Structural stress and strain analysis method and device based on artificial intelligence

Abstract

The present invention discloses a structural stress and strain analysis method and device based on artificial intelligence. The method includes: receiving input stress sensing information, structural drawings and monitoring images and extracting corresponding basic feature information; extracting corresponding comparative feature information from a three-dimensional structural model; judging whether the basic feature information and the comparative feature information match according to preset matching judgment rules; if they do not match, inputting the basic feature information and the comparative feature information into a preset artificial intelligence model for correlation analysis to obtain corresponding correlation analysis results; and obtaining strain measures corresponding to the correlation analysis results from a preset stress and strain database. During the structural construction process, the above method can combine actual working conditions and analyze structural deformation during the construction process through artificial intelligence to obtain strain measures and adjust the construction structure, and can efficiently perform structural stress and strain analysis when the building structure is deformed.

Description

Technical Field

[0001] The present invention relates to the field of intelligent analysis technology, and in particular to a structural stress and strain analysis method and device based on artificial intelligence. Background Art

[0002] Long-span construction projects often involve arching of the structure to improve its reliability when stress and strain later in the construction process pose a threat to the structural safety. During the construction of long-span or cantilevered structures, arching values ​​are set for the structure or components. In complex structures, sensor plates are installed during construction to detect stress and strain in the structure, allowing for real-time monitoring of structural changes.

[0003] When cantilever or large-span structures are constructed using traditional methods, significant deformation occurs after the structure is completed, making it difficult to change the structure in a timely manner. At this point, some of the arching value has been damaged, or the structure has already deformed, which has a certain impact on the later service life of the building structure. In the existing technology, the construction plan is determined through prescribed processes and solidified experience such as feasibility discussions, pilot experiments, monitoring and certification, expert demonstration, and design supervision confirmation. The changes in cantilever or large-span structures are monitored through arching or real-time detection. However, it is impossible to conduct timely and effective structural stress and strain analysis to make local structural adjustments. Therefore, the existing technical methods have the problem of being unable to efficiently perform structural stress and strain analysis when the building structure is deformed. Summary of the Invention

[0004] In order to overcome the shortcomings of existing technical solutions, the embodiments of the present invention provide a structural stress and strain analysis method and device based on artificial intelligence, aiming to solve the problem in the existing technology that structural stress and strain analysis cannot be efficiently performed when the building structure is deformed.

[0005] The technical solution adopted by the present invention to solve its technical problem is:

[0006] In a first aspect, an embodiment of the present invention provides a structural stress and strain analysis method based on artificial intelligence, the method comprising:

[0007] If the input stress sensing information, structural drawings and monitoring images are received, the corresponding basic feature information is extracted according to the preset stress feature extraction rules;

[0008] Extracting corresponding contrast feature information from a preset three-dimensional structure model;

[0009] Determining whether the basic feature information matches the comparison feature information according to a preset matching judgment rule;

[0010] If there is no match, the basic feature information and the comparative feature information are input into a preset artificial intelligence model for correlation analysis to obtain a corresponding correlation analysis result;

[0011] The strain measures corresponding to the correlation analysis results are obtained from a preset stress-strain database.

[0012] In a second aspect, an embodiment of the present invention further provides a structural stress and strain analysis device based on artificial intelligence, the device comprising:

[0013] A basic feature information acquisition unit is configured to extract corresponding basic feature information according to preset stress feature extraction rules upon receiving input stress sensing information, structural drawings, and monitoring images;

[0014] A contrast feature information acquisition unit, configured to extract corresponding contrast feature information from a preset three-dimensional structure model;

[0015] a matching judgment unit, configured to judge whether the basic feature information matches the comparison feature information according to a preset matching judgment rule;

[0016] an association analysis result acquisition unit, configured to input the basic feature information and the comparative feature information into a preset artificial intelligence model for association analysis if there is no match, and obtain a corresponding association analysis result;

[0017] The strain measure acquisition unit is used to acquire the strain measure corresponding to the correlation analysis result from a preset stress-strain database.

[0018] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a processor, a network interface, a memory, and a communication bus, wherein the processor, the network interface, and the memory communicate with each other via the communication bus;

[0019] Memory for storing computer programs;

[0020] The processor is configured to implement any of the steps of the artificial intelligence-based structural stress and strain analysis method described above when executing the program stored in the memory.

[0021] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned artificial intelligence-based structural stress and strain analysis methods.

[0022] The specific embodiment of the present invention discloses a structural stress and strain analysis method and device based on artificial intelligence, which includes: receiving input stress sensing information, structural drawings and monitoring images and extracting corresponding basic feature information; extracting corresponding comparative feature information from a three-dimensional structural model; judging whether the basic feature information and the comparative feature information match according to preset matching judgment rules; if they do not match, inputting the basic feature information and the comparative feature information into a preset artificial intelligence model for correlation analysis to obtain corresponding correlation analysis results; and obtaining strain measures corresponding to the correlation analysis results from a preset stress and strain database. During the structural construction process, the above method can combine actual working conditions and analyze the structural deformation during the construction process through artificial intelligence to obtain strain measures and adjust the construction structure, and can efficiently perform structural stress and strain analysis when the building structure is deformed. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 is a method flow chart of a structural stress and strain analysis method based on artificial intelligence provided by an embodiment of the present invention;

[0025] Figure 2 is a schematic block diagram of an artificial intelligence-based structural stress and strain analysis device provided by an embodiment of the present invention;

[0026] Figure 3 is a schematic block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0029] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0030] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] An embodiment of the present invention provides an artificial intelligence-based structural stress and strain analysis method, which is applied to a terminal device or server, and the terminal device or server executes a stored software program to implement the above-mentioned artificial intelligence-based structural stress and strain analysis method.

[0032] like Figure 1 As shown, the method includes steps S110 to S150.

[0033] S110 : If input stress sensing information, structural drawings, and monitoring images are received, corresponding basic feature information is extracted according to preset stress feature extraction rules.

[0034] Users (project managers) can input stress sensing information, structural drawings, and monitoring images. Stress sensing information is information detected by stress-sensing sensors installed on the physical building structure. The sensors can sense the stress values ​​generated by gravity compression in the local area of ​​the building structure. The resulting stress sensing information includes stress values ​​corresponding to multiple points in the building structure. Structural drawings are drawings produced through scanning and surveying during or after construction. Monitoring images are images of the building structure captured by image acquisition devices installed on the side of the building structure. Multiple image acquisition devices can be installed around the building structure to capture corresponding monitoring images, with each monitoring image captured corresponding to one image acquisition device. Based on stress feature extraction rules, corresponding basic feature information can be extracted from the stress sensing information, structural drawings, and monitoring images. This basic feature information can be used to reflect the structural characteristics of the physical building structure at a specific point in time.

[0035] In a specific embodiment, step S110 includes sub-steps: normalizing the stress sensing information according to the normalization formula in the stress feature extraction rule to obtain corresponding normalized feature information; extracting corresponding structural contour information from the structural drawings and monitoring images according to the contour extraction parameters in the stress feature extraction rule; and combining the normalized feature information with the structural contour information to obtain corresponding basic feature information.

[0036] The stress values ​​contained in the stress sensing information are normalized according to the normalization formula in the stress feature extraction rule. Each stress value corresponds to a normalized value. The value range of the obtained normalized value is [0, 1]. The obtained normalized value can be used as normalized feature information.

[0037] Furthermore, structural contour information is extracted from structural drawings and monitoring images according to contour extraction parameters. Structural drawings are drawings obtained by scanning and mapping the building structure from a specific angle. The structural drawings may include a front view, a left view, and a top view. Corresponding contour information can be extracted from the structural drawings according to the pixel color parameters set in the contour extraction parameters. The structural drawings include black solid lines, hidden light lines, dimension notes, and other information. Since the contour information only needs to obtain the external physical contour of the building structure, the pixel color parameters can be set to black. Black solid lines can be extracted from the structural drawings as corresponding contour information according to the pixel color parameters.

[0038] Corresponding contour information is extracted from the monitoring image based on contour extraction parameters, which also include a dissolution ratio parameter. To extract contour information from the monitoring image, the pixel contrast of each pixel in the monitoring image is calculated. The pixel contrast of a pixel is the difference between that pixel and its surrounding pixels. The greater the difference in pixel value between a pixel and its surrounding pixels, the greater the pixel contrast. After calculating the pixel contrast of each pixel in the monitoring image, the pixels are sorted from highest to lowest based on pixel contrast. A portion of the pixels from this sorted pixel is intercepted based on the dissolution ratio parameter. These intercepted pixels are then combined to obtain the corresponding contour information.

[0039] Two sets of contour information are extracted from the structural drawings and the monitoring images respectively, which can be combined into the corresponding structural contour information; the basic feature information can be obtained by combining the normalized feature information with the structural contour information.

[0040] S120: extracting corresponding contrast feature information from a preset three-dimensional structure model.

[0041] Comparative feature information can be extracted from a pre-set 3D structural model, which is a virtual model (Building Information Modeling, BIM) generated based on the building's design plan. The comparative feature information extracted from the 3D structural model can then be used to reflect the structural characteristics of the building's design plan.

[0042] In a specific embodiment, step S120 includes sub-steps: performing local stress calculation on the three-dimensional structural model to obtain corresponding stress calculation information; cutting the three-dimensional structural model according to a preset section to obtain a cutting contour image corresponding to the cutting plane; positioning monitoring the three-dimensional structural model according to preset monitoring points to obtain a monitoring contour image corresponding to each of the monitoring points; normalizing the stress calculation information according to a preset normalization formula to obtain corresponding stress calculation feature information; combining the stress calculation feature information with the cutting contour image and the monitoring contour image to obtain corresponding contrast feature information.

[0043] Specifically, local stress calculations can be performed on the three-dimensional structural model, and the physical connection structure can be simulated according to the material and connection relationship of each component in the three-dimensional structural model. Mechanical analysis and calculations can be performed based on the simulated physical connection structure, so that the stress calculation values ​​of the corresponding calculation points can be determined. The stress calculation values ​​of each calculation point can be obtained and combined to obtain the corresponding stress calculation information.

[0044] The three-dimensional structure model is sectioned according to a preset section, and each sectioning can correspond to a sectioning plane, and the virtual structure contour of the sectioning plane can be obtained to obtain a sectioning contour image.

[0045] The 3D structural model is further positioned and monitored based on pre-set monitoring points. These monitoring points are virtual coordinate points in the 3D space where the 3D structural model resides, corresponding to the orientation of the image acquisition device. Each image acquisition device can determine a corresponding virtual coordinate point in the 3D space. Positioning and monitoring the 3D structural model using the monitoring points, in the same orientation as the image acquisition device, is equivalent to capturing the contour of the 3D structural model in 3D space, thereby obtaining a corresponding monitoring contour image.

[0046] Similarly, the stress calculation values ​​at each calculation point can be normalized according to the above normalization formula to obtain the corresponding stress calculation feature information. The obtained stress calculation feature information can be combined with the section contour image and the monitoring contour image to obtain the corresponding comparative feature information.

[0047] In a specific embodiment, before the stress trial calculation information is normalized according to a preset normalization formula to obtain the corresponding stress trial calculation characteristic information, it also includes: obtaining a target trial calculation value in the stress trial calculation information corresponding to the standard value in a pre-stored standard data table; judging whether each of the target trial calculation values ​​matches the corresponding standard value in the standard data table; if each of the target trial calculation values ​​matches the corresponding standard value, executing the step of normalizing the stress trial calculation information according to the preset normalization formula; if any of the target trial calculation values ​​does not match the corresponding standard value, generating an alarm prompt information.

[0048] Before normalizing the stress trial calculation information, the stress trial calculation values ​​corresponding to the respective standard values ​​in the standard data table can be obtained from the stress trial calculation information as target trial calculation values. Thus, a stress trial value corresponding to each standard value can be obtained as the corresponding target trial calculation value. Further, it is determined whether each target trial calculation value matches the corresponding standard value. The standard value can be a numerical interval, which is used to limit the corresponding trial calculation value to a reasonable interval based on the mechanical standard. It is then determined whether the target trial value is within the numerical interval corresponding to the standard value. If the target trial value is within the numerical interval corresponding to the standard value, it is determined that the target trial value matches the standard value; otherwise, it is determined that the target trial value does not match the standard value.

[0049] If all target trial values ​​match the corresponding standard values, the subsequent steps are continued. If any target trial value does not match the corresponding standard value, an alarm prompt message is generated.

[0050] S130: Determine whether the basic feature information matches the comparison feature information according to a preset matching judgment rule.

[0051] It is further possible to determine whether the basic feature information matches the comparison feature information based on the matching judgment rules.

[0052] In a specific embodiment, step S130 includes sub-steps: obtaining characteristic difference values ​​between the normalized characteristic information in the basic characteristic information and the stress calculation characteristic information in the comparative characteristic information; judging whether each of the characteristic difference values ​​is within the difference interval set in the matching judgment rule; obtaining the size deviation value between the structural contour information in the basic characteristic information and the section contour image and the monitoring contour image in the comparative characteristic information; judging whether each of the size deviation values ​​is within the deviation interval set in the matching judgment rule; if the characteristic difference values ​​are all within the difference interval and the size deviation values ​​are all within the deviation interval, it is judged that the basic characteristic information matches the comparative characteristic information; if any of the characteristic difference values ​​is not within the difference interval or any of the size deviation values ​​is not within the deviation interval, it is judged that the basic characteristic information does not match the comparative characteristic information.

[0053] The normalized feature information in the basic feature information contains multiple normalized values. The stress calculation feature information in the comparison feature information also contains multiple normalized values. The feature difference is obtained by subtracting the two normalized values ​​of the same item in the normalized feature information and the stress calculation feature information and calculating the absolute value. The obtained feature difference is determined to see if it falls within the difference range specified in the matching judgment rule.

[0054] Furthermore, the dimensional deviation values ​​between the structural contour information and the cut contour image and the monitoring contour image are obtained. A contour image corresponding to each contour information in the structural contour information can be obtained from the cut contour image and the monitoring contour image as a comparison contour image. The line length difference and line angle difference between the contour information and the comparison contour image are obtained as the corresponding dimensional deviation value. A determination is then made as to whether the dimensional deviation value is within the deviation range.

[0055] If the feature difference values ​​are all within the difference interval and the size deviation values ​​are all within the deviation interval, then it is determined that the basic feature information matches the comparison feature information; otherwise, it is determined that the basic feature information does not match the comparison feature information.

[0056] S140: If there is no match, the basic feature information and the comparative feature information are input into a preset artificial intelligence model for association analysis to obtain a corresponding association analysis result.

[0057] If a match is found, the subsequent steps for obtaining strain measures are skipped; the above steps are repeated after the stress sensing information, structural drawings, and monitoring images are input again. If a match is not found, the basic feature information and the comparison feature information are input into a pre-set artificial intelligence model, which performs a correlation analysis on the two sets of input feature information to obtain the correlation analysis results.

[0058] In a specific embodiment, step S140 includes sub-steps: obtaining difference information between the basic feature information and the comparative feature information; combining the difference information with the comparative feature information and inputting them into the artificial intelligence model for association analysis to obtain corresponding association analysis results.

[0059] Specifically, the difference information between the basic feature information and the comparison feature information can be obtained. Using the comparison feature information as a reference, the difference between each value in the basic feature information and the value in the comparison feature information is obtained to obtain the corresponding difference information. If the difference of a value in the difference information is greater than zero, it indicates that the value in the basic feature information exceeds the corresponding value in the comparison feature information; if the difference of a value in the difference information is less than zero, it indicates that the value in the basic feature information is less than the corresponding value in the comparison feature information; if the difference of a value in the difference information is zero, it indicates that the two values ​​in the basic feature information and the comparison feature information are equal.

[0060] The obtained difference information and contrast feature information are combined to obtain a combined feature, which is then input into an artificial intelligence model for association analysis. The number of difference values ​​in the difference information is equal to the number of numerical values ​​contained in the contrast feature information. Specifically, the artificial intelligence model is a neural network model constructed based on artificial intelligence. The artificial intelligence model includes an input layer, an association analysis layer, and an output layer. The input layer includes multiple input nodes, and the number of input nodes contained in the input layer is twice the number of numerical values ​​in the contrast feature information. The association analysis layer includes one or more groups of association nodes, one group of association nodes is arranged vertically, and multiple groups of association nodes are arranged in a multi-column distribution. The association nodes establish corresponding association formulas with input nodes, output nodes, or other association nodes in an adjacent group of association nodes. The association formulas are configured with corresponding coefficient values; the association formulas can then establish an association relationship between the two nodes. The output layer includes multiple output nodes, one of which corresponds to an output difference coefficient, and the other output nodes each correspond to a difference type.

[0061] After inputting the combined features into the input node of the artificial intelligence model, the corresponding node value can be obtained from the output node. The output node corresponding to the difference coefficient can correspond to the output coefficient value; the output node corresponding to the difference type can correspond to the output matching value, and the difference type with the highest matching value is obtained as the difference type that matches the input feature. The matching difference type is combined with the coefficient value to obtain the corresponding association analysis result.

[0062] S150: Acquire strain measures corresponding to the correlation analysis results from a preset stress-strain database.

[0063] The stress-strain database contains strain measures corresponding to different deformation scenarios. Based on the correlation analysis results, matching strain measures can be retrieved from the stress-strain database. The resulting strain measures can be used to adjust the building structure accordingly. Local structural adjustments can be made using these strain measures to correct stress hazards caused by local deformation.

[0064] In a specific embodiment, step S150 includes sub-steps: obtaining the strain type corresponding to the association analysis result in the stress-strain database; obtaining strain adjustment information corresponding to the association analysis result according to the strain adjustment rule corresponding to the strain type in the stress-strain database; and combining the strain type and the strain adjustment information into a strain measure corresponding to the association analysis result.

[0065] The stress-strain database contains multiple strain types, each corresponding to a difference type. Examples of strain types in the stress-strain database include increasing the structural arch value, setting up local supports, using hydraulic devices (such as jacks) for top-down support, changing the rebar laying conditions (adjusting rebar diameter and spacing), and demolishing and reconstructing. The difference type in the association analysis results can be matched with the strain type to obtain the strain type that matches the difference type.

[0066] The stress-strain database also includes strain adjustment rules corresponding to each strain type. Different strain types have different strain adjustment rules. Based on the strain adjustment rule for the currently matched strain type, strain adjustment information corresponding to the coefficient value in the association analysis results can be obtained. For example, if the coefficient value in the association analysis result is 0.6, the strain type is increased structural camber, and the strain adjustment rule corresponding to this strain type has a coefficient range of [0.5, 0.75] that matches this coefficient value, then the strain adjustment information corresponding to this coefficient range is 200 kN. Therefore, 200 kN is determined to be the strain adjustment information that matches this strain type.

[0067] By combining the obtained strain types and strain adjustment information, the strain measures corresponding to the correlation analysis results can be obtained.

[0068] The artificial intelligence-based structural stress and strain analysis method and device disclosed in the above embodiments include: receiving input stress sensing information, structural drawings, and monitoring images and extracting corresponding basic feature information; extracting corresponding comparative feature information from a three-dimensional structural model; judging whether the basic feature information and the comparative feature information match according to preset matching judgment rules; if they do not match, inputting the basic feature information and the comparative feature information into a preset artificial intelligence model for correlation analysis to obtain corresponding correlation analysis results; and obtaining strain measures corresponding to the correlation analysis results from a preset stress and strain database. During the structural construction process, the above method can combine actual working conditions and analyze structural deformation during construction through artificial intelligence to obtain strain measures and adjust the construction structure, and can efficiently perform structural stress and strain analysis when the building structure is deformed.

[0069] The present invention also provides an artificial intelligence-based structural stress and strain analysis device, which can be configured in a terminal device or a server. The artificial intelligence-based structural stress and strain analysis device is used to perform any embodiment of the artificial intelligence-based structural stress and strain analysis method. Figure 2 , Figure 2 A schematic block diagram of an artificial intelligence-based structural stress and strain analysis device provided in an embodiment of the present invention.

[0070] like Figure 2 As shown, the artificial intelligence-based structural stress and strain analysis device 100 includes a basic feature information acquisition unit 110, a comparison feature information acquisition unit 120, a matching judgment unit 130, a correlation analysis result acquisition unit 140 and a strain measure acquisition unit 150.

[0071] The basic feature information acquisition unit 110 is configured to extract corresponding basic feature information according to preset stress feature extraction rules upon receiving input stress sensing information, structural drawings, and monitoring images.

[0072] The contrast feature information acquisition unit 120 is configured to extract corresponding contrast feature information from a preset three-dimensional structure model.

[0073] The matching judgment unit 130 is configured to judge whether the basic feature information matches the comparison feature information according to a preset matching judgment rule.

[0074] The association analysis result acquisition unit 140 is used to input the basic feature information and the comparative feature information into a preset artificial intelligence model for association analysis if there is no match, so as to obtain a corresponding association analysis result.

[0075] The strain measure acquisition unit 150 is configured to acquire strain measures corresponding to the correlation analysis result from a preset stress-strain database.

[0076] The artificial intelligence-based structural stress and strain analysis device provided in the embodiment of the present invention applies the artificial intelligence-based structural stress and strain analysis method described above, receives input stress sensing information, structural drawings, and monitoring images, and extracts corresponding basic feature information; extracts corresponding comparative feature information from the three-dimensional structural model; determines whether the basic feature information and the comparative feature information match according to preset matching judgment rules; if they do not match, inputs the basic feature information and the comparative feature information into a preset artificial intelligence model for correlation analysis to obtain corresponding correlation analysis results; and obtains strain measures corresponding to the correlation analysis results from a preset stress and strain database. During the structural construction process, the above method can combine actual working conditions and analyze structural deformation during the construction process through artificial intelligence to obtain strain measures and adjust the construction structure, and can efficiently perform structural stress and strain analysis when the building structure is deformed.

[0077] The above-mentioned artificial intelligence-based structural stress and strain analysis device can be implemented in the form of a computer program. The computer program can be used in Figure 3 Runs on the computer device shown.

[0078] See also Figure 3 , Figure 3 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device may be a terminal device or a server for executing an artificial intelligence-based structural stress and strain analysis method to perform stress and strain analysis on a building structure.

[0079] See Figure 3 The computer device 500 includes a processor 502 , a memory, and a network interface 505 connected via a communication bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0080] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the artificial intelligence-based structural stress and strain analysis method. The storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0081] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0082] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the structural stress and strain analysis method based on artificial intelligence.

[0083] The network interface 505 is used for network communication, such as providing data information transmission. Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0084] The processor 502 is configured to run a computer program 5032 stored in the memory to implement corresponding functions in the aforementioned artificial intelligence-based structural stress and strain analysis method.

[0085] Those skilled in the art will understand that Figure 3 The embodiment of the computer device shown in the figure does not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and processor are the same as those in the figure. Figure 3 The embodiments shown are consistent and will not be described again here.

[0086] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0087] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be volatile or non-volatile. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps included in the aforementioned artificial intelligence-based structural stress and strain analysis method.

[0088] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0089] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, or units with the same function may be combined into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0090] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.

[0091] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0093] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A structural stress and strain analysis method based on artificial intelligence, characterized in that: The method comprises: If the input stress sensing information, structural drawings and monitoring images are received, the corresponding basic feature information is extracted according to the preset stress feature extraction rules; Extracting corresponding contrast feature information from a preset three-dimensional structure model; Determining whether the basic feature information matches the comparison feature information according to a preset matching judgment rule; If there is no match, the basic feature information and the comparative feature information are input into a preset artificial intelligence model for correlation analysis to obtain a corresponding correlation analysis result; The strain measures corresponding to the correlation analysis results are obtained from a preset stress-strain database.

2. The artificial intelligence-based structural stress and strain analysis method according to claim 1, characterized in that: If the input stress sensing information, structural drawings and monitoring images are received, corresponding basic feature information is extracted according to preset stress feature extraction rules, including: Normalizing the stress sensing information according to the normalization formula in the stress feature extraction rule to obtain corresponding normalized feature information; Extracting corresponding structural contour information from the structural drawings and monitoring images according to the contour extraction parameters in the stress feature extraction rule; The normalized feature information is combined with the structural profile information to obtain corresponding basic feature information.

3. The artificial intelligence-based structural stress and strain analysis method according to claim 1, characterized in that: The step of extracting corresponding contrast feature information from the preset three-dimensional structure model includes: Performing local stress calculation on the three-dimensional structural model to obtain corresponding stress calculation information; Cutting the three-dimensional structure model according to a preset section plane to obtain a cutting contour image corresponding to the cutting plane; Positioning and monitoring the three-dimensional structure model according to preset monitoring points to obtain a monitoring contour image corresponding to each monitoring point; Normalizing the stress calculation information according to a preset normalization formula to obtain corresponding stress calculation characteristic information; The stress calculation feature information is combined with the section contour image and the monitoring contour image to obtain corresponding comparison feature information.

4. The artificial intelligence-based structural stress and strain analysis method according to claim 3, characterized in that: Before normalizing the stress trial calculation information according to a preset normalization formula to obtain corresponding stress trial calculation characteristic information, the method further includes: Obtaining a target calculation value in the stress calculation information corresponding to a standard value in a pre-stored standard data table; Determining whether each of the target trial values ​​matches the corresponding standard value in the standard data table; If all the target trial calculation values ​​match the corresponding standard values, performing the step of normalizing the stress trial calculation information according to a preset normalization formula; If any of the target trial calculated values ​​does not match the corresponding standard value, an alarm prompt message is generated.

5. The artificial intelligence-based structural stress and strain analysis method according to claim 1, characterized in that: The determining whether the basic feature information matches the comparison feature information according to a preset matching judgment rule includes: Obtaining a characteristic difference between the normalized characteristic information in the basic characteristic information and the stress calculation characteristic information in the comparative characteristic information; Determining whether each of the feature differences is within the difference interval set in the matching judgment rule; Obtaining a size deviation value between the structural contour information in the basic feature information and the cut contour image and the monitoring contour image in the comparison feature information; Determining whether each of the size deviation values ​​is within the deviation interval set in the matching judgment rule; If the feature difference values ​​are both within the difference range and the size deviation values ​​are both within the deviation range, it is determined that the basic feature information matches the comparison feature information; If any of the feature difference values ​​is not within the difference range or any of the size deviation values ​​is not within the deviation range, it is determined that the basic feature information does not match the comparison feature information.

6. The artificial intelligence-based structural stress and strain analysis method according to claim 1 or 5, characterized in that: The inputting the basic feature information and the comparative feature information into a preset artificial intelligence model for association analysis to obtain corresponding association analysis results includes: Obtaining difference information between the basic feature information and the comparison feature information; The difference information is combined with the contrast feature information and input into the artificial intelligence model for association analysis to obtain corresponding association analysis results.

7. The artificial intelligence-based structural stress and strain analysis method according to claim 1, characterized in that: The obtaining of strain measures corresponding to the correlation analysis results from a preset stress-strain database includes: Obtaining the strain type corresponding to the correlation analysis result in the stress-strain database; acquiring strain adjustment information corresponding to the association analysis result according to the strain adjustment rule corresponding to the strain type in the stress-strain database; The strain type and the strain adjustment information are combined into a strain measure corresponding to the association analysis result.

8. A structural stress and strain analysis device based on artificial intelligence, characterized in that: The device comprises: A basic feature information acquisition unit is configured to extract corresponding basic feature information according to preset stress feature extraction rules upon receiving input stress sensing information, structural drawings, and monitoring images; A contrast feature information acquisition unit, configured to extract corresponding contrast feature information from a preset three-dimensional structure model; a matching judgment unit, configured to judge whether the basic feature information matches the comparison feature information according to a preset matching judgment rule; an association analysis result acquisition unit, configured to input the basic feature information and the comparative feature information into a preset artificial intelligence model for association analysis if there is no match, and obtain a corresponding association analysis result; The strain measure acquisition unit is used to acquire the strain measure corresponding to the correlation analysis result from a preset stress-strain database.

9. A computer device, characterized in that: The device includes a processor, a network interface, a memory and a communication bus, wherein the processor, the network interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; The processor is configured to implement the steps of the artificial intelligence-based structural stress and strain analysis method according to any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the artificial intelligence-based structural stress and strain analysis method according to any one of claims 1 to 7 are implemented.

Images