Multi-span beam rapid modeling method and equipment based on machine vision

Abstract

The invention provides a multi-span beam rapid modeling method and equipment based on machine vision, and the method comprises a model training module which is used for building a multi-span beam structure information recognition model based on an annotation sketch; and inputting the multi-span beam structure sketch to be identified into the multi-span beam structure information identification model, and outputting a multi-span beam structure modeling information file including beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material attribute information. The method can solve the problems that the modeling process of the multi-span beam structure is tedious and consumes long time, modeling information of the multi-span beam structure can be rapidly extracted and a standard modeling information file can be output by manually drawing a sketch diagram of the multi-span beam structure, professional calculation software such as a structural mechanics solver can be imported through an interface, a calculation model of the multi-span beam structure can be rapidly established, and the modeling efficiency of the multi-span beam structure is improved. The problems of complex modeling process and long calculation time of traditional finite element software and other professional software calculation are solved, and the calculation and modeling efficiency is improved.

Description

Technical Field

[0001] The invention relates to a machine vision-based multi-span beam rapid modeling method and equipment. Background Art

[0002] The force calculation of multi-span beam structures is used in many engineering fields such as building structures, bridge engineering, road engineering, etc. It has a wide range of applications and a large demand for calculations.

[0003] Existing calculations often require the use of special computing software such as finite element software or structural mechanics solvers. The finite element software modeling process is complex and has high technical requirements for operators; structural mechanics solver calculations require manual input of multiple parameters such as nodes, units, loads, boundary conditions, etc., which is inefficient and time-consuming. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for rapid modeling of multi-span beams based on machine vision.

[0005] To solve the above problems, the present invention provides a method for rapid modeling of multi-span beams based on machine vision, comprising:

[0006] Step S1, training information collection and processing module, collecting sample multi-span beam structure schematics containing different working conditions, and collecting beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information therein, and marking each information at a corresponding position on the corresponding multi-span beam structure schematic to obtain a marked schematic;

[0007] Step S2, a model training module, based on the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information annotated in the annotated diagram, uses an artificial intelligence method to establish a multi-span beam structure information recognition model;

[0008] Step S3, inputting the multi-span beam structure schematic to be identified into the multi-span beam structure information identification model, the multi-span beam structure information identification model identifies the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information in the multi-span beam structure schematic to be identified, and outputs a multi-span beam structure modeling information file containing the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information.

[0009] Furthermore, in the above method, in step S1, the node information includes: the number of nodes and the node number, wherein the number of nodes is n, and the nodes are numbered and labeled from left to right starting from the left side of the sample multi-span beam structure schematic; wherein a beam is called a beam unit, the beam units are connected end to end, and the two ends of each beam unit are beam nodes.

[0010] Furthermore, in the above method, in step S1, the beam unit information beam includes: unit quantity, unit number and unit length; wherein each beam unit corresponds to a unit length data L1~L n-1 , the unit length is in mm; the number of units is the number of nodes - 1, and the units are numbered from left to right starting from the left side of the sample multi-span beam structure diagram, and there is a beam unit between two beam nodes.

[0011] Furthermore, in the above method, in step S1, the beam node boundary condition information includes: the support types under beam node 1 and beam node n, wherein the support types include: hinged support JZ, fixed support GZ and directional support DX, a total of 3 types; the hinged support constrains the horizontal displacement and vertical displacement of the beam node thereon; the fixed support constrains the horizontal displacement, vertical displacement and rotation angle of the beam node thereon, and the directional support constrains the horizontal displacement and rotation angle of the node; in the sample multi-span beam structure schematic, the beam nodes other than the head and tail are hinged supports by default.

[0012] Furthermore, in the above method, in step S1, the beam unit load condition information includes: load quantity, load number, load type, load value, and load position; wherein the load quantity is consistent with the number of beam units, which is n-1, and the loads are numbered and marked from left to right starting from the left side of the sample multi-span beam structure schematic; the load type, load value, and load position are marked.

[0013] Furthermore, in the above method, the load types include: concentrated force Q F , concentrated bending moment Q M He Junbuli Q JB There are 3 types in total;

[0014] Load value Q unit: concentrated force Q F The load value is in kN, and the concentrated bending moment Q M The load value unit is kN·m, and the uniform force Q JB The load value unit is kN / m; each beam element corresponds to a load value;

[0015] Concentration Q F and concentrated bending moment Q M The load position is: concentrated force Q F and concentrated bending moment Q M The ratio S of the distance between the load action point and the left node of the unit and the unit length; the uniform force Q JB The load position is: the ratio of the distance from the starting point of the uniform force to the beam node at the left end of the unit to the unit length S1 and the ratio of the distance from the end point of the uniform force to the beam node at the right end of the unit to the unit length S2; where the concentrated force Q F and concentrated bending moment QM The load distance is the concentrated force Q F and concentrated bending moment Q M The load distance of uniform force is the distance from the starting point of uniform force to the beam node at the left end of the unit, or the distance from the end point of uniform force to the beam node at the right end of the unit.

[0016] When there is no load on a beam element, the load type is selected as concentrated force Q F , load value Q is 0, and load position S is 0.

[0017] Furthermore, in the above method, in step S1, the material property information includes: beam elastic modulus E, in units of MPa, beam section resistance moment I, in units of mm4.

[0018] Furthermore, in the above method, in step S3, the schematic diagram of the multi-span beam structure to be identified is annotated with: material attribute information, support type, length of each beam unit and load distance; concentrated force Q in the load type F , concentrated bending moment Q M and uniform force Q JB Load arrows of various shapes with load values ​​marked on them.

[0019] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0020] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0021] Processor; and

[0022] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0023] Compared with the prior art, the present invention collects sample multi-span beam structure diagrams containing different working conditions through a training information acquisition and processing module, and collects beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information therein, and marks each type of information at a corresponding position on the corresponding multi-span beam structure diagram to obtain a marked diagram; a model training module, based on the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information marked in the marked diagram, uses an artificial intelligence method to establish a multi-span beam structure information recognition model; the multi-span beam structure diagram to be identified is input into the multi-span beam structure information recognition model, and the multi-span beam structure information recognition model is used for the multi-span beam structure information recognition model to be identified. The beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information in the multi-span beam structure schematic are identified, and a multi-span beam structure modeling information file containing beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information is output. This can solve the problem that the multi-span beam structure modeling process is cumbersome and time-consuming. By hand-drawing the multi-span beam structure schematic, the multi-span beam structure modeling information can be quickly extracted and a standard modeling information file can be output. The file can be imported into professional calculation software such as structural mechanics solvers through interfaces to quickly establish a multi-span beam structure calculation model, solving the problem that the modeling process of traditional finite element software and other professional software is complicated and time-consuming, thereby improving the calculation and modeling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a method for rapid modeling of multi-span beams based on machine vision according to an embodiment of the present invention;

[0025] Figure 2 is a schematic diagram of a hinge support according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of a fixed support according to an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of a directional support according to an embodiment of the present invention;

[0028] Figure 5 is a schematic diagram of a simplified diagram of a multi-span beam structure to be identified according to an embodiment of the present invention;

[0029] Figure 6 Identified and marked Figure 5 Schematic diagram of the node and unit numbering in ;

[0030] Figure 7 Identified and marked Figure 5 Schematic diagram of medium load. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] like Figures 1 to 7 As shown, the present invention provides a method for rapid modeling of multi-span beams based on machine vision, comprising:

[0033] Step S1, training information collection and processing module, collecting sample multi-span beam structure schematics containing different working conditions, and collecting beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information therein, and marking each information at a corresponding position on the corresponding multi-span beam structure schematic to obtain a marked schematic;

[0034] Here, the sample multi-span beam structure diagram may be a hand-drawn multi-span beam structure diagram; the training information acquisition and processing module is mainly responsible for the acquisition and processing of training data, collecting multi-span beam structure diagrams containing multi-span beam structures under different working conditions, and collecting beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information therein, and marking each type of information at a corresponding position on the corresponding multi-span beam structure diagram;

[0035] Step S2, a model training module, based on the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information annotated in the annotated diagram, uses an artificial intelligence method to establish a multi-span beam structure information recognition model;

[0036] Here, the model form of the multi-span beam structure information recognition model is not limited, and models such as CNN, RNN and ResNet can be used to establish the multi-span beam structure information recognition model; to ensure the training effect, the training set needs to have more than 1000 sets of data.

[0037] The model training process can use algorithms such as stochastic gradient descent and adaptive gradient algorithm to train the model until the loss function is less than a preset value and the training ends.

[0038] Step S3, inputting the multi-span beam structure schematic to be identified into the multi-span beam structure information identification model, the multi-span beam structure information identification model identifies the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information in the multi-span beam structure schematic to be identified, and outputs a multi-span beam structure modeling information file containing the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information.

[0039] Here, if Figure 5 As shown in FIG. 1 , the input of the multi-span beam structure information recognition model is the hand-drawn structure diagrams of various multi-span beams to be identified; the multi-span beam structure diagrams to be identified are marked with: material attribute information, support type, and the length of each beam unit, such as Figure 5 4000, 4000, 5000, 3000 in; the type of load is concentrated force Q F , concentrated bending moment Q M , uniform force Q JB The load arrows are marked with load values, such as Figure 5 10kN / m, 15kN / m and kN / m, the load distance is as follows Figure 5 500, 800, 300 and 600.

[0040] like Figure 6 and 7 The model output is a multi-span beam structure modeling information file containing beam node information, beam unit information, beam node boundary condition information, beam unit load condition information, and beam material property information. Figure 6 In the figure, 5 nodes and 4 units are identified. Figure 7 The various load locations are calculated and marked.

[0041] It should be noted that the units of the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information input in actual use should be consistent with the data units used in model training.

[0042] The present invention can solve the problem that the modeling process of multi-span beam structures is complicated and time-consuming. By hand-drawing a simple diagram of the multi-span beam structure, the modeling information of the multi-span beam structure can be quickly extracted, and a standard modeling information file can be output. The file can be imported into professional computing software such as a structural mechanics solver through an interface to quickly establish a calculation model of the multi-span beam structure, thereby solving the problem that the modeling process of traditional finite element software and other professional software is complicated and time-consuming, and improving the efficiency of computing and modeling.

[0043] In one embodiment of the multi-span beam rapid modeling method based on machine vision of the present invention, in step S1, the node information includes: the number of nodes and the node number, wherein the number of nodes is n, and the nodes are numbered from left to right starting from the left side of the sample multi-span beam structure diagram, and the number names are, for example, JD1 to JD n ; Among them, a beam is called a beam unit, the beam units are connected end to end, and the two ends of each beam unit are beam nodes.

[0044] In one embodiment of the multi-span beam rapid modeling method based on machine vision of the present invention, in step S1, the beam unit information beam includes: unit quantity, unit number and unit length; wherein each beam unit corresponds to a unit length data L1~L n-1 , the unit length is in mm; the number of units is the number of nodes minus 1 (i.e. n-1), and the units are numbered from left to right starting from the left side of the sample multi-span beam structure diagram. There is a beam unit between two beam nodes, and the number names can be DY1~DY n-1 .

[0045] In one embodiment of the multi-span beam rapid modeling method based on machine vision of the present invention, in step S1, the beam node boundary condition information includes: the support type (supported under the node) under beam node 1 and beam node n, wherein the support type includes: Figure 2 The hinge support JZ shown in Figure 3 The fixed support GZ shown and Figure 5 There are three types of directional supports DX shown; the hinged supports constrain the horizontal and vertical displacements of the beam nodes thereon; the fixed supports constrain the horizontal, vertical and rotational displacements of the beam nodes thereon, and the directional supports constrain the horizontal displacement and rotational angle of the nodes; in the sample multi-span beam structure schematic, beam nodes other than the head and tail are hinged supports by default.

[0046] In one embodiment of the multi-span beam rapid modeling method based on machine vision of the present invention, in step S1, the beam unit load condition information includes: load quantity, load number, load type, load value, and load position; wherein the load quantity is consistent with the number of beam units, which is n-1, and the loads are numbered and marked from left to right starting from the left side of the sample multi-span beam structure diagram, and the load number names are HZ1~HZ n-1 ; Mark the load type, load value and load location;

[0047] Load types include: Concentrated force Q F , concentrated bending moment Q M , uniform force Q JB There are 3 types in total;

[0048] Load value Q unit: concentrated force Q F The load value is in kN, and the concentrated bending moment Q M The load value unit is kN·m, and the uniform force Q JB The load value unit is kN / m; each unit corresponds to a load value;

[0049] Concentration Q F and concentrated bending moment Q M The load position is: concentrated force Q F and concentrated bending moment Q MThe ratio S of the distance between the load action point and the left node of the unit and the unit length; the uniform force Q JB The load position is: the ratio of the distance from the starting point of the uniform force to the beam node at the left end of the unit to the unit length S1 and the ratio of the distance from the end point of the uniform force to the beam node at the right end of the unit to the unit length S2; where the concentrated force Q F and concentrated bending moment Q M The load distance is the concentrated force Q F and concentrated bending moment Q M The load distance of uniform force is the distance from the starting point of uniform force to the beam node at the left end of the unit, or the distance from the end point of uniform force to the beam node at the right end of the unit.

[0050] When there is no load on a unit, the load type is selected as concentrated force Q F , load value Q is 0, and load position S is 0.

[0051] In one embodiment of the multi-span beam rapid modeling method based on machine vision of the present invention, in step S1, the material property information includes: beam elastic modulus E, in units of MPa, beam section resistance moment I, in units of mm4.

[0052] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0053] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0054] Processor; and

[0055] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0056] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0057] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in 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 the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may 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.

[0058] Obviously, those skilled in the art can make various changes and modifications to the invention without departing from the spirit and scope of the invention. Thus, if these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. A method for rapid modeling of multi-span beams based on machine vision, characterized in that: include: Step S1, training information collection and processing module, collecting sample multi-span beam structure schematics containing different working conditions, and collecting beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information therein, and marking each information at a corresponding position on the corresponding multi-span beam structure schematic to obtain a marked schematic; Step S2, a model training module, based on the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information annotated in the annotated diagram, uses an artificial intelligence method to establish a multi-span beam structure information recognition model; Step S3, inputting the multi-span beam structure schematic to be identified into the multi-span beam structure information identification model, the multi-span beam structure information identification model identifies the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information in the multi-span beam structure schematic to be identified, and outputs a multi-span beam structure modeling information file containing the beam node information, beam unit information, beam node boundary condition information, beam unit load condition information and beam material property information.

2. The method for rapid modeling of multi-span beams based on machine vision as claimed in claim 1, characterized in that: In step S1, the node information includes: the number of nodes and the node number, wherein the number of nodes is n, and the nodes are numbered from left to right starting from the left side of the sample multi-span beam structure diagram; wherein a beam is called a beam unit, the beam units are connected end to end, and the two ends of each beam unit are beam nodes.

3. The method for rapid modeling of multi-span beams based on machine vision as claimed in claim 2, characterized in that: In step S1, the beam unit information includes: unit quantity, unit number and unit length; wherein each beam unit corresponds to a unit length data L1~L n-1 , the unit length is in mm; the number of units is the number of nodes - 1, and the units are numbered from left to right starting from the left side of the sample multi-span beam structure diagram, and there is a beam unit between two beam nodes.

4. The method for rapid modeling of multi-span beams based on machine vision as claimed in claim 2, characterized in that: In step S1, the beam node boundary condition information includes: the support types under beam node 1 and beam node n, wherein the support types include: hinged support JZ, fixed support GZ and directional support DX; the hinged support constrains the horizontal displacement and vertical displacement of the beam node thereon; the fixed support constrains the horizontal displacement, vertical displacement and rotation angle of the beam node thereon, and the directional support constrains the horizontal displacement and rotation angle of the node; in the sample multi-span beam structure schematic, the beam nodes other than the head and tail are hinged supports by default.

5. The method for rapid modeling of multi-span beams based on machine vision as claimed in claim 2, characterized in that: In step S1, the beam unit load condition information includes: load quantity, load number, load type, load value, and load position; wherein the load quantity is consistent with the number of beam units, which is n-1, and the loads are numbered and marked from left to right starting from the left side of the sample multi-span beam structure schematic; the load type, load value, and load position are marked.

6. The method for rapid modeling of multi-span beams based on machine vision as claimed in claim 1, characterized in that: Load types include: Concentrated force Q F , concentrated bending moment Q M He Junbuli Q JB There are 3 types in total; Load value Q unit: concentrated force Q F The load value is in kN, and the concentrated bending moment Q M The load value unit is kN·m, and the uniform force Q JB The load value unit is kN / m; each beam element corresponds to a load value; Concentration Q F and concentrated bending moment Q M The load position is: concentrated force Q F and concentrated bending moment Q M The ratio S of the distance between the load action point and the left node of the unit and the unit length; the uniform force Q JB The load position is: the ratio of the distance from the starting point of the uniform force to the beam node at the left end of the unit to the unit length S1 and the ratio of the distance from the end point of the uniform force to the beam node at the right end of the unit to the unit length S2; where the concentrated force Q F and concentrated bending moment Q M The load distance is the concentrated force Q F and concentrated bending moment Q M The load distance of uniform force is the distance from the starting point of uniform force to the beam node at the left end of the unit, or the distance from the end point of uniform force to the beam node at the right end of the unit. When there is no load on a beam element, the load type is selected as concentrated force Q F , load value Q is 0, and load position S is 0.

7. The method for rapid modeling of multi-span beams based on machine vision as claimed in claim 1, characterized in that: In step S1, the material property information includes: beam elastic modulus E, in units of MPa, and beam section resistance moment I, in units of mm4.

8. The method for rapid modeling of multi-span beams based on machine vision as claimed in claim 6, characterized in that: In step S3, the schematic diagram of the multi-span beam structure to be identified is marked with: material attribute information, support type, length of each beam unit and load distance; concentrated force Q in the load type F , concentrated bending moment Q M and uniform force Q JB Load arrows of various shapes with load values ​​marked on them.

9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to: perform the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: perform a method as claimed in any one of claims 1 to 8.

Images