Crane monitoring method, computer equipment and storage medium based on digital twin

Abstract

The present invention discloses a crane monitoring method, computer equipment, and storage medium based on digital twins, which relate to the field of crane technology. The method includes: constructing a crane arm grid model; inputting real-time dynamic data into a pre-trained RBF proxy model to output real-time coarse grid deformation data and real-time coarse grid stress data of coarse grid nodes; coloring the crane arm grid model according to the real-time coarse grid deformation data or the real-time coarse grid stress data to generate a crane arm model with a cloud effect; processing a pre-constructed crane arm proportional three-dimensional model according to real-time component relationships to generate a prototype model without a cloud effect; and constructing a stress-strain digital twin model of the crane arm based on the crane arm model and the prototype model. By adopting the present invention, the changes in the crane's geometric shape and stress-strain state during operation can be accurately understood, ensuring the safe operation of the crane and reducing safety hazards during construction.

Description

Technical Field

[0001] The present invention relates to the field of crane technology, and in particular to a crane monitoring method, computer equipment, and storage medium based on digital twins. Background Art

[0002] Cranes are widely used in factories, construction sites, ports, deep-sea operations and other fields. When performing lifting operations under different working conditions, they will be affected by different factors, and their stress state will show a time-varying dynamic effect. The damage to the crane boom structure may cause serious consequences. Therefore, the safety monitoring of the crane boom structure should be given high attention.

[0003] However, in the existing lifting system, there is no crane monitoring system platform designed based on digital twins. Operators cannot understand the geometric shape and stress-strain state of the crane during operation in real time, which is insufficient to ensure the safe operation of the crane. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a crane monitoring method, computer equipment and storage medium based on digital twins, which can accurately understand the changes in the geometric shape and stress-strain state of the crane during operation, and reduce safety hazards during construction.

[0005] In order to solve the above technical problems, the present invention provides a crane monitoring method based on digital twins, including: constructing a crane arm grid model of a target crane according to coarse grid node position data of preset coarse grid nodes; obtaining real-time dynamic data of the target crane in physical space, and inputting the real-time dynamic data into a pre-trained RBF proxy model to output real-time coarse grid deformation data and real-time coarse grid stress data of the coarse grid nodes; coloring the crane arm grid model according to the real-time coarse grid deformation data or the real-time coarse grid stress data to generate a crane arm model with a cloud effect; obtaining the real-time component relationship of the target crane, and processing the pre-constructed crane arm proportional three-dimensional model according to the real-time component relationship to generate a prototype model without a cloud effect; constructing a stress-strain digital twin model of the crane arm according to the crane arm model and the prototype model.

[0006] As an improvement to the above scheme, the training steps of the RBF proxy model include: performing fine grid division and finite element calculation on the proportional three-dimensional model of the crane arm to generate fine grid node position data, fine grid deformation data and fine grid stress data based on the fine grid; performing coarse grid division on the proportional three-dimensional model of the crane arm to generate coarse grid node position data based on the coarse grid; performing interpolation operation based on the fine grid node position data, fine grid deformation data, fine grid stress data and coarse grid node position data to generate coarse grid deformation data and coarse grid stress data; obtaining historical dynamic data of the target crane under different working conditions in the physical space; constructing an RBF neural network, and using the historical dynamic data as the input of the RBF neural network, and using the coarse grid deformation data and coarse grid stress data as the output of the RBF neural network to generate RBF proxy models of different coarse grid nodes; and encapsulating the RBF proxy model.

[0007] As an improvement to the above scheme, the proportional three-dimensional model of the crane arm is divided into fine grids or coarse grids according to the force characteristics of the target crane, wherein fine grid division is performed at positions where the force density is greater than or equal to the preset density, and coarse grid division is performed at positions where the force density is less than the preset density.

[0008] As an improvement to the above-mentioned solution, when the proportional three-dimensional model of the crane arm is divided into fine grids, the divided grids are subjected to irrelevant detection, wherein, when the increase in the number of grids has an impact on the results of the finite element calculation that is greater than or equal to a preset threshold, the divided grids continue to be refined; when the increase in the number of grids has an impact on the results of the finite element calculation that is less than the preset threshold, the divided grids are no longer refined.

[0009] As an improvement to the above solution, when performing interpolation operations based on the fine grid node position data, fine grid deformation data, fine grid stress data and coarse grid node position data, shape functions are used for interpolation operations.

[0010] As an improvement to the above solution, the step of coloring the crane arm mesh model according to the real-time coarse mesh deformation data or the real-time coarse mesh stress data includes: adjusting the color of the coarse mesh node according to the real-time coarse mesh deformation data, wherein when the real-time coarse mesh deformation data is greater than or equal to the allowable deformation value of the material, the coarse mesh node is set to a first preset color; when the real-time coarse mesh deformation data is 0, the coarse mesh node is set to a second preset color; when the real-time coarse mesh deformation data is between 0 and the allowable deformation value of the material, the hue value of the HSV color model is calculated according to the formula H=2([ε]-ε1) / 3[ε] to adjust the color of the coarse mesh node, wherein H is the hue value of the HSV color model, [ε] is the allowable deformation value of the material, and ε1 is the real-time coarse mesh deformation data; or

[0011] The color of the coarse mesh node is adjusted according to the real-time coarse mesh stress data, wherein when the real-time coarse mesh stress data is greater than or equal to the allowable stress of the material, the coarse mesh node is set to a first preset color; when the real-time coarse mesh stress data is 0, the coarse mesh node is set to a second preset color; when the real-time coarse mesh stress data is between 0 and the allowable stress of the material, the hue value of the HSV color model is calculated according to the formula H=2([σ]-σ1) / 3[σ] to adjust the color of the coarse mesh node, wherein H is the hue value of the HSV color model, [σ] is the allowable stress of the material, and σ1 is the real-time coarse mesh stress data.

[0012] As an improvement to the above solution, the steps of constructing the proportional three-dimensional model of the crane arm include: obtaining the benchmark data of the target crane in the physical space; and constructing the proportional three-dimensional model of the crane arm based on the benchmark data.

[0013] As an improvement of the above-mentioned scheme, the crane monitoring method based on digital twins also includes: simulating different working conditions of the target crane through the movement of the six-degree-of-freedom platform in the physical space; setting sensors in the target crane, and collecting real-time dynamic data of the target crane through the sensors, and the dynamic data includes crane posture data, wire rope tension data, hoisted object data and distance data.

[0014] Correspondingly, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein the processor implements the steps of the above-mentioned digital twin-based crane monitoring method when executing the computer program.

[0015] Correspondingly, the present invention also provides a computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the above-mentioned crane monitoring method based on digital twins are implemented.

[0016] The implementation of the present invention has the following beneficial effects:

[0017] The dynamic data of the sensors in the physical space of the present invention can be transmitted to the controller in real time, so that the stress-strain digital twin model can be updated in real time, and its structural performance display can approach the working conditions in real time; at the same time, the present invention only establishes a stress-strain digital twin model for the key load-bearing components of the crane (crane arm), which can save computing costs and speed up the calculation speed; therefore, the operator can use the stress-strain digital twin model to understand the geometric shape and stress-strain state changes of the crane in real time and accurately during operation, ensure the safe operation of the crane, and reduce safety hazards during construction.

[0018] Furthermore, the present invention can simulate the operation mode of the crane under different working conditions through a six-degree-of-freedom platform, making the time-varying dynamic effect of the crane force more realistic; at the same time, the present invention also completes the stress and deformation interpolation of the coarse grid nodes according to the spatial position of the fine grid nodes. The interpolated coarse grid node stress and deformation data are used for RBF neural network training, which can greatly improve the accuracy of the model; in addition, the present invention establishes an RBF proxy model for each node of the coarse grid and encapsulates the RBF proxy model for easy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic diagram of the interpolation operation in the present invention;

[0020] Figure 2 It is a schematic diagram of the RBF neural network in the present invention;

[0021] Figure 3 This is a flow chart of an embodiment of the crane monitoring method based on digital twins of the present invention. DETAILED DESCRIPTION

[0022] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be described in further detail below with reference to the accompanying drawings.

[0023] It should be noted that before crane monitoring, it is necessary to build a physical space based on the target crane, construct a proportional three-dimensional model of the crane arm, and train the RBF agent model.

[0024] The steps to build a physical space based on the target crane include:

[0025] (1) Simulate different working conditions of the target crane through the movement of a six-degree-of-freedom platform in physical space;

[0026] (2) Several sensors are installed in the target crane, and the real-time dynamic data of the target crane is collected through the sensors.

[0027] It should be noted that the sensors include an IMU attitude sensor, a tension sensor, a gyroscope, and a rope sensor, and dynamic data includes crane attitude data, wire rope tension data, load data, and distance data. The IMU attitude sensor is used to measure crane attitude data, including displacement, velocity, acceleration, angle, angular velocity, and angular acceleration in three spatial directions; the tension sensor is used to measure wire rope tension data; the gyroscope is used to measure load data, such as the load's inclination, angular velocity, and angular acceleration in three spatial directions; and the rope sensor is used to measure the linear distance between the load and the rope sensor.

[0028] Therefore, in the physical space, the direction and speed of the servo motor can be controlled by client devices such as PLC and computer to simulate different working conditions of the target crane and read the real-time dynamic data collected by the sensor.

[0029] In addition, the steps for building a proportional 3D model of the crane arm include:

[0030] (1) Obtaining reference data of the target crane in physical space; wherein the reference data includes, but is not limited to, dimensional characteristics and material properties.

[0031] (2) Construct a proportional 3D model of the crane arm based on the benchmark data. In practical applications, SolidWorks software can be used to complete the proportional 3D modeling of the crane arm.

[0032] Accordingly, the training steps of the RBF surrogate model include:

[0033] (1) Perform fine mesh division and finite element calculation on the crane arm's proportional three-dimensional model to generate fine mesh node position data, fine mesh deformation data, and fine mesh stress data based on the fine mesh;

[0034] After importing the crane arm's proportional 3D model into the finite element software, the matching relationship and material properties of the crane arm's proportional 3D model are defined in the finite element software. Meshing and mesh independence testing are then performed, and forces and constraints are added to enable simulation calculations under different working conditions. Finally, the elements for which calculation results need to be displayed are selected, and fine mesh node position data, fine mesh deformation data, and fine mesh stress data based on the fine mesh are exported.

[0035] It should be noted that the fit relationship is the "binding constraint" between the various components of the crane arm, derived from the static analysis of the crane arm. That is, the contact interfaces are welded together and cannot separate or slide. The material properties can be defined based on the material of the actual object. The material used in the crane arm model is "structural steel".

[0036] (2) Perform coarse mesh division on the proportional three-dimensional model of the crane arm and generate coarse mesh node position data based on the coarse mesh;

[0037] Similarly, a coarser mesh division of the crane arm can be completed in the finite element software, and the coarse mesh node position data based on the coarse mesh can be exported.

[0038] It should be noted that when fine meshing or coarse meshing is performed on the proportional three-dimensional model of the crane arm, meshing can be performed according to the force characteristics of the target crane; among them, fine meshing is performed at positions where the force density is greater than or equal to the preset density, and coarse meshing is performed at positions where the force density is less than the preset density.

[0039] Therefore, the present invention can refine the mesh where the force is concentrated or complex, and make the mesh coarser where the force is less, so as to simulate the force state of the crane arm more realistically.

[0040] At the same time, when fine-meshing the proportional three-dimensional model of the crane arm according to the force characteristics of the target crane, the divided grids need to be tested for irrelevance. When the increase in the number of grids has an impact on the results of the finite element calculation that is greater than or equal to a preset threshold, the divided grids continue to be refined. When the increase in the number of grids has an impact on the results of the finite element calculation that is less than a preset threshold, the divided grids are no longer refined.

[0041] That is to say, when the increase in the number of grids has little effect on the calculation results, there is no need to continue to refine the grid, that is, to reduce the calculation cost while ensuring the authenticity of the numerical simulation results.

[0042] (3) Perform interpolation operations based on the fine grid node position data, fine grid deformation data, fine grid stress data, and coarse grid node position data to generate coarse grid deformation data and coarse grid stress data;

[0043] That is to say, based on the fine grid node position data, fine grid deformation data, and fine grid stress data under different working conditions, the coarse grid deformation data and coarse grid stress data under different working conditions can be calculated using the interpolation algorithm.

[0044] Furthermore, when performing interpolation operations based on the fine grid node position data, the fine grid deformation data, the fine grid stress data, and the coarse grid node position data, shape functions are used for interpolation operations.

[0045] like Figure 1As shown in the figure, e is a coarse mesh node, and a, b, c, and d are fine mesh nodes. Take the four known points a, b, c, and d closest to the point to be determined, and assign weights to points a, b, c, and d based on their linear distances from e. Then, the stress (deformation) data of points a, b, c, and d are multiplied by the weights and summed. This sum is the stress (deformation) data of point e.

[0046] In this embodiment, the weight of point d is L d =V e-abc / V d-abc , the weight of point c is L c =V e-abd / V c-abd , the weight of point b is L b =V e-acd / V b-acd , the weight of point a is L a =V e-bcd / V a-bcd , where V e-abc is the volume of tetrahedron eabc, V d-abc is the volume of tetrahedron dabc, V e-abd is the volume of tetrahedron eabd, V c-abd is the volume of the tetrahedron cabd, V e-acd is the volume of tetrahedron eacd, V b-acd is the volume of tetrahedron bacd, V e-bcd is the volume of the tetrahedron ebcd, V a-bcd is the volume of tetrahedron abcd.

[0047] (4) Obtain historical dynamic data of the target crane under different working conditions in physical space;

[0048] (5) Constructing an RBF neural network, taking historical dynamic data as the input of the RBF neural network, and taking coarse grid deformation data and coarse grid stress data as the output of the RBF neural network to generate RBF proxy models of different coarse grid nodes;

[0049] like Figure 2 As shown in the figure, the input layer of the RBF neural network is a one-dimensional vector [F1, F2, F3…], and the output layer is [σ, ε]. The dynamic data of the sensor is selected as the input, and the stress and deformation values ​​of the rough grid nodes are used as the output to obtain the RBF proxy model under each node.

[0050] (6) Encapsulate the RBF proxy model.

[0051] Preferably, the RBF proxy model can be encapsulated using the joblib.dump() function in PyCharm.

[0052] See also Figure 3 , Figure 3 The flowchart of an embodiment of the crane monitoring method based on digital twin of the present invention is shown, which includes:

[0053] S101, constructing a crane arm grid model of a target crane according to coarse grid node position data of preset coarse grid nodes;

[0054] In practical applications, a crane arm mesh model of a target crane can be established in Unity software based on the coarse mesh node position data of the coarse mesh nodes.

[0055] S102, acquiring real-time dynamic data of a target crane in a physical space, and inputting the real-time dynamic data into a pre-trained RBF proxy model to output real-time coarse grid deformation data and real-time coarse grid stress data of coarse grid nodes;

[0056] Specifically, the real-time dynamic data collected by sensors in the physical space are transmitted to the controller via Bluetooth communication / wireless network communication / HslCommunication communication / wired communication to serve as input data for the RBF agent model.

[0057] S103, performing coloring processing on the crane arm mesh model according to the real-time coarse mesh deformation data or the real-time coarse mesh stress data to generate a crane arm model with a cloud effect;

[0058] The present invention can use the HSV (Hue, Saturation, Value) mode to display colors in Unity according to the real-time coarse grid deformation data or real-time coarse grid stress data of each coarse grid node output by the RBF proxy model, wherein the parameter H in the HSV mode represents hue, the parameter S represents saturation, and the parameter V represents lightness.

[0059] In the present invention, the parameters S and V in the HSV mode are first set to 1, and then the value of the parameter H is adjusted according to the real-time coarse grid deformation data, so as to achieve the effect of displaying a cloud map.

[0060] Specifically, the steps of adjusting the colors of the coarse grid nodes according to the real-time coarse grid deformation data to color the crane arm grid model include:

[0061] (1) When the real-time coarse mesh deformation data is greater than or equal to the allowable deformation value of the material, the coarse mesh nodes are set to the first preset color;

[0062] For example, when H=2 / 3, S=1, and V=1, the color is blue;

[0063] (2) When the real-time coarse grid deformation data is 0, the coarse grid nodes are set to the second preset color;

[0064] For example, when H=0, S=1, and V=1, the color is red;

[0065] (3) When the real-time coarse mesh deformation data is between 0 and the allowable deformation value of the material, the hue value of the HSV color model is calculated according to the formula H = 2([ε0] - ε1) / 3[ε] to adjust the color of the coarse mesh nodes, where H is the hue value of the HSV color model, [ε0] is the allowable deformation value of the material, and ε1 is the real-time coarse mesh deformation data.

[0066] At the same time, the steps of adjusting the color of the coarse mesh nodes according to the real-time coarse mesh stress data to color the crane arm mesh model include:

[0067] (1) When the real-time coarse grid stress data is greater than or equal to the allowable stress of the material, the coarse grid nodes are set to the first preset color;

[0068] (2) When the real-time coarse grid stress data is 0, the coarse grid nodes are set to the second preset color;

[0069] (3) When the real-time coarse mesh stress data is between 0 and the allowable stress of the material, the hue value of the HSV color model is calculated according to the formula H = 2([σ0] - σ1) / 3[σ] to adjust the color of the coarse mesh nodes, where H is the hue value of the HSV color model, [σ0] is the allowable stress of the material, and σ1 is the real-time coarse mesh stress data.

[0070] Therefore, the present invention can assign different colors to the crane arm mesh model in Unity software based on the relative size of real-time coarse mesh deformation data or real-time coarse mesh stress data, thereby achieving a cloud map effect. The real-time coarse mesh deformation data or real-time coarse mesh stress data output by the RBF proxy model can be input into Unity via socket communication.

[0071] S104, obtaining the real-time component relationships of the target crane, and processing the pre-built proportional three-dimensional model of the crane arm according to the real-time component relationships to generate a prototype model without cloud effects;

[0072] Specifically, a proportional three-dimensional model of the crane arm is imported into Unity software, and real-time component relationships of various components in the prototype are set in Unity software; wherein the real-time component relationships include motion constraint relationships and parent-child relationships.

[0073] S105: Construct a stress-strain digital twin model of the crane arm based on the crane arm model and the prototype model.

[0074] After completing the establishment of the crane arm model and prototype model, the stress-strain digital twin model of the crane arm under different working conditions can be established in Unity software, thereby realizing the visualization and three-dimensional spatial motion display of the stress-strain digital twin model.

[0075] In summary, the present invention has the following beneficial effects:

[0076] 1. The present invention can simulate the operation mode of the crane under different working conditions through a six-degree-of-freedom platform, making the time-varying dynamic effect of the crane force more realistic;

[0077] 2. The present invention completes the stress and deformation interpolation of the coarse grid nodes according to the spatial position of the fine grid nodes. The interpolated coarse grid node stress and deformation data are used for RBF neural network training, which can greatly improve the accuracy of the model;

[0078] 4. The present invention establishes an RBF proxy model for each node of the coarse grid and encapsulates the RBF proxy model for easy management;

[0079] 3. The present invention only establishes a stress-strain digital twin model for the key load-bearing components of the crane (crane arm), which can save computing costs and speed up the calculation;

[0080] 3. The dynamic data of sensors in the physical space can be transmitted to the controller in real time, so that the stress-strain digital twin model can be updated in real time, and its structural performance display can approach the working conditions in real time;

[0081] 5. Operators can use the stress-strain digital twin model to accurately understand the changes in the crane's geometric shape and stress-strain state during operation in real time, ensuring the crane's safe operation and reducing safety hazards during construction.

[0082] Accordingly, the present invention further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein when the processor executes the computer program, the steps of the above-mentioned crane monitoring method based on digital twins are implemented. Furthermore, the present invention further provides a computer-readable storage medium storing the computer program, wherein when the processor executes the computer program, the steps of the above-mentioned crane monitoring method based on digital twins are implemented.

[0083] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A crane monitoring method based on digital twins, characterized in that: include: Constructing a crane arm grid model of the target crane according to the coarse grid node position data of the preset coarse grid nodes; Acquire real-time dynamic data of the target crane in the physical space, and input the real-time dynamic data into a pre-trained RBF proxy model to output real-time coarse grid deformation data and real-time coarse grid stress data of the coarse grid nodes; performing coloring processing on the crane arm mesh model according to the real-time coarse mesh deformation data or the real-time coarse mesh stress data to generate a crane arm model with a cloud effect; Obtaining the real-time component relationships of the target crane, and processing the pre-built proportional three-dimensional model of the crane arm according to the real-time component relationships to generate a prototype model without cloud effects; Constructing a stress-strain digital twin model of the crane arm based on the crane arm model and the prototype model; The training steps of the RBF proxy model include: Performing fine mesh division and finite element calculation on the proportional three-dimensional model of the crane arm to generate fine mesh node position data, fine mesh deformation data, and fine mesh stress data based on the fine mesh; Performing coarse grid division on the three-dimensional model of the crane arm in proportion to the coarse grid to generate coarse grid node position data based on the coarse grid; performing interpolation operations based on the fine grid node position data, the fine grid deformation data, the fine grid stress data, and the coarse grid node position data to generate coarse grid deformation data and coarse grid stress data; Obtain historical dynamic data of the target crane under different working conditions in physical space; Constructing an RBF neural network, and using the historical dynamic data as input of the RBF neural network, and using the coarse grid deformation data and coarse grid stress data as output of the RBF neural network, so as to generate RBF proxy models of different coarse grid nodes; The RBF proxy model is encapsulated.

2. The crane monitoring method based on digital twin according to claim 1, characterized in that: According to the force characteristics of the target crane, the three-dimensional model of the crane arm is divided into fine grids or coarse grids, wherein: Fine meshing is performed at locations where the force density is greater than or equal to the preset density. Coarse grid division is performed at locations where the force density is less than the preset density.

3. The crane monitoring method based on digital twin according to claim 1, characterized in that: When the three-dimensional model of the crane arm is divided into fine grids, the divided grids are subjected to irrelevant detection, wherein: When the effect of the increase in the number of grids on the result of the finite element calculation is greater than or equal to a preset threshold, the divided grids are further refined. When the effect of the increase in the number of grids on the result of the finite element calculation is less than the preset threshold, the divided grids are no longer refined.

4. The crane monitoring method based on digital twin according to claim 1, characterized in that: When performing interpolation operations based on the fine grid node position data, fine grid deformation data, fine grid stress data, and coarse grid node position data, shape functions are used for interpolation operations.

5. The crane monitoring method based on digital twin according to claim 1, characterized in that: The step of coloring the crane arm mesh model according to the real-time coarse mesh deformation data or the real-time coarse mesh stress data comprises: The color of the coarse grid nodes is adjusted according to the real-time coarse grid deformation data, wherein: When the real-time coarse grid deformation data is greater than or equal to the allowable deformation value of the material, the coarse grid node is set to the first preset color. When the real-time coarse grid deformation data is 0, the coarse grid nodes are set to the second preset color. When the real-time coarse mesh deformation data is between 0 and the allowable deformation value of the material, the hue value of the HSV color model is calculated according to the formula H=2([ε]-ε1) / 3[ε] to adjust the color of the coarse mesh node, where H is the hue value of the HSV color model, [ε] is the allowable deformation value of the material, and ε1 is the real-time coarse mesh deformation data; or The color of the coarse grid nodes is adjusted according to the real-time coarse grid stress data, wherein: When the real-time coarse grid stress data is greater than or equal to the allowable stress of the material, the coarse grid nodes are set to the first preset color. When the real-time coarse grid stress data is 0, the coarse grid nodes are set to the second preset color. When the real-time coarse mesh stress data is between 0 and the allowable stress of the material, the hue value of the HSV color model is calculated according to the formula H=2([σ]-σ1) / 3[σ] to adjust the color of the coarse mesh node, where H is the hue value of the HSV color model, [σ] is the allowable stress of the material, and σ1 is the real-time coarse mesh stress data.

6. The crane monitoring method based on digital twin according to claim 1, characterized in that: The steps of constructing the proportional three-dimensional model of the crane arm include: Obtaining benchmark data of the target crane in physical space; A proportional three-dimensional model of the crane arm is constructed according to the reference data.

7. The crane monitoring method based on digital twin according to claim 1, characterized in that: Also includes: Simulating different working conditions of the target crane by moving the six-degree-of-freedom platform in the physical space; A sensor is set in the target crane, and the real-time dynamic data of the target crane is collected by the sensor. The dynamic data includes crane posture data, wire rope tension data, hanging object data and distance data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images