Non-standard hanging basket internal force calculation method and device based on machine learning

Abstract

The invention provides a non-standard hanging basket internal force calculation method and equipment based on machine learning, and aims at solving the problems that the non-standard hanging basket internal force calculation process is tedious and long in time consumption, and modeling needs to be repeated under different working conditions, obtaining a non-standard hanging basket internal force calculation model through an information acquisition and processing module and a model training module, and calculating the internal force of a non-standard hanging basket in a construction site. Technicians only need to input corresponding non-standard hanging basket parameters according to on-site working conditions, and the non-standard hanging basket internal force calculation model can obtain the hanging basket internal force. According to the method based on artificial intelligence, the internal force of each component of the non-standard hanging basket can be quickly obtained through simple parameter input, the problems that a traditional finite element analysis method is complex in modeling process and long in calculation time and needs repeated calculation under different working conditions are solved, and the calculation efficiency is improved.

Description

Technical Field

[0001] The invention relates to a method and device for calculating the internal force of a non-standard hanging basket based on machine learning. Background Art

[0002] As a flexible aerial work platform, the hanging basket has a wide range of application scenarios, covering almost every stage of construction projects from foundation construction to decoration and renovation. It is widely used in exterior wall construction, curtain wall installation, insulation layer construction, paint painting, glass cleaning, steel structure welding, concrete pouring and various high-altitude maintenance operations.

[0003] However, due to irregular working surfaces, special working requirements, space limitations, etc., it is often not possible to use Figure 1 The standard hanging basket shown in the figure must be used instead of a non-standard hanging basket, which greatly increases the safety risk.

[0004] The extension length of the front beam of a standard suspended basket and the distance between the front and rear brackets are limited to a certain extent, and the height of the bracket is also limited. This limitation often cannot meet the requirements of current complex and variously shaped building construction. The rear bracket of a standard suspended basket is usually equipped with a counterweight to prevent the suspended basket from tipping over. However, due to the limitations of conditions and sites,

[0005] Some hanging baskets cannot be equipped with counterweights. In this case, the original structure is mostly used, and the hanging basket and the structure are connected. The length of the rear cross bar L1, front cross bar L2, upper vertical bar L3 and lower vertical bar L4 of each rod may exceed the limit. This kind of hanging basket is called a non-standard hanging basket.

[0006] In the process of evaluating the safety of non-standard hanging baskets, calculating the internal forces of the hanging baskets is an indispensable step. The existing calculation of the internal forces of the hanging baskets requires designers to perform finite element modeling calculations or calculate the non-standard hanging basket structures based on structural mechanics formulas. When calculating different working conditions, different finite element models need to be established, and modeling operations such as boundary condition setting, component information entry, load information entry, and mesh division need to be repeated. The process is cumbersome and time-consuming. Summary of the invention

[0007] The object of the present invention is to provide a method and device for calculating the internal force of a non-standard hanging basket based on machine learning.

[0008] In order to solve the above problems, the present invention provides a method for calculating the internal force of a non-standard hanging basket based on machine learning, comprising:

[0009] The information collection and processing module collects the calculation basis materials including the internal forces of different non-standard hanging baskets;

[0010] The information acquisition and processing module extracts the geometric information, load information, support information and internal force information of the non-standard hanging basket based on the calculation basis materials shown;

[0011] The model training module uses artificial intelligence methods to establish a non-standard hanging basket internal force calculation model based on the acquired non-standard hanging basket geometry information, load information, support information and internal force information;

[0012] The geometric information, load information and support information of the non-standard hanging basket to be calculated are input into the non-standard hanging basket internal force calculation model to obtain the internal force information of the non-standard hanging basket to be calculated.

[0013] Furthermore, in the above method, the calculation is based on materials including: calculation sheets for internal force calculations of different non-standard hanging baskets, construction plans, and finite element calculation result data.

[0014] Furthermore, in the above method, the non-standard hanging basket includes: a rear crossbar, a front crossbar, an upper vertical bar, a lower vertical bar, a front support ZH1, a rear support ZH2 and a rear tie rod or a cable, wherein:

[0015] The rear end of the rear cross bar is connected to the upper end of the rear tie rod or the cable, and the front end of the rear cross bar is connected to the rear end of the front cross bar;

[0016] The lower end of the rear tie rod or the cable is connected to the rear support;

[0017] The front end of the front crossbar is connected to the hanging basket box through a first cable;

[0018] The lower end of the upper upright is connected to the connection node of the front crossbar and the rear crossbar;

[0019] The upper end of the lower upright is connected to the connection node of the front cross bar and the rear cross bar, and the lower end of the lower upright is connected to the front support;

[0020] The rear end of the rear cross bar is connected to the upper end of the upper upright bar through a second cable; the front end of the front cross bar is connected to the upper end of the upper upright bar through a third cable.

[0021] Furthermore, in the above method, the geometric information includes: the length of the rear cross bar L1, the length of the front cross bar L2, the length of the upper vertical bar L3, the length of the lower vertical bar L4, the length of the rear tie rod or cable L5, and the angle θ between the rear tie rod or cable and the rear cross bar; the unit of L1~L5 is m, and the unit of θ is "°".

[0022] Furthermore, in the above method, the load information includes: the design value F of the hanging basket load, in kN.

[0023] Furthermore, in the above method, the support information includes: types of the front support and the rear support, wherein the type of the front support is a fixed support or a hinged support, and the type of the rear support is a hinged support.

[0024] Furthermore, in the above method, the internal force information includes: axial force and bending moment of the front cross bar, rear cross bar, upper vertical bar and lower vertical bar, and axial force of the rear cable or rear tie rod, wherein the unit of axial force is kN, and the unit of bending moment is kN·m.

[0025] Furthermore, in the above method, the non-standard hanging basket internal force calculation model includes: DNN, RNN or Transformer model.

[0026] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0027] According to another aspect of the present invention, there is provided a computer device, comprising:

[0028] Processor; and

[0029] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform a method as described in any one of the above.

[0030] In summary, based on the above-mentioned problem that the calculation process of the internal force of the non-standard hanging basket is cumbersome, time-consuming, and repeated modeling is required for different working conditions, the present invention proposes a new method for calculating the internal force of a non-standard hanging basket, and its main technical components are as follows: a non-standard hanging basket internal force calculation model is obtained through an information acquisition and processing module and a model training module. At the construction site, the technician only needs to input the corresponding non-standard hanging basket parameters according to the on-site working conditions, and the non-standard hanging basket internal force calculation model will calculate the internal force of the hanging basket. The present invention is based on an artificial intelligence method, and the internal forces of each component of the non-standard hanging basket can be quickly obtained through simple parameter input, which solves the problems of the traditional finite element analysis method having a complex modeling process, a long calculation time, and repeated calculations required for different working conditions, and improves calculation efficiency.

[0031] Compared with the current non-standard hanging basket internal force calculation method, the beneficial effects of the present invention are mainly as follows:

[0032] (1) High calculation efficiency. The present invention provides a non-standard hanging basket internal force calculation method based on machine learning. After the parameters are input, the calculation time only takes a few seconds, which is much faster than traditional methods such as finite element calculation and formula calculation.

[0033] (2) Simple operation. Compared with the existing calculation methods, the present invention only requires construction site personnel to input a few simple parameters to obtain the internal force data of non-standard hanging baskets, without the need to learn professional finite element software;

[0034] (3) Strong adaptability. The calculation method of the present invention can be applied to the calculation of non-standard hanging baskets with any crossbar length, vertical pole length, rear straw / cable length and angle, and can cover most non-standard hanging basket application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of an existing marked hanging basket;

[0036] Figure 2 It is a schematic diagram of a method for calculating internal forces of a non-standard hanging basket based on machine learning according to an embodiment of the present invention;

[0037] Figure 3 It is a schematic diagram of parameters of non-standard hanging basket components according to an embodiment of the present invention;

[0038] Figure 4 It is a schematic diagram of components of a non-standard hanging basket according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] like Figure 2 As shown, the present invention provides a method for calculating the internal force of a non-standard hanging basket based on machine learning, comprising:

[0041] Step S1, the information collection and processing module collects materials containing calculation basis of different non-standard hanging basket internal forces;

[0042] Preferably, the information collection and processing module is mainly responsible for data collection and processing, and collects calculation books, construction plans, and finite element calculation result data of internal force calculations of different non-standard hanging baskets as calculation basis materials;

[0043] Step S2, the information collection and processing module extracts the geometric information, load information, support information and internal force information of the non-standard hanging basket based on the calculation basis material shown;

[0044] Here, the information collection and processing module can extract the geometric information, load information, support information and internal force information of the non-standard hanging basket based on the calculation book, construction plan and finite element calculation result data of the internal force calculation of the non-standard hanging basket. Figure 3 and 4 As shown;

[0045] Optional, such as Figure 3 and 4 As shown, the non-standard hanging basket includes: a rear cross bar, a front cross bar, an upper vertical bar, a lower vertical bar, a front support ZH1, a rear support ZH2 and a rear tie rod or a cable, wherein:

[0046] The rear end of the rear cross bar is connected to the upper end of the rear tie rod or the cable, and the front end of the rear cross bar is connected to the rear end of the front cross bar;

[0047] The lower end of the rear tie rod or cable is connected to the rear support ZH2;

[0048] The front end of the front crossbar is connected to the hanging basket box through a first cable;

[0049] The lower end of the upper upright is connected to the connection node of the front crossbar and the rear crossbar;

[0050] The upper end of the lower upright is connected to the connection node of the front crossbar and the rear crossbar, and the lower end of the lower upright is connected to the front support ZH1;

[0051] The rear end of the rear cross bar is connected to the upper end of the upper upright bar through a second cable L6; the front end of the front cross bar is connected to the upper end of the upper upright bar through a third cable L5.

[0052] Preferably, the geometric information includes: the length of the rear crossbar L1, the length of the front crossbar L2, the length of the upper vertical bar L3, the length of the lower vertical bar L4, the length of the rear tie rod or cable L5, and the angle θ between the rear tie rod or cable and the length of the rear crossbar; the units of L1 to L5 are m, and the unit of θ is "°";

[0053] The load information includes: the design value F of the hanging basket load, in kN;

[0054] The support information includes: the types of the front support ZH1 and the rear support ZH2, the type of the front support ZH1 is a fixed support or a hinged support, and the type of the rear support ZH2 is a hinged support;

[0055] The internal force information includes: the axial force and bending moment of the front crossbar, the rear crossbar, the upper vertical bar and the lower vertical bar, and the axial force of the rear cable or the rear tie rod, wherein the unit of the axial force is kN, and the unit of the bending moment is kN·m;

[0056] Step S3, the model training module uses an artificial intelligence method to establish a non-standard hanging basket internal force calculation model based on the acquired non-standard hanging basket geometry information, load information, support information and internal force information;

[0057] Here, the model training module uses artificial intelligence methods to establish a non-standard hanging basket internal force calculation model based on the acquired non-standard hanging basket geometry information, load information, support information and internal force information.

[0058] Optionally, the form of the non-standard hanging basket internal force calculation model is not limited, and models such as DNN, RNN and Transformer can be used to establish the non-standard hanging basket internal force calculation model;

[0059] To ensure the training effect, the training set needs more than 10,000 sets of data.

[0060] The model training process can use optimization algorithms such as SGD and Adam until the target loss function reaches the preset expected value, and then the training can be stopped. After the training is completed, the non-standard hanging basket internal force calculation model is obtained.

[0061] Step S4, inputting the geometric information, load information and support information of the non-standard hanging basket to be calculated into the non-standard hanging basket internal force calculation model to obtain the internal force information of the non-standard hanging basket to be calculated, such as: the axial force and bending moment of the front cross bar, the rear cross bar, the upper vertical bar and the lower vertical bar, and the axial force of the rear cable or the rear pull rod.

[0062] Here, the model inputs are the length of the rear crossbar L1, the length of the front crossbar L2, the length of the upper vertical bar L3, the length of the lower vertical bar L4, the length of the rear tie rod / cable L5 and the tie rod / cable angle θ, the type of the front support ZH1, the type of the rear support ZH2, and the design value F of the basket load;

[0063] The model output is the axial force and bending moment of the front and rear cross bars and the upper and lower vertical bars of the non-standard hanging basket, and the axial force of the rear cable or rear rod.

[0064] In actual calculation, input the crossbar length L1, front crossbar length L2, upper vertical bar length L3, lower vertical bar length L4, rear tie rod / cable length L5 and tie rod / cable angle θ, the type of front support ZH1, the type of rear support ZH2 and the design value of the basket load F into the non-standard hanging basket internal force calculation model. The model will then output the axial force and bending moment of the front and rear crossbars and upper and lower vertical bars of the non-standard hanging basket, and the axial force of the cable or tie rod;

[0065] It should be noted that the unit of the input value in the actual calculation should be consistent with the training data unit when training the model.

[0066] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0067] According to another aspect of the present invention, there is provided a computer device, comprising:

[0068] Processor; and

[0069] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform a method as described in any one of the above.

[0070] In summary, based on the above-mentioned problem that the calculation process of the internal force of the non-standard hanging basket is cumbersome, time-consuming, and repeated modeling is required for different working conditions, the present invention proposes a new method for calculating the internal force of a non-standard hanging basket, and its main technical components are as follows: a non-standard hanging basket internal force calculation model is obtained through an information acquisition and processing module and a model training module. At the construction site, the technician only needs to input the corresponding non-standard hanging basket parameters according to the on-site working conditions, and the non-standard hanging basket internal force calculation model will calculate the internal force of the hanging basket. The present invention is based on an artificial intelligence method, and the internal forces of each component of the non-standard hanging basket can be quickly obtained through simple parameter input, which solves the problems of the traditional finite element analysis method having a complex modeling process, a long calculation time, and repeated calculations required for different working conditions, and improves calculation efficiency.

[0071] Compared with the current non-standard hanging basket internal force calculation method, the beneficial effects of the present invention are mainly as follows:

[0072] (1) High calculation efficiency. The present invention provides a non-standard hanging basket internal force calculation method based on machine learning. After the parameters are input, the calculation time only takes a few seconds, which is much faster than traditional methods such as finite element calculation and formula calculation.

[0073] (2) Simple operation. Compared with the existing calculation methods, the present invention only requires construction site personnel to input a few simple parameters to obtain the internal force data of non-standard hanging baskets, without the need to learn professional finite element software;

[0074] (3) Strong adaptability. The calculation method of the present invention can be applied to the calculation of non-standard hanging baskets with any crossbar length, vertical pole length, rear straw / cable length and angle, and can cover most non-standard hanging basket application scenarios.

[0075] 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.

[0076] 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.

[0077] 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 calculating the internal force of a non-standard hanging basket based on machine learning, characterized in that: include: The information collection and processing module collects the calculation basis materials including the internal forces of different non-standard hanging baskets; The information acquisition and processing module extracts the geometric information, load information, support information and internal force information of the non-standard hanging basket based on the calculation basis materials shown; The model training module uses artificial intelligence methods to establish a non-standard hanging basket internal force calculation model based on the acquired non-standard hanging basket geometry information, load information, support information and internal force information; The geometric information, load information and support information of the non-standard hanging basket to be calculated are input into the non-standard hanging basket internal force calculation model to obtain the internal force information of the non-standard hanging basket to be calculated.

2. The method for calculating the internal force of a non-standard hanging basket based on machine learning as claimed in claim 1 is characterized in that: The calculation basis materials include: calculation sheets for internal force calculations of different non-standard hanging baskets, construction plans, and finite element calculation result data.

3. The method for calculating the internal force of a non-standard hanging basket based on machine learning as claimed in claim 1 is characterized in that: The non-standard hanging basket comprises: a rear crossbar, a front crossbar, an upper vertical bar, a lower vertical bar, a front support ZH1, a rear support ZH2 and a rear tie rod or a cable, wherein: The rear end of the rear cross bar is connected to the upper end of the rear tie rod or the cable, and the front end of the rear cross bar is connected to the rear end of the front cross bar; The lower end of the rear tie rod or the cable is connected to the rear support; The front end of the front crossbar is connected to the hanging basket box through a first cable; The lower end of the upper upright is connected to the connection node of the front crossbar and the rear crossbar; The upper end of the lower upright is connected to the connection node of the front cross bar and the rear cross bar, and the lower end of the lower upright is connected to the front support; The rear end of the rear cross bar is connected to the upper end of the upper upright bar through a second cable; the front end of the front cross bar is connected to the upper end of the upper upright bar through a third cable.

4. The method for calculating the internal force of a non-standard hanging basket based on machine learning as claimed in claim 3 is characterized in that: The geometric information includes: the length of the rear crossbar L1, the length of the front crossbar L2, the length of the upper vertical bar L3, the length of the lower vertical bar L4, the length of the rear tie rod or cable L5, and the angle θ between the rear tie rod or cable and the rear crossbar; the unit of L1-L5 is m, and the unit of θ is "°".

5. The method for calculating the internal force of a non-standard hanging basket based on machine learning as claimed in claim 3 is characterized in that: The load information includes: the design value F of the hanging basket load, in kN.

6. The method for calculating the internal force of a non-standard hanging basket based on machine learning as claimed in claim 3 is characterized in that: The support information includes: the types of the front support and the rear support, wherein the type of the front support is a fixed support or a hinged support, and the type of the rear support is a hinged support.

7. The method for calculating the internal force of a non-standard hanging basket based on machine learning as claimed in claim 3 is characterized in that: The internal force information includes: axial force and bending moment of the front crossbar, the rear crossbar, the upper vertical bar and the lower vertical bar, and the axial force of the rear cable or the rear rod, wherein the unit of the axial force is kN, and the unit of the bending moment is kN·m.

8. The method for calculating the internal force of a non-standard hanging basket based on machine learning as claimed in claim 1, characterized in that: The forms of non-standard hanging basket internal force calculation models include: DNN, RNN or Transformer model.

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