Method and system for calculating initial prestress distribution of cable net structure

Abstract

The invention provides a method and a system for calculating initial prestress distribution of a cable net structure. The method comprises the following steps: acquiring coordinates of each boundary node and coordinates of each free node of the cable net structure; inputting each boundary node coordinate into a deep learning force finding model, and outputting a coordinate prediction value of each free node; calculating the sum of the mean square residual error of the physical balance equations of all the free nodes and the mean square error of the coordinate predicted value and the true value, namely a loss function value; adjusting parameters of the deep learning force finding model and the cable prestress according to the loss function value, updating the deep learning force finding model until the calculated loss function is smaller than a set error, and obtaining the cable prestress, namely the initial prestress distribution of the cable net structure. According to the method, the boundary node coordinates of the cable net structure serve as the input of the deep learning force finding model, the free node coordinates serve as the output, the initial prestress distribution of the cable net structure is found through the deep learning force finding model, and compared with existing manual force finding, the calculation efficiency is high, and rapidness and accuracy are achieved.

Description

Technical Field

[0001] The present invention relates to the field of construction, and more specifically, to a method and system for calculating initial prestress distribution of a cable net structure. Background Art

[0002] The cable net structure is novel, beautiful and lightweight, and is widely used in large space structures. Due to the influence of geometric nonlinearity, the geometric shape of the structure will change significantly from the zero stress state to the initial prestressed state or load state, affecting the mechanical performance of the structure. Therefore, the initial prestressed state plays a vital role in the mechanical performance of the structure and affects the rationality of subsequent design and analysis.

[0003] When designing a cable net structure, the geometric position of the initial prestressed state of the structure is generally determined by the architectural shape designed by the architect, that is, the initial state of the cable net structure is determined. However, the initial prestress distribution is unknown and needs to be determined through force analysis. Currently, the commonly used force finding methods include force density method, dynamic relaxation method, nonlinear finite element method, analytical method, etc. These methods have been well applied in actual engineering.

[0004] However, in the above methods, either the mathematical theory is complicated and difficult for structural engineers to master, or the stiffness matrix is ​​prone to singular convergence difficulties or requires repeated debugging to determine the appropriate initial value. The debugging process is cumbersome and time-consuming, and the cable net structure form-finding efficiency is low. Summary of the invention

[0005] For cable net structures, it is necessary to propose a quick and easy-to-apply force finding method. The present invention provides a method and system for calculating the initial prestress distribution of a cable net structure.

[0006] According to a first aspect of the present invention, a method for calculating initial prestress distribution of a cable net structure is provided, comprising: Step 1, when the initial geometric shape of the cable net structure is known, obtain the coordinates of each boundary node and each free node of the cable net structure; Step 2, setting the initial parameters of the deep learning force finding model and the initial cable prestress; Step 3, input the coordinates of each boundary node into the deep learning force finding model, and output the predicted value of each free node coordinate; Step 4, calculating the mean square residual of the physical balance equation of all free nodes and the mean square error between the predicted value and the true value of the coordinates of all free nodes, and calculating the loss function value of the deep learning force finding model according to the mean square residual of the physical balance equation and the mean square error; Step 5, adjust the parameters of the deep learning force finding model and the cable prestress according to the loss function value, update the deep learning force finding model, and repeat steps 3 to 5 until the calculated loss function is less than the set error, and obtain the cable prestress, that is, the initial prestress distribution of the cable net structure.

[0007] According to a second aspect of the present invention, there is provided a system for calculating initial prestress distribution of a cable net structure, comprising: An acquisition module is used to acquire the coordinates of each boundary node and each free node of the cable net structure when the initial geometric shape of the cable net structure is known; The setting module is used to set the initial parameters of the deep learning force-finding model and the initial cable prestress; A prediction module, used to input the coordinates of each boundary node into the deep learning force finding model and output the predicted value of each free node coordinate; A calculation module, used to calculate the mean square residual of the physical balance equation of all free nodes and the mean square error between the predicted value and the true value of the coordinates of all free nodes, and to calculate the loss function value of the deep learning force finding model according to the mean square residual of the physical balance equation and the mean square error; An adjustment module is used to adjust the parameters of the deep learning force finding model and the cable prestress according to the loss function value, update the deep learning force finding model, repeatedly call the prediction module, the calculation module and the adjustment module until the calculated loss function is less than the set error, and obtain the cable prestress, that is, the initial prestress distribution of the cable net structure.

[0008] The present invention provides a method and system for calculating the initial prestress distribution of a cable net structure, which obtains the coordinates of each boundary node and each free node of the cable net structure; inputs each boundary node coordinate into a deep learning force finding model, and outputs a predicted value of each free node coordinate; calculates the mean square residual of the physical balance equation of all free nodes and the mean square error of the predicted value of all free node coordinates and the true value, and calculates the loss function value of the deep learning force finding model according to the mean square residual and the mean square error of the physical balance equation; adjusts the parameters and cable prestress of the deep learning force finding model according to the loss function value, and updates the deep learning force finding model until the calculated loss function is less than the set error, and obtains the cable prestress, that is, the initial prestress distribution of the cable net structure. The present invention uses the boundary node coordinates of the cable net structure as the input of the deep learning force finding model, and the free node coordinates as the output, and uses the deep learning force finding model to find the initial prestress distribution of the cable net structure. Compared with the existing manual force finding, the calculation efficiency is high, and it is fast and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flow chart of a method for calculating the initial prestress distribution of a cable net structure provided by the present invention; Figure 2 A schematic diagram of the structure of the force-finding model for deep learning; Figure 3 This is a schematic diagram of the chain derivation rule; Figure 4 Schematic diagram of node numbering, boundary nodes and free nodes of orthogonal cable net structure; Figure 5 It is a schematic diagram of the initial state of the orthogonal cable net structure; Figure 6 This is a schematic diagram of the orthogonal cable net force finding results; Figure 7 It is a schematic diagram of the node numbering, boundary nodes and free nodes of the oblique cable net structure; Figure 8 It is a schematic diagram of the initial state of the oblique cable net structure; Fig. 9 This is a schematic diagram of the force finding results of the oblique cable net; Fig.10 Schematic diagram of node numbering, boundary nodes and free nodes of irregular cable net structure; Fig.11 It is a schematic diagram of the initial state of the irregular cable net structure; Fig.12 Schematic diagram of force finding results for irregular cable net structure; Fig.13 A structural schematic diagram of an initial prestress distribution calculation system for a cable net structure provided by the present invention. DETAILED DESCRIPTION

[0010] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention can be arbitrarily combined with each other to form a feasible technical solution. This combination is not subject to the constraints of the sequence of steps and / or the structural composition mode, but must be based on the ability of ordinary technicians in this field to achieve. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0011] In view of the defects in the background technology, the present invention proposes a deep learning force finding model for cable net structure driven by physical law-data coupling. The deep learning force finding model solves the initial prestress distribution of the structure when the initial geometric shape of the cable net structure is known: the boundary node coordinates are used as the input layer, the free node coordinates are used as the output layer, and the cable prestress is used as the unknown variable. F , establish the physical balance equation and add the loss function in the deep learning force finding model. At the same time, introduce the mean square error between the output value of the free node and the true value into the loss function, driving the deep learning model to reduce the loss function value through semi-supervised training and gradually approach zero, thereby achieving the force finding purpose of the cable net structure.

[0012] Figure 1 The present invention provides a flow chart of a method for calculating the initial prestress distribution of a cable net structure, which is written in Python and developed based on the Pytorch library. Figure 1 As shown, the method includes: Step 1: When the initial geometric shape of the cable net structure is known, obtain the coordinates of each boundary node and each free node of the cable net structure.

[0013] It can be understood that when the initial geometric shape of the cable net structure is known, the coordinates of each boundary node and each free node of the cable net structure can be obtained respectively.

[0014] Step 2: Set the initial parameters of the deep learning force-finding model and the initial cable prestress.

[0015] It is understandable that two nodes in the cable net structure are connected by a cable unit, and the prestress of the cable unit needs to be solved to obtain the coordinates of each boundary node and each free node of the cable net structure. The present invention obtains the cable prestress of the cable net structure through a deep learning force finding model.

[0016] At the beginning, the initial parameters of the deep learning force-finding model and the initial cable prestress are set.

[0017] Step 3: Input the coordinates of each boundary node into the deep learning force finding model and output the predicted value of each free node coordinate.

[0018] Among them, see Figure 2 The deep learning force-finding model includes an input layer, multiple hidden layers, and an output layer. Therefore, in step 2, when setting the initial parameters and initial cable prestress of the deep learning force-finding model, the weight coefficient and bias coefficient of each layer of the deep learning force-finding model, as well as the initial cable prestress, are set. F .

[0019] Each input boundary node coordinate is passed to multiple hidden layers through the input layer, and the neurons in each hidden layer receive the data transmitted by the neurons in the previous hidden layer, and pass it to the neurons in the next hidden layer after weighted summation and activation processing. After passing through multiple hidden layers, the predicted value of each free node coordinate is output through the output layer.

[0020] The weighted summation and activation processing of each hidden layer includes: ,

[0021]

[0022] In the formula, i For the i The hidden layer is n+1, the output layer is n+1. y i For the i The output value of the hidden layer, z Find the output value of the force model for deep learning, is the activation function, w i and b i For the i The weight coefficients and bias coefficients of the hidden layers are the parameters of the deep learning force model. is the weight coefficient of the output layer, is the bias coefficient of the output layer.

[0023] Step 4, calculate the mean square residual of the physical balance equation of all the free nodes and the mean square error between the predicted value and the true value of the coordinates of all the free nodes, and calculate the loss function value of the deep learning force finding model based on the mean square residual of the physical balance equation and the mean square error.

[0024] The calculation of the mean square residual of the physical balance equation of all the free nodes includes:

[0025]

[0026]

[0027] Calculate the mean square error between the predicted values ​​and the true values ​​of all free node coordinates, including:

[0028] Calculating the loss function value of the deep learning force finding model according to the mean square residual of the physical balance equation and the mean square error includes: Ltotal = MSE x + MSE y + MSE z + MSE m In the formula, MSE x , MSE y and MSE z The mean square error of the physical equilibrium equations in the x, y and z directions at the free nodes, MSE m is the mean square error between the predicted value of the free node coordinate and the true value of the free node coordinate, N s is the number of free nodes, m For free nodes j The number of connected cable elements, L jk and F jk Free nodes j With Node k The cable unit length and cable force between ( x j , y j , z j ) is a free node j The coordinates of ( x k , y k , z k ) is a node k The coordinates of ( x j , y j , z j ) pred and u true ( x j , y j , z j ) true are the predicted value and the true value of the free node coordinates respectively.

[0029] Step 5, adjust the parameters of the deep learning force finding model and the cable prestress according to the loss function value, update the deep learning force finding model, and repeat steps 3 to 5 until the calculated loss function is less than the set error, and obtain the cable prestress, that is, the initial prestress distribution of the cable net structure.

[0030] If the loss function value is greater than the set error range, the gradient of the loss function to the weight coefficient and bias coefficient of each hidden layer and the cable prestress in the back propagation of the deep learning force finding model are calculated by the chain rule. F The derivative of is used to update the weight coefficient, bias coefficient and cable prestress of the deep learning force model through the optimization algorithm. F , to update the deep learning force finding model. Figure 3 As shown, the gradient of the loss function with respect to the weights and biases of each layer is calculated by automatic differentiation of error back propagation.

[0031] Based on the updated deep learning force-finding model, steps 2 to 5 are repeated, and the loss function is continuously calculated until the loss function is less than the set error to obtain the cable prestress, that is, the initial prestress distribution of the cable net structure.

[0032] The following is a description of the method for calculating the initial prestress distribution of the cable net structure provided by the present invention using multiple embodiments.

[0033] Example 1: Orthogonal cable net structure, node numbering and structure initial state are as follows: Figure 4 and Figure 5 As shown, among which, Figure 4 As shown, the nodes numbered 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12 are boundary nodes, and the nodes numbered 13, 14, 15, 16, 17, 18, 19, 20, and 21 are free nodes. F 1 and F 2. The boundary nodes are fixed on the saddle surface, and its equation is Z=(X 2 -Y 2 ) / 50, by Figure 2 Determine the boundary node coordinates ( x f , y f , z f ), the free node coordinates are shown in Table 1.

[0034] Table 1 Coordinates of free nodes in the initial state of orthogonal cable net structure

[0035] For the orthogonal cable net structure, the calculation steps of the model of the present invention are as follows: (1) Input boundary node coordinates ( x f , y f , z f ), select the optimizer Adamax, and the learning rate is 0.01. Input the boundary node coordinates, pass them to the hidden layer (6 layers) and the output layer through the input layer, and each layer of neurons (32) receives the data transmitted by the neurons in the previous layer, and passes them to the next layer after weighted summation and activation (Tanh function) processing until the output data.

[0036] (2) After the data is output, the loss function is calculated. If the loss function value is greater than the set error range, the gradient and variable of the loss function for each layer weight and bias in the back propagation of the deep learning model are calculated by the chain rule. F The derivative of , updates the weights, biases and variables of the model through the optimization algorithm F , recalculate.

[0037] (3) The deep learning model automatically repeats steps 1 and 2 until the loss function is less than the set error, and the output variable F , which is the required initial prestress distribution.

[0038] Figure 6 Find the force results for the orthogonal cable net structure. Figure 6 As can be seen from the figure, after n=3000 steps of training, F 2 / F 1 gradually approaches 1, which is consistent with the theoretical ratio F 2 / F 1=1 is a better match.

[0039] Example 2: Oblique cable net structure, node numbering and structure initial state are as follows: Figure 7 and Figure 8 As shown, Figure 7 In the diagram, nodes numbered 1, 3, 3, 4, and 5 are boundary nodes, and nodes numbered 6, 7, 8, 9, and 10 are free nodes. The cable forces are F 1. F 2. F 3. F 4 and F 5. The boundary node is fixed on the saddle surface, and its equation is Z=(X 2 -Y 2 ) / 50, by Figure 6 Determine the boundary node coordinates ( x f , y f , z f ), the free node coordinates are shown in Table 2.

[0040] Table 2 Coordinates of free nodes in the initial state of the oblique cable net structure

[0041] The calculation steps are the same as those in the first embodiment.

[0042] Fig. 9 Find the force results for the oblique cable net structure. Fig. 9 As can be seen from the figure, after n=4000 steps of training, F 2 / F 1. F 3 / F 1. F 4 / F 1. F 5 / F 1 gradually approaches 1, which is consistent with the theoretical ratio F 1: F 2: F 3: F 4: F 5=1:1:1:1:1 is a better match.

[0043] Example 3: Irregular cable net structure, node numbering and structure initial state are as follows: Fig.10 and Fig.11 As shown, Fig.10 In the diagram, nodes numbered 1, 2, 3, 4, 5, 6, 7, 8, 9, and 10 are boundary nodes, and nodes numbered 11, 12, 13, 14, 15, and 16 are free nodes. The cable forces are F 1. F 2. F 3. F 4 and F 5. By Fig.10 and Table 3 to determine the boundary node coordinates ( x f , y f , z f ), the free node coordinates are shown in Table 4.

[0044] Table 3 Z coordinates of boundary nodes of irregular cable net structure

[0045] Table 4 Coordinates of free nodes in the initial state of irregular cable net structure

[0046] The calculation steps are the same as those in the first embodiment.

[0047] Fig.12Find the force results for the irregular cable net structure. Fig.12 As can be seen from the figure, after n=4000 steps of training, F 2 / F 1. F 3 / F 1. F 4 / F 1. F 5 / F 1 gradually approaches 1, which is consistent with the theoretical ratio F 1: F 2: F 3: F 4: F 5=1:1:1:1:1 is a better match.

[0048] The above three embodiments all show that the force finding results of the model of the present invention are in good agreement with the theoretical solution, with high accuracy, and the time taken is no more than 1 minute, with high calculation efficiency.

[0049] See also Fig.13 , provides a cable net structure initial prestress distribution calculation system of the present invention, the system comprising: An acquisition module 1301 is used to acquire the coordinates of each boundary node and each free node of the cable net structure when the initial geometric shape of the cable net structure is known; A setting module 1302 is used to set initial parameters of the deep learning force finding model and initial cable prestress; Prediction module 1303, used to input the coordinates of each boundary node into the deep learning force finding model, and output the predicted value of each free node coordinate; A calculation module 1304 is used to calculate the mean square residuals of the physical balance equations of all the free nodes and the mean square errors between the predicted values ​​and the true values ​​of the coordinates of all the free nodes, and calculate the loss function value of the deep learning force finding model according to the mean square residuals of the physical balance equations and the mean square errors; The adjustment module 1305 is used to adjust the parameters of the deep learning force finding model and the cable prestress according to the loss function value, update the deep learning force finding model, repeatedly call the prediction module, the calculation module and the adjustment module until the calculated loss function is less than the set error, and obtain the cable prestress, that is, the initial prestress distribution of the cable net structure.

[0050] It can be understood that the initial prestress distribution calculation system of the cable net structure provided by the present invention corresponds to the initial prestress distribution calculation method of the cable net structure provided by the aforementioned embodiments. The relevant technical features of the initial prestress distribution calculation system of the cable net structure can refer to the relevant technical features of the initial prestress distribution calculation method of the cable net structure, which will not be repeated here.

[0051] A method for calculating the initial prestress distribution of a cable net structure provided by an embodiment of the present invention comprises the following steps: obtaining the coordinates of each boundary node and each free node of the cable net structure; inputting each boundary node coordinate into a deep learning force finding model, and outputting a predicted value of each free node coordinate; calculating the mean square residual of the physical balance equation of all free nodes and the mean square error between the predicted value and the true value of all free node coordinates, and calculating the loss function value of the deep learning force finding model according to the mean square residual of the physical balance equation and the mean square error; adjusting the parameters and cable prestress of the deep learning force finding model according to the loss function value, and updating the deep learning force finding model until the calculated loss function is less than the set error, and obtaining the cable prestress, that is, the initial prestress distribution of the cable net structure. The present invention uses the boundary node coordinates of the cable net structure as the input of the deep learning force finding model, and the free node coordinates as the output, and uses the deep learning force finding model to find the initial prestress distribution of the cable net structure. Compared with the existing manual force finding, the calculation efficiency is high, and it is fast and accurate.

[0052] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0053] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0055] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0057] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

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

Claims

1. A method for calculating the initial prestress distribution of a cable net structure, characterized in that: include: Step 1, when the initial geometric shape of the cable net structure is known, obtain the coordinates of each boundary node and each free node of the cable net structure; Step 2, setting the initial parameters of the deep learning force finding model and the initial cable prestress; Step 3, input the coordinates of each boundary node into the deep learning force finding model, and output the predicted value of each free node coordinate; Step 4, calculating the mean square residual of the physical balance equation of all free nodes and the mean square error between the predicted value and the true value of the coordinates of all free nodes, and calculating the loss function value of the deep learning force finding model according to the mean square residual of the physical balance equation and the mean square error; Step 5, adjust the parameters of the deep learning force finding model and the cable prestress according to the loss function value, update the deep learning force finding model, and repeat steps 3 to 5 until the calculated loss function value is less than the set error, and obtain the cable prestress, that is, the initial prestress distribution of the cable net structure.

2. The method for calculating the initial prestress distribution of a cable net structure according to claim 1, characterized in that: The deep learning force finding model includes an input layer, multiple hidden layers and an output layer. The step 3 inputs each boundary node coordinate into the deep learning force finding model and outputs each free node coordinate prediction value, including: The coordinates of each boundary node input are passed to multiple hidden layers through the input layer. The neurons in each hidden layer receive the data transmitted by the neurons in the previous hidden layer, and after weighted summation and activation processing, they are passed to the neurons in the next hidden layer. After passing through multiple hidden layers, the predicted value of each free node coordinate is output through the output layer.

3. The method for calculating the initial prestress distribution of a cable net structure according to claim 2, characterized in that: The step 2, setting the initial parameters of the deep learning force finding model and the initial cable prestress, includes: Set the weight coefficient and bias coefficient of each layer of the deep learning force finding model, as well as the initial cable prestress F .

4. The method for calculating the initial prestress distribution of a cable net structure according to claim 2, characterized in that: The weighted summation and activation processing of each hidden layer includes: ， In the formula, i For the i The hidden layer is n+1, the output layer is n+1. y i For the i The output value of the hidden layer, z Find the output value of the force model for deep learning, is the activation function, w i and b i For the i The weight coefficients and bias coefficients of the hidden layers are the parameters of the deep learning force model. is the weight coefficient of the output layer, is the bias coefficient of the output layer.

5. The method for calculating the initial prestress distribution of a cable net structure according to claim 1, characterized in that: The step 4, calculating the mean square residual of the physical balance equation of all free nodes and the mean square error between the predicted value and the true value of the coordinates of all free nodes, includes: The loss function value of the deep learning force finding model is calculated according to the mean square residual of the physical balance equation and the mean square error between the predicted value and the true value of the free node coordinates, including: L total = MSE x + MSE y + MSE z + MSE m In the formula, MSE x , MSE y and MSE z The mean square residuals of the physical equilibrium equations in the x, y and z directions at the free nodes, MSE m is the mean square error between the predicted values ​​of all free node coordinates and the true values ​​of all free node coordinates, N s is the number of free nodes, m For free nodes j The number of connected cable elements, L jk and F jk Free nodes j With Node k The cable unit length and cable force between ( x j , y j , z j ) is a free node j The coordinates of ( x k , y k , z k ) is a node k The coordinates of ( x j , y j , z j ) pred and u true ( x j , y j , z j ) true are the predicted value and the true value of the free node coordinates respectively.

6. The method for calculating the initial prestress distribution of a cable net structure according to claim 1, characterized in that: The step 5, adjusting the parameters of the deep learning force finding model and the cable prestress according to the loss function value, and updating the deep learning force finding model, comprises: If the loss function value is greater than the set error range, the gradient of the loss function to the weight coefficient and bias coefficient of each layer and the cable prestress in the back propagation of the deep learning force finding model are calculated by the chain rule. F The derivative of is used to update the weight coefficient, bias coefficient and cable prestress of the deep learning force model through the optimization algorithm. F .

7. A cable net structure initial prestress distribution calculation system, characterized in that: include: An acquisition module is used to acquire the coordinates of each boundary node and each free node of the cable net structure when the initial geometric shape of the cable net structure is known; The setting module is used to set the initial parameters of the deep learning force-finding model and the initial cable prestress; A prediction module, used to input the coordinates of each boundary node into the deep learning force finding model and output the predicted value of each free node coordinate; A calculation module, used to calculate the mean square residual of the physical balance equation of all free nodes and the mean square error between the predicted value and the true value of the coordinates of all free nodes, and to calculate the loss function value of the deep learning force finding model according to the mean square residual of the physical balance equation and the mean square error; An adjustment module is used to adjust the parameters of the deep learning force finding model and the cable prestress according to the loss function value, update the deep learning force finding model, repeatedly call the prediction module, the calculation module and the adjustment module until the calculated loss function is less than the set error, and obtain the cable prestress, that is, the initial prestress distribution of the cable net structure.

Images