Intelligent identification method and system for electrical drawings

Abstract

The present application relates to the technical field of intelligent identification, and particularly relates to an intelligent identification method and system for electrical drawings, the steps of the method comprising: obtaining multi-version electrical drawing data of a target factory and historical operation and maintenance data of electrical equipment; evaluating drawing evolution risks and drawing lag risks based on the multi-version electrical drawing data; constructing an electrical system risk matrix of the target factory based on the historical operation and maintenance data and in combination with the evaluation results of the drawing evolution risks and the drawing lag risks; obtaining equipment attribute data of newly added electrical equipment and combining the electrical system risk matrix to evaluate risk superposition effects and risk diffusion effects after the newly added electrical equipment is connected; and performing electrical system risk early warning based on the evaluation results of the risk superposition effects and the risk diffusion effects. The present application quantifies drawing evolution risks and drawing lag risks and evaluates risk superposition and diffusion effects when newly added electrical equipment is connected, thereby effectively improving the accuracy and reliability of electrical system risk early warning.

Description

Technical Field

[0001] This invention relates to the field of intelligent recognition technology, and in particular to an intelligent recognition method and system for electrical drawings. Background Technology

[0002] In industrial production, as factories expand or production processes are upgraded, electrical systems often need to be adjusted and expanded accordingly. During this process, electrical drawings, as key technical documents recording and guiding the layout and connections of electrical systems, are crucial; their accuracy and timeliness directly affect the safe and stable operation of the electrical system.

[0003] Existing technologies for digitizing electrical drawings based on image recognition methods are still limited to symbol recognition or structure extraction. For example, the invention patent with publication number CN117912023A discloses an automated identification method and terminal for hydropower plant electrical drawings. This method uses a segmentation and discrimination model to segment and distinguish the electrical drawings of the hydropower plant to be identified, obtaining the graphic elements, text, and categories of the drawings. Based on the categories, the graphic elements are identified to obtain graphic element information, and the text is semantically recognized to obtain text information. In this way, the segmentation and discrimination model automatically identifies and separates the graphic elements, text, and categories of the hydropower plant electrical drawings. Then, graphic element recognition and semantic recognition are performed separately, which can achieve automated, comprehensive, and accurate electrical drawing identification. The output identification results can be used for further analysis and processing, thereby effectively realizing the informatization and intelligentization of electrical drawings. However, the above methods lack a systematic analysis of the differences between multiple versions of drawings, making it difficult to accurately assess the evolutionary risks of electrical drawings during version iteration. At the same time, they fail to effectively consider the problem of drawing lag, that is, the electrical drawings fail to reflect the inconsistencies caused by on-site change events in a timely manner. Such lag may have a serious impact on the diagnosis of electrical equipment faults and the decision-making of expansion and renovation.

[0004] Furthermore, as electrical systems become increasingly complex, the addition of new electrical equipment often leads to the superposition and spread of risks. For example, new equipment may exacerbate the risks of weak links in the original electrical system, or transmit risks to a wider range through topological relationships. Existing technologies usually focus on the reliability analysis of single equipment and lack a comprehensive assessment method that combines the risks of drawing evolution, the risks of drawing lag, and historical operation and maintenance data. This makes it impossible to provide comprehensive and dynamic risk prediction and early warning support for the expansion or renovation of electrical systems. Summary of the Invention

[0005] To overcome the defects and shortcomings of existing technologies, this invention provides an intelligent recognition method and system for electrical drawings. By quantitatively assessing the risks of drawing evolution and drawing lag, and combining historical operation and maintenance data to construct an electrical system risk matrix, the accuracy and reliability of electrical system risk early warning are effectively improved.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides an intelligent recognition method for electrical drawings, comprising:

[0008] Acquire multiple versions of electrical drawings and historical operation and maintenance data of electrical equipment for the target factory. The multiple versions of electrical drawings include the current version of electrical drawings and historical versions of electrical drawings.

[0009] Based on multiple versions of electrical drawing data and deep learning models, electrical features are extracted from electrical drawings to assess the risks of drawing evolution and drawing lag.

[0010] Based on historical operation and maintenance data and combined with the risk assessment results of drawing evolution and drawing lag, an electrical system risk matrix for the target factory is constructed.

[0011] Obtain the equipment attribute data of newly added electrical equipment and combine it with the electrical system risk matrix to assess the risk superposition effect and risk diffusion effect after the new electrical equipment is connected;

[0012] Electrical system risk early warning is based on the assessment results of risk superposition and risk diffusion effects.

[0013] Furthermore, assess the risks associated with the evolution of the aforementioned drawings, including:

[0014] Based on multiple versions of electrical drawing data and combined with a deep learning model, electrical features are extracted from each version of electrical drawings. The electrical feature extraction includes drawing symbol recognition, topological relationship extraction, and equipment parameter parsing.

[0015] The electrical drawings of each version are arranged in chronological order of release time, and the difference sets of adjacent versions of electrical drawings are extracted based on the electrical feature extraction results to determine the sets of newly added equipment, deleted equipment, equipment with attribute changes, and topology relationship changes.

[0016] The drawing evolution risk factor of adjacent versions of electrical drawings is calculated based on the difference set. The drawing evolution risk factor is obtained by weighted summation of the topology difference factor, equipment change rate factor and drawing evolution cycle factor of adjacent versions of electrical drawings.

[0017] The average of the drawing evolution risk factors of all adjacent versions of electrical drawings is used as the drawing evolution risk coefficient, which is used to characterize the drawing evolution risk caused by the magnitude of change and instability of electrical drawings during version iteration.

[0018] Furthermore, assess the risk of the aforementioned drawings being outdated, including:

[0019] Based on the current version of the electrical drawings, extract the set of electrical features and based on historical operation and maintenance data, extract the set of all change events involving changes in the electrical system structure;

[0020] Based on the electrical feature set and change event set, identify the drawing lag change event and construct the drawing lag change event set. The drawing lag change event is a change event that occurs after the release time of the current version of the electrical drawing and is not reflected in the current version of the electrical drawing;

[0021] The ratio of the number of events in the set of delayed change events to the number of events in the set of change events is used as the drawing lag risk coefficient, which is used to characterize the drawing lag risk caused by the difference between the current version of electrical drawings and the site.

[0022] Furthermore, the construction of the electrical system risk matrix for the target factory includes:

[0023] Obtain historical operation and maintenance data, drawing evolution risk coefficient, and drawing lag risk coefficient for electrical equipment;

[0024] Based on historical operation and maintenance data, operation and maintenance risk factors for each electrical device are extracted and operation and maintenance risk coefficients are calculated. The operation and maintenance risk factors include failure rate factor, failure range factor and failure duration factor.

[0025] Using electrical equipment as the basic unit, the comprehensive risk coefficient of each basic unit is calculated based on the drawing evolution risk coefficient, drawing lag risk coefficient, and operation and maintenance risk coefficient.

[0026] An electrical system risk matrix is ​​constructed based on the comprehensive risk coefficient to characterize the risk distribution of the target factory's electrical system in different areas and equipment dimensions.

[0027] Furthermore, the assessment of the risk superposition and risk diffusion effects after the addition of new electrical equipment includes:

[0028] Obtain the equipment attribute data of newly added electrical equipment. The equipment attribute data includes equipment type, equipment rated power, equipment voltage level, and equipment topology.

[0029] The equipment attribute data of newly added electrical equipment is mapped to access risk factors, and the risk superposition effect coefficient is determined by combining the comprehensive risk coefficient in the electrical system risk matrix.

[0030] Based on the analysis of equipment topology, the impact range of the access of new electrical equipment is analyzed and the risk diffusion effect coefficient is determined;

[0031] The risk superposition effect coefficient and the risk diffusion effect coefficient are weighted and summed to obtain the access risk effect coefficient of the new electrical equipment, which is used to characterize the impact of the access of the new electrical equipment on the overall risk distribution of the electrical system.

[0032] Furthermore, the aforementioned electrical system risk warning includes:

[0033] Obtain the access risk effect coefficient of newly added electrical equipment. When the access risk effect coefficient is greater than or equal to the preset access risk effect threshold, conduct an electrical system risk warning; when the access risk effect coefficient is less than the preset access risk effect threshold, do not conduct an electrical system risk warning.

[0034] In a second aspect, the present invention provides an intelligent recognition system for electrical drawings, comprising:

[0035] The data acquisition module is used to acquire multiple versions of electrical drawings data and historical operation and maintenance data of electrical equipment from the target factory. The multiple versions of electrical drawings data include the current version of electrical drawings and historical versions of electrical drawings.

[0036] The drawing risk assessment module is used to extract electrical features from electrical drawings based on multi-version electrical drawing data and deep learning models, and to assess the risks of drawing evolution and drawing lag.

[0037] The risk matrix construction module is used to construct the electrical system risk matrix of the target factory based on historical operation and maintenance data and combined with the risk assessment results of drawing evolution and drawing lag.

[0038] The access risk assessment module is used to obtain the equipment attribute data of newly added electrical equipment and combine it with the electrical system risk matrix to assess the risk superposition effect and risk diffusion effect after the new electrical equipment is connected.

[0039] The risk warning module is used to provide early warnings of electrical system risks based on the assessment results of risk superposition and risk diffusion effects.

[0040] Thirdly, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an intelligent recognition method for electrical drawings by calling the computer program stored in the memory.

[0041] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an intelligent recognition method for electrical drawings.

[0042] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0043] (1) This invention quantitatively assesses the risk of electrical drawing evolution by extracting features and analyzing the difference set of multiple versions of electrical drawings. This avoids the shortcomings of existing technologies that rely solely on manual comparison or symbol recognition, which cannot accurately identify structural changes and instabilities in the process of electrical drawing version iteration. This effectively improves the accuracy of identifying the risk of electrical drawing evolution.

[0044] (2) Based on the joint analysis of electrical drawings and historical operation and maintenance data, this invention can effectively identify the event of delayed change of drawings and quantify the risk of delayed drawings. It overcomes the problem that it is difficult to detect and quantify the inconsistency between electrical drawings and on-site layout in the prior art in a timely manner, and improves the credibility of drawings and the reliability of operation and maintenance management of electrical equipment.

[0045] (3) This invention constructs an electrical system risk matrix by integrating the risks of drawing evolution, drawing lag and historical operation and maintenance, and further evaluates the risk superposition effect and risk diffusion effect when new electrical equipment is connected, thereby realizing dynamic prediction and early warning of the overall risk of the electrical system. It breaks through the limitation of existing technology that can only perform single equipment reliability analysis, and provides comprehensive technical guarantee for the safe operation of electrical systems during factory expansion and renovation. Attached Figure Description

[0046] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0047] Figure 1 This is a flowchart illustrating the intelligent recognition method for electrical drawings provided in an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram of the intelligent recognition system for electrical drawings provided in an embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0050] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0051] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of the intelligent recognition method for electrical drawings provided in an embodiment of the present invention, which specifically includes the following steps:

[0052] S100: Obtain multiple versions of electrical drawing data and historical operation and maintenance data of electrical equipment from the target factory. The multiple versions of electrical drawing data include the current version of electrical drawings and historical versions of electrical drawings.

[0053] S200: Based on multiple versions of electrical drawing data and combined with a deep learning model, electrical features are extracted from electrical drawings to assess the risk of drawing evolution and the risk of drawing lag.

[0054] Drawing evolution risk refers to the instability and uncertainty brought about by changes in electrical drawings during version iterations, such as topology adjustments, equipment additions or deletions, and equipment parameter changes. When electrical drawings undergo frequent structural changes within a short period, it indicates that the electrical system is in a high state of dynamic evolution. This high dynamic evolution increases potential risks in the operation and maintenance of the electrical system. For example, during factory expansion, a version of the electrical drawing might show a substation with only two main transformers, but a third main transformer might be added in a later version, and the topology of the related busbars might be adjusted. When such changes occur frequently across multiple electrical drawing versions, it indicates that the system structure is in an unstable evolutionary stage, potentially leading to uncertainties in power distribution capacity assessment, protection configuration, and fault isolation strategies, thereby increasing the operational risk of the electrical system. Similarly, if a piece of equipment experiences multiple changes in rated power or voltage level parameters within a short period, it indicates that the design scheme is not yet stable and may face the risk of mismatch with actual load during future operation. Therefore, assessing drawing evolution risk helps reveal the magnitude and instability of changes in electrical drawings during the design and iteration process, and allows for the early detection of potential risks in the electrical system design phase. The assessment of drawing evolution risk includes:

[0055] Based on multiple versions of electrical drawing data and combined with a deep learning model, electrical features are extracted from each version of electrical drawings. The electrical feature extraction includes drawing symbol recognition, topological relationship extraction, and equipment parameter parsing.

[0056] The electrical drawings of each version are arranged in chronological order of release time, and the difference sets of adjacent versions of electrical drawings are extracted based on the electrical feature extraction results to determine the sets of newly added equipment, deleted equipment, equipment with attribute changes, and topology relationship changes.

[0057] The drawing evolution risk factor for adjacent versions of electrical drawings is calculated based on the difference set. This risk factor is obtained by weighted summation of the topology difference factor, equipment change rate factor, and drawing evolution cycle factor for adjacent versions of electrical drawings. Specifically, the topology difference factor is calculated by statistically analyzing the number of newly added, deleted, or altered nodes and lines based on the connection relationships between devices in adjacent versions of electrical drawings, and then standardizing this ratio to the total number of topology nodes and lines. The equipment change rate factor is calculated by statistically analyzing the number of newly added, deleted, and attribute-changed devices in adjacent versions of electrical drawings, and then using the ratio of the number of changes to the total number of devices as the equipment change rate. The drawing evolution cycle factor is calculated by comparing the release time interval of adjacent versions of electrical drawings with the average release time of all versions of electrical drawings.

[0058] The average of the drawing evolution risk factors of all adjacent versions of electrical drawings is used as the drawing evolution risk coefficient, which is used to characterize the drawing evolution risk caused by the magnitude of change and instability of electrical drawings during version iteration.

[0059] The risk of outdated drawings refers to the risk arising from the failure of the current version of electrical drawings to reflect the actual changes in the on-site electrical system in a timely manner. Since there is usually a time lag in updating electrical drawings, if on-site construction, equipment changes, or topology adjustments have been completed but are not yet reflected in the drawings, this discrepancy can lead to inconsistencies between the drawing information relied upon for maintenance and expansion decisions and the actual system status, thus creating potential hazards. For example, in a factory electrical system, a power distribution line may be replaced with a newer model circuit breaker during maintenance due to equipment aging, but this change may not be updated in the electrical drawings, which may still show the old model equipment. If maintenance personnel rely on these outdated drawings for fault handling, they may misjudge the equipment capacity and protection characteristics, affecting system recovery efficiency. Assessing the risk of outdated drawings allows for a quantitative measurement of the difference between electrical drawings and the actual on-site situation, providing a more realistic basis for reliability analysis and risk prediction of electrical systems. The assessment of this risk includes:

[0060] Based on the current version of the electrical drawings, extract the set of electrical features and based on historical operation and maintenance data, extract the set of all change events involving changes in the electrical system structure;

[0061] Based on the electrical feature set and change event set, identify the drawing lag change event and construct the drawing lag change event set. The drawing lag change event is a change event that occurs after the release time of the current version of the electrical drawing and is not reflected in the current version of the electrical drawing;

[0062] The ratio of the number of events in the set of delayed change events to the number of events in the set of change events is used as the drawing lag risk coefficient, which is used to characterize the drawing lag risk caused by the difference between the current version of electrical drawings and the site.

[0063] S300, based on historical operation and maintenance data and combined with the risk assessment results of drawing evolution and drawing lag, constructs the electrical system risk matrix of the target factory;

[0064] The electrical system risk matrix is ​​a risk distribution representation model formed by taking electrical equipment as the basic unit and comprehensively considering multi-dimensional risk factors such as drawing evolution risk, drawing lag risk, and historical operation and maintenance risk. It can accurately reflect the potential risk level of the electrical system in different locations and equipment categories, providing basic data support for the risk assessment of subsequent new electrical equipment integration. By quantifying the comprehensive risk distribution of different areas and different equipment, it enables the assessment not only of the superposition effect of the new equipment's own attributes on existing high-risk units, but also the analysis of its risk diffusion effect on surrounding equipment and areas based on topological relationships. This allows for comprehensive prediction and accurate early warning of the overall risk changes of the electrical system after the integration of new equipment. The construction of the electrical system risk matrix for the target factory includes:

[0065] Obtain historical operation and maintenance data, drawing evolution risk coefficient, and drawing lag risk coefficient for electrical equipment;

[0066] Based on historical operation and maintenance data, operation and maintenance risk factors for each electrical device are extracted and operation and maintenance risk coefficients are calculated. The operation and maintenance risk factors include failure rate factor, failure range factor, and failure duration factor. Among them, the failure rate factor is the ratio of the number of failures of electrical devices in the statistical period to the average number of failures of all electrical devices in the statistical period. The failure range factor is the ratio of the number of devices affected by the equipment failure to the total number of devices. The failure duration factor is the ratio of the cumulative downtime of equipment failure to the total uptime of the equipment. The operation and maintenance risk coefficient is obtained by weighted summation of the failure rate factor, failure range factor, and failure duration factor.

[0067] Using electrical equipment as the basic unit, the comprehensive risk coefficient of each basic unit is calculated based on the drawing evolution risk coefficient, the drawing lag risk coefficient, and the operation and maintenance risk coefficient. The comprehensive risk coefficient is calculated by weighted summation of the drawing evolution risk coefficient, the drawing lag risk coefficient, and the operation and maintenance risk coefficient.

[0068] An electrical system risk matrix is ​​constructed based on the comprehensive risk coefficient to characterize the risk distribution of the target factory's electrical system in different areas and equipment dimensions.

[0069] S400: Obtain the equipment attribute data of the newly added electrical equipment and combine it with the electrical system risk matrix to assess the risk superposition effect and risk diffusion effect after the new electrical equipment is connected;

[0070] The risk superposition effect refers to the phenomenon where the inherent risk attributes (such as high power and high voltage levels) of newly added electrical equipment are superimposed and amplified by the existing high risk level at the proposed connection location, leading to a sharp increase in risk in that local area. The risk diffusion effect refers to the phenomenon where, after the addition of new equipment, due to its position and connection in the entire electrical topology network, when it malfunctions or experiences an anomaly, the risk propagates along a predetermined electrical path (such as power supply lines and control circuits), triggering a chain reaction that affects downstream equipment or related areas, thus expanding systemic risk. Essentially, it is a dynamic, networked risk propagation, focusing on the risk spread path along the network. The assessment of the risk superposition and risk diffusion effects after the addition of new electrical equipment includes:

[0071] Obtain the equipment attribute data of newly added electrical equipment. The equipment attribute data includes equipment type, equipment rated power, equipment voltage level, and equipment topology.

[0072] The equipment attribute data of the newly added electrical equipment is mapped to the access risk factor and the risk superposition effect coefficient is determined by combining the comprehensive risk coefficient in the electrical system risk matrix. The calculation process of the risk superposition effect coefficient is as follows: (1) Based on the equipment attribute data of the newly added electrical equipment, the equipment attribute data is quantified into independent access risk factors through preset risk mapping rules; (2) The access target position of the newly added electrical equipment in the electrical system risk matrix is ​​determined and the corresponding comprehensive risk coefficient is obtained; (3) The product of the access risk factor of the newly added electrical equipment and the comprehensive risk coefficient corresponding to the access target position is used as the risk superposition effect coefficient.

[0073] The risk diffusion effect coefficient is determined by analyzing the access impact range of newly added electrical equipment based on the equipment topology relationship. The calculation process of the risk diffusion effect coefficient is as follows: (1) Based on the equipment topology relationship of the newly added electrical equipment, the graph theory analysis method is used to determine the impact range of the newly added electrical equipment in the entire electrical system network after access, and the downstream equipment and related lines affected by its operating status or fault are determined; (2) The comprehensive risk coefficient of all equipment within the impact range is extracted from the electrical system risk matrix and different propagation weights are assigned according to the electrical distance between the affected equipment and the newly added electrical equipment; (3) The risk diffusion effect coefficient is obtained by weighted summing of the comprehensive risk coefficient of all affected equipment and its corresponding propagation weight.

[0074] The risk superposition effect coefficient and the risk diffusion effect coefficient are weighted and summed to obtain the access risk effect coefficient of the new electrical equipment, which is used to characterize the impact of the access of the new electrical equipment on the overall risk distribution of the electrical system.

[0075] S500, based on the assessment results of risk superposition effect and risk diffusion effect, conducts early warning of electrical system risks;

[0076] Electrical system risk early warning is based on the assessment results of risk superposition and risk diffusion effects. This not only considers the direct superposition impact of newly added electrical equipment on existing high-risk units, but also combines topological analysis to determine its potential diffusion effect on surrounding areas. This results in a comprehensive quantitative assessment of the overall risk changes in the electrical system. The electrical system risk early warning includes:

[0077] Obtain the access risk effect coefficient of newly added electrical equipment. When the access risk effect coefficient is greater than or equal to the preset access risk effect threshold, conduct an electrical system risk warning; when the access risk effect coefficient is less than the preset access risk effect threshold, do not conduct an electrical system risk warning.

[0078] In this embodiment of the invention, the determination of parameters such as weighting weights and preset access risk effect thresholds can be achieved by: constructing a dataset by acquiring multiple versions of electrical drawing data, historical operation and maintenance data, and equipment attribute data; substituting these data into the dataset to calculate the drawing evolution risk factor, comprehensive risk coefficient, operation and maintenance risk coefficient, and access risk effect coefficient; simultaneously acquiring expert judgments on the drawing evolution risk of adjacent versions of electrical drawings, the operation and maintenance risk of electrical equipment, the comprehensive risk of each basic unit of the electrical system risk matrix, and the access risk effect of newly added electrical equipment; importing the calculated drawing evolution risk factor, access risk effect coefficient, and judgment results into fitting software; and outputting the weighting weights and preset access risk effect thresholds that meet the maximum judgment accuracy.

[0079] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an intelligent recognition system for electrical drawings provided in an embodiment of the present invention, including:

[0080] Data acquisition module 210 is used to acquire multiple versions of electrical drawing data and historical operation and maintenance data of electrical equipment of the target factory. The multiple versions of electrical drawing data include the current version of electrical drawings and historical versions of electrical drawings.

[0081] The drawing risk assessment module 220 is used to extract electrical features from electrical drawings based on multi-version electrical drawing data and a deep learning model, and to assess the risk of drawing evolution and the risk of drawing lag.

[0082] The risk matrix construction module 230 is used to construct the electrical system risk matrix of the target factory based on historical operation and maintenance data and combined with the risk assessment results of drawing evolution and drawing lag.

[0083] The access risk assessment module 240 is used to obtain the equipment attribute data of the newly added electrical equipment and combine it with the electrical system risk matrix to assess the risk superposition effect and risk diffusion effect after the new electrical equipment is connected.

[0084] The risk warning module 250 is used to provide early warning of electrical system risks based on the assessment results of risk superposition effect and risk diffusion effect.

[0085] In this embodiment of the invention, the drawing risk assessment module 220 is used to extract electrical features from electrical drawings based on multi-version electrical drawing data and a deep learning model, and to assess the risk of drawing evolution and the risk of drawing lag. The assessment of drawing evolution risk includes:

[0086] Based on multiple versions of electrical drawing data and combined with a deep learning model, electrical features are extracted from each version of electrical drawings. The electrical feature extraction includes drawing symbol recognition, topological relationship extraction, and equipment parameter parsing.

[0087] The electrical drawings of each version are arranged in chronological order of release time, and the difference sets of adjacent versions of electrical drawings are extracted based on the electrical feature extraction results to determine the sets of newly added equipment, deleted equipment, equipment with attribute changes, and topology relationship changes.

[0088] The drawing evolution risk factor of adjacent versions of electrical drawings is calculated based on the difference set. The drawing evolution risk factor is obtained by weighted summation of the topology difference factor, equipment change rate factor and drawing evolution cycle factor of adjacent versions of electrical drawings.

[0089] The average of the drawing evolution risk factors of all adjacent versions of electrical drawings is used as the drawing evolution risk coefficient, which is used to characterize the drawing evolution risk caused by the magnitude of change and instability of electrical drawings during version iteration.

[0090] The assessment of the risk of delayed drawings includes:

[0091] Based on the current version of the electrical drawings, extract the set of electrical features and based on historical operation and maintenance data, extract the set of all change events involving changes in the electrical system structure;

[0092] Based on the electrical feature set and change event set, identify the drawing lag change event and construct the drawing lag change event set. The drawing lag change event is a change event that occurs after the release time of the current version of the electrical drawing and is not reflected in the current version of the electrical drawing;

[0093] The ratio of the number of events in the set of delayed change events to the number of events in the set of change events is used as the drawing lag risk coefficient, which is used to characterize the drawing lag risk caused by the difference between the current version of electrical drawings and the site.

[0094] In this embodiment of the invention, the risk matrix construction module 230 is used to construct an electrical system risk matrix for the target factory based on historical operation and maintenance data and combined with the risk assessment results of drawing evolution and drawing lag, including:

[0095] Obtain historical operation and maintenance data, drawing evolution risk coefficient, and drawing lag risk coefficient for electrical equipment;

[0096] Based on historical operation and maintenance data, operation and maintenance risk factors for each electrical device are extracted and operation and maintenance risk coefficients are calculated. The operation and maintenance risk factors include failure rate factor, failure range factor and failure duration factor.

[0097] Using electrical equipment as the basic unit, the comprehensive risk coefficient of each basic unit is calculated based on the drawing evolution risk coefficient, drawing lag risk coefficient, and operation and maintenance risk coefficient.

[0098] An electrical system risk matrix is ​​constructed based on the comprehensive risk coefficient to characterize the risk distribution of the target factory's electrical system in different areas and equipment dimensions.

[0099] In this embodiment of the invention, the access risk assessment module 240 is used to acquire the equipment attribute data of the newly added electrical equipment and, in conjunction with the electrical system risk matrix, assess the risk superposition effect and risk diffusion effect after the new electrical equipment is connected, including:

[0100] Obtain the equipment attribute data of newly added electrical equipment. The equipment attribute data includes equipment type, equipment rated power, equipment voltage level, and equipment topology.

[0101] The equipment attribute data of newly added electrical equipment is mapped to access risk factors, and the risk superposition effect coefficient is determined by combining the comprehensive risk coefficient in the electrical system risk matrix.

[0102] Based on the analysis of equipment topology, the impact range of the access of new electrical equipment is analyzed and the risk diffusion effect coefficient is determined;

[0103] The risk superposition effect coefficient and the risk diffusion effect coefficient are weighted and summed to obtain the access risk effect coefficient of the new electrical equipment, which is used to characterize the impact of the access of the new electrical equipment on the overall risk distribution of the electrical system.

[0104] In this embodiment of the invention, the risk warning module 250 is used to perform electrical system risk warning based on the assessment results of risk superposition effect and risk diffusion effect, including:

[0105] Obtain the access risk effect coefficient of newly added electrical equipment. When the access risk effect coefficient is greater than or equal to the preset access risk effect threshold, conduct an electrical system risk warning; when the access risk effect coefficient is less than the preset access risk effect threshold, do not conduct an electrical system risk warning.

[0106] The parameters and steps of each unit module in the intelligent recognition system for electrical drawings of the present invention that implement the corresponding functions can be referred to the parameters and steps in the embodiments of the intelligent recognition method for electrical drawings described above, and will not be repeated here.

[0107] Please refer to Figure 3 Embodiments of the present invention also provide an electronic device 300, including a memory 310, a processor 320, and a communication bus 330; the memory 310 and the processor 320 are connected via the communication bus 330. The memory 310 stores an intelligent recognition method for electrical drawings, as provided in the above embodiments, which can be loaded and executed by the processor 320.

[0108] The memory 310 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 310 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the intelligent recognition method for electrical drawings provided in the above embodiments, etc. The data storage area may store data involved in the intelligent recognition method for electrical drawings provided in the above embodiments, etc.

[0109] Processor 320 may include one or more processing cores. Processor 320 executes instructions, programs, code sets, or instruction sets stored in memory 310, and calls data stored in memory 310 to perform various functions and process data according to the present invention. Processor 320 may be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of processor 320 may also be other types, and the embodiments of the present invention do not specifically limit this.

[0110] The communication bus 330 may include a path for transmitting information between the aforementioned components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 330 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double arrow, but this does not mean that there is only one bus or one type of bus.

[0111] This invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for the intelligent recognition method of electrical drawings.

[0112] In this embodiment of the invention, the computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), lectern random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0113] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0114] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to the technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this invention.

Claims

1. A method for intelligent recognition of electrical drawings, characterized in that, include: Acquire multiple versions of electrical drawings and historical operation and maintenance data of electrical equipment for the target factory. The multiple versions of electrical drawings include the current version of electrical drawings and historical versions of electrical drawings. Based on multiple versions of electrical drawing data and deep learning models, electrical features are extracted from electrical drawings to assess the risks of drawing evolution and drawing lag. Based on historical operation and maintenance data and combined with the risk assessment results of drawing evolution and drawing lag, an electrical system risk matrix for the target factory is constructed. Obtain the equipment attribute data of newly added electrical equipment and combine it with the electrical system risk matrix to assess the risk superposition effect and risk diffusion effect after the new electrical equipment is connected; Electrical system risk early warning is based on the assessment results of risk superposition and risk diffusion effects. Assess the risks associated with the evolution of the drawings, including: Based on multiple versions of electrical drawing data and combined with a deep learning model, electrical features are extracted from each version of electrical drawings. The electrical feature extraction includes drawing symbol recognition, topological relationship extraction, and equipment parameter parsing. The electrical drawings of each version are arranged in chronological order of release time, and the difference sets of adjacent versions of electrical drawings are extracted based on the electrical feature extraction results to determine the sets of newly added equipment, deleted equipment, equipment with attribute changes, and topology relationship changes. The drawing evolution risk factor of adjacent versions of electrical drawings is calculated based on the difference set. The drawing evolution risk factor is obtained by weighted summation of the topology difference factor, equipment change rate factor and drawing evolution cycle factor of adjacent versions of electrical drawings. The average of the drawing evolution risk factors of all adjacent versions of electrical drawings is used as the drawing evolution risk coefficient, which is used to characterize the drawing evolution risk caused by the magnitude of change and instability of electrical drawings during version iteration.

2. The intelligent recognition method for electrical drawings according to claim 1, characterized in that, Assess the risk of delays in the drawings, including: Based on the current version of the electrical drawings, extract the set of electrical features and based on historical operation and maintenance data, extract the set of all change events involving changes in the electrical system structure; Based on the electrical feature set and change event set, identify the drawing lag change event and construct the drawing lag change event set. The drawing lag change event is a change event that occurs after the release time of the current version of the electrical drawing and is not reflected in the current version of the electrical drawing; The ratio of the number of events in the set of delayed change events to the number of events in the set of change events is used as the drawing lag risk coefficient, which is used to characterize the drawing lag risk caused by the difference between the current version of the electrical drawings and the site.

3. The intelligent recognition method for electrical drawings according to claim 1, characterized in that, The construction of the electrical system risk matrix for the target factory includes: Obtain historical operation and maintenance data, drawing evolution risk coefficient, and drawing lag risk coefficient for electrical equipment; Based on historical operation and maintenance data, operation and maintenance risk factors for each electrical device are extracted and operation and maintenance risk coefficients are calculated. The operation and maintenance risk factors include failure rate factor, failure range factor and failure duration factor. Using electrical equipment as the basic unit, the comprehensive risk coefficient of each basic unit is calculated based on the drawing evolution risk coefficient, drawing lag risk coefficient, and operation and maintenance risk coefficient. An electrical system risk matrix is ​​constructed based on the comprehensive risk coefficient to characterize the risk distribution of the target factory's electrical system in different areas and equipment dimensions.

4. The intelligent recognition method for electrical drawings according to claim 1, characterized in that, The assessment of the risk superposition and risk diffusion effects after the addition of new electrical equipment includes: Obtain the equipment attribute data of newly added electrical equipment. The equipment attribute data includes equipment type, equipment rated power, equipment voltage level, and equipment topology. The equipment attribute data of newly added electrical equipment is mapped to access risk factors, and the risk superposition effect coefficient is determined by combining the comprehensive risk coefficient in the electrical system risk matrix. Based on the analysis of equipment topology, the impact range of the access of new electrical equipment is analyzed and the risk diffusion effect coefficient is determined; The risk superposition effect coefficient and the risk diffusion effect coefficient are weighted and summed to obtain the access risk effect coefficient of the new electrical equipment, which is used to characterize the impact of the access of the new electrical equipment on the overall risk distribution of the electrical system.

5. The intelligent recognition method for electrical drawings according to claim 1, characterized in that, The aforementioned electrical system risk warning includes: Obtain the access risk effect coefficient of newly added electrical equipment. When the access risk effect coefficient is greater than or equal to the preset access risk effect threshold, conduct an electrical system risk warning; when the access risk effect coefficient is less than the preset access risk effect threshold, do not conduct an electrical system risk warning.

6. An intelligent recognition system for electrical drawings, used to implement the intelligent recognition method for electrical drawings as described in any one of claims 1-5, characterized in that, The system includes: The data acquisition module is used to acquire multiple versions of electrical drawings data and historical operation and maintenance data of electrical equipment from the target factory. The multiple versions of electrical drawings data include the current version of electrical drawings and historical versions of electrical drawings. The drawing risk assessment module is used to extract electrical features from electrical drawings based on multi-version electrical drawing data and deep learning models, and to assess the risks of drawing evolution and drawing lag. The risk matrix construction module is used to construct the electrical system risk matrix of the target factory based on historical operation and maintenance data and combined with the risk assessment results of drawing evolution and drawing lag. The access risk assessment module is used to obtain the equipment attribute data of the newly added electrical equipment and combine it with the electrical system risk matrix to assess the risk superposition effect and risk diffusion effect after the new electrical equipment is connected. The risk warning module is used to provide early warnings of electrical system risks based on the assessment results of risk superposition and risk diffusion effects.

7. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the intelligent recognition method for electrical drawings as described in any one of claims 1-5 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that, The device stores instructions that, when executed on a computer, cause the computer to perform the intelligent recognition method for electrical drawings as described in any one of claims 1-5.

Images