Adaptive optimization method and device for flexible assembly technology

Abstract

The present application proposes an adaptive optimization method and device for flexible assembly technology, which relates to the field of flexible assembly technology. The method obtains the final position of the robot used for assembly and the assembly data of each successful assembly process after each successful assembly of the flexible assembly system; obtains the time weight value, six-dimensional force weight value and pressure weight value corresponding to the robot in each successful assembly process according to the assembly data; obtains the target weight value corresponding to the robot in each successful assembly process according to the time weight value, six-dimensional force weight value and pressure weight value; and determines the initial position of the robot in the next assembly process according to the preset position mapping relationship based on the final position and the target weight value. The present application obtains a more appropriate initial position for the next assembly process to improve assembly efficiency, and enables the model to be continuously iterated during the assembly process to adapt to different batches of parts. At the same time, all weight items can be adjusted according to the batch quantity to make the model more flexible.

Description

Technical Field

[0001] The present application relates to the field of flexible assembly technology, and in particular to a self-adaptive optimization method and device for flexible assembly technology. Background Art

[0002] When facing the shaft hole problem, most flexible assembly methods have different working principles, but all use robots with six-dimensional mechanical sensors at the end to complete flexible assembly through corresponding force perception and position posture correction. For some workstations with process rhythm requirements, the uncertainty of the initial position is large, so the time fluctuation of flexible assembly is large, and the models trained in most flexible assembly methods are only applicable to the current application scenarios and robots, and are not universally applicable. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, one purpose of the present application is to propose an adaptive optimization method suitable for flexible assembly technology, by obtaining the final position of the robot used for assembly after each successful assembly of the flexible assembly system and the assembly data of each successful assembly process; according to the assembly data, obtaining the time weight value, six-dimensional force weight value and pressure weight value corresponding to the robot in each successful assembly process; according to the time weight value, six-dimensional force weight value and pressure weight value, obtaining the target weight value corresponding to the robot in each successful assembly process; according to the final position and the target weight value, according to the preset position mapping relationship, determining the initial position of the robot in the next assembly process.

[0005] This application obtains a more appropriate initial position for the next assembly process to improve assembly efficiency, and enables the model to form continuous iterations in the subsequent assembly process, can adapt to different batches of parts, and autonomously iterate and update the model according to the characteristics of different batches of parts. At the same time, all weight items can be adjusted according to the batch quantity, making the model more flexible.

[0006] The second objective of the present application is to propose an adaptive optimization device suitable for flexible assembly technology.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth object of the present application is to provide a non-transitory computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above-mentioned objectives, the first aspect of the present application proposes an adaptive optimization method suitable for flexible assembly technology, by obtaining the final position of the robot used for assembly and the assembly data of each successful assembly process after each successful assembly of the flexible assembly system; according to the assembly data, the time weight value, six-dimensional force weight value and pressure weight value corresponding to the robot in each successful assembly process are obtained; according to the time weight value, six-dimensional force weight value and pressure weight value, the target weight value corresponding to the robot in each successful assembly process is obtained; according to the final position and the target weight value, according to the preset position mapping relationship, the initial position of the robot in the next assembly process is determined.

[0011] This application obtains a more appropriate initial position for the next assembly process to improve assembly efficiency, and enables the model to form continuous iterations in the subsequent assembly process, can adapt to different batches of parts, and autonomously iterate and update the model according to the characteristics of different batches of parts. At the same time, all weight items can be adjusted according to the batch quantity, making the model more flexible.

[0012] According to one embodiment of the present application, the process of obtaining the time weight value includes: obtaining the assembly time corresponding to the robot from the start of assembly to successful assembly in each assembly process based on the assembly data; obtaining the assembly time threshold and the preset time weight reference value corresponding to the robot; determining the time weight value according to the assembly time, the assembly time threshold and the time weight reference value and the preset time weight value mapping relationship.

[0013] According to one embodiment of the present application, the process of obtaining the six-dimensional force weight value includes: obtaining the force duration corresponding to the six-dimensional mechanical sensor of the robot in each assembly process and the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment within the force duration according to the assembly data; obtaining the average six-dimensional force value corresponding to the six-dimensional mechanical sensor in the assembly process according to the force duration and the real-time six-dimensional force value; obtaining the preset six-dimensional force weight reference value corresponding to the robot, and obtaining the maximum average six-dimensional force value from all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor; obtaining the six-dimensional force weight value according to the average six-dimensional force value, the maximum average six-dimensional force value and the six-dimensional force weight reference value according to the preset six-dimensional force weight value mapping relationship.

[0014] According to one embodiment of the present application, based on the assembly data, the force duration corresponding to the six-dimensional mechanical sensor of the robot in each assembly process is obtained, including: obtaining the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment in each assembly process, and determining the starting force moment of the six-dimensional mechanical sensor according to the real-time six-dimensional force value; obtaining a preset six-dimensional force threshold corresponding to the robot; during the assembly process, in response to the sum of the discrete first-order derivatives of the real-time six-dimensional force value being less than or equal to the six-dimensional force threshold, obtaining the ending force moment of the six-dimensional mechanical sensor; based on the starting force moment and the ending force moment, obtaining the force duration corresponding to the six-dimensional mechanical sensor in the current assembly process.

[0015] According to one embodiment of the present application, the process of obtaining the pressure weight value includes: obtaining the real-time pressure value of the pressure sensor on the assembled body at each moment within the force duration based on the assembly data; obtaining the average pressure value corresponding to the pressure sensor during the assembly process based on the force duration and the real-time pressure value; obtaining a preset pressure weight reference value, and obtaining the maximum average pressure value from all historical average pressure values ​​of the assembled body; obtaining the pressure weight value according to the average pressure value, the maximum average pressure value, and the pressure weight reference value according to the preset pressure weight value mapping relationship.

[0016] According to one embodiment of the present application, the sum of the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value is a preset value.

[0017] According to an embodiment of the present application, the adaptive optimization method of the flexible assembly technology further includes: in response to the flexible assembly system failing to assemble in any assembly process, using the initial position of the assembly process as the initial position of the next assembly process.

[0018] To achieve the above-mentioned purpose, the second aspect of the present application proposes an adaptive optimization device suitable for flexible assembly technology, including: a first acquisition module, used to obtain the final position of the robot used for assembly and the assembly data of each successful assembly process after each successful assembly of the flexible assembly system; a second acquisition module, used to obtain the time weight value, six-dimensional force weight value and pressure weight value corresponding to the robot in each successful assembly process according to the assembly data; a third acquisition module, used to obtain the target weight value corresponding to the robot in each successful assembly process according to the time weight value, six-dimensional force weight value and pressure weight value; a position determination module, used to determine the initial position of the robot in the next assembly process according to the final position and the target weight value and a preset position mapping relationship.

[0019] According to one embodiment of the present application, the second acquisition module is also used to: obtain the assembly time corresponding to the robot from the start of assembly to successful assembly in each assembly process based on the assembly data; obtain the assembly time threshold and the preset time weight reference value corresponding to the robot; determine the time weight value according to the assembly time, the assembly time threshold and the time weight reference value and the preset time weight value mapping relationship.

[0020] According to one embodiment of the present application, the second acquisition module is also used to: obtain the force duration corresponding to the robot's six-dimensional mechanical sensor in each assembly process, and the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment within the force duration according to the assembly data; obtain the average six-dimensional force value corresponding to the six-dimensional mechanical sensor in the assembly process according to the force duration and the real-time six-dimensional force value; obtain the preset six-dimensional force weight reference value corresponding to the robot, and obtain the maximum average six-dimensional force value from all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor; obtain the six-dimensional force weight value according to the average six-dimensional force value, the maximum average six-dimensional force value, and the six-dimensional force weight reference value according to the preset six-dimensional force weight value mapping relationship.

[0021] According to one embodiment of the present application, the second acquisition module is also used to: obtain the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment in each assembly process, and determine the starting force moment of the six-dimensional mechanical sensor based on the real-time six-dimensional force value; obtain the preset six-dimensional force threshold corresponding to the robot; during the assembly process, in response to the sum of the discrete first-order derivatives of the real-time six-dimensional force value being less than or equal to the six-dimensional force threshold, obtain the ending force moment of the six-dimensional mechanical sensor; based on the starting force moment and the ending force moment, obtain the corresponding force duration of the six-dimensional mechanical sensor in the current assembly process.

[0022] According to one embodiment of the present application, the second acquisition module is also used to: obtain the real-time pressure value of the pressure sensor on the assembled body at each moment within the force duration according to the assembly data; obtain the average pressure value corresponding to the pressure sensor during the assembly process according to the force duration and the real-time pressure value; obtain a preset pressure weight reference value, and obtain the maximum average pressure value from all historical average pressure values ​​of the assembled body; obtain the pressure weight value according to the average pressure value, the maximum average pressure value, and the pressure weight reference value according to the preset pressure weight value mapping relationship.

[0023] According to one embodiment of the present application, the sum of the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value is a preset value.

[0024] According to an embodiment of the present application, the position determination module is further used to: in response to the flexible assembly system failing to assemble in any assembly process, use the initial position of the assembly process as the initial position of the next assembly process.

[0025] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the adaptive optimization method suitable for flexible assembly technology as described in the first aspect embodiment of the present application.

[0026] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the adaptive optimization method applicable to flexible assembly technology as described in the first aspect embodiment of the present application.

[0027] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the adaptive optimization method applicable to flexible assembly technology as described in the first aspect of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0029] Figure 1 An exemplary implementation of an adaptive optimization method applicable to flexible assembly technology is shown in an embodiment of the present application.

[0030] Figure 2 This is an exemplary implementation of a process for obtaining a time weight value shown in an embodiment of the present application.

[0031] Figure 3 It is an exemplary implementation of a process for obtaining a six-dimensional force weight value shown in an embodiment of the present application.

[0032] Figure 4 This is an exemplary implementation of a process for obtaining a pressure weight value shown in an embodiment of the present application.

[0033] Figure 5 It is a flow chart of an adaptive optimization method applicable to flexible assembly technology shown in an embodiment of the present application.

[0034] Figure 6 It is a schematic diagram of an adaptive optimization device suitable for flexible assembly technology shown in an embodiment of the present application.

[0035] Figure 7 It is a schematic diagram of an electronic device shown in one embodiment of the present application. DETAILED DESCRIPTION

[0036] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0037] Figure 1 This is an exemplary embodiment of an adaptive optimization method suitable for flexible assembly technology shown in this application, such as Figure 1 As shown, the adaptive optimization method suitable for flexible assembly technology includes the following steps:

[0038] S101, obtaining the final position of the robot used for assembly and assembly data of each successful assembly process after each successful assembly of the flexible assembly system.

[0039] At present, a large number of flexible assembly methods are mainly aimed at shaft-hole assembly tasks, which are assembled by flexible assembly systems. In this application, the final position data P of the assembly robot is obtained after each successful assembly of the flexible assembly system. i , and obtain the assembly data of each successful assembly process.

[0040] Among them, the assembly data includes the assembly time corresponding to the assembly start to the successful assembly of the robot in each assembly process, the force duration corresponding to the robot's six-dimensional mechanical sensor in each assembly process, the real-time six-dimensional force value of the six-dimensional mechanical sensor on the robot at each moment during the force duration, and the real-time pressure value of the pressure sensor on the assembled body at each moment during the force duration.

[0041] S102, according to the assembly data, obtaining the time weight value, six-dimensional force weight value and pressure weight value corresponding to each successful assembly process of the robot.

[0042] The adaptive optimization method for flexible assembly technology proposed in this application does not participate in the overall flexible assembly process, but only seeks the most suitable and optimal initial position. According to the previous position data information, the assembly time, mechanical sensor process data, pressure sensor process data, assembly success result signal, etc. of this assembly are weighted and analyzed, so as to adjust the weight and gradually update the optimal initial position.

[0043] Among them, the time weight value can be determined according to the assembly time in the assembly process, the preset assembly time threshold and the preset time weight reference value, according to the preset time weight value mapping relationship.

[0044] Among them, according to the six-dimensional mechanical sensor carried by the six-axis robotic arm on the robot, the average six-dimensional force value during the time when the six-dimensional mechanical sensor is subjected to force is obtained, and according to the average six-dimensional force value, the maximum average six-dimensional force value among all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor, and the preset six-dimensional force weight reference value, according to the preset six-dimensional force weight value mapping relationship, the six-dimensional force weight value is obtained.

[0045] Among them, according to the pressure sensor carried by the assembled object, the average pressure value corresponding to the stress duration of the pressure sensor during the assembly process is obtained, and according to the average pressure value, the maximum average pressure value among all historical average pressure values ​​of the assembled object, and the preset pressure weight reference value, the pressure weight value is obtained according to the preset pressure weight value mapping relationship.

[0046] S103, obtaining the target weight value corresponding to each successful assembly process of the robot according to the time weight value, the six-dimensional force weight value and the pressure weight value.

[0047] According to the time weight value, six-dimensional force weight value and pressure weight value determined above, the target weight value corresponding to each successful assembly process of the robot is obtained. Among them, the expression of the target weight value is:

[0048] λ=λ I / O ·(f t (t)+f f (F)+f P (P))

[0049] In the above formula, λ I / O The term is the assembly signal, f t (t) is the time weight value, f f (F) is the six-dimensional force weight value, f P (P) is the pressure weight value.

[0050] Where: I / O =1 means successful assembly, λ I / O =0 means assembly failure, which means that if the assembly fails, all data during the assembly failure will not be processed or recorded, and the target weight value is 0. If the assembly is successful, the target weight value is the sum of the time weight value, the six-dimensional force weight value and the pressure weight value.

[0051] S104, determining the initial position of the robot in the next assembly process according to the final position and the target weight value and a preset position mapping relationship.

[0052] According to the final position and target weight value determined above, the initial position of the robot in the next assembly process is determined according to the preset position mapping relationship. The expression of the position mapping relationship is:

[0053]

[0054] In the above formula, P i represents the final position after the successful i-th assembly, P0 represents the initial position of the i+1-th assembly, k is the total number of assemblies, i is a certain assembly, and λ is the target weight value.

[0055] The position mapping relationship formula adopts a high-order iteration method. According to the progressive number of assembly times, the weights in the weight algorithm are continuously iterated, and the proportion of past data in the whole is gradually reduced according to the number of assembly times, thereby achieving continuous iterative upgrades of the model.

[0056] The embodiment of the present application proposes an adaptive optimization method suitable for flexible assembly technology, by obtaining the final position of the robot used for assembly after each successful assembly of the flexible assembly system and the assembly data of each successful assembly process; according to the assembly data, the time weight value, six-dimensional force weight value and pressure weight value corresponding to the robot in each successful assembly process are obtained; according to the time weight value, six-dimensional force weight value and pressure weight value, the target weight value corresponding to the robot in each successful assembly process is obtained; according to the final position and the target weight value, according to the preset position mapping relationship, the initial position of the robot in the next assembly process is determined. The present application obtains a more appropriate initial position for the next assembly process to improve assembly efficiency, and enables the model to form continuous iterations in the subsequent assembly process, which can adapt to different batches of parts, and according to the characteristics of different batches of parts, the model is autonomously iterated and updated, and all weight items can be adjusted according to the number of batches, making the model more flexible.

[0057] Furthermore, if the flexible assembly system fails in any assembly process, the initial position of the assembly process is used as the initial position of the next assembly process. For example, if the 10th assembly fails, the initial position of the 10th assembly is used as the initial position of the 11th assembly.

[0058] Figure 2 This is an exemplary implementation of a process for obtaining a time weight value shown in the present application, such as Figure 2 As shown, the process of obtaining the time weight value includes the following steps:

[0059] S201, obtaining the assembly time corresponding to the start of assembly to successful assembly of the robot in each assembly process according to the assembly data.

[0060] The length of the assembly time is the distance between the current successful assembly position and the position provided by the model. The longer the time, the farther the point is from the model. The batch parts may be replaced and the model needs to be updated. Therefore, it is necessary to obtain the assembly time corresponding to the start of the robot to the successful assembly in each assembly process.

[0061] S202, obtaining an assembly time threshold and a preset time weight reference value corresponding to the robot.

[0062] Get the preset assembly time threshold t corresponding to the robot max and the preset time weight reference value λ t .

[0063] S203, determining a time weight value according to the assembly time, the assembly time threshold and the time weight reference value and a preset time weight value mapping relationship.

[0064] According to the above-determined assembly time, assembly time threshold and time weight reference value, the time weight value is determined according to the preset time weight value mapping relationship. The expression of the time weight value mapping relationship is:

[0065]

[0066] In the above formula, f t (t) is the time weight value, λ t is the time weight reference value, t max is the assembly time threshold, and t is the assembly time.

[0067] The embodiment of the present application determines the time weight value through assembly time, assembly time threshold and time weight reference value according to a preset time weight value mapping relationship, so that the time weight value of each assembly process can be more accurately obtained according to the different circumstances of each assembly process, so as to facilitate the subsequent acquisition of a more appropriate initial position for the next assembly process, thereby improving assembly efficiency.

[0068] Figure 3 This is an exemplary implementation of a six-dimensional force weight value acquisition process shown in this application, such as Figure 3 As shown, the process of obtaining the six-dimensional force weight value includes the following steps:

[0069] S301, according to the assembly data, obtaining the force duration corresponding to the six-dimensional mechanical sensor of the robot during each assembly process, and the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment within the force duration.

[0070] According to the six-dimensional mechanical sensor at the end of the robot, the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment in each assembly process is obtained. The force condition given by the six-dimensional mechanical sensor is a six-dimensional array of six degrees of freedom. In this method, the reference weights of the six-dimensional force in each direction are the same, so the six-dimensional force resultant at each moment is selected as the reference standard for the real-time six-dimensional force value.

[0071] The starting force moment T0 of the six-dimensional mechanical sensor is determined according to the real-time six-dimensional force value, and the preset six-dimensional force threshold Th corresponding to the robot is obtained. During the assembly process, in response to the sum of the discrete first-order derivatives of the real-time six-dimensional force value being less than or equal to the six-dimensional force threshold, the ending force moment of the six-dimensional mechanical sensor is obtained. Based on the starting force moment and the ending force moment, the corresponding force duration of the six-dimensional mechanical sensor in the current assembly process is obtained.

[0072] Among them, the expression corresponding to the force duration is:

[0073]

[0074] In the above formula, T is the force duration, T0 is the starting force moment, t1 is each moment from the starting force moment to the ending force moment, Th is the six-dimensional force threshold, and F is the real-time six-dimensional force value.

[0075] S302, obtaining an average six-dimensional force value corresponding to the six-dimensional mechanical sensor during the assembly process according to the force duration and the real-time six-dimensional force value.

[0076] According to the force duration and the real-time six-dimensional force value, the average six-dimensional force value corresponding to the six-dimensional mechanical sensor in the assembly process is obtained. The expression for obtaining the average six-dimensional force value is:

[0077]

[0078] In the above formula, F avg is the average six-dimensional force value, T is the force duration, and F is the real-time six-dimensional force value.

[0079] S303, obtaining a preset six-dimensional force weight reference value corresponding to the robot, and obtaining a maximum average six-dimensional force value from all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor.

[0080] Get the preset six-dimensional force weight reference value λ corresponding to the robot F , and, from all the historical average six-dimensional force values ​​of the six-dimensional mechanical sensor, obtain the maximum average six-dimensional force value F max ,

[0081] S304, obtaining the six-dimensional force weight value according to the average six-dimensional force value, the maximum average six-dimensional force value, and the six-dimensional force weight reference value and the preset six-dimensional force weight value mapping relationship.

[0082] According to the average six-dimensional force value, the maximum average six-dimensional force value, and the six-dimensional force weight reference value, the six-dimensional force weight value is obtained according to the preset six-dimensional force weight value mapping relationship. Among them, the expression of the six-dimensional force weight value mapping relationship is:

[0083]

[0084] In the above formula, f f (F) is the six-dimensional force weight value, F avg is the average six-dimensional force value, F max is the maximum average six-dimensional force value, λ F is the reference value of the six-dimensional force weight.

[0085] The embodiment of the present application obtains the six-dimensional force weight value according to the average six-dimensional force value, the maximum average six-dimensional force value, and the six-dimensional force weight reference value in accordance with a preset six-dimensional force weight value mapping relationship, so that the six-dimensional force weight value in each assembly process can be more accurately obtained according to the different circumstances of each assembly process, so as to facilitate the subsequent acquisition of a more appropriate initial position for the next assembly process, thereby improving assembly efficiency.

[0086] Figure 4 This is an exemplary implementation of a process for obtaining a pressure weight value shown in the present application. Figure 4 As shown, based on the above embodiment, the process of obtaining the pressure weight value includes the following steps:

[0087] S401, obtaining the real-time pressure value of the pressure sensor on the assembled body at each moment within the force duration according to the assembly data.

[0088] The real-time pressure value P of the pressure sensor on the assembled body is obtained from the start time to the end time, that is, the real-time pressure value P of the pressure sensor on the assembled body is obtained at each time during the force duration. The method for obtaining the force duration can refer to the relevant introduction in step S301, which will not be repeated here.

[0089] S402, obtaining an average pressure value corresponding to the pressure sensor during the assembly process according to the force duration and the real-time pressure value.

[0090] According to the force duration and the real-time pressure value, the average pressure value corresponding to the pressure sensor during the assembly process is obtained.

[0091] The expression for obtaining the average pressure value is:

[0092]

[0093] In the above formula, P avg is the average pressure value, T is the force duration, and P is the real-time pressure value.

[0094] S403, obtaining a preset pressure weight reference value, and obtaining a maximum average pressure value from all historical average pressure values ​​of the assembled body.

[0095] Get the preset pressure weight reference value λ P , and, from all the historical average pressure values ​​of the assembled body, obtain the maximum average pressure value P max .

[0096] S404, obtaining a pressure weight value according to the average pressure value, the maximum average pressure value, and the pressure weight reference value in accordance with a preset pressure weight value mapping relationship.

[0097] According to the average pressure value, the maximum average pressure value, and the pressure weight reference value, the pressure weight value is obtained according to the preset pressure weight value mapping relationship. The expression of the pressure weight value mapping relationship is:

[0098]

[0099] In the above formula, f P (P) is the pressure weight value, P avg is the average pressure value, P max is the maximum average pressure value, λ P is the pressure weight reference value.

[0100] The embodiment of the present application obtains the pressure weight value according to the average pressure value, the maximum average pressure value, and the pressure weight reference value in accordance with a preset pressure weight value mapping relationship, so that the pressure weight value in each assembly process can be more accurately obtained according to the different conditions of each assembly process, so as to facilitate the subsequent acquisition of a more appropriate initial position for the next assembly process, thereby improving assembly efficiency.

[0101] Furthermore, the sum of the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value is a preset value. The preset value can be adjusted according to the part batch. Optionally, the preset value can be between [0.05, 0.5]. For a large number of parts with a large number of parts, the preset value can be adjusted to be larger so that the model is updated faster and more stable. For a small batch of parts with a small number of parts, the preset value can be adjusted to be smaller so that the model changes more slowly and the model is more accurate.

[0102] After determining the preset value, the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value can be assigned according to the actual situation, and the assignment must satisfy the sum of the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value to be the preset value. For example, if the preset value is 0.1, the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value can be 0.04, 0.03 and 0.03 respectively. The proportion of the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value to the preset value can be adjusted according to the actual situation.

[0103] Figure 5 is a flow chart of an adaptive optimization method for flexible assembly technology proposed in this application, such as Figure 5 As shown in FIG. 1 , the adaptive optimization method for flexible assembly technology first sets a preset value according to the part batch, and then determines the time weight reference value λ according to the preset value. t , six-dimensional force weight reference value λ F and pressure weight reference value λ P , where the time weight reference value λ t , six-dimensional force weight reference value λ F and pressure weight reference value λ P The sum of is the preset value. In addition, to facilitate the subsequent calculation of the time weight value f t (t), six-dimensional force weight value f f (F) and the pressure weight value f P (P), pre-set the assembly time threshold t max and the six-dimensional force threshold Th.

[0104] The flexible assembly is started according to the initial position of the robot. If the flexible assembly is successful, the final position data P of the assembly robot is obtained after each successful assembly of the flexible assembly system. i , and obtain the force duration T of the six-dimensional mechanical sensor during this assembly process.

[0105] Among them, the expression corresponding to the force duration is:

[0106]

[0107] In the above formula, T is the force duration, T0 is the starting force moment, t1 is each moment from the starting force moment to the ending force moment, Th is the six-dimensional force threshold, and F is the real-time six-dimensional force value.

[0108] According to the force duration and the real-time six-dimensional force value, the average six-dimensional force value corresponding to the six-dimensional mechanical sensor in the assembly process is obtained. The expression for obtaining the average six-dimensional force value is:

[0109]

[0110] In the above formula, F avg is the average six-dimensional force value, T is the force duration, and F is the real-time six-dimensional force value.

[0111] And, according to the force duration and the real-time pressure value, the average pressure value corresponding to the pressure sensor in the assembly process is obtained. The expression for obtaining the average pressure value is:

[0112]

[0113] In the above formula, P avg is the average pressure value, T is the force duration, and P is the real-time pressure value.

[0114] According to the assembly time in the assembly process, the preset assembly time threshold and the preset time weight reference value, the time weight value can be determined according to the preset time weight value mapping relationship, wherein the expression of the time weight value mapping relationship is:

[0115]

[0116] In the above formula, f t (t) is the time weight value, λ t is the time weight reference value, t max is the assembly time threshold, and t is the assembly time.

[0117] According to the average six-dimensional force value, the maximum average six-dimensional force value among all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor, and the preset six-dimensional force weight reference value, the six-dimensional force weight value is obtained according to the preset six-dimensional force weight value mapping relationship, wherein the expression of the six-dimensional force weight value mapping relationship is:

[0118]

[0119] In the above formula, f f (F) is the six-dimensional force weight value, F avg is the average six-dimensional force value, F max is the maximum average six-dimensional force value, λ F is the reference value of the six-dimensional force weight.

[0120] According to the average pressure value, the maximum average pressure value among all historical average pressure values ​​of the assembled body, and the preset pressure weight reference value, the pressure weight value is obtained according to the preset pressure weight value mapping relationship. The expression of the pressure weight value mapping relationship is:

[0121]

[0122] In the above formula, f P (P) is the pressure weight value, P avgis the average pressure value, P max is the maximum average pressure value, λ P is the pressure weight reference value.

[0123] Then, according to the time weight value, six-dimensional force weight value and pressure weight value determined above, the target weight value corresponding to each successful assembly process of the robot is obtained.

[0124] The expression of the target weight value is:

[0125] λ=λ I / O ·(f t (t)+f f (F)+f P (P))

[0126] In the above formula, λ I / O The term is the assembly signal, f t (t) is the time weight value, f f (F) is the six-dimensional force weight value, f P (P) is the pressure weight value, λ I / O =1 means successful assembly, λ I / O =0 means assembly failed.

[0127] According to the final position and target weight value determined above, the initial position of the robot in the next assembly process is determined according to the preset position mapping relationship to update the initial position of this assembly process. The expression of the position mapping relationship is:

[0128]

[0129] In the above formula, P i represents the final position after the successful i-th assembly, P0 represents the initial position of the i+1-th assembly, k is the total number of assemblies, i is a certain assembly, and λ is the target weight value.

[0130] Furthermore, if the flexible assembly system fails in any assembly process, the initial position of the assembly process is used as the initial position of the next assembly process.

[0131] An embodiment of the present application proposes an adaptive optimization method suitable for flexible assembly technology, which obtains the final position of the robot used for assembly and the assembly data of each successful assembly process after each successful assembly of the flexible assembly system; obtains the time weight value, six-dimensional force weight value and pressure weight value corresponding to the robot in each successful assembly process based on the assembly data; obtains the target weight value corresponding to the robot in each successful assembly process based on the time weight value, six-dimensional force weight value and pressure weight value; and determines the initial position of the robot in the next assembly process based on the final position and the target weight value and in accordance with a preset position mapping relationship.

[0132] The embodiment of the present application improves assembly efficiency by obtaining a more appropriate initial position for the next assembly process. It can be used directly without a large amount of experimental data as support, and for different batches of parts, the model does not need to be retrained. The model can be updated autonomously, reducing the frequent debugging process in the later stage. At the same time, it has various weighted items, which provides stronger inclusiveness and accuracy for the model data, and only relies on the existing data, and can be used without additional hardware equipment.

[0133] Figure 6 A schematic diagram of an adaptive optimization device suitable for flexible assembly technology is proposed, e.g. Figure 6 As shown, the adaptive optimization device 600 applicable to the flexible assembly technology includes a first acquisition module 601, a second acquisition module 602, a third acquisition module 603 and a position determination module 604, wherein:

[0134] The first acquisition module 601 is used to acquire the final position of the robot used for assembly and the assembly data of each successful assembly process after each successful assembly of the flexible assembly system;

[0135] The second acquisition module 602 is used to acquire the time weight value, six-dimensional force weight value and pressure weight value corresponding to each successful assembly process of the robot according to the assembly data;

[0136] The third acquisition module 603 is used to acquire the target weight value corresponding to each successful assembly process of the robot according to the time weight value, the six-dimensional force weight value and the pressure weight value;

[0137] The position determination module 604 is used to determine the initial position of the robot in the next assembly process according to the final position and the target weight value and a preset position mapping relationship.

[0138] The adaptive optimization device suitable for flexible assembly technology proposed in this application obtains a more appropriate initial position for the next assembly process to improve assembly efficiency, and enables the model to form continuous iterations in the subsequent assembly process. It can adapt to different batches of parts and components, and autonomously iterate and update the model according to the characteristics of different batches of parts and components. At the same time, all weight items can be adjusted according to the batch quantity, making the model more flexible.

[0139] Furthermore, the second acquisition module 602 is also used to: obtain the assembly time corresponding to the robot from the start of assembly to the successful assembly in each assembly process according to the assembly data; obtain the assembly time threshold and the preset time weight reference value corresponding to the robot; determine the time weight value according to the assembly time, the assembly time threshold and the time weight reference value and the preset time weight value mapping relationship.

[0140] Furthermore, the second acquisition module 602 is also used to: obtain the force duration corresponding to the robot's six-dimensional mechanical sensor in each assembly process, and the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment within the force duration according to the assembly data; obtain the average six-dimensional force value corresponding to the six-dimensional mechanical sensor in the assembly process according to the force duration and the real-time six-dimensional force value; obtain the preset six-dimensional force weight reference value corresponding to the robot, and obtain the maximum average six-dimensional force value from all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor; obtain the six-dimensional force weight value according to the average six-dimensional force value, the maximum average six-dimensional force value, and the six-dimensional force weight reference value according to the preset six-dimensional force weight value mapping relationship.

[0141] Furthermore, the second acquisition module 602 is also used to: obtain the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment in each assembly process, and determine the starting force moment of the six-dimensional mechanical sensor based on the real-time six-dimensional force value; obtain the preset six-dimensional force threshold corresponding to the robot; during the assembly process, in response to the sum of the discrete first-order derivatives of the real-time six-dimensional force value being less than or equal to the six-dimensional force threshold, obtain the ending force moment of the six-dimensional mechanical sensor; based on the starting force moment and the ending force moment, obtain the corresponding force duration of the six-dimensional mechanical sensor in the current assembly process.

[0142] Furthermore, the second acquisition module 602 is also used to: obtain the real-time pressure value of the pressure sensor on the assembled body at each moment within the force duration according to the assembly data; obtain the average pressure value corresponding to the pressure sensor during the assembly process according to the force duration and the real-time pressure value; obtain a preset pressure weight reference value, and obtain the maximum average pressure value from all historical average pressure values ​​of the assembled body; obtain the pressure weight value according to the average pressure value, the maximum average pressure value, and the pressure weight reference value according to the preset pressure weight value mapping relationship.

[0143] Furthermore, the sum of the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value is a preset value.

[0144] Furthermore, the position determination module 604 is further configured to: in response to the flexible assembly system failing to assemble in any assembly process, use the initial position of the assembly process as the initial position of the next assembly process.

[0145] In order to implement the above embodiment, the present application embodiment also proposes an electronic device 700, such as Figure 7 As shown, the electronic device 700 includes: a processor 701 and a memory 702 communicatively connected to the processor, the memory 702 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 701 to implement the adaptive optimization method suitable for flexible assembly technology as shown in the above embodiment.

[0146] In order to implement the above embodiment, the embodiment of the present application also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to implement the adaptive optimization method applicable to flexible assembly technology as shown in the above embodiment.

[0147] In order to implement the above embodiments, the embodiments of the present application further provide a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements the adaptive optimization method applicable to the flexible assembly technology as shown in the above embodiments.

[0148] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0149] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0150] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0151] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An adaptive optimization method suitable for flexible assembly technology, characterized in that: include: Obtain the final position of the robot used for assembly after each successful assembly of the flexible assembly system and the assembly data of each successful assembly process; According to the assembly data, a time weight value, a six-dimensional force weight value, and a pressure weight value corresponding to each successful assembly process of the robot are obtained; According to the time weight value, the six-dimensional force weight value and the pressure weight value, obtaining a target weight value corresponding to each successful assembly process of the robot; According to the final position and the target weight value, and in accordance with a preset position mapping relationship, determining the initial position of the robot in the next assembly process; The process of obtaining the time weight value includes: obtaining the assembly time corresponding to the robot from the start of assembly to the successful assembly in each assembly process according to the assembly data; obtaining the assembly time threshold and the preset time weight reference value corresponding to the robot; determining the time weight value according to the assembly time, the assembly time threshold and the time weight reference value according to the preset time weight value mapping relationship; wherein the expression of the time weight value mapping relationship is: In the above formula, f t (t) is the time weight value, λ t is the time weight reference value, t max is the assembly time threshold, t is the assembly time; Among them, the acquisition process of the six-dimensional force weight value includes: according to the assembly data, obtaining the force duration corresponding to the six-dimensional mechanical sensor of the robot in each assembly process, and the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment within the force duration; according to the force duration and the real-time six-dimensional force value, obtaining the average six-dimensional force value corresponding to the six-dimensional mechanical sensor in the assembly process; obtaining the preset six-dimensional force weight reference value corresponding to the robot, and obtaining the maximum average six-dimensional force value from all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor; according to the average six-dimensional force value, the maximum average six-dimensional force value, and the six-dimensional force weight reference value, according to the preset six-dimensional force weight value mapping relationship, obtaining the six-dimensional force weight value; wherein, the expression of the six-dimensional force weight value mapping relationship is: In the above formula, f f (F) is the six-dimensional force weight value, F avg is the average six-dimensional force value, F max is the maximum average six-dimensional force value, λ F is the reference value of the six-dimensional force weight; The process of obtaining the pressure weight value includes: obtaining the real-time pressure value of the pressure sensor on the assembled body at each moment within the force duration according to the assembly data; obtaining the average pressure value corresponding to the pressure sensor in the assembly process according to the force duration and the real-time pressure value; obtaining a preset pressure weight reference value, and obtaining the maximum average pressure value from all historical average pressure values ​​of the assembled body; obtaining the pressure weight value according to the average pressure value, the maximum average pressure value, and the pressure weight reference value according to the preset pressure weight value mapping relationship; wherein the expression of the pressure weight value mapping relationship is: In the above formula, f P (P) is the pressure weight value, P avg is the average pressure value, P max is the maximum average pressure value, λ P is the pressure weight reference value; According to the time weight value, the six-dimensional force weight value and the pressure weight value, the target weight value corresponding to each successful assembly process of the robot is obtained, and the expression of the target weight value is: λ=λ I / O ·(f t (t)+f f (F)+f P (P)) In the above formula, λ I / O The term is the assembly signal, f t (t) is the time weight value, f f (F) is the six-dimensional force weight value, f P (P) is the pressure weight value, λ I / O =1 means successful assembly, λ I / O =0 means assembly failure; Among them, according to the final position and the target weight value, according to the preset position mapping relationship, when the initial position of the robot in the next assembly process is determined, the expression of the position mapping relationship is: In the above formula, P i represents the final position after the successful i-th assembly, P0 represents the initial position of the i+1-th assembly, k is the total number of assemblies, i is a certain assembly, and λ is the target weight value.

2. The method according to claim 1, characterized in that The step of obtaining the force duration corresponding to the six-dimensional mechanical sensor of the robot during each assembly process according to the assembly data includes: Acquire the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment in each assembly process, and determine the starting force-bearing moment of the six-dimensional mechanical sensor according to the real-time six-dimensional force value; Obtaining a preset six-dimensional force threshold corresponding to the robot; During the assembly process, in response to the sum of the discrete first-order derivatives of the real-time six-dimensional force value being less than or equal to the six-dimensional force threshold, acquiring the force termination moment of the six-dimensional mechanical sensor; According to the starting force-bearing time and the ending force-bearing time, the force-bearing time duration corresponding to the six-dimensional mechanical sensor in the current assembly process is obtained.

3. The method according to claim 1, characterized in that The sum of the time weight reference value, the six-dimensional force weight reference value and the pressure weight reference value is the target weight value.

4. The method according to claim 1, characterized in that: The method further comprises: In response to the flexible assembly system failing in any assembly process, the initial position of the assembly process is used as the initial position of the next assembly process.

5. An adaptive optimization device suitable for flexible assembly technology, characterized in that: include: A first acquisition module is used to acquire the final position of the robot used for assembly and the assembly data of each successful assembly process after each successful assembly of the flexible assembly system; A second acquisition module is used to acquire, according to the assembly data, a time weight value, a six-dimensional force weight value, and a pressure weight value corresponding to each successful assembly process of the robot; A third acquisition module is used to acquire a target weight value corresponding to each successful assembly process of the robot according to the time weight value, the six-dimensional force weight value and the pressure weight value; A position determination module, used to determine the initial position of the robot in the next assembly process according to the final position and the target weight value and a preset position mapping relationship; The process of obtaining the time weight value includes: obtaining the assembly time corresponding to the robot from the start of assembly to the successful assembly in each assembly process according to the assembly data; obtaining the assembly time threshold and the preset time weight reference value corresponding to the robot; determining the time weight value according to the assembly time, the assembly time threshold and the time weight reference value according to the preset time weight value mapping relationship; wherein the expression of the time weight value mapping relationship is: In the above formula, f t (t) is the time weight value, λ t is the time weight reference value, t max is the assembly time threshold, t is the assembly time; Among them, the acquisition process of the six-dimensional force weight value includes: according to the assembly data, obtaining the force duration corresponding to the six-dimensional mechanical sensor of the robot in each assembly process, and the real-time six-dimensional force value of the six-dimensional mechanical sensor at each moment within the force duration; according to the force duration and the real-time six-dimensional force value, obtaining the average six-dimensional force value corresponding to the six-dimensional mechanical sensor in the assembly process; obtaining the preset six-dimensional force weight reference value corresponding to the robot, and obtaining the maximum average six-dimensional force value from all historical average six-dimensional force values ​​of the six-dimensional mechanical sensor; according to the average six-dimensional force value, the maximum average six-dimensional force value, and the six-dimensional force weight reference value, according to the preset six-dimensional force weight value mapping relationship, obtaining the six-dimensional force weight value; wherein, the expression of the six-dimensional force weight value mapping relationship is: In the above formula, f f (F) is the six-dimensional force weight value, F avg is the average six-dimensional force value, F max is the maximum average six-dimensional force value, λ F is the reference value of the six-dimensional force weight; The process of obtaining the pressure weight value includes: obtaining the real-time pressure value of the pressure sensor on the assembled body at each moment within the force duration according to the assembly data; obtaining the average pressure value corresponding to the pressure sensor in the assembly process according to the force duration and the real-time pressure value; obtaining a preset pressure weight reference value, and obtaining the maximum average pressure value from all historical average pressure values ​​of the assembled body; obtaining the pressure weight value according to the average pressure value, the maximum average pressure value, and the pressure weight reference value according to the preset pressure weight value mapping relationship; wherein the expression of the pressure weight value mapping relationship is: In the above formula, f P (P) is the pressure weight value, P avg is the average pressure value, P max is the maximum average pressure value, λ P is the pressure weight reference value; According to the time weight value, the six-dimensional force weight value and the pressure weight value, the target weight value corresponding to each successful assembly process of the robot is obtained, and the expression of the target weight value is: λ=λ I / O ·(f t (t)+f f (F)+f P (P)) In the above formula, λ I / O The term is the assembly signal, f t (t) is the time weight value, f f (F) is the six-dimensional force weight value, f P (P) is the pressure weight value, λ I / O =1 means successful assembly, λ I / O =0 means assembly failure; Among them, according to the final position and the target weight value, according to the preset position mapping relationship, when the initial position of the robot in the next assembly process is determined, the expression of the position mapping relationship is: In the above formula, P i represents the final position after the successful i-th assembly, P0 represents the initial position of the i+1-th assembly, k is the total number of assemblies, i is a certain assembly, and λ is the target weight value.

6. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

Images