Steel structure construction management and control method and equipment based on machine vision

Abstract

The invention provides a steel structure construction management and control method and equipment based on machine vision, and the method comprises a construction error analysis system which carries out the recognition of the image and video data of a construction site, and obtains the structural error of a current construction state; the structure error of the current construction state is transmitted to a structure forming prediction module, a judgment module and a safety function judgment module are used for judging whether the final forming state of the steel structure meets requirements or not, and if not, a judgment result and error information are input to a construction state intelligent adjustment module; and the intelligent adjusting module gives an installation adjusting command of the steel structure component, and the component adjusting device adjusts the site construction state according to the installation adjusting command until the requirement is met, and the steel structure component is fixed. On the basis of the artificial intelligence technology, the structure construction error is monitored in real time, the influence of the error on subsequent installation and the overall performance of the structure is evaluated in real time, and the construction process of the large-span space structure can be managed and controlled in real time.

Description

Technical Field

[0001] The invention relates to a steel structure construction control method and equipment based on machine vision. Background Art

[0002] Large-span space structures are widely used in stadiums, airport terminals, exhibition centers, theater stages, etc. Such structures require high design precision, and control over the construction process is particularly important. However, due to the characteristics of large-span space structures, their components have large spans, and the overall structure is sensitive to environmental factors such as wind and temperature. Some construction errors that occurred in the early stages of their construction, after accumulating through large-span assembly, can lead to problems with components at both ends being unable to be spliced, and may affect subsequent construction of the overall structure, and even cause safety hazards.

[0003] Traditionally, the construction accuracy control of such structures mainly relies on total station measurement, which has problems such as large workload, errors caused by human operation, and difficulty in arranging measurement points due to space limitations. Summary of the invention

[0004] The object of the present invention is to provide a steel structure construction control method and equipment based on machine vision.

[0005] In order to solve the above problems, the present invention provides a steel structure construction control method based on machine vision, comprising:

[0006] After the steel structure components are installed in place, the on-site construction status is collected through visual acquisition equipment to obtain images and video data of the construction site;

[0007] Apply the construction error analysis system to identify the image and video data of the construction site and obtain the structural error information of the current construction status;

[0008] The structural error information of the current construction state is transmitted to the structural forming prediction module, and the structural forming prediction module predicts the final forming state of the steel structure according to the preset structural design model;

[0009] The construction judgment module and the safety function judgment module judge whether the final forming state of the steel structure meets the requirements.

[0010] Furthermore, in the above method, the structural error information of the current construction state is transmitted to the structural forming prediction module, and the structural forming prediction module predicts the final forming state of the steel structure according to the preset structural design model, including:

[0011] The structural formation prediction module converts the preset structural design model into a prediction model that takes into account construction stage errors based on the construction structure error information transmitted by the construction error analysis system.

[0012] Furthermore, in the above method, the construction judgment module and the safety function judgment module judge whether the final forming state of the steel structure meets the requirements, including:

[0013] The prediction model is input into a subsequent construction judgment module and a safety function judgment module to determine whether the prediction model meets the requirements.

[0014] Furthermore, in the above method, the prediction model is input into a subsequent construction judgment module and a safety function judgment module to judge whether the prediction model meets the requirements, including:

[0015] The construction judgment module judges the subsequent construction of the prediction model, including but not limited to judging the impact of the existing error on the curtain wall installation, the impact on the mechanical and electrical installation, the impact on the subsequent component installation, and whether the maximum error that may occur in the subsequent installation process exceeds the limit.

[0016] The safety function judgment module analyzes the static and dynamic stress performance of the prediction model to determine whether it meets the design requirements.

[0017] Furthermore, in the above method, after the prediction model is input into the subsequent construction judgment module and the safety function judgment module to judge whether the prediction model meets the requirements, the method further includes:

[0018] If the requirements are not met, the judgment result and error information will be input into the intelligent adjustment module of the construction status. The intelligent adjustment module of the construction status will give the installation adjustment command of the steel structure component. The component adjustment device will adjust the on-site construction status according to the installation adjustment command until the requirements are met. After that, the steel structure component will be fixed and the installation of the next steel structure component will be started.

[0019] Furthermore, in the above method, the on-site construction structural error information is the overall error of the current state of the steel structure component, that is, the error between the spatial coordinates of each node of the component and the structural design coordinates.

[0020] Furthermore, in the above method, the construction error analysis system is applied to identify the image and video data of the construction site, including:

[0021] The construction error analysis system is based on CNN or RNN machine learning technology to identify the image and video data of the on-site construction site and export the on-site construction structure error information to the structure forming prediction module.

[0022] Furthermore, in the above method, the visual acquisition equipment includes: a high-definition camera, a drone and / or a laser scanner installed at the construction site.

[0023] 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: adopt any of the methods described above.

[0024] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0025] Processor; and

[0026] A memory arranged to store computer executable instructions which, when executed, cause the processor to: adopt any of the methods described above.

[0027] In summary, in order to solve the above-mentioned problems of difficult construction control of large-span steel structures and large impact of construction errors, a new large-span steel structure construction control method based on machine vision is proposed, including: after the steel structure components are installed in place, the on-site construction status is collected by visual acquisition equipment to obtain images and video data of the construction site; the construction error analysis system is applied to identify the images and video data of the construction site to obtain the structural error of the current construction state; the structural error of the current construction state is transmitted to the structural forming prediction module, and the structural forming prediction module predicts the final forming state of the steel structure according to the preset structural design model; the construction judgment module and the safety function judgment module judge whether the final forming state of the steel structure meets the requirements. Preferably, if the requirements are not met, the judgment result and error information are input into the construction status intelligent adjustment module, the intelligent adjustment module gives the installation adjustment command of the steel structure component, and the component adjustment device adjusts the on-site construction status according to the installation adjustment command until the requirements are met, the steel structure component is fixed, and the installation of the next steel structure component is started. The present invention is based on artificial intelligence technology, which can realize real-time monitoring of structural construction errors and real-time evaluation of the impact of the errors on subsequent installation and the overall performance of the structure. It can also manage the construction process of large-span spatial structures in real time to ensure that the construction errors are within the allowable range and will not affect the subsequent construction or safety of the structure.

[0028] Compared with the current large-span spatial structure construction control method, the beneficial effects of the present invention are mainly as follows:

[0029] (1) Strong real-time performance. The present invention provides a large-span steel structure construction control method based on machine vision, which can automatically collect on-site construction errors, intelligently analyze the impact of the errors, give corresponding adjustment commands, and dynamically adjust the construction stage model to avoid inconvenience or inability to adjust when problems are discovered later;

[0030] (2) Comprehensive consideration. This method not only analyzes the error of a single component, but also considers the overall error at this stage and makes predictions for subsequent construction and installation to avoid situations where requirements are met locally but the cumulative error exceeds the limit. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of a steel structure construction control method based on machine vision according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] 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.

[0033] like Figure 1 As shown, the present invention provides a steel structure construction control method based on machine vision, comprising:

[0034] Step S1, after the steel structure components are installed in place, the on-site construction status is collected through visual acquisition equipment to obtain image and video data of the construction site;

[0035] Preferably, visual monitoring equipment such as high-definition cameras, drones, laser scanners, etc. can be installed at the construction site to capture images and video data of the construction site in real time.

[0036] Step S2, applying the construction error analysis system to identify the image and video data of the construction site to obtain the structural error information of the current construction status;

[0037] Preferably, the construction error analysis system is based on machine learning technologies such as CNN and RNN to identify the image and video data of the on-site construction site and export the on-site construction structure error information to the structure forming prediction module;

[0038] Preferably, the on-site construction structural error information is the overall error of the current state of the steel structure component, that is, the error between the spatial coordinates of each node of the component and the structural design coordinates. The spatial coordinate axis needs to be determined by the on-site construction personnel according to the construction environment, and the coordinate unit is mm;

[0039] Step S3, transmitting the structural error information of the current construction state to the structural forming prediction module, and the structural forming prediction module predicts the final forming state of the steel structure according to a preset structural design model;

[0040] Preferably, the structural forming prediction module converts the preset structural design model into a prediction model taking into account construction stage errors based on the construction structural error information transmitted by the construction error analysis system;

[0041] Step S4: The construction judgment module and the safety function judgment module judge whether the final forming state of the steel structure meets the requirements.

[0042] Preferably, the prediction model can be input into a subsequent construction judgment module and a safety function judgment module to determine whether the prediction model meets the requirements.

[0043] Preferably, the construction judgment module judges the subsequent construction of the prediction model, including but not limited to judging the impact of the existing error on the curtain wall installation, the impact on the electromechanical installation, the impact on the subsequent component installation and whether the maximum error that may occur in the subsequent installation process exceeds the limit.

[0044] The safety function judgment module analyzes the static and dynamic stress performance of the prediction model to determine whether it meets the design requirements.

[0045] Preferably, after step S4, the method further includes:

[0046] Step S5: If the requirements are not met, the judgment result and error information are input into the intelligent adjustment module of the construction status. The intelligent adjustment module of the construction status gives an installation adjustment command for the steel structure component. The component adjustment device adjusts the on-site construction status according to the installation adjustment command until the requirements are met. After that, the steel structure component is fixed and the installation of the next steel structure component is started.

[0047] Preferably, the construction status intelligent adjustment module compares the error information with the steel structure design status and issues an adjustment command. For example, if the coordinate error of the i-th node of the steel structure component n in the x direction is -10, the adjustment command is "please adjust the i-th node of component n in the positive x direction by 10 mm";

[0048] It should be noted that on-site adjustments do not necessarily require 10mm adjustments, as long as the requirements of the above two judgment modules are met. For example, when the adjustment is 5mm, the subsequent construction judgment module and the safety function judgment module will be judged as "passed". At this time, component n can be fixed and component n+1 can be installed.

[0049] Specifically, steel structures with a span of more than 30 meters are generally called large-span steel structures.

[0050] Here, in order to solve the above-mentioned problems of difficult construction control of large-span steel structures and large impact of construction errors, a new large-span steel structure construction control method based on machine vision is proposed, and its main technical composition scheme is as follows: after the steel structure components are installed in place, the on-site construction status is collected by visual acquisition equipment to obtain images and video data of the construction site; the construction error analysis system is applied to identify the images and video data of the construction site to obtain the structural error of the current construction state; the structural error of the current construction state is transmitted to the structural forming prediction module, and the structural forming prediction module predicts the final forming state of the steel structure according to the preset structural design model; the construction judgment module and the safety function judgment module judge whether the final forming state of the steel structure meets the requirements. Preferably, if the requirements are not met, the judgment result and error information are input into the construction status intelligent adjustment module, the intelligent adjustment module gives the installation adjustment command of the steel structure component, and the component adjustment device adjusts the on-site construction status according to the installation adjustment command until the requirements are met, the steel structure component is fixed, and the installation of the next steel structure component is started. The present invention is based on artificial intelligence technology, which can realize real-time monitoring of structural construction errors and real-time evaluation of the impact of the errors on subsequent installation and the overall performance of the structure. It can also manage the construction process of large-span spatial structures in real time to ensure that the construction errors are within the allowable range and will not affect the subsequent construction or safety of the structure.

[0051] 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: adopt any of the methods described above.

[0052] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0053] Processor; and

[0054] A memory arranged to store computer executable instructions which, when executed, cause the processor to: adopt any of the methods described above.

[0055] Compared with the current large-span spatial structure construction control method, the beneficial effects of the present invention are mainly as follows:

[0056] (1) Strong real-time performance. The present invention provides a large-span steel structure construction control method based on machine vision, which can automatically collect on-site construction errors, intelligently analyze the impact of the errors, give corresponding adjustment commands, and dynamically adjust the construction stage model to avoid inconvenience or inability to adjust when problems are discovered later;

[0057] (2) Comprehensive consideration. This method not only analyzes the error of a single component, but also considers the overall error at this stage and makes predictions for subsequent construction and installation to avoid situations where requirements are met locally but the cumulative error exceeds the limit.

[0058] 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.

[0059] 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.

[0060] 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 steel structure construction control method based on machine vision, characterized in that: include: After the steel structure components are installed in place, the on-site construction status is collected through visual acquisition equipment to obtain images and video data of the construction site; Apply the construction error analysis system to identify the image and video data of the construction site and obtain the structural error information of the current construction status; The structural error information of the current construction state is transmitted to the structural forming prediction module, and the structural forming prediction module predicts the final forming state of the steel structure according to the preset structural design model; The construction judgment module and the safety function judgment module judge whether the final forming state of the steel structure meets the requirements.

2. The method for controlling steel structure construction based on machine vision according to claim 1, characterized in that: The structural error information of the current construction status is transmitted to the structural forming prediction module, and the structural forming prediction module predicts the final forming state of the steel structure according to the preset structural design model, including: The structural formation prediction module converts the preset structural design model into a prediction model that takes into account construction stage errors based on the construction structure error information transmitted by the construction error analysis system.

3. The method for controlling steel structure construction based on machine vision according to claim 2, characterized in that: The construction judgment module and the safety function judgment module judge whether the final forming state of the steel structure meets the requirements, including: The prediction model is input into a subsequent construction judgment module and a safety function judgment module to determine whether the prediction model meets the requirements.

4. The method for controlling steel structure construction based on machine vision according to claim 1, characterized in that: The prediction model is input into the subsequent construction judgment module and the safety function judgment module to judge whether the prediction model meets the requirements, including: The construction judgment module judges the subsequent construction of the prediction model, including but not limited to judging the impact of the existing error on the curtain wall installation, the impact on the mechanical and electrical installation, the impact on the subsequent component installation, and whether the maximum error that may occur in the subsequent installation process exceeds the limit. The safety function judgment module analyzes the static and dynamic stress performance of the prediction model to determine whether it meets the design requirements.

5. The method for controlling steel structure construction based on machine vision according to claim 1, characterized in that: After inputting the prediction model into a subsequent construction judgment module and a safety function judgment module to judge whether the prediction model meets the requirements, the method further includes: If the requirements are not met, the judgment result and error information will be input into the intelligent adjustment module of the construction status. The intelligent adjustment module of the construction status will give the installation adjustment command of the steel structure component. The component adjustment device will adjust the on-site construction status according to the installation adjustment command until the requirements are met. After that, the steel structure component will be fixed and the installation of the next steel structure component will be started.

6. The method for controlling steel structure construction based on machine vision according to claim 1, characterized in that: The on-site construction structural error information is the overall error of the current state of the steel structure component, that is, the error between the spatial coordinates of each node of the component and the structural design coordinates.

7. The method for controlling steel structure construction based on machine vision according to claim 1, characterized in that: The construction error analysis system is used to identify the image and video data of the construction site, including: The construction error analysis system is based on CNN or RNN machine learning technology to identify the image and video data of the on-site construction site and export the on-site construction structure error information to the structure forming prediction module.

8. The method for controlling steel structure construction based on machine vision according to claim 1, characterized in that: The visual acquisition equipment includes: high-definition cameras, drones and / or laser scanners installed at the construction site.

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: adopt 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: employ a method as claimed in any one of claims 1 to 8.

Images