Assembly method and electronic device

Abstract

The application discloses an assembling method and electronic equipment, and relates to the manufacturing field. The method is applied to the electronic equipment, and the method comprises the following steps: constructing a group of component-to-be-assembled models according to a group of first measurement parameters obtained by measuring a group of component-to-be-assembled, and constructing a group of bearing component models according to a group of second measurement parameters obtained by measuring a group of bearing components; updating initial control parameters according to a simulation assembling result obtained by performing a simulation assembling operation by using the initial control parameters, until the simulation assembling result reaches a target assembling condition, so as to obtain target control parameters; and performing actual assembling operation of assembling the group of component-to-be-assembled to the group of bearing components according to the target control parameters and assembling process parameters. By the application, the technical problem that the assembling reliability of equipment components is low due to the same control parameters used for performing the assembling operation is solved, and the technical effect of improving the assembling reliability of equipment components is achieved.

Description

Technical Field

[0001] This application relates to the field of manufacturing, and more particularly to an assembly method and an electronic device. Background Technology

[0002] In related technologies, robotic arms or other assembly equipment can be used to automatically assemble equipment components according to pre-set control parameters. However, due to factors such as production batches and processing precision, different equipment components may have different characteristics. When using the same control parameters to perform assembly operations, incomplete assembly or damage to equipment components can easily occur, resulting in low assembly reliability. Summary of the Invention

[0003] This application provides an assembly method and an electronic device to at least solve the problem of low assembly reliability of equipment components in related technologies.

[0004] This application provides an assembly method applied to an electronic device. The method includes: constructing a set of component models to be assembled based on a set of first measurement parameters, and constructing a set of carrier component models based on a set of second measurement parameters. The first set of measurement parameters indicates component features of the set of components to be assembled obtained by measuring the set of components to be assembled; the second set of measurement parameters indicates component features of the set of carrier components obtained by measuring the set of carrier components; the set of components to be assembled is to be assembled onto the set of carrier components; the set of component models is used to simulate the set of components to be assembled on a computer; and the set of carrier component models is used to simulate the set of carrier components on a computer. The method also includes performing a simulated assembly operation using initial control parameters. The obtained simulated assembly results update the initial control parameters until the simulated assembly results reach the target assembly conditions, thus obtaining the target control parameters. The simulated assembly operation simulates the assembly of a set of component models to be assembled onto a set of supporting component models. The target control parameters indicate the changes in the physical relationship between the set of components to be assembled and the set of supporting components during the actual assembly operation. The actual assembly operation is the assembly of a set of components to be assembled onto a set of supporting components. The actual assembly operation is executed based on the target control parameters and the assembly process parameters. The assembly process parameters indicate the changes in the component parameters of the set of components to be assembled and / or the changes in the component parameters of the set of supporting components during the execution of the actual assembly operation.

[0005] This application also provides an assembly apparatus, comprising: a construction module, configured to construct a set of component models to be assembled based on a set of first measurement parameters, and a set of support component models based on a set of second measurement parameters, wherein the first measurement parameters indicate component features of the set of components to be assembled obtained by measuring the set of components to be assembled, and the second measurement parameters indicate component features of the set of support components obtained by measuring the set of support components, the set of components to be assembled is to be assembled onto the set of support components, the set of component models to be assembled is used to simulate the set of components to be assembled on a computer, and the set of support component models is used to simulate the set of support components on a computer; and an update module, configured to update the assembly model obtained by performing a simulated assembly operation using initial control parameters. The simulated assembly results are used to update the initial control parameters until the simulated assembly results reach the target assembly conditions, thus obtaining the target control parameters. The simulated assembly operation is a simulation of assembling a set of component models to be assembled into a set of supporting component models. The target control parameters are used to indicate the changes in the physical relationship between the set of components to be assembled and the set of supporting components during the actual assembly operation. The actual assembly operation is an assembly operation of assembling a set of components to be assembled into a set of supporting components. The execution module is used to execute the actual assembly operation according to the target control parameters and the assembly process parameters. The assembly process parameters are used to indicate the changes in the component parameters of the set of components to be assembled and / or the changes in the component parameters of the set of supporting components during the execution of the actual assembly operation.

[0006] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-described assembly methods.

[0007] This application also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of any of the above-described assembly methods.

[0008] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described assembly methods.

[0009] This application first constructs a set of component models and a set of support component models based on a set of first measurement parameters obtained from measuring a set of components to be assembled and a set of second measurement parameters obtained from measuring a set of support components. This allows the component models used in the simulated assembly operation to simulate the actual set of components to be assembled and the actual support components. Then, the initial control parameters are updated based on the simulated assembly results obtained by performing the simulated assembly operation using initial control parameters, until the simulated assembly results reach the target assembly conditions, thus obtaining the target control parameters. Finally, the actual assembly operation is performed based on the target control parameters and assembly process parameters. This ensures that the actual assembly operation considers both the actual component characteristics of the set of components to be assembled and the actual support components, as well as the changes in component parameters of the set of components to be assembled and / or the actual support components during the assembly process. This reduces the possibility of incomplete assembly or damage to equipment components due to mismatch between control parameters and the actual component characteristics. Therefore, this application solves the technical problem of low assembly reliability of equipment components in related technologies and achieves the technical effect of improving the assembly reliability of equipment components. Attached Figure Description

[0010] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a hardware structure block diagram of a computer device according to an embodiment of this application;

[0012] Figure 2 This is a flowchart of an assembly method according to an embodiment of this application;

[0013] Figure 3 This is a schematic diagram of a scenario of an assembly method according to an embodiment of this application;

[0014] Figure 4 This is a flowchart of a control parameter update method according to an embodiment of this application;

[0015] Figure 5 This is a control flowchart of an actual assembly operation according to an embodiment of this application;

[0016] Figure 6 This is a schematic diagram of an assembly system according to an embodiment of this application;

[0017] Figure 7 This is a structural block diagram of an assembly device according to an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0019] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0020] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] The methods and embodiments provided in this application can be executed in a computer device or similar electronic device. Taking execution on a computer device as an example, Figure 1 This is a hardware structure block diagram of a computer device according to an embodiment of this application. Figure 1 As shown, a computer device may include one or more ( Figure 1(Only one is shown in the image) Processor 102 and memory 104. Processor 102 is connected to memory 104, which stores computer programs, such as application software programs and modules, like the computer program corresponding to the assembly method in this embodiment. Processor 102 executes various functional applications and data processing by running the computer programs stored in memory 104, thus implementing the aforementioned method. The computer device may include, but is not limited to, servers, industrial computers, workstations, personal computers, controllers, or other devices with data processing capabilities. Processor 102 may include, but is not limited to, a central processing unit (CPU), a microcontroller unit (MCU), a field-programmable gate array (FPGA), or other processing devices capable of performing data processing operations. Memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, memory 104 may also include memories remotely located relative to processor 102, which can be connected to the computer device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0022] Optionally, the computer device may further include a transmission device 106 and an input / output device 108. The transmission device 106 can be used for data transmission between the computer device and other devices, and the input / output device 108 can be used to receive input information or output processing results. The processor 102, memory 104, transmission device 106, and input / output device 108 can be connected via a bus or other connection methods. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of computer equipment. For example, computer equipment may also include components that are more... Figure 1 Showing more or fewer components, or having with Figure 1 The different configurations shown.

[0023] This embodiment provides an assembly method applied to electronic devices. Figure 2 This is a flowchart of an assembly method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0024] Step S202: Construct a set of component models to be assembled based on a set of first measurement parameters, and construct a set of support component models based on a set of second measurement parameters. The set of first measurement parameters is used to indicate the component features of the set of components to be assembled obtained by measuring the set of components to be assembled, and the set of second measurement parameters is used to indicate the component features of the set of support components obtained by measuring the set of support components. The set of components to be assembled is to be assembled onto the set of support components. The set of component models to be assembled is used to simulate the set of components to be assembled on a computer, and the set of support component models is used to simulate the set of support components on a computer.

[0025] Step S204: Update the initial control parameters according to the simulation assembly results obtained by performing the simulation assembly operation using the initial control parameters until the simulation assembly results reach the target assembly conditions, and obtain the target control parameters. The simulation assembly operation is an assembly operation that simulates the assembly of a set of component models to be assembled to a set of supporting component models. The target control parameters are used to indicate the changes in the physical relationship between a set of components to be assembled and a set of supporting components in the actual assembly operation. The actual assembly operation is an assembly operation that assembles a set of components to be assembled to a set of supporting components.

[0026] Step S206: Perform actual assembly operations according to target control parameters and assembly process parameters, wherein the assembly process parameters are used to indicate the changes in component parameters of a set of parts to be assembled and / or the changes in component parameters of a set of supporting parts during the actual assembly operations.

[0027] Through the above steps, firstly, based on a set of first measurement parameters obtained from measuring a set of components to be assembled and a set of second measurement parameters obtained from measuring a set of supporting components, a set of component models to be assembled and a set of supporting component models are constructed respectively. This allows the component models used in the simulated assembly operation to simulate the component characteristics of the actual components to be assembled and the supporting components involved in the assembly. Then, the initial control parameters are updated based on the simulated assembly results obtained by performing the simulated assembly operation using the initial control parameters, until the simulated assembly results reach the target assembly conditions, thus obtaining the target control parameters. Finally, the actual assembly operation is performed based on the target control parameters and the assembly process parameters. This ensures that the actual assembly operation considers both the actual component characteristics of the components to be assembled and the supporting components, as well as the changes in the component parameters of the components to be assembled and / or the supporting components during the assembly process. This reduces the possibility of incomplete assembly or damage to equipment components due to mismatch between the control parameters and the actual component characteristics, thereby improving the assembly reliability of the equipment components.

[0028] Optionally, in this embodiment, a set of components to be assembled and a set of supporting components may be, but are not limited to, equipment components in the assembled device. The assembled device refers to the assembly object corresponding to the components to be assembled and the supporting components, such as a server, computer equipment, communication equipment, or smart terminal. A set of components to be assembled includes one or more components to be assembled participating in the same assembly operation, and a set of supporting components includes one or more supporting components participating in the same assembly operation. The number of components included in a set of components to be assembled and the number of components included in a set of supporting components may be the same or different. There may be a one-to-one correspondence, a one-to-many relationship, a many-to-one relationship, or a many-to-many relationship between a set of components to be assembled and a set of supporting components. Taking server assembly as an example, when the equipment components are server components, a server motherboard can be assembled onto multiple supporting components in the chassis in the same assembly operation, and multiple connector plugs can be respectively assembled onto (inserted into) multiple connector sockets on the same server backplane in the same assembly operation. That is to say, a component to be assembled can be assembled onto multiple supporting components in the same assembly operation, multiple components to be assembled can be jointly assembled onto the same supporting component, or multiple components to be assembled can be separately assembled onto multiple supporting components.

[0029] For ease of description, without needing to distinguish the number of parts, the following will refer to one or more parts to be assembled in a group as "parts to be assembled," and one or more load-bearing parts in a group as "load-bearing parts." The following descriptions of parts to be assembled and load-bearing parts also apply to cases where a group of parts includes multiple parts.

[0030] Optionally, the component to be assembled can be a device component that undergoes assembly movement relative to the supporting component during the actual assembly operation, and the supporting component can be a device component that forms an assembly mating relationship with the component to be assembled. The assembly movement can be a positional change process of the component to be assembled relative to the supporting component, including but not limited to translational movement, rotational movement, insertion movement, disassembly movement, or a combination of the above movements. Taking server assembly as an example, the component to be assembled and the supporting component can be a memory module and memory slot, a connector pin assembly and connector slot, or a supporting component in the server motherboard and chassis, respectively.

[0031] Figure 3 This is a schematic diagram illustrating a scenario of an assembly method according to an embodiment of this application. Figure 3 As shown, the assembly system may include computer equipment 302, one or more ( Figure 3 Only one measuring device 304 is shown in the image. Figure 3 (Only one is shown in the image) Assembly device 306. Measuring device 304 and assembly device 306 can be connected to computer device 302 respectively.

[0032] Computer device 302 can be used to receive and process data collected by measuring device 304, execute simulated assembly operations, and send control commands to assembly device 306 according to target control parameters. Computer device 302 may have... Figure 1 The hardware structure shown is used to execute the assembly method in this embodiment by running a computer program.

[0033] The measuring device 304 can be used to measure the parts to be assembled and the supporting parts before the actual assembly operation begins, and can also collect the component parameters of the parts to be assembled and / or the supporting parts during the actual assembly operation. The measuring device 304 may include, but is not limited to, laser measuring devices, displacement measuring devices, force measuring devices, temperature measuring devices, infrared thermal imaging devices, or other devices capable of collecting component characteristics or component parameters. Different types of data can be collected separately by different measuring devices 304, or they can be collected by the same measuring device 304.

[0034] Assembly equipment 306 can be used to receive and respond to control commands sent by computer equipment 302 to assemble components to be assembled onto carrier components. Assembly equipment 306 may include, but is not limited to, robotic arms, assembly robots, or other equipment capable of performing assembly actions such as movement, alignment, insertion, pressing, or fixing. Assembly equipment 306 may also include sensors for acquiring component parameters. Component parameters during the assembly process can be acquired by measuring equipment 304 or by the sensors included in assembly equipment 306.

[0035] Optionally, in the embodiment provided in step S202 above, the component features may include at least one of the geometric features, spatial distribution features, structural features, and material response features of the component to be assembled or the load-bearing component before the actual assembly operation begins. Geometric features may include length, width, height, thickness, hole diameter, slot width, or contour, etc.; spatial distribution features may include pin center coordinates, mounting hole coordinates, connection end coordinates, or relative spatial relationships between different structures, etc.; structural features may include the number of structures, the arrangement of structures, or the form of connection structures, etc.; material response features may include the deformation amount, equivalent stiffness, or elastic modulus of the component under a preset load, etc.

[0036] Optionally, the first and second measurement parameters may be measured in real time by the measuring device and sent to the computer device, or they may be associated with the corresponding component identifier and stored in a storage space accessible to the computer device. The computer device may, but is not limited to, obtain the first and second measurement parameters based on the component identifier corresponding to the current assembly task. The first and second measurement parameters may, but are not limited to, be represented by numerical data, coordinate data, point cloud data, contour data, image data, or a combination of the above.

[0037] Optionally, the models of the components to be assembled and the supporting components can be three-dimensional geometric models, rigid body models, flexible body models, finite element models, or models formed by a combination of the above models. When a group of components to be assembled or a group of supporting components includes multiple components, models can be created for each component separately, and the assembly relationships between the component models can be set. For example, when a server motherboard is to be assembled to multiple supporting components, a server motherboard model and multiple supporting component models can be constructed, and the assembly relationships between multiple mounting areas on the server motherboard model and the multiple supporting component models can be set.

[0038] In one alternative implementation, the computer device may, but is not limited to, construct a model of the component to be assembled based on a first measurement parameter. For example, if the first measurement parameter includes surface point cloud data of the component to be assembled, coordinate transformation, noise point removal, and surface fitting may be performed on the surface point cloud data, and a model of the component to be assembled may be generated based on the processed surface point cloud data.

[0039] In another alternative implementation, the computer device may, but is not limited to, invoke a parametric model corresponding to the component type of the component to be assembled, and set the corresponding model parameters to the component features indicated by the first measurement parameter to obtain a model of the component to be assembled. For example, when the component to be assembled is a pin assembly, the model parameters in the parametric model used to represent the center coordinates of the pins can be set to the measured center coordinates of the pins to obtain a model of the component to be assembled that can simulate the current pin arrangement state.

[0040] It is understood that computer devices may, but are not limited to, construct a model of the load-bearing component based on the second measurement parameters in the same or similar manner, which will not be elaborated here.

[0041] In another alternative implementation, the computer device can update the reference component model based on the deviation between the measured component features and the nominal component features to obtain the component model to be assembled and the load-bearing component model. A set of component models to be assembled can be constructed based on a set of first measurement parameters in the following manner, including: determining a set of first deviation parameters based on a set of first measurement parameters and a set of first specification parameters, wherein the set of first deviation parameters indicates the deviation between the set of first measurement parameters and the set of first specification parameters, and the set of first specification parameters indicates the nominal component features of the component model to be assembled; updating a set of first reference component models to a set of component models to be assembled based on the set of first deviation parameters, wherein the set of first reference component models is a component model constructed based on the set of first specification parameters.

[0042] Optionally, a set of first specification parameters can be obtained from the design model, design drawings, or component specification files of the component to be assembled. A set of first reference component models can be pre-built and stored in a model library, or they can be built when executing the assembly method in this embodiment. The first deviation parameter can be determined based on the difference, ratio, or vector offset between the corresponding measured component features and nominal component features. For example, the first deviation parameter may include the coordinate offset of the measured pin center coordinates relative to the nominal pin center coordinates; it may also include the thickness difference or thickness ratio between the measured thickness and the nominal thickness. When the first measurement parameters and the first specification parameters use different coordinate systems, units of measurement, or data formats, coordinate transformation, unit transformation, or data format transformation can be performed first.

[0043] Optionally, but not limited to, the model parameters of the first reference component model can be adjusted according to the first deviation parameter to obtain the component model to be assembled.

[0044] As an optional approach, a set of first reference component models can be updated to a set of component models to be assembled based on a set of first deviation parameters in the following manner: the spatial distribution parameters of the pin sub-assemblies in a set of first reference component models are updated based on the pin center position offset, wherein the set of first deviation parameters includes the pin center position offset.

[0045] Optionally, the computer device can adjust the coordinates of the corresponding pin sub-assemblies in the first reference component model based on the pin center position offset of each pin, so that the updated pin center coordinates match the measured pin center coordinates. When a pin assembly includes multiple pins, or a group of components to be assembled includes multiple pin assemblies, the pin center position offset of each pin can be determined separately, and the coordinates of the corresponding pin sub-assemblies can be updated separately.

[0046] As an optional approach, a set of load-bearing component models can be constructed based on a set of second measurement parameters in the following manner: determining a set of second deviation parameters based on a set of second measurement parameters and a set of second specification parameters, wherein the set of second deviation parameters is used to indicate the deviation between the set of second measurement parameters and the set of second specification parameters, and the set of second specification parameters is used to indicate the nominal component characteristics of the set of load-bearing components; updating a set of second reference component models to a set of load-bearing component models based on a set of second deviation parameters, wherein the set of second reference component models is a component model constructed based on a set of second specification parameters.

[0047] Optionally, the methods for obtaining the second specification parameters, constructing the second reference component model, determining the second deviation parameters, and updating the second reference component model can refer to the processing methods corresponding to the first specification parameters, the first reference component model, and the first deviation parameters, respectively, and will not be repeated here. The steps of constructing a set of component models to be assembled based on a set of first measurement parameters and constructing a set of load-bearing component models based on a set of second measurement parameters can be performed simultaneously or in any order.

[0048] As an alternative approach, a set of second reference component models can be updated to a set of load-bearing component models based on a set of second deviation parameters in the following manner: updating the model parameters of the inner surface of the slot in a set of second reference component models based on the slot inner wall profile deviation, wherein the set of second deviation parameters includes the slot inner wall profile deviation.

[0049] Optionally, the slot inner wall profile deviation can be used to indicate the deviation of the measured slot inner wall profile relative to the nominal slot inner wall profile. A computer device can spatially register the measured slot inner wall profile with the second reference component model, calculate the normal distance from each mesh node on the slot inner surface to the measured profile, and adjust the position of the corresponding mesh nodes according to the following formula:

[0050] ;

[0051] in, This indicates the adjusted grid node coordinates. This indicates the coordinates of the grid nodes before adjustment. This represents the normal distance from the grid node to the measured profile. This represents the unit normal vector of the surface where the mesh node is located. After adjusting the mesh nodes, Laplacian smoothing can be applied to the mesh nodes to reduce mesh distortion.

[0052] For example, if the nominal width of the slot is 5.00 mm, and the measured inner wall of one side of the slot is offset by 0.05 mm at a preset depth, so that the local width at that location changes from 5.00 mm to 4.95 mm, the inner surface mesh nodes of the corresponding area in the second reference component model can be adjusted by 0.05 mm towards the inside of the slot, so that the updated load-bearing component model can simulate the local offset of the slot.

[0053] As an alternative, but not limited to, a set of second reference component models can be updated to a set of load-bearing component models based on a set of second deviation parameters by updating the material property parameters of the snap-fit ​​region in a set of second reference component models according to the elastic deformation deviation of the snap-fit ​​structure, wherein the set of second deviation parameters includes the elastic deformation deviation of the snap-fit ​​structure.

[0054] Optionally, the elastic deformation deviation of the snap-fit ​​structure can be used to indicate the deviation between the measured elastic deformation and the nominal elastic deformation of the snap-fit ​​structure under the same measurement conditions. The elastic deformation deviation of the snap-fit ​​structure can be determined according to the following formula:

[0055] ;

[0056] in, This indicates the deviation in elastic deformation of the snap-fit ​​structure. This represents the measured elastic deformation of the snap-fit ​​structure under a preset load. It represents the nominal elastic deformation of the nominal snap-fit ​​structure under the same preset load.

[0057] Under the same preset load, the stiffness of the snap-fit ​​structure is negatively correlated with its elastic deformation. Computer equipment can determine the ratio of the measured elastic deformation to the nominal elastic deformation of the snap-fit ​​structure. This ratio can be determined using the following formula:

[0058] ;

[0059] in, This represents the ratio of stiffness changes. This represents the nominal physical stiffness of the current snap-fit ​​structure.

[0060] Computer equipment can determine the equivalent elastic modulus of the latching area based on the stiffness change ratio. The equivalent elastic modulus can be determined according to the following formula:

[0061] ;

[0062] in, and These represent the equivalent elastic modulus and the nominal elastic modulus, respectively.

[0063] In this embodiment, the geometric parameters of the snap-fit ​​region in the second reference component model can be kept unchanged, and the elastic modulus of the snap-fit ​​region can be updated to the equivalent elastic modulus to simulate the stiffness change of the current snap-fit ​​structure relative to the nominal snap-fit ​​structure through material property parameters. For example, the material of the nominal snap-fit ​​is standard nylon, and the nominal elastic modulus is... (MPa). Under the same preset load, the nominal elastic deformation of the snap-fit ​​structure is 1.00 mm, the measured elastic deformation of the current snap-fit ​​structure is 1.20 mm, and the elastic deformation deviation of the snap-fit ​​structure is 0.20 mm. Then the stiffness change ratio is: The corresponding equivalent elastic modulus is: The computer device can update the elastic modulus of the snap-fit ​​region in the second reference component model to 1666 MPa, enabling the updated load-bearing component model to simulate the actual deformation state of the current snap-fit ​​structure under stress.

[0064] Through the above steps, the reference component model used to simulate the nominal component state can be updated based on the deviation of the measured component characteristics from the nominal component characteristics. This allows the obtained component model to be assembled and the load-bearing component model to simulate the component characteristics of the component actually involved in the assembly, thereby improving the matching degree between the subsequent simulated assembly operation and the actual assembly operation.

[0065] Optionally, in the embodiment provided in step S204 above, the computer device can use initial control parameters in a virtual assembly environment to control the change of the physical relationship between the model of the part to be assembled and the model of the carrier component, so as to simulate the process of assembling the part to be assembled to the carrier component.

[0066] Optionally, the initial control parameters can be preset according to the component type of the equipment, determined based on historical assembly records of similar equipment components, or input by the operator. The control parameters may include a set of poses of the component to be assembled relative to the supporting component, a set of contact forces, and the temporal relationship between each pose and each contact force. The control parameters can be represented by a parameter sequence, which may include corresponding control moments, the pose corresponding to that control moment, and the contact force corresponding to that control moment.

[0067] For example, control parameters can instruct the assembly equipment to first control the part to be assembled to move from the initial position to the alignment position, then from the alignment position to the contact position, and after contact occurs, move to the assembly position according to the corresponding contact force.

[0068] During simulated assembly operations, the computer equipment can update the pose of the component model to be assembled relative to the supporting component model and the contact state between the two according to control parameters, and calculate the physical quantities generated during the assembly process through the virtual assembly environment. The simulated assembly results can include at least one of multiple assembly indicators such as final pose, assembly depth, pose deviation, assembly time, peak contact force, maximum component deformation, maximum equivalent stress of the component, contact state, or the completion state of the simulated assembly operation.

[0069] Optionally, whether the simulated assembly result meets the target assembly conditions can be determined in the following ways, but not limited to: For example, the computer equipment can determine the overall assembly state based on one or more assembly indicators in the simulated assembly result, and determine that the simulated assembly result meets the target assembly conditions when the overall assembly state meets the preset requirements. Another example is that the computer equipment can also determine that the simulated assembly result meets the target assembly conditions when the overall assembly state meets the preset requirements and remains stable over multiple consecutive control parameter update cycles. Yet another example is that the computer equipment can compare the simulated assembly results before and after the control parameter update. If the improvement of the updated simulated assembly result relative to the original simulated assembly result is less than a preset level, and the overall assembly state reflected by the updated simulated assembly result meets the preset requirements, then the simulated assembly result is determined to have met the target assembly conditions.

[0070] Optionally, but not limited to, the initial control parameters can be updated in the following ways: For example, the computer device can generate multiple sets of reference control parameters based on the currently used control parameters, perform simulated assembly operations using each set of reference control parameters, compare the simulated assembly results corresponding to the multiple sets of reference control parameters, and select the reference control parameters that can improve the simulated assembly results from the multiple sets of reference control parameters as the updated control parameters. As another example, the computer device can determine the physical parameters to be adjusted and their adjustment directions in the current control parameters based on the simulated assembly results, and adjust the corresponding physical parameters according to a preset adjustment amount. For example, if the simulated assembly results indicate a large pose deviation of the component to be assembled, the pose corresponding to one or more control moments can be adjusted; if the simulated assembly results indicate a large contact force, the contact force corresponding to one or more control moments can be adjusted, and / or the timing relationship between adjacent poses can be adjusted.

[0071] As an optional approach, the initial control parameters can be updated until the simulated assembly result reaches the target assembly condition, and the target control parameters can be obtained by means of, but not limited to, the following: Using the initial control parameters as the initial current control parameters, repeat the following steps until the simulated assembly result reaches the target assembly condition, and determine the current control parameter that makes the simulated assembly result reach the target assembly condition as the target control parameter: Perform a simulated assembly operation using the current control parameters to obtain the current simulated assembly result; check whether the current simulated assembly result has reached the target assembly condition; if the current simulated assembly result has not reached the target assembly condition, predict the next current control parameter based on the current control parameters and the current simulated assembly result.

[0072] Optionally, in this embodiment, when the simulated assembly operation is performed for the first time, the current control parameter is the initial control parameter; when the simulated assembly operation is performed subsequently, the current control parameter is the control parameter predicted based on the previous current control parameter and the corresponding current simulated assembly result.

[0073] Optionally, if the current simulated assembly result meets the target assembly conditions, the update of the current control parameters can be stopped, and the current control parameters used in this simulated assembly operation can be determined as the target control parameters. If the current simulated assembly result does not meet the target assembly conditions, the next current control parameter can be predicted based on the current control parameters and the current simulated assembly result, and the next current control parameter can be used as the new current control parameter to re-execute the simulated assembly operation.

[0074] Optionally, the computer equipment can record the current control parameters used in each simulated assembly operation and the corresponding current simulated assembly result. When predicting the next current control parameter, the control parameters and simulation assembly results obtained from the current simulated assembly operation and at least one historical simulated assembly operation can be referenced to avoid adjusting the current control parameter to a parameter range that has already yielded poor simulated assembly results. For example, if the component deformation indicated by the current simulated assembly result continues to increase after increasing the contact force at a certain control moment in two consecutive simulated assembly operations, then subsequent simulated assembly operations can stop adjusting in the direction of increasing the contact force, and instead reduce the contact force, or adjust the timing relationship between the corresponding poses.

[0075] Through the above steps, the initial control parameters are used as the initial current control parameters, and the next current control parameters are predicted based on the current simulation assembly results obtained in each simulation assembly operation, forming an iterative update process for the control parameters. This allows the control parameters to be gradually adjusted in a direction that meets the target assembly conditions, reducing the need for unfounded adjustments to control parameters or repeated verification of control parameters with poor assembly performance. This improves the efficiency of determining the target control parameters and makes the obtained target control parameters more compatible with the component characteristics of the part to be assembled and the supporting component.

[0076] As an optional approach, the following methods can be used, but are not limited to, to detect whether the current simulated assembly result meets the target assembly conditions: Based on multiple disturbance simulation assembly results, detect the current reliability parameter and current success rate parameter of the current control parameters. The current simulated assembly result includes multiple disturbance simulation assembly results, obtained by performing multiple simulated assembly operations using the current control parameters and multiple disturbance parameters. The multiple disturbance parameters are used to simulate random disturbances in actual assembly operations on a computer. The current reliability parameter indicates the assembly reliability of the current control parameters performing simulated assembly operations under multiple disturbance parameters, and the current success rate parameter indicates the assembly success rate of the current control parameters performing simulated assembly operations under multiple disturbance parameters. Detect whether the change amplitude between the current reliability parameter and the historical reliability parameter detected by the consecutive target number of operations is less than an amplitude threshold, and detect whether the current success rate parameter is greater than or equal to a success rate threshold. If the change amplitude is less than the amplitude threshold and the current success rate parameter is greater than or equal to the success rate threshold, determine that the current simulated assembly result meets the target assembly conditions. If the change amplitude is greater than or equal to the amplitude threshold, and / or the current success rate parameter is less than the success rate threshold, determine that the current simulated assembly result does not meet the target assembly conditions.

[0077] Optionally, Figure 4 This is a flowchart of a control parameter update method according to an embodiment of this application. Figure 4 As shown, the computer equipment can first determine the initial control parameters as the current control parameters, then use the current control parameters and multiple disturbance parameters to perform multiple simulated assembly operations, and determine the current reliability parameters and current success rate parameters based on the obtained results of the multiple disturbance simulation assembly operations. The computer equipment checks whether the current simulated assembly result meets the target assembly conditions based on the current reliability parameters, historical reliability parameters, and current success rate parameters. If the current simulated assembly result meets the target assembly conditions, the current control parameters are determined as the target control parameters; if the current simulated assembly result does not meet the target assembly conditions, the next current control parameter is predicted, and this next current control parameter is used as the new current control parameter. The computer then returns to perform multiple simulated assembly operations until the current simulated assembly result meets the target assembly conditions.

[0078] Optionally, the computer equipment can perform multiple simulated assembly operations using the same current control parameters and multiple different disturbance parameters, obtaining multiple disturbance simulation assembly results corresponding one-to-one with the multiple disturbance parameters. The disturbance parameters can be used to adjust the initial relative pose of the component model to be assembled relative to the carrier component model, and / or to simulate control execution deviations in the assembly operation, thereby simulating component placement deviations or assembly equipment execution errors that may occur in actual assembly operations. The value range of the disturbance parameters can be determined based on measurement errors, repeated positioning errors of the assembly equipment, or historical assembly data.

[0079] Optionally, before performing each disturbance simulation assembly operation, the model of the component to be assembled and the model of the supporting component can be restored to the same initial simulation state, and then the corresponding simulation parameters can be adjusted according to the disturbance parameters. The contents included in the disturbance simulation assembly results can refer to the aforementioned simulation assembly results.

[0080] Optionally, the assembly success condition is used to determine whether a single disturbance simulation assembly operation is successful. For example, if the model of the component to be assembled reaches a preset assembly state (e.g., the assembly pose reaches a preset assembly pose and the snap-fit ​​structure is engaged), and the peak contact force, the maximum equivalent stress of the component, and the assembly time are all within the corresponding allowable ranges, then the disturbance simulation assembly result can be determined to meet the assembly success condition. The current success rate parameter can be the proportion of disturbance simulation assembly results that meet the assembly success condition among multiple disturbance simulation assembly results.

[0081] Optionally, the historical reliability parameters detected during consecutive target counts can be the reliability parameters corresponding to the control parameters for each consecutive target count before the current control parameter. If the number of historical reliability parameters is less than the target count, it is determined that the current simulated assembly result has not met the target assembly conditions.

[0082] Optionally, the variation range can be the difference between the maximum and minimum values ​​of the current reliability parameter and the historical reliability parameter detected by the consecutive target count; or it can be the maximum value of the absolute values ​​of the differences between the current reliability parameter and each historical reliability parameter. The target count, amplitude threshold, and success rate threshold can be preset or selected according to the component type or assembly requirements of the component to be assembled and the supporting component.

[0083] By following the steps above, we can determine whether the current control parameters meet the requirements for stopping updates based on the assembly success rate under multiple random disturbances and the changes in assembly reliability during multiple consecutive control parameter updates. This reduces the likelihood of prematurely stopping control parameter updates due to accidental success in a single simulated assembly operation.

[0084] As an optional approach, the current reliability parameter and current success rate parameter of the current control parameter can be detected based on multiple disturbance simulation assembly results in the following ways: The current stability parameter of the current control parameter is determined based on the degree of difference between multiple disturbance simulation assembly results, and the current success rate parameter is determined based on the proportion of disturbance simulation assembly results that meet the assembly success conditions. The current stability parameter indicates the assembly stability of the current control parameter when performing simulated assembly operations under multiple disturbance parameters, and assembly stability is negatively correlated with the degree of difference. The current reliability parameter is calculated based on the current stability parameter and the current success rate parameter, where the assembly reliability indicated by the current reliability parameter is positively correlated with both assembly stability and assembly success rate.

[0085] Optionally, the computer equipment can extract the same assembly index from multiple disturbance simulation assembly results and determine the degree of difference based on the dispersion of each assembly index in multiple disturbance simulation assembly operations. Assembly indexes may include at least one of pose deviation, assembly time, peak contact force, maximum component deformation, or maximum equivalent stress. The degree of difference can be determined based on the difference, variance, or standard deviation between the maximum and minimum values ​​of the same assembly index; when using multiple assembly indexes, each index can be normalized before weighting. The weights of each assembly index can be preset according to the component type or assembly requirements of the component to be assembled and the supporting component.

[0086] Optionally, the computer device can convert the degree of difference into a current stability parameter according to a negative correlation with the degree of difference. For example, after normalizing the degree of difference to a preset range, the difference between the upper limit of this range and the normalized degree of difference can be determined as the current stability parameter; alternatively, the current stability parameter can be calculated based on the degree of difference using a pre-set monotonically decreasing function. The smaller the difference between multiple disturbance simulation assembly results, the higher the assembly stability indicated by the current stability parameter.

[0087] Optionally, the current stability parameter and the current success rate parameter can be obtained by weighted summation or multiplication. The weights for both the current stability parameter and the current success rate parameter are positive values; when using a weighted summation method, the sum of all weights can be one. The current stability parameter and the current success rate parameter can take the same value range.

[0088] As an optional approach, the next current control parameter can be predicted, but is not limited to, in the following ways: Add the current control parameter and the current simulated assembly result to historical training data to obtain current training data, and use the current training data to train a first surrogate model to obtain a second surrogate model. The first surrogate model is obtained by training an initial surrogate model using historical training data, which includes historical control parameters and historical simulated assembly results. Input multiple candidate control parameters into the second surrogate model to obtain the predicted assembly result and uncertainty features output by the second surrogate model. The uncertainty features characterize the degree of uncertainty between the simulated assembly result obtained by performing the simulated assembly operation using the candidate control parameters and the predicted assembly result. The candidate control parameters are sampled from the control parameter space where the current control parameter resides. Based on the predicted assembly result, uncertainty features, and reference simulated assembly result, select the next current control parameter from the multiple candidate control parameters. The reference simulated assembly result is the simulated assembly result obtained in historical time where the assembly quality reaches the target quality.

[0089] Before implementing this embodiment, the historical training data may include at least one historical simulated assembly result in which the assembly quality reaches the target quality. This result may come from historical assembly tasks of the same part type or pre-executed simulated assembly operations.

[0090] Optionally, a surrogate model can be used to characterize the correspondence between control parameters and simulated assembly results. A set of historical control parameters and their corresponding historical simulated assembly results can constitute a training sample. The initial surrogate model can be a Gaussian process model. The first surrogate model can be a surrogate model that has been trained before the current control parameter update. After obtaining the current simulated assembly result corresponding to the current control parameters, both can be added to the historical training data as new training samples, and the model parameters can be updated based on the first surrogate model to obtain the second surrogate model; alternatively, the current training data containing the new training samples can be used to retrain a surrogate model with the same structure as the first surrogate model to obtain the second surrogate model. The second surrogate model can output predicted values ​​of the assembly results for candidate control parameters and use the prediction variance or prediction standard deviation as uncertainty features.

[0091] Optionally, the control parameter space can be determined based on the pose range, contact force range, and time interval range allowed by the assembly equipment. Multiple candidate control parameters can be sampled from the entire control parameter space or from a parameter range near the current control parameter. The predicted assembly results can be referenced from the aforementioned simulated assembly results.

[0092] Optionally, when the predicted assembly result includes multiple assembly indicators, a surrogate model corresponding to each assembly indicator can be established separately, or multiple assembly indicators can be normalized and integrated to obtain the predicted result used to represent the assembly quality.

[0093] Optionally, when the historical training data includes multiple historical simulated assembly results where the assembly quality reaches the target quality, the historical simulated assembly result with the highest assembly quality can be determined as the reference simulated assembly result.

[0094] Optionally, but not limited to, the next current control parameter can be selected from multiple candidate control parameters in the following manner: Based on the predicted assembly result, uncertainty characteristics, and reference simulated assembly result corresponding to each candidate control parameter, the acquisition function value of each candidate control parameter is calculated, whereby the acquisition function is used to evaluate the expected improvement degree of the candidate control parameter relative to the reference simulated assembly result; the candidate control parameter with the largest expected improvement degree is determined as the next current control parameter. The higher the assembly quality reflected by the predicted assembly result relative to the reference simulated assembly result, or the higher the uncertainty of the predicted assembly result, the greater the expected improvement degree that the candidate control parameter may have. Therefore, both candidate control parameters with higher predicted assembly quality can be selected, and candidate control parameters with higher predicted uncertainty but potentially higher assembly quality can be verified.

[0095] As an optional approach, the next current control parameter can be selected from multiple candidate control parameters based on the predicted assembly results, uncertainty characteristics, and reference simulated assembly results in the following manner: The contribution parameter of the candidate control parameter is determined based on the predicted assembly results and the reference simulated assembly results, wherein the contribution parameter indicates the degree of improvement in assembly quality of the predicted assembly results relative to the assembly quality of the reference simulated assembly results; the sampling priority of the candidate control parameter is determined based on the contribution parameter and uncertainty characteristics, wherein the sampling priority is positively correlated with both the contribution parameter and the uncertainty characteristics; and the candidate control parameter with the highest sampling priority among the multiple candidate control parameters is determined as the next current control parameter.

[0096] Optionally, the predicted assembly quality corresponding to the candidate control parameters can be determined based on the predicted assembly results, and the reference assembly quality can be determined based on the reference simulated assembly results. Determining the assembly quality based on the assembly results includes calculating the assembly evaluation parameters of the simulated assembly results using the following formula:

[0097] ;

[0098] in, This indicates the assembly time included in the simulated assembly results. This represents the peak contact force included in the simulated assembly results. This represents the maximum equivalent stress of the components included in the current simulated assembly results. This parameter represents the success rate of the simulated assembly results. , These represent the normalized lower bound and normalized upper bound of assembly time, respectively; , These represent the normalized lower bound and normalized upper bound of the peak contact force, respectively. , These represent the normalized lower and upper bounds of the maximum equivalent stress of the component, respectively. These normalization boundaries can be determined before the control parameter update, based on pre-executed simulation assembly results, historical simulation assembly results, or assembly requirements within the control parameter space, and remain unchanged during the current control parameter update. Each normalization upper bound is greater than its corresponding normalization lower bound; for assembly indices exceeding the normalization boundaries, the normalization result can be limited to a value range of 0 to 1. , , , The weights are non-negative, each representing the relative importance of assembly efficiency, contact safety, structural integrity, and assembly success rate in the current assembly operation, and they sum to one. The assembly evaluation parameters are then converted into assembly quality using the following formula: ;in, Indicates assembly quality.

[0099] Optionally, the contribution parameter can be determined based on the difference between the predicted assembly quality and the reference assembly quality, or the improvement ratio. The greater the improvement in predicted assembly quality relative to the reference assembly quality, the larger the contribution parameter corresponding to the candidate control parameter.

[0100] Optionally, the sampling priority can be determined by weighting the normalized contribution parameters and uncertainty characteristics. Candidate control parameters with larger contribution parameters have higher expected assembly quality, while candidate control parameters with larger uncertainty characteristics have greater value for verification. For example, if a simulated assembly operation has been performed using control parameters corresponding to two candidate contact forces, and the assembly quality corresponding to the larger contact force is higher, the surrogate model can predict the assembly results and uncertainty characteristics of adjacent parameter ranges based on existing training samples, and prioritize the candidate control parameter with higher sampling priority, rather than randomly selecting the next control parameter from the entire control parameter space.

[0101] By following the steps above, while prioritizing the screening of candidate control parameters with high assembly quality, we can also sample candidate control parameters that have not yet been fully verified but may yield good simulated assembly results. This avoids the screening of control parameters being overly concentrated within the existing parameter range, improves the screening efficiency of the next current control parameter, and increases the likelihood of finding a better control parameter.

[0102] Optionally, in the embodiment provided in step S206 above, the computer device can first generate initial control commands based on the target control parameters and send them to the assembly equipment; during the actual assembly operation, assembly process parameters are acquired, and subsequent control commands are generated based on the target control parameters and the assembly process parameters. Component parameters may include the pose, contact force, deformation, stress, or temperature of the component to be assembled or the supporting component. Assembly process parameters may directly include the acquired component parameters, or they may include data obtained after processing the acquired component parameters.

[0103] Optionally, during the actual assembly operation, the computer equipment can determine the expected physical relationship at the current moment based on the target control parameters, determine the actual assembly state based on the acquired assembly process parameters, and then generate subsequent control commands based on the expected physical relationship and the actual assembly state, and send the subsequent control commands to the assembly equipment. For example, if the target control parameters indicate that the component to be assembled should move to the first target pose at the current moment, but the assembly process parameters indicate that the component to be assembled has not reached the first target pose, the computer equipment can control the assembly equipment to continue moving the component to be assembled toward the first target pose; if the assembly process parameters indicate that the component to be assembled has reached the first target pose, the computer equipment can control the assembly equipment to execute the next assembly action according to the target control parameters.

[0104] Optionally, the target control parameters can be divided into multiple parameter segments according to the assembly stage. Each parameter segment includes the target pose and target contact force with a temporal relationship within the corresponding assembly stage. During the actual assembly operation, the computer equipment can identify the current assembly stage based on the assembly process parameters and call the control mode corresponding to the current assembly stage. The assembly stage can include the approach stage, alignment stage, insertion stage, and locking stage. For example, a six-dimensional contact force signal (including contact force in three directions and torque in three directions) can be collected by a six-dimensional force sensor installed at the end of the assembly equipment. The end pose can be read by the controller of the assembly equipment, and a timestamp can be added to the six-dimensional contact force signal and the end pose signal. When the assembly equipment clamps the part to be assembled, the end pose can be used to represent the pose of the part to be assembled. The six-dimensional contact force signal, the end pose signal, and the timestamp can be combined into a stage identification sequence according to a fixed time window. The computer equipment can input the stage identification sequence into the stage identification model to obtain the current assembly stage. In one implementation, the stage recognition model can be a lightweight one-dimensional convolutional neural network, comprising three convolutional layers, each followed by a batch normalization layer and an activation layer, and then a global average pooling layer and a fully connected classification layer. The stage recognition model can output probabilities corresponding to the approach stage, alignment stage, insertion stage, and locking stage, respectively, and determine the assembly stage corresponding to the highest probability as the current assembly stage. The sampling frequency of the six-dimensional contact force signal can be set according to the needs of stage recognition, for example, not less than 500 Hz. The assembly stages can be labeled using the six-dimensional contact force signal, end-effector pose, and timestamp collected from historical actual assembly operations, and the labeled stage recognition sequence can be used to train the stage recognition model.

[0105] During the approach phase, the assembly equipment can control the component to be assembled to approach the carrier component according to a set of target poses indicated by the target control parameters. During the alignment phase, the subsequent target poses can be adjusted according to the contact force in the horizontal plane to align the component to be assembled with the carrier component. During the insertion phase, the component to be assembled can be controlled to move along the assembly direction according to the corresponding target contact force, and small-amplitude periodic pose changes can be superimposed in the target pose to reduce the influence of static friction on the insertion process. During the locking phase, the component can first move along the locking direction according to the corresponding target contact force, and after confirming that it is in place, lateral pose adjustment can be performed to make the snap-fit ​​structure complete the locking.

[0106] In one implementation of the alignment stage, the contact force component in the horizontal plane of the six-dimensional contact force signal can be extracted and filtered. The filtered contact force is then input into the admittance control model. The expected motion of the end effector in the horizontal plane is obtained according to the mass-spring-damping relationship. The pose correction amount is then generated based on the expected motion amount and superimposed on the subsequent target pose.

[0107] In one implementation of the locking stage, the positioning status can be confirmed based on the contact force and torque in the horizontal plane and the pose change of the component to be assembled along the assembly direction. For example, if the contact force and torque in the horizontal plane decay to a corresponding threshold range, and the pose change or pose deviation along the assembly direction is less than the corresponding tolerance within multiple consecutive control cycles, it can be determined that the component to be assembled has been positioned, and subsequent lateral pose adjustment can be performed.

[0108] The target pose, target contact force, and their timing relationships used in the different assembly stages can be obtained from the target control parameters. Therefore, different control methods can be switched according to the actual assembly state, and assembly operations can be performed according to the target control parameters adapted to the currently assembled components.

[0109] As an optional approach, the actual assembly operation can be performed based on target control parameters and assembly process parameters in the following manner, but not limited to: The actual assembly operation is performed using target control parameters, which include: a set of physical parameters with a temporal relationship, the set of physical parameters indicating a set of poses of a set of components to be assembled relative to a set of supporting components and a set of contact forces between the components to be assembled and the supporting components during the actual assembly operation; during the execution of the actual assembly operation, the component parameters of the set of components to be assembled and / or the component parameters of the set of supporting components are collected multiple times to obtain a parameter sequence, wherein the assembly process parameters include the parameter sequence; assembly abnormalities are detected based on the parameter sequence; and when an assembly abnormality indicates that an assembly abnormality exists in the actual assembly operation, the set of physical parameters and / or temporal relationships are adjusted.

[0110] Optionally, Figure 5 This is a control flowchart of an actual assembly operation according to an embodiment of this application. Figure 5 As shown, the computer equipment can use target control parameters to control the assembly equipment to perform actual assembly operations. During the actual assembly operation, it collects component parameters of the parts to be assembled and / or the component parameters of the supporting components. Based on the collected component parameters, it detects whether there are assembly abnormalities in the actual assembly operation. If an assembly abnormality exists, it adjusts a set of physical parameters and / or timing relationships that have not yet been executed after the current moment, and continues to collect component parameters to detect whether there are assembly abnormalities in the actual assembly operation again. If no assembly abnormality exists, it checks whether the actual assembly operation is completed. If the actual assembly operation is not completed, it continues to collect component parameters; if the actual assembly operation is completed, it ends the actual assembly operation.

[0111] Optionally, the parameter sequence may include multiple parameter values ​​arranged according to acquisition time and the acquisition time corresponding to each parameter value. If an assembly anomaly is detected in the actual assembly operation, the target pose, target contact force, and / or timing relationship that have not yet been executed after the current moment can be adjusted. For example, the adjustment range of subsequent target poses relative to the current pose can be reduced, the subsequent target contact force can be reduced, and / or the time interval between adjacent target poses can be extended.

[0112] In one alternative implementation, the parameter sequence may include a contact force subsequence and a temperature subsequence. The computer device 302 can time-align the contact force subsequence and the temperature subsequence based on timestamps. If the contact force subsequence and the temperature subsequence do not have the same acquisition time, the contact force and temperature corresponding to the same acquisition time can be determined by interpolating adjacent acquisition values ​​or selecting the acquisition value closest in time.

[0113] The temperature subsequence can be determined based on infrared temperature field images continuously acquired by an infrared thermal imaging device. The target connection area can be the region where the component to be assembled has already come into contact with or is about to come into contact with the supporting component. For example, an infrared thermal imaging device can be set up at the assembly station, and infrared temperature field images of the target connection area can be continuously acquired at a preset acquisition frequency during the actual assembly operation. The preset acquisition frequency can be no less than 30 Hz. The computer equipment can identify the target connection area in each infrared temperature field image based on a pre-calibrated component template, extract the highest temperature value in the target connection area at each acquisition time, and form a temperature subsequence based on the acquisition time of multiple highest temperature values.

[0114] Computer equipment can smooth the temperature subsequence and determine the temperature rise rate at the current acquisition moment based on the change of the smoothed temperature value over time. The computer equipment can extract the amplitude of the normal contact force along the assembly direction at the current acquisition moment from the contact force subsequence. The thermodynamic safety parameters at the current data acquisition moment are calculated based on the normal contact force and the rate of temperature rise. For example, but not limited to, the following formulas can be used to calculate the thermodynamic safety parameters:

[0115] ;

[0116] in, This indicates the mechanical and thermal safety parameters corresponding to the current data acquisition moment; This represents the magnitude of the target contact force in the target control parameters corresponding to the current acquisition time, and ; This indicates the preset reference temperature rise rate, and ; This represents the force and heat weighting parameter, and The thermal weighting parameters can be set according to the thermal sensitivity of the component material and the structural strength. If the value exceeds a preset safety threshold, an assembly anomaly can be identified to indicate an assembly anomaly in the actual assembly operation; If the value is less than or equal to the preset safety threshold, the assembly abnormality status can be determined to indicate that there is no assembly abnormality in the actual assembly operation.

[0117] If an assembly anomaly is detected during the actual assembly operation, the computer equipment can execute a tiered response. In a level one response, the time interval between adjacent target poses after the current acquisition moment can be extended to reduce the pose change of the component to be assembled per unit time, and / or reduce the amplitude of the target contact force at subsequent control moments. If the duration of the assembly anomaly exceeds a duration threshold, a level two response can be executed, pausing the assembly movement of the assembly equipment. If the assembly anomaly persists after pausing, for example, if the force and thermal safety parameters still exceed a preset safety threshold, a level three response can be executed, controlling the component to be assembled to move a preset distance in the opposite direction of the assembly direction and re-execute the alignment operation.

[0118] Optionally, after adjusting a set of physical parameters and / or timing relationships, the component parameters of a set of parts to be assembled and / or a set of supporting components can be collected multiple times to obtain an updated parameter sequence. The assembly anomaly state is then detected again based on the updated parameter sequence. When the assembly anomaly state indicates that there are no assembly anomalies in the actual assembly operation, the target pose, target contact force, and / or timing relationship that have not yet been executed after the current moment can be gradually restored to the corresponding target values ​​indicated by the target control parameters over multiple control cycles, and the actual assembly operation can continue. This avoids assembly deviations caused by adjustments to control parameters, allowing the actual assembly operation to smoothly recover to the target assembly process, thereby improving the stability, safety, and success rate of the assembly process.

[0119] As an optional approach, assembly anomaly status can be detected based on parameter sequences in the following ways, but not limited to: detecting parameter growth rate based on parameter sequence, where the parameter growth rate indicates the amount of change in component parameters per unit time; comparing parameter growth rate with a rate threshold; determining assembly anomaly status when the parameter growth rate is greater than the rate threshold to indicate that an assembly anomaly exists in the actual assembly operation; and determining assembly anomaly status when the parameter growth rate is less than or equal to the rate threshold to indicate that no assembly anomaly exists in the actual assembly operation.

[0120] Optionally, when the parameter sequence includes multiple subsequences corresponding to component parameters, the parameter growth rate of each subsequence can be detected separately. For example, the parameter growth rate can be determined based on the difference between two adjacent parameter values ​​and the time interval between corresponding acquisition times. Different types of component parameters can correspond to different rate thresholds. When the parameter growth rate of any component parameter is greater than the corresponding rate threshold, it can be determined that there is an assembly abnormality in the actual assembly operation.

[0121] By combining the component characteristics measured before assembly, the target control parameters determined by the simulated assembly operation, and the component parameters collected during the actual assembly operation, the physical parameters and / or timing relationships that have not yet been executed can be adjusted in a timely manner when there are abnormal normal contact forces, abnormal local temperature rises, or both of them together create assembly risks. This reduces the possibility of structural damage or heat accumulation to equipment components during the actual assembly process.

[0122] Optionally, in this embodiment, in order to better understand the assembly process of the above-mentioned equipment components, the assembly process of the above-mentioned equipment components is described below using the assembly of the server backplane connector as an example, but it is not intended to limit the technical solution of the embodiments of this application.

[0123] Figure 6 This is a schematic diagram of an assembly system according to an embodiment of this application, such as... Figure 6 As shown, the server backplane can be fixed to the assembly station. The connector slot (equivalent to a load-bearing component) is mounted on the server backplane, and the connector pin assembly (equivalent to the component to be assembled) is held by a robot gripper. The robot gripper is located at the robot's end effector, and a six-dimensional force sensor is positioned between the robot's end effector and the robot gripper. A laser scanner (equivalent to a measuring device) is positioned towards the connector pin assembly and connector slot, and an infrared thermal imager (equivalent to a measuring device) is positioned towards the target connection area of ​​both.

[0124] Before the actual assembly operation begins, the laser scanner can scan the connector pin assembly and the connector slot separately, and send the scan data to the computer device. The computer device can obtain the pin center position offset and the slot inner wall contour deviation based on the scan data, and update the corresponding reference component model in the aforementioned manner to obtain the connector pin assembly model (equivalent to the component model to be assembled) and the connector slot model (equivalent to the load-bearing component model).

[0125] Computer equipment can perform simulated assembly operations using connector pin assembly models and connector slot models, and obtain target control parameters through the aforementioned control parameter update process. Target control parameters may include the target pose, target contact force, and corresponding timing relationships of the connector pin assembly at different control moments.

[0126] During actual assembly operations, the computer equipment sends control commands to the robot controller based on target control parameters. The robot controller controls the robot end effector to move the connector pin assembly towards the connector slot, enabling the connector pin assembly to sequentially approach, align, insert, and lock. The robot end effector's pose can be used to represent the pose of the connector pin assembly, and a six-dimensional force sensor can simultaneously collect the contact force and torque between the connector pin assembly and the connector slot. The computer equipment can identify the current assembly stage based on the six-dimensional contact force signal, the robot end effector's pose, and the corresponding timestamp. Based on the current acquisition time, the current assembly stage, and the timing relationship indicated by the target control parameters, the computer equipment determines the current and subsequent target poses and target contact forces to be executed from the parameter segment corresponding to the current assembly stage. For example, during alignment, the subsequent target pose of the connector pin assembly can be corrected based on the contact force in the horizontal plane; during insertion, the connector pin assembly can be controlled to insert into the connector slot based on the contact force along the assembly direction; during locking, the connector pin assembly can be controlled to move to the locking position and the locking structure can be driven to complete the locking process.

[0127] During the insertion of the connector pin assembly into the connector slot, an infrared thermal imager can continuously acquire infrared temperature field images of the target connection area. Computer equipment can determine the temperature rise rate of the target connection area based on these infrared temperature field images, and combine this with the normal contact force along the assembly direction from the six-dimensional contact force signal to detect assembly abnormalities.

[0128] If no assembly abnormality is detected, the computer equipment can continue to control the connector pin assembly to perform insertion and locking operations according to the target control parameters.

[0129] If an assembly anomaly is detected, the computer device can adjust the target pose, target contact force, and / or timing relationships that have not yet been executed since the current moment. For example, it can reduce the subsequent target contact force and / or extend the time interval between adjacent target poses. After adjustment, the computer device can continue to acquire the six-dimensional contact force signal, the robot end-effector pose, and the infrared temperature field image, and re-detect the assembly anomaly. If the assembly anomaly is eliminated, the target pose, target contact force, and timing relationships that are subsequently executed can be gradually restored to the corresponding parameters indicated by the target control parameters, and the insertion and locking operations can continue to be executed.

[0130] If the duration of an assembly anomaly exceeds a certain threshold, the computer equipment can pause the movement of the robot's end effector. If the temperature rise rate does not decrease after the pause, the connector pin assembly can be controlled to move a preset distance in the opposite direction of the assembly direction, and the alignment operation can be re-executed. After re-alignment, the insertion and locking operations can be performed again, and the assembly anomaly and assembly completion status can continue to be monitored until the actual assembly operation of the server backplane connector is completed.

[0131] When the connector pin assembly reaches the preset assembly position and the latching structure is locked, and the position of the connector pin assembly and the contact force between it and the connector slot are within the corresponding allowable range for multiple consecutive control cycles, the computer equipment can determine that the actual assembly operation of the server backplane connector is completed and control the assembly equipment to stop performing the assembly action.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0133] Based on this understanding, the technical solution of this application, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0134] This embodiment also provides an assembly apparatus for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0135] Figure 7 This is a structural block diagram of an assembly device according to an embodiment of this application, such as... Figure 7 As shown, the device includes:

[0136] The construction module 702 is used to construct a set of assembly component models based on a set of first measurement parameters, and to construct a set of support component models based on a set of second measurement parameters. The set of first measurement parameters is used to indicate the component features of the set of assembly components obtained by measuring the set of assembly components, and the set of second measurement parameters is used to indicate the component features of the set of support components obtained by measuring the set of support components. The set of assembly components is to be assembled onto the set of support components. The set of assembly component models is used to simulate the set of assembly components on a computer, and the set of support component models is used to simulate the set of support components on a computer.

[0137] The update module 704 is used to update the initial control parameters based on the simulation assembly results obtained by performing the simulation assembly operation using the initial control parameters until the simulation assembly results reach the target assembly conditions, thereby obtaining the target control parameters. The simulation assembly operation is a simulation of assembling a set of component models to be assembled into a set of supporting component models. The target control parameters are used to indicate the changes in the physical relationship between a set of components to be assembled and a set of supporting components in the actual assembly operation. The actual assembly operation is an assembly operation of assembling a set of components to be assembled into a set of supporting components.

[0138] The execution module 706 is used to perform actual assembly operations according to target control parameters and assembly process parameters, wherein the assembly process parameters are used to indicate the changes in the component parameters of a set of parts to be assembled and / or the changes in the component parameters of a set of supporting parts during the execution of the actual assembly operations.

[0139] The assembly apparatus provided in the embodiments of this application is also configured to perform the steps in any of the above assembly method embodiments. For the description of the features in the embodiments corresponding to the assembly apparatus, please refer to the relevant descriptions of the embodiments corresponding to the assembly methods, which will not be repeated here.

[0140] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0141] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above-described assembly method embodiments.

[0142] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0143] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0144] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above-described assembly method embodiments when it is run.

[0145] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0146] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above-described assembly method embodiments.

[0147] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above assembly method embodiments.

[0148] Any of the components, modules, units, parts, methods, and operations described herein can be implemented using software, firmware, hardware (e.g., fixed logic circuitry), manual processing, or any combination thereof. Alternatively or additionally, any functionality described herein can be executed at least in part by one or more hardware logic components, such as, but not limited to, CPUs, FPGAs, Application-Specific Integrated Circuits (ASICs), Application-Specific Standard Products (ASSPs), Systems on Chips (SoCs), Complex Programmable Logic Devices (CPLDs), Microcontroller Units (MCUs), etc. The terms "system," "computing device," or "apparatus" as used herein encompass various means, devices, and machines for processing data, including, for example, one or more programmable processors, computers, SoCs, or combinations thereof. The apparatus may also include code that creates an execution environment for the computer program in question, such as code constituting processor firmware, protocol stacks, database management systems, operating systems, cross-platform runtime environments, virtual machines, or combinations thereof. The aforementioned computer program (also known as a program, software, software application, application (APP), script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and can be deployed in any form, including as a standalone program or as a module, component, subroutine, object, or other unit suitable for a computing environment.

[0149] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0150] The assembly method and electronic device provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. An assembly method, characterized in that, The method is applied to an electronic device, and the method includes: A set of component models to be assembled is constructed based on a set of first measurement parameters, and a set of support component models is constructed based on a set of second measurement parameters. The first set of measurement parameters indicates the component features of the set of components to be assembled obtained by measuring the set of components to be assembled, and the second set of measurement parameters indicates the component features of the set of support components obtained by measuring the set of support components. The set of components to be assembled is to be assembled onto the set of support components. The set of component models to be assembled is used to simulate the set of components to be assembled on a computer, and the set of support component models is used to simulate the set of support components on a computer. The initial control parameters are updated based on the simulated assembly results obtained by performing the simulated assembly operation using the initial control parameters until the simulated assembly results reach the target assembly conditions, thereby obtaining the target control parameters. The simulated assembly operation is an assembly operation that simulates assembling the set of component models to be assembled onto the set of supporting component models. The target control parameters are used to indicate the changes in the physical relationship between the set of components to be assembled and the set of supporting components during the actual assembly operation. The actual assembly operation is an assembly operation that assembles the set of components to be assembled onto the set of supporting components. The actual assembly operation is performed according to the target control parameters and assembly process parameters, wherein the assembly process parameters are used to indicate the changes in the component parameters of the group of components to be assembled and / or the changes in the component parameters of the group of supporting components during the execution of the actual assembly operation. The step of performing the actual assembly operation based on the target control parameters and assembly process parameters includes: The actual assembly operation is performed using the target control parameters, wherein the target control parameters include: a set of physical parameters having a temporal relationship, the set of physical parameters being used to indicate a set of poses of the set of components to be assembled relative to the set of supporting components and a set of contact forces between the set of components to be assembled and the set of supporting components in the actual assembly operation; During the actual assembly operation, the component parameters of the group of parts to be assembled and / or the component parameters of the group of supporting parts are collected multiple times to obtain a parameter sequence, wherein the assembly process parameters include the parameter sequence; Detect assembly anomalies based on the parameter sequence; When the assembly anomaly status indicates that there is an assembly anomaly in the actual assembly operation, adjust the set of physical parameters and / or the timing relationship.

2. The method according to claim 1, characterized in that, The step of updating the initial control parameters based on the simulated assembly results obtained by performing simulated assembly operations using initial control parameters until the simulated assembly results reach the target assembly conditions, thereby obtaining the target control parameters, includes: Using the initial control parameters as the initial current control parameters, repeat the following steps until the simulated assembly result reaches the target assembly condition. The current control parameter that causes the simulated assembly result to reach the target assembly condition is then determined as the target control parameter. The simulated assembly operation is performed using the current control parameters to obtain the current simulated assembly result; Check whether the current simulated assembly result meets the target assembly conditions; If the current simulated assembly result does not meet the target assembly condition, predict the next current control parameter based on the current control parameter and the current simulated assembly result.

3. The method according to claim 2, characterized in that, The prediction of the next current control parameter based on the current control parameters and the current simulation assembly results includes: The current control parameters and the current simulation assembly results are added to the historical training data to obtain the current training data. The first surrogate model is then trained using the current training data to obtain the second surrogate model. The first surrogate model is obtained by training the initial surrogate model using the historical training data, which includes historical control parameters and historical simulation assembly results. Multiple candidate control parameters are input into the second surrogate model to obtain the predicted assembly result and uncertainty characteristics output by the second surrogate model. The uncertainty characteristics are used to characterize the degree of uncertainty that the simulated assembly result obtained by performing the simulated assembly operation using the candidate control parameters is the predicted assembly result. The candidate control parameters are sampled from the control parameter space where the current control parameter is located. The next current control parameter is selected from the plurality of candidate control parameters based on the predicted assembly result, the uncertainty characteristics, and the reference simulated assembly result, wherein the reference simulated assembly result is the simulated assembly result obtained in historical time where the assembly quality reaches the target quality.

4. The method according to claim 3, characterized in that, The step of selecting the next current control parameter from the plurality of candidate control parameters based on the predicted assembly result, the uncertainty characteristics, and the reference simulation assembly result includes: The contribution parameter of the candidate control parameter is determined based on the predicted assembly result and the reference simulated assembly result, wherein the contribution parameter is used to indicate the degree of improvement of the assembly quality of the predicted assembly result relative to the assembly quality of the reference simulated assembly result. The sampling priority of the candidate control parameters is determined based on the contribution parameter and the uncertainty characteristic, wherein the sampling priority is positively correlated with both the contribution parameter and the uncertainty characteristic; The candidate control parameter with the highest sampling priority among the multiple candidate control parameters is determined as the next current control parameter.

5. The method according to claim 2, characterized in that, The step of detecting whether the current simulated assembly result meets the target assembly conditions includes: The current reliability parameter and current success rate parameter of the current control parameters are detected based on the assembly results of multiple disturbance simulations. The current assembly results include the multiple disturbance simulation results, which are obtained by performing the simulated assembly operation multiple times using the current control parameters and multiple disturbance parameters. The multiple disturbance parameters are used to simulate random disturbances in the actual assembly operation on a computer. The current reliability parameter is used to indicate the assembly reliability of the current control parameters when performing the simulated assembly operation under the multiple disturbance parameters. The current success rate parameter is used to indicate the assembly success rate of the current control parameters when performing the simulated assembly operation under the multiple disturbance parameters. The system detects whether the change in the current reliability parameter and the historical reliability parameter detected by the consecutive target count is less than the magnitude threshold, and detects whether the current success rate parameter is greater than or equal to the success rate threshold. If the change amplitude is less than the amplitude threshold and the current success rate parameter is greater than or equal to the success rate threshold, it is determined that the current simulated assembly result has reached the target assembly condition. If the change magnitude is greater than or equal to the magnitude threshold, and / or the current success rate parameter is less than the success rate threshold, it is determined that the current simulated assembly result has not met the target assembly condition.

6. The method according to claim 5, characterized in that, The step of detecting the current reliability parameter and the current success rate parameter of the current control parameters based on multiple disturbance simulation assembly results includes: The current stability parameter of the current control parameter is determined based on the degree of difference between the multiple disturbance simulation assembly results, and the current success rate parameter is determined based on the proportion of the disturbance simulation assembly results that meet the assembly success conditions. The current stability parameter is used to indicate the assembly stability of the current control parameter when performing the simulated assembly operation under the multiple disturbance parameters, and the assembly stability is negatively correlated with the degree of difference. The current reliability parameter is calculated based on the current stability parameter and the current success rate parameter, wherein the assembly reliability indicated by the current reliability parameter is positively correlated with both the assembly stability and the assembly success rate.

7. The method according to claim 1, characterized in that, The step of detecting assembly abnormality based on the parameter sequence includes: The parameter growth rate is detected based on the parameter sequence, wherein the parameter growth rate is used to indicate the amount of change of the component parameter per unit time. Compare the growth rate of the parameter with the rate threshold; If the parameter growth rate is greater than the rate threshold, the assembly abnormality state is determined to indicate that there is an assembly abnormality in the actual assembly operation. If the parameter growth rate is less than or equal to the rate threshold, the assembly anomaly status is determined to indicate that there is no assembly anomaly in the actual assembly operation.

8. The method according to claim 1, characterized in that, The step of constructing a set of component models to be assembled based on a set of first measurement parameters, and constructing a set of load-bearing component models based on a set of second measurement parameters, includes: A set of first deviation parameters is determined based on the set of first measurement parameters and the set of first specification parameters, and a set of second deviation parameters is determined based on the set of second measurement parameters and the set of second specification parameters. The set of first deviation parameters indicates the deviation between the set of first measurement parameters and the set of first specification parameters, the set of second deviation parameters indicates the deviation between the set of second measurement parameters and the set of second specification parameters, the set of first specification parameters indicates the nominal component characteristics of the set of components to be assembled, and the set of second specification parameters indicates the nominal component characteristics of the set of load-bearing components. A set of first reference component models is updated to the set of component models to be assembled based on the first set of first deviation parameters, and a set of second reference component models is updated to the set of load-bearing component models based on the second set of second deviation parameters, wherein the first set of first reference component models are component models constructed based on the first set of first specification parameters, and the second set of second reference component models are component models constructed based on the second set of second specification parameters.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the assembly method as described in any one of claims 1 to 8.

Images