrical equipment storage panel design support system, inputting required specification items and priorities of the required specification items in the specification of the electrical equipment storage panel as required specification data; The system compares the past design data of the electrical equipment storage panel stored in a database with the input required specification data, and outputs an edited design proposal for the electrical equipment storage panel that satisfies the required specification data as output data using a first machine learning model learned from the past design data of the electrical equipment storage panel. [Effects of the Invention]

[0007] According to the electrical equipment storage panel design support system of the present disclosure, it is possible to suppress the occurrence of human error and significantly reduce the design time. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a schematic configuration of an electrical equipment storage panel design support system according to a first embodiment. [Figure 2]FIG. 2 is a diagram showing a basic flow of the design support system for an electrical equipment storage panel according to the first embodiment. [Figure 3] FIG. 2 is a diagram showing a basic design flow of each design phase of the electrical equipment storage panel design support system according to the first embodiment. [Figure 4] FIG. 3 is a diagram showing an example of a specification sheet for the electrical equipment storage panel according to the first embodiment. [Figure 5] FIG. 3 is a diagram showing an example of a specification sheet for the electrical equipment storage panel according to the first embodiment. [Figure 6] FIG. 3 is a diagram showing an example of image data of a single line diagram according to the first embodiment. [Figure 7] 1 is a block diagram showing a circuit configuration of a single line diagram design unit according to the first embodiment. FIG. [Figure 8] FIG. 3 is a diagram showing a design flow of a single line diagram design unit according to the first embodiment. [Figure 9] FIG. 2 is a diagram showing an example of image data of an array diagram according to the first embodiment. [Figure 10] 2 is a block diagram showing a circuit configuration of an array diagram design unit according to the first embodiment; FIG. [Figure 11] FIG. 10 is a diagram showing a design flow of an array diagram design unit according to the first embodiment. [Figure 12] 2 is a block diagram showing a circuit configuration of a structural design unit according to the first embodiment. FIG. [Figure 13] FIG. 3 is a diagram showing a design flow of a structural design unit according to the first embodiment. [Figure 14] FIG. 10 is a diagram showing a basic flow of each design phase according to the second embodiment. [Figure 15] FIG. 11 is a diagram showing a basic flow of each design phase according to the third embodiment. [Figure 16] FIG. 10 is a diagram showing a basic flow of the design support system for an electrical equipment storage panel according to the fourth embodiment. [Figure 17] FIG. 13 is a diagram showing a basic flow of each design phase according to the fourth embodiment. [Figure 18] FIG. 13 is a diagram showing a basic flow of each design phase according to the fifth embodiment. [Figure 19]FIG. 2 is a block diagram showing an example of hardware of each design unit according to the embodiment. [Figure 20] FIG. 3 is a diagram showing an example of system circuit analysis model data according to the first embodiment. [Figure 21] FIG. 3 is a diagram showing an example of simulated electric room model data according to the first embodiment. [Figure 22] FIG. 2 is a diagram showing an example of a structural design drawing of the electrical equipment storage panel according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] (Basic concept of the electrical equipment storage panel design support system disclosed herein) The design of electrical equipment storage panels, such as distribution panels (hereafter referred to as switchgear), is typically modified from the standard specifications or standard layout of the switchgear to suit the user's operating environment. However, the operating environment that must be considered when creating the modified design requires taking into account various factors, such as the size of the electrical room, the capacity of the load equipment, the breaking capacity, thermal strength, mechanical strength, and compliance with standards, which can result in long design times. Furthermore, because the designer must consider a large number of factors, there is a high incidence of human error, leading to frequent rework of the completed design proposal. This disclosure proposes a design support system for electrical equipment storage panels that uses machine learning models to reduce the time required for editing and design and as a means of preventing human error.

[0010] The machine learning model used in this disclosure searches for projects similar to the required specifications in the source database and proposes edited design proposals. To propose highly similar edited design proposals, the model has a function for inputting the required specification items and their priorities, and then comparing them with the source database. Furthermore, this function can be operated by the user or by a machine learning model (e.g., machine learning models such as Stable Diffusion, Canva, and Bing Image Creator, hereinafter referred to as image-generating AI (Artificial Intelligence)). In this way, the machine learning model evaluates similarity and proposes design proposals that are close to the required specification items in a balanced and comprehensive manner, thereby shortening design time. In addition, single-line diagram design, arrangement diagram design, and structural design can be generated from specifications in one step, minimizing the items that users need to set, and shortening estimation and design time. Furthermore, not only can past data be compared, but even in designs outside of data, shortcomings can be supplemented using machine learning models (for example, machine learning models such as ChatGPT, LLM, Gemini, etc., hereafter abbreviated as character generation AI), which reduces the number of work items and enables product design in a short delivery time.

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of the electrical equipment storage panel design support system of the present disclosure will be described in detail with reference to the accompanying drawings.

[0012] Embodiment 1 (1) Basic configuration of the electrical equipment storage panel design support system FIG. 1 is a block diagram showing a schematic configuration of an electrical equipment storage panel design support system according to the first embodiment. As shown in FIG. 1, the design support system 100 for an electrical equipment storage panel according to the first embodiment includes a specification creation unit 10 and a design unit 60, and the design unit 60 includes a single line diagram design unit 20, an arrangement diagram design unit 30, and a structural design unit 40. The specification creation unit 10 plays a role in creating a specification for the electrical equipment storage panel. The single line diagram design unit 20 plays a role in designing a single line diagram for an electrical equipment storage panel. The layout diagram design unit 30 plays a role in designing the layout diagram of the electrical equipment storage panel. The structural design section 40 plays a role in designing the structural design drawing of the electrical equipment storage panel. The operations of the specification creation unit 10, the single line diagram design unit 20, the arrangement diagram design unit 30 and the structural design unit 40 will be described in detail later.

[0013] (2) Basic flow of the electrical equipment storage panel design support system FIG. 2 is a diagram showing a basic flow of the design support system for an electrical equipment storage panel according to the first embodiment. In FIG. 2, the basic flow of the design support system for an electrical equipment storage panel according to the first embodiment includes step S01, which is a specification creation phase, and step S06, which is a design phase. Step S06, which is the design phase, includes step S02, which is the single line diagram design phase, step S03, which is the array diagram design phase, and step S04, which is the structural design phase. The specification creation phase of step S01 is a phase in which the specification creation unit 10 creates a specification for the electrical equipment storage panel. The single line diagram design phase of step S02 is a phase in which the single line diagram design unit 20 designs a single line diagram of the electrical equipment storage panel. The layout diagram design phase of step S03 is a phase in which the layout diagram design unit 30 designs the layout diagram of the electrical equipment storage panel. The structural design phase of step S04 is a phase in which structural design unit 40 designs a structural design drawing of the electrical equipment storage panel. Details of the specification creation phase S01, the single line diagram design phase S02, the arrangement diagram design phase S03, and the structural design phase S04 will be described later.

[0014] (3) Basic design flow for each design phase FIG. 3 is a diagram showing a basic design flow S100 of each design phase of the electrical equipment storage panel design support system according to the first embodiment. Step S10 in FIG. 3 is an input step for inputting required specification data with the required priorities assigned to the required specification items in each design phase S06 in FIG. 2 (single line diagram design phase S02, arrangement diagram design phase S03, and structural design phase S04). The user reads information from the specifications created in the specification creation phase S01 in FIG. 2 and inputs the required specification items necessary for each design phase with priorities assigned. Steps S11 and S12 are a database matching step S11 and a machine learning model step S12, which select highly similar past design cases from a past design database based on the input data entered in step S10, and propose candidate edited design proposals that satisfy the input required specification data using a first machine learning model (e.g., an image generation type AI). Step S13 is an output step for outputting the edited design plan candidates proposed in steps S11 and S12.

[0015] (4) Summary of basic design flow The single line diagram design unit 20, the array diagram design unit 30, and the structural design unit 40, which are part of the design unit 60, use a first machine learning model (for example, an image generation type AI) to propose edited design proposal candidates for an electrical equipment storage panel that are suitable for the required specification items. In this case, the priority of the required specification items is determined, and the single line diagram design unit 20, the array diagram design unit 30, and the structural design unit 40, which are part of the design unit 60, evaluate the similarity between the required specification items and their priority from a past design database, and use the first machine learning model to fill in any deficiencies. The basic design flow is as follows: (4-1) The user reads information from the specifications created in the specification creation phase S01, prioritizes the required specification items required for each design phase S06, namely, the single line diagram design phase S02, the array diagram design phase S03, and the structural design phase S04, and inputs the information as input data to the single line diagram design unit 20, the array diagram design unit 30, and the structural design unit 40, which are the design units 60. (4-2) The single line diagram design unit 20, the arrangement diagram design unit 30, and the structural design unit 40, which are the design unit 60, select highly similar past design cases from a past design database based on the above input data, and output and propose edited design proposal candidates that satisfy the input required specification items and their priorities using a first machine learning model (e.g., image generation type AI). (4-3) The user selects the most appropriate proposal from the output edited design proposal candidates. As described above, single-line diagram design, layout diagram design, and structural design can be generated from specifications in one stop for each phase, shortening design time and reducing rework. Below, each phase, that is, the specification creation phase S01, the single line diagram design phase S02, the array diagram design phase S03, and the structural design phase S04, will be described in detail.

[0016] (5) Detailed explanation of each phase (5-1) Specification Creation Phase S01 A specification creation unit 10 creates a specification for the electrical equipment storage panel that the user intends to design. Examples of specifications for electrical equipment storage panels are shown in Figs. 4 and 5. In the specifications in Figures 4 and 5, the standard specification description describes the specifications of a standard electrical equipment storage panel, and the required specification description describes the specifications of the electrical equipment storage panel to be designed. Then, the user reads information from the specifications created by the specification creation unit 10, for example, the specifications in Figures 4 and 5, and inputs the required specification items and the data with the priority of the required specification items required for each design phase into each design phase (single line diagram design phase S02, array diagram design phase S03, and structural design phase S04). Here, the required specification items required for each design phase and the data prioritizing the required specification items refer to required specification data in text or image data format that includes at least the required specification items indicating the equipment capacity, the size of the building or electrical room, the power receiving method, standards, and whether or not options are provided, as well as the priorities of the required specification items. Here, regarding the required specification items, The facility capacity is determined by the rated voltage and rated current of the user's facility that uses the power, and refers to the total capacity to consume the power contracted with the power company. The size of the building or electrical room means the floor area and height of the building or electrical room reserved for placing electrical equipment in a building owned by a user who uses electricity. The power receiving method refers to how the power company's distribution lines are pulled in and how an electric path is formed to the user's equipment. Standards are a term that refers to the standards to which distribution boards and storage devices comply. For example, in Japan there are JIS (Japanese Industrial Standards) standards, and overseas there are IEC (International Electrotechnical Commission) standards. Options include paint color, protection rating (waterproof, dustproof, earthquake-resistant), etc. Priority refers to the priority given at the time of design in terms of the aforementioned equipment capacity, size of the building or electrical room, power receiving method, standards, and whether or not options are provided.

[0017] (5-2) Single Line Diagram Design Phase S02 In the single line diagram design phase S02, required specification data in text or image data format, which describes the required specification items of the electrical equipment storage panel specifications created in the specification creation phase S01 and the priority of those required specification items, is input as input data to the single line diagram design unit 20. That is, required specification data in text or image data format, which describes at least the required specification items including the equipment capacity, building size, power receiving method, standards, and whether or not options are provided, and the priority of those required specification items, is input as input data to the single line diagram design unit 20. Based on the input required specification data, the single line diagram design unit 20 searches for similar past cases that are close to the required specification data, and uses image generation AI (Artificial Intelligence) to propose candidate edited design proposals for single line diagrams that satisfy the required specification data. The output format of the single line diagram design unit 20 is to output image data of the single line diagram or candidates for system circuit analysis model data together with the past case data used as reference. In the present disclosure, image data of a single line diagram and system circuit analysis model data are referred to as single line diagram data. A single-line diagram is a design drawing that clearly shows the connection information of installed equipment using single lines. Figure 6 shows an example of image data of a single-line diagram, which contains information such as the path from the power source to the load, the power receiving method, the equipment (power source, transformer, circuit breaker, etc.) and their capacities in the design support system for electrical equipment storage panels. The system circuit analysis model data is data that can be used to confirm whether the designed system circuit operates correctly in accordance with the design intent when switching systems, shutting down the system circuit, etc. Figure 20 shows an example of the system circuit analysis model data.

[0018] FIG. 7 is a block diagram showing a circuit configuration of the single line diagram design unit according to the first embodiment. In FIG. 7, the single line diagram design unit 20 includes an information processing unit 21 and an artificial intelligence unit 22. The information processing unit 21 has a data acquisition unit 23 and a control unit 24, and the artificial intelligence unit 22 has a model control unit 25 and a trained model storage unit 26. The artificial intelligence unit 22 refers to an artificial intelligence (AI) having intelligent functions such as inference and judgment, and its operating environment. When the information processing unit 21 receives the B1 input, it uses the artificial intelligence unit 22 to obtain and output the C1 output. The B1 input is required specification data in text or image data format that describes required specification items including at least the facility capacity, building size, power receiving method, standards, and whether or not options are provided, as well as the priority of these required specification items. The C1 output is image data of a single line diagram or a candidate for system circuit analysis model data, that is, single line diagram data.

[0019] FIG. 8 is a diagram showing a design flow of the single line diagram design unit according to the first embodiment. 8, the data acquisition unit 23 of the information processing unit 21 acquires the B1 input. The data acquisition unit 23 outputs the acquired B1 input to the control unit 24. In step S22, the control unit 24 inputs the acquired B1 input to the artificial intelligence unit 22, and acquires from the artificial intelligence unit 22 the C1 output corresponding to the B1 input. Here, the artificial intelligence unit 22 is a model and its operating environment configured to output a C1 output corresponding to a B1 input when the B1 input is input. When the artificial intelligence unit 22 receives a B1 input from the control unit 24, it outputs a C1 output based on the B1 input and the trained model stored in the trained model storage unit 26. In step S23, the control unit 24 outputs the C1 output obtained from the artificial intelligence unit 22.

[0020] The trained model and the information used by the artificial intelligence unit 22 may be prepared in advance, or may be acquired via a network as needed.

[0021] (5-3) Array design phase S03 In the array diagram design phase S03, the array diagram design unit 30 (a) Required specification data in text or image data format that includes at least the required specification items, including the facility capacity, building size, power receiving method, standards, and whether or not options are provided, as well as the priority of those required specification items; (b) image data or system circuit analysis model data of a single line diagram selected from the candidates output in the single line diagram design phase S02; Enter as B2 input. Based on the input B2, the array diagram design unit 30 searches for similar past cases that are close to the required specifications, and proposes satisfactory array diagram edit design candidates using image generation AI. The output format of the layout diagram design unit 30 is to output image data of the layout diagram, or simulated electrical room model data that simulates an electrical room in which electrical equipment storage panels (switchgears) are arranged, along with the past case data used as reference. In this disclosure, image data of the layout diagram and simulated electrical room model data are referred to as layout diagram data. The image data of the arrangement diagram means image data that describes information necessary for the arrangement of devices housed in an electrical device housing panel (switchboard; switchgear), for example, as shown in FIG. The simulated electric room model data means 3D model data that simulates an actual electric room in which devices stored in an electric device storage panel are arranged. Fig. 21 is a diagram showing an example of the simulated electric room model data.

[0022] FIG. 10 is a block diagram showing a circuit configuration of the array diagram design unit according to the first embodiment. In FIG. 10, the sequence diagram design unit 30 includes an information processing unit 31 and an artificial intelligence unit 32. The information processing unit 31 has a data acquisition unit 33 and a control unit 34, and the artificial intelligence unit 32 has a model control unit 35 and a trained model storage unit 36. The artificial intelligence unit 32 refers to an artificial intelligence having intelligent functions such as inference and judgment, and its operating environment. When the information processing unit 31 receives the B2 input, it uses the artificial intelligence unit 32 to obtain and output the C2 output.

[0023] FIG. 11 is a diagram showing a design flow of the array diagram design unit according to the first embodiment. 11, the data acquisition unit 33 of the information processing unit 31 acquires the B2 input. The data acquisition unit 33 outputs the acquired B2 input to the control unit . In step S32, the control unit 34 inputs the acquired B2 input to the artificial intelligence unit 32, and acquires from the artificial intelligence unit 32 the C2 output corresponding to the B2 input. Here, the artificial intelligence unit 32 is a model and its operating environment configured to output a C2 output corresponding to a B2 input when the B2 input is input. When the artificial intelligence unit 32 receives a B2 input from the control unit 34, it outputs a C2 output based on the B2 input and the trained model stored in the trained model storage unit 36. In step S33, the control unit 34 outputs the C2 output obtained from the artificial intelligence unit 32.

[0024] (5-4) Structural Design Phase S04 In the structural design phase S04, the structural design department 40 (c) Required specification data in text or image data format that describes at least the required specification items, including the facility capacity, building size, power receiving method, standards, and whether or not options are provided, as well as the priority of those required specification items; and (d) Sequence diagram data selected from the candidates output in the sequence diagram design phase S03; Enter as B3 input. Based on the input B3, the structural design unit 40 searches for similar past cases that are close to the required specifications, and uses image generation AI to propose satisfactory edited design proposals for structural design drawings. The output format of the structural design unit 40 is a structural design drawing or structural model data in which equipment parts such as circuit breakers, transformers, conductors, etc. are arranged for each side of the electrical equipment storage panel (distribution panel; switchgear), together with the data of past projects used as reference, and strength analysis data for each side of the electrical equipment storage panel (distribution panel; switchgear). In this disclosure, the structural design drawing, structural model data, and strength analysis data of the electrical equipment storage panel are referred to as structural design drawing data. A structural design drawing of an electrical equipment storage panel is a drawing that shows the layout of equipment (e.g., CTs (Current Transformers), VCBs (Vacuum Circuit Breakers), VTs (Voltage Transformers), etc.) inside the electrical equipment storage panel, the layout of current-carrying circuits, etc. Figure 22 is a diagram showing an example of a structural design drawing of an electrical equipment storage panel. Structural model data for an electrical equipment storage panel refers to 3D model data that shows the layout of equipment and current-carrying circuits within the electrical equipment storage panel. The strength analysis data of the electrical equipment storage panel refers to analysis data that analyzes the degree of deformation when an external force is applied to the equipment and structures inside the electrical equipment storage panel.

[0025] FIG. 12 is a block diagram showing a circuit configuration of the structural design unit according to the first embodiment. In FIG. 12, a structural design unit 40 includes an information processing unit 41 and an artificial intelligence unit 42. The information processing unit 41 has a data acquisition unit 43 and a control unit 44, and the artificial intelligence unit 42 has a model control unit 45 and a trained model storage unit 46. The artificial intelligence unit 42 refers to an artificial intelligence having intelligent functions such as inference and judgment, and its operating environment. When the information processing unit 41 receives the B3 input, it uses the artificial intelligence unit 42 to obtain and output the C3 output.

[0026] FIG. 13 is a diagram showing a design flow of the structural design unit according to the first embodiment. 13, the data acquisition unit 43 of the information processing unit 41 acquires the B3 input. The data acquisition unit 43 outputs the acquired B3 input to the control unit 44. In step S42, the control unit 44 inputs the acquired B3 input to the artificial intelligence unit 42, and acquires from the artificial intelligence unit 42 the C3 output corresponding to the B3 input. Here, the artificial intelligence unit 42 is a model and its operating environment configured to output a C3 output corresponding to a B3 input when the B3 input is input. When the artificial intelligence unit 42 receives a B3 input from the control unit 44, it outputs a C3 output based on the B3 input and the trained model stored in the trained model storage unit 46. In step S43, the control unit 44 outputs the C3 output obtained from the artificial intelligence unit 42.

[0027] As described above, according to the first embodiment, in the design section of the design support system for electrical equipment storage panels, the required specification items of the specifications for the electrical equipment storage panel and the priority order of the required specification items are input as required specification data, past design data for the electrical equipment storage panel stored in a database is compared with the input required specification data, and an edited design proposal for the electrical equipment storage panel that satisfies the required specification data is output as output data using a first machine learning model learned from the past design data for the electrical equipment storage panel. This reduces the occurrence of human error and significantly reduces design time.

[0028] The design unit includes a single line diagram design unit, an arrangement diagram design unit, and a structure design unit, the single line diagram design unit inputs the required specification items and the priority order of the required specification items of the specification sheet for the electrical equipment storage panel as the required specification data, and outputs single line diagram data for the electrical equipment storage panel as output data; the array diagram design unit receives, as input data, the required specification items of the electrical equipment storage panel, the priority order of the required specification items, and the single-line diagram data of the electrical equipment storage panel, and outputs, as output data, array diagram data of the electrical equipment storage panel; The structural design unit inputs the required specification items and the priority order of the required specification items of the electrical equipment storage panel, and the layout diagram data of the electrical equipment storage panel as input data, and outputs structural design diagram data of the electrical equipment storage panel as output data. Single-line diagram design, arrangement diagram design, and structural design can be generated from specifications in one step, minimizing the number of items that users need to set and shortening design time.

[0029] Embodiment 2 The design support system for an electrical equipment storage panel according to the second embodiment provides a design support system for an electrical equipment storage panel that has a function for adjusting output data output from each design phase. In other words, when the output data output from each design phase needs to be supplemented, the user or the second machine learning model (e.g., a character generation type AI) inputs instructions to adjust the output data into the first machine learning model (e.g., an image generation type AI) of each design department 20, 30, 40, and adjusts the input data to adjust the result data.

[0030] FIG. 14 is a diagram showing a basic flow S200 of each design phase according to the second embodiment. In step S201 of FIG. 14, a user reads information from the specifications created by the specifications creation unit 10, prioritizes the required specification items necessary for each design phase, and inputs them to the design units 20, 30, and 40 as required specification data. In steps S202 and S203, each design department 20, 30, 40 selects past design cases with high similarity from a past design database based on the above input data, and proposes candidate edited design proposals that satisfy the input required specification data using a first machine learning model (e.g., image generation type AI). In step S204, the user selects the most appropriate edited design plan from the output edited design plan candidates. In step S205, if the selected edited design proposal needs to be supplemented, the user or the second machine learning model (e.g., a character generation type AI) inputs instructions for adjusting the output data to the first machine learning model (e.g., an image generation type AI) of each design department 20, 30, 40, and an appropriate edited design proposal is obtained by the first machine learning model (e.g., an image generation type AI) of each design department 20, 30, 40.

[0031] According to the basic design flow of the first embodiment, if some adjustment is required in the output data of each design phase, it becomes necessary to go back and start over by correcting the required specification data. However, the electrical equipment storage panel design support system of the second embodiment has a function of complementing output data, which has the effect of eliminating the need for the above-mentioned rework.

[0032] Embodiment 3 In the design support system for electrical equipment storage panels of embodiment 3, in each design phase, prioritized required specification data can be input by a third machine learning model (e.g., a character generation AI) through repeated conversations with the user.

[0033] FIG. 15 is a diagram showing a basic flow S300 of each design phase according to the third embodiment. In steps S301, S302, S303, and S304 of Figure 15, the user or a third machine learning model (character generation AI) reads information from the specifications created by the specification creation unit 10, and while repeatedly conversing with the user, prioritizes the input data required for each design phase and inputs it to each design unit 20, 30, and 40. In steps S305 and S306, each design department 20, 30, 40 selects past design cases with high similarity from a past design database based on the above input data, and proposes candidate edited design proposals that satisfy the input specification data using a first machine learning model (e.g., image generation type AI). In step S307, the user selects the most appropriate edited design plan from the output edited design plan candidates.

[0034] According to the electrical equipment storage panel design support system of the third embodiment, the time required to prioritize required specification data can be reduced with the assistance of character generation AI. In addition, the accuracy of the prioritization is improved, and the accuracy of the output edited design data is also improved.

[0035] Embodiment 4 In the design support system for electrical equipment storage panels of embodiment 4, each design department 20, 30, 40 has multiple machine learning models (for example, character generation AI, image generation AI, etc.), and each design department 20, 30, 40 reads the information necessary for creating single-line diagram design, arrangement diagram design, and structural design drawings from the information in the design specifications, selects highly similar cases from a past design database, and proposes edited design proposals.

[0036] FIG. 16 is a diagram showing a basic flow of the design support system for an electrical equipment storage panel according to the fourth embodiment, and FIG. 17 is a diagram showing a basic flow S500 of each design phase according to the fourth embodiment. The design support flow for the electrical equipment storage panel according to the fourth embodiment will be described with reference to FIGS. In step S501, the fourth machine learning model (for example, a character generation AI) of each of the design units 20, 30, 40 reads the specification created by the specification creation unit 10 (specification creation phase S01). In step S502, the fourth machine learning model (e.g., a character generation AI) of each design unit 20, 30, 40 outputs required specification data with adjusted priorities required for each design phase based on the input specification information. In steps S503 and S504, each design department 20, 30, 40 selects highly similar past design cases from a past design database based on the required specification data with the adjusted priorities required for each design phase, and proposes edited design proposal candidates that satisfy the input required specification data using a first machine learning model (e.g., an image generation type AI). In step S505, the user selects the most appropriate edited design plan from the output edited design plan candidates.

[0037] As described above, according to the electrical equipment storage panel design support system of the fourth embodiment, the design flow is fully automated, so that the design time can be significantly reduced.

[0038] Embodiment 5. In the design support system for electrical equipment storage panels of embodiment 5, each design department 20, 30, 40 uses an existing first machine learning model (for example, an existing image generation AI such as Stable Diffusion, Canva, or Bing Image Creator), and is equipped with a function to convert input data to match the input specifications of the existing machine learning model.

[0039] FIG. 18 is a diagram showing a basic flow S600 of each design phase according to the fifth embodiment. In step S601 of FIG. 18, a user reads information from the specifications created by the specifications creation unit 10, prioritizes the required specification items necessary for each design phase, and inputs them to the design units 20, 30, and 40 as required specification data. In steps S602 to S604, each design department 20, 30, 40 selects past design cases with high similarity from a past design database based on the above input data, and proposes candidate edited design proposals that satisfy the input required specification data using a first machine learning model (e.g., an existing image generation AI such as Stable Diffusion, Canva, or Bing Image Creator). In this case, in step S603, the input data is converted to conform to the input specifications of the existing first machine learning model. Then, in step S605, the user selects the most appropriate edited design plan from the edited design plan candidates that are the output data of step S604.

[0040] As described above, according to the design support system for electrical equipment storage panels of embodiment 5, input data can be converted to match an existing machine learning model, which has the effect of making it easy to reuse or replace the machine learning model.

[0041] 19 shows an example of hardware, each of the design units 20, 30, and 40 of the above-described embodiment is configured with a processor 1000 and a storage device 1010. The storage device 1010 includes a volatile storage device such as a random access memory and a non-volatile auxiliary storage device such as a flash memory, both of which are not shown. Furthermore, a hard disk auxiliary storage device may be provided instead of flash memory. Processor 1000 executes a program input from storage device 1010. In this case, the program is input from the auxiliary storage device to processor 1000 via a volatile storage device. Processor 1000 may output data such as calculation results to the volatile storage device of storage device 1010, or may store data in the auxiliary storage device via the volatile storage device.

[0042] Although the present disclosure describes various exemplary embodiments and examples, the various features, aspects, and functions described in one or more embodiments are not limited to application to a particular embodiment, but may be applied to the embodiments alone or in various combinations. Therefore, countless variations not exemplified are conceivable within the scope of the technology disclosed in this specification, including, for example, cases where at least one component is modified, added, or omitted, and cases where at least one component is extracted and combined with components of another embodiment.

[0043] Various aspects of the present disclosure are summarized below as appendices.

[0044] (Appendix 1) In the design section of the electrical equipment storage panel design support system, inputting required specification items and priorities of the required specification items in the specification of the electrical equipment storage panel as required specification data; A design support system for electrical equipment storage panels that compares past design data for the electrical equipment storage panel stored in a database with the input required specification data, and outputs as output data an edited design proposal for the electrical equipment storage panel that satisfies the required specification data using a first machine learning model that has learned from the past design data for the electrical equipment storage panel. (Appendix 2) 2. The electrical equipment storage panel design support system according to claim 1, wherein the design unit includes a single line diagram design unit, an arrangement diagram design unit, and a structural design unit. (Appendix 3) the single line diagram design unit inputs the required specification items and the priority of the required specification items in the specification document for the electrical equipment storage panel as the required specification data, and outputs single line diagram data for the electrical equipment storage panel as output data. (Appendix 4) the array diagram design unit inputs the required specification items and the priority order of the required specification items of the electrical equipment storage panel, as well as the single-line diagram data of the electrical equipment storage panel, as input data, and outputs array diagram data of the electrical equipment storage panel as output data. (Appendix 5) the structural design unit inputs, as input data, the required specification items of the electrical equipment storage panel and their priorities, as well as the array diagram data of the electrical equipment storage panel, and outputs, as output data, structural design diagram data of the electrical equipment storage panel. (Appendix 6) The design support system for electrical equipment storage panels described in Appendix 5, wherein a second machine learning model corrects the structural design drawing data of the electrical equipment storage panel and inputs it again into the first machine learning model. (Appendix 7) 7. The design support system for electrical equipment storage panels according to claim 1, wherein the input data to be input to the first machine learning model is generated using a third machine learning model that repeatedly inputs user feedback. (Appendix 8) a fourth machine learning model that receives a specification of the electrical equipment storage panel and outputs required specification items and priorities of the required specification items in the specification as required specification data; 8. The electrical equipment storage panel design support system according to claim 1, wherein past design data of the electrical equipment storage panel stored in the database is compared with the required specification data input from the fourth machine learning model, and an edited design proposal for the electrical equipment storage panel that satisfies the required specification data is output as output data using the first machine learning model that has learned from the past design data of the electrical equipment storage panel. (Appendix 9) A design support system for electrical equipment storage panels described in any one of Appendix 1 to Appendix 8, which performs preprocessing to convert data to be input into the first machine learning model and inputs the data into the first machine learning model. (Appendix 10) The design support system for electrical equipment storage panels according to any one of Supplementary Note 1 to Supplementary Note 9, wherein the required specification data is at least required specification items including equipment capacity, building size, power receiving method, standards, and whether or not options are provided, and a priority order of the required specification items. [Explanation of symbols]

[0045] 10 Specification Creation Department, 20 Single Line Diagram Design Department, 30 Array Diagram Design Department, 40 Structural Design Department, 60 Design Department, 21 Information Processing Department, 22 Artificial Intelligence Department, 23 Data Acquisition Department, 24 control unit, 25 model control unit, 26 trained model storage unit, 31 information processing unit, 32 Artificial Intelligence Department, 33 Data Acquisition Department, 34 Control Department, 35 Model Control Department, 36 Trained model memory unit, 41 Information processing unit, 42 Artificial intelligence unit, 43 data acquisition unit, 44 control unit, 45 model control unit, 46 learned model memory unit, 100 electrical equipment storage panel design support system, 1000 processor, 1010 Storage device.

Claims

1. In the design section of the electrical equipment storage panel design support system, inputting required specification items and priorities of the required specification items in the specification of the electrical equipment storage panel as required specification data; A design support system for electrical equipment storage panels that compares past design data for the electrical equipment storage panel stored in a database with the input required specification data, and outputs as output data an edited design proposal for the electrical equipment storage panel that satisfies the required specification data using a first machine learning model that has learned from the past design data for the electrical equipment storage panel.

2. 2. The electrical equipment storage panel design support system according to claim 1, wherein the design unit comprises a single-line diagram design unit, an arrangement diagram design unit, and a structure design unit.

3. 3. The electrical equipment storage panel design support system according to claim 2, wherein the single line diagram design unit inputs the required specification items and the priority of the required specification items of the specification document for the electrical equipment storage panel as the required specification data, and outputs single line diagram data of the electrical equipment storage panel as output data.

4. 4. The electrical equipment storage panel design support system according to claim 3, wherein the array diagram design unit inputs the required specification items and the priority order of the required specification items of the electrical equipment storage panel, and the single-line diagram data of the electrical equipment storage panel as input data, and outputs array diagram data of the electrical equipment storage panel as output data.

5. 5. The electrical equipment storage panel design support system according to claim 4, wherein the structural design unit inputs the required specification items and the priority order of the required specification items of the electrical equipment storage panel, and the layout diagram data of the electrical equipment storage panel as input data, and outputs structural design drawing data of the electrical equipment storage panel as output data.

6. The design support system for an electrical equipment storage panel according to claim 5 , wherein a second machine learning model corrects the structural design drawing data of the electrical equipment storage panel and inputs the corrected structural design drawing data into the first machine learning model again.

7. 7. The design support system for electrical equipment storage panels according to claim 1, wherein the input data to be input to the first machine learning model is generated using a third machine learning model that repeatedly inputs user feedback.

8. a fourth machine learning model that receives a specification of the electrical equipment storage panel and outputs required specification items of the specification and priorities of the required specification items as required specification data; 7. The electrical equipment storage panel design support system according to claim 1, wherein past design data of the electrical equipment storage panel stored in the database is compared with the required specification data input from the fourth machine learning model, and an edited design proposal for the electrical equipment storage panel that satisfies the required specification data is output as output data using the first machine learning model that has learned from the past design data of the electrical equipment storage panel.

9. The design support system for electrical equipment storage panels according to claim 1 , wherein preprocessing is performed to convert data to be input to the first machine learning model, and the data is input to the first machine learning model.

10. 7. The design support system for an electrical equipment storage panel according to claim 1, wherein the required specification data is at least required specification items including an equipment capacity, a building size, a power receiving method, a standard, and whether or not options are provided, and a priority order of the required specification items.

Citation Information

Patent Citations

  • Design support system and design support method for electric apparatus housing board

    JP2017146640A