Position adaptive method and device for flexible assembly technology

Abstract

The present disclosure proposes a position adaptive method and device for flexible assembly technology, wherein the method includes: obtaining the final position of a robot used for assembly and the final force value fed back by a six-dimensional mechanical sensor after the flexible assembly system successfully assembles a target component; based on the final position, determining the target category to which the target component belongs in a set plurality of categories; updating the center of mass of components of the target category in a target center of mass matrix of components of a plurality of categories according to the final position and the final force value; determining the target center of mass of components of the category with the maximum assembly probability from the target center of mass matrix, and determining the initial position of the robot in the next assembly process according to the target center of mass, thereby the robot can obtain a more appropriate initial position for the next assembly process in advance, and can also adapt to components of different categories, thereby reducing the flexible assembly time and improving the assembly efficiency.

Description

Technical Field

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

[0002] When facing the shaft hole problem, the flexible assembly method uses a robot with a six-dimensional mechanical sensor at the end to complete the flexible assembly through corresponding force perception and position posture correction. Due to the large uncertainty of the initial position, the time fluctuation of the flexible assembly is large. Therefore, for some workstations with process cycle requirements, how to solve the long assembly time has become an urgent problem to be solved. Summary of the invention

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

[0004] To this end, the first purpose of the present invention is to propose a position adaptive method for flexible assembly technology, so as to determine the target category to which the currently assembled parts belong according to the final position of the current assembly of the robot and the final force value fed back by the six-dimensional mechanical sensor, and update the center of mass of the parts of the target category, so that in the target center of mass matrix, the initial position of the robot in the next assembly process is determined according to the center of mass of the parts of the category with the maximum assembly probability. Thus, the final position after the flexible assembly is completed and the final force value fed back by the six-dimensional mechanical sensor are subjected to data analysis, so that the robot can obtain a more appropriate initial position for the next assembly process in advance, and can also adapt to different categories of parts, thereby reducing the flexible assembly time and improving the assembly efficiency.

[0005] A second objective of the present disclosure is to provide a position adaptive device for flexible assembly technology.

[0006] A third objective of the present disclosure is to provide an electronic device.

[0007] A fourth object of the present disclosure is to provide a non-transitory computer-readable storage medium.

[0008] A fifth object of the present disclosure is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first aspect of the present disclosure proposes a position adaptation method for flexible assembly technology, including: obtaining the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target component; based on the final position, determining the target category to which the target component belongs in the set multiple categories; according to the final position and the final force value, updating the center of mass of the components of the target category in the target center of mass matrix of the components of the multiple categories; wherein the target center of mass matrix is ​​generated based on the initial center of mass matrix of the components of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the initial center of mass of the components of each category; from the target center of mass matrix, determining the target center of mass of the components of the category with the maximum assembly probability, and determining the initial position of the robot in the next assembly process based on the target center of mass.

[0010] The position adaptive method for flexible assembly technology of the disclosed embodiment obtains the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target parts; based on the final position, determines the target category to which the target parts belong in the set multiple categories; according to the final position and the final force value, updates the center of mass of the parts of the target category in the target center of mass matrix of the parts of the multiple categories; wherein the target center of mass matrix is ​​generated according to the initial center of mass matrix of the parts of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the center of mass of the parts of each category; from the target center of mass matrix, determines the target center of mass of the parts of the category with the maximum assembly probability, and determines the initial position of the robot in the next assembly process according to the target center of mass, thereby, according to the final position after the flexible assembly is completed and the final force value fed back by the six-dimensional mechanical sensor, the robot can obtain a more appropriate initial position for the next assembly process in advance, and can also adapt to different categories of parts, thereby reducing the flexible assembly time and improving the assembly efficiency.

[0011] To achieve the above-mentioned purpose, the second aspect of the present disclosure proposes a position adaptive device for flexible assembly technology, including: an acquisition module, used to obtain the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target component; a first determination module, used to determine the target category to which the target component belongs based on the final position; an update module, used to update the center of mass of the components of the target category in the target center of mass matrix of the components of the multiple categories based on the final position and the final force value; wherein the target center of mass matrix is ​​generated based on the initial center of mass matrix of the components of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the center of mass of the components of each category; a second determination module, used to determine the target center of mass of the components of the category with the maximum assembly probability from the target center of mass matrix, and determine the initial position of the robot in the next assembly process based on the target center of mass.

[0012] To achieve the above-mentioned purpose, the third aspect embodiment of the present disclosure 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 so that the at least one processor can execute the position adaptation method for flexible assembly technology described in the first aspect embodiment of the present disclosure.

[0013] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present disclosure proposes a non-temporary computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the position adaptation method for flexible assembly technology described in the first aspect embodiment of the present disclosure is implemented.

[0014] In order to achieve the above-mentioned purpose, the fifth aspect of the present disclosure provides a computer program product. When the instruction processor in the computer program product is executed, the method described in the first aspect of the present disclosure is executed.

[0015] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A schematic flow chart of a position adaptation method for flexible assembly technology provided by an embodiment of the present disclosure;

[0018] Figure 2A schematic flow chart of another position adaptation method for flexible assembly technology provided by an embodiment of the present disclosure;

[0019] Figure 3 A schematic flow chart of another position adaptation method for flexible assembly technology provided by an embodiment of the present disclosure;

[0020] Figure 4 A schematic flow chart of a position adaptation method for flexible assembly technology provided in this embodiment;

[0021] Figure 5 A schematic diagram of the structure of a position adaptive device for flexible assembly technology provided by an embodiment of the present disclosure;

[0022] Figure 6 The invention is a block diagram of an electronic device showing a position adaptive method for flexible assembly technology according to an exemplary embodiment. DETAILED DESCRIPTION

[0023] Embodiments of the present disclosure are described in detail below, examples of which 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 disclosure, and should not be construed as limiting the present disclosure.

[0024] At present, a large number of flexible assembly methods are mainly aimed at shaft-hole assembly tasks. Different flexible assembly methods are adapted according to different scenarios, but the flexible assembly methods are different in performance. Therefore, different optimization methods have emerged for flexible assembly methods. For example, through different algorithm models, manual assembly experience data, simulation data, assembly matching fitness data, etc. are used as model training data to train the model. Then, the actual data of each axis of the current assembly is used as input data, and the pre-trained model analyzes the input data, and then provides the robot with the optimal action plan.

[0025] However, when facing the shaft hole problem, different 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. Due to the large uncertainty of the initial position, the time fluctuation of flexible assembly is large. For some workstations with process beat requirements, an optimization method is needed to solve the problem of long assembly time. In the actual application process, different batches of parts have deviations in different degrees and directions, resulting in the inapplicability of large batches of established training models. And for the possibility of no training, it is difficult for the model to provide the optimal assembly solution, and the model cannot be updated in time.

[0026] In view of the above problems, the present disclosure proposes a position self-adaptation method and device for flexible assembly technology.

[0027] The following describes the position adaptation method and device for flexible assembly technology according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0028] Figure 1 A schematic flow chart of a position adaptation method for flexible assembly technology provided in an embodiment of the present disclosure.

[0029] like Figure 1 As shown, the position adaptive method for flexible assembly technology may include the following steps:

[0030] Step 101, obtaining the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target component.

[0031] It should be understood that currently a large number of flexible assemblies are mainly aimed at shaft-hole assembly tasks, which are assembled by flexible assembly systems. In the embodiment of the present disclosure, the final position P of the robot used for assembly can be obtained after the flexible assembly system successfully assembles the target parts. i And the final force value F fed back by the six-dimensional mechanical sensor.

[0032] Step 102: Based on the final position, determine the target category to which the target component belongs among the set multiple categories.

[0033] As an example, based on the target distances between the final position and the centroids of each category of parts in the target centroid matrix, the category corresponding to the minimum distance in the target distances can be used as the target category to which the target part belongs.

[0034] In the disclosed embodiment, when the target parts are assembled for the first time, the target centroid matrix may be the initial centroid matrix, and when the target parts are assembled for a non-first time, the target centroid matrix may be obtained by updating the initial centroid matrix at least once. That is, when the target parts are assembled for the second time, the target centroid matrix is ​​obtained by updating the initial centroid matrix once, and when the target parts are assembled for the third time, the target centroid matrix is ​​obtained by updating the initial centroid matrix after updating once, and so on, when the target parts are assembled for the Nth time, the target centroid matrix is ​​obtained by updating the initial centroid matrix based on the updated N-2 times of the initial centroid matrix.

[0035] Among them, it should be noted that before using the robot to flexibly assemble the target parts, the robot can be used to assemble parts of multiple categories, and after the assembly is successful, the robot's stop position and the force data fed back by the six-dimensional mechanical sensor are obtained; according to the robot's stop position, the initial center of mass of the parts of multiple categories are determined, and according to the force data fed back by the six-dimensional mechanical sensor, the maximum force value of the parts of each category is determined; according to the initial center of mass of the parts of multiple categories, an initial center of mass matrix is ​​generated; according to the maximum force value of the parts of multiple categories, an initial force matrix is ​​generated; according to the initial quantity of the parts of multiple categories, an initial quantity matrix is ​​generated.

[0036] Step 103 , updating the mass center of the target category of parts in the target mass center matrix of the multiple categories of parts according to the final position and the final force value.

[0037] The target centroid matrix is ​​generated based on the initial centroid matrices of parts of multiple categories, and each element in the target centroid matrix is ​​used to indicate the centroid of each category of parts.

[0038] In the disclosed embodiment, the force weight value corresponding to the final force value can be determined according to the final force value and the maximum force value of the target category of parts, so that the centroid of the target category of parts in the target centroid matrix is ​​updated according to the final position and the force weight value corresponding to the final force value. It should be noted that the target centroid matrix is ​​generated according to the initial centroid matrix of parts of multiple categories, and each element in the target centroid matrix is ​​used to indicate the initial centroid of each category of parts.

[0039] Step 104, determining the target centroid of the parts of the category with the maximum assembly probability from the target centroid matrix, and determining the initial position of the robot in the next assembly process according to the target centroid.

[0040] Furthermore, in the embodiment of the present disclosure, the probability matrix corresponding to each category of parts can be determined according to the number of assemblies of each category of parts, the maximum assembly probability can be determined from the probability matrix, and the target center of mass of the parts of the category corresponding to the maximum assembly probability in the target center of mass matrix can be used as the initial position of the robot in the next assembly process.

[0041] In summary, after the flexible assembly system successfully assembles the target parts, the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor are obtained; based on the final position, the target category to which the target parts belong in the set multiple categories is determined; according to the final position and the final force value, the center of mass of the target category parts is updated in the target center of mass matrix of parts in multiple categories; wherein the target center of mass matrix is ​​generated according to the initial center of mass matrix of parts in multiple categories, and each element in the center of mass matrix is ​​used to indicate the initial center of mass of parts in each category; from the target center of mass matrix, the target center of mass of the parts in the category with the maximum assembly probability is determined, and according to the target center of mass, the initial position of the robot in the next assembly process is determined, thereby, according to the final position after the flexible assembly is completed and the final force value fed back by the six-dimensional mechanical sensor, data analysis is performed, the robot can obtain a more appropriate initial position for the next assembly process in advance, and can also adapt to different categories of parts, reduce the flexible assembly time, and improve assembly efficiency.

[0042] In order to clearly illustrate how the above embodiment updates the centroid of parts of a target category in a target centroid matrix of parts of multiple categories according to the final position and the final force value, the present disclosure proposes another position adaptation method for flexible assembly technology.

[0043] Figure 2 A schematic flow chart of another position adaptation method for flexible assembly technology provided in an embodiment of the present disclosure.

[0044] like Figure 2 As shown, the position adaptive method for flexible assembly technology may include the following steps:

[0045] Step 201, obtaining the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target component.

[0046] Step 202: Based on the final position, determine the target category to which the target component belongs among the set multiple categories.

[0047] Step 203: Determine the maximum force value of the target category according to the final force value.

[0048] As an example, a target force matrix corresponding to multiple categories of components is obtained; wherein the target force matrix is ​​generated based on the initial force matrix of multiple categories of components, and when the final force value is greater than or equal to the force value of the target category of components in the target force matrix, the final force value is used as the maximum force value of the target category of components in the target force matrix; when the final force value is less than the force value of the target category of components in the target force matrix, the force value of the target category of components in the target force matrix is ​​used as the maximum force value of the target category.

[0049] In the disclosed embodiment, when the target component is assembled for the first time, the target force matrix may be the initial force matrix, and when the target component is not assembled for the first time, the target force matrix may be obtained by updating the initial force matrix at least once. That is, after the target component is assembled successfully for the first time, if the final force value is greater than or equal to the force value of the target category component in the initial force matrix, the final force value is used as the maximum force value of the target category component in the target force matrix for the next assembly of the target component; if the final force value is less than the force value of the target category component in the initial force matrix, the force value of the target category component in the initial force matrix is ​​used as the maximum force value of the target category in the target force matrix for the first assembly of the target component.

[0050] After the target component is successfully assembled for a non-first time, the target force matrix obtained after the last successful assembly of the target component is updated to obtain the target force matrix for the next assembly of the target component, wherein the process of updating the target force matrix is ​​as follows: when the final force value is greater than or equal to the force value of the component of the target category in the target force matrix, the final force value is used as the maximum force value of the component of the target category in the target force matrix; when the final force value is less than the force value of the component of the target category in the target force matrix, the force value of the component of the target category in the target force matrix is ​​used as the maximum force value of the target category.

[0051] Among them, in the embodiment of the present disclosure, a robot can be used to assemble multiple categories of parts, and after the assembly is successful, the force data fed back by the six-dimensional mechanical sensor is obtained, and the force data fed back by the six-dimensional mechanical sensor is used as the maximum force value of the corresponding category of parts. Then, according to the maximum force value of each category of parts, an initial force matrix is ​​generated.

[0052] After the robot successfully assembles the target component, the final force value fed back by the six-dimensional mechanical sensor can be compared with the force value of the target category component in the force matrix to which the target component belongs. If the final force value is greater than or equal to the force value of the target category component in the force matrix, the final force value is used as the maximum force value of the target category component in the force matrix; if the final force value is less than the force value of the target category component in the target force matrix, the force value of the target category component in the target force matrix is ​​used as the maximum force value of the target category. That is, the final force value F and the maximum force value corresponding to the target category are compared using the following formula to obtain whether the maximum force value is updated:

[0053] F i =max(F,F i ).

[0054] Among them, F i is the maximum force value of the target category components, and F is the final force value.

[0055] Step 204, determining a force weight value corresponding to the final force value according to the final force value and the maximum force value.

[0056] Then, according to the final force value and the maximum force value, the force weight value corresponding to the final force value is determined, which can be specifically expressed by the following formula:

[0057]

[0058] Among them, the force weight value λ∈[0,1], F represents the final force value, F i Indicates the maximum force value.

[0059] Step 205 , obtaining the target quantity of parts under the target category from the target quantity matrix corresponding to the multiple categories of parts.

[0060] The target quantity matrix is ​​generated based on the initial quantity matrices of parts of multiple categories, and the target quantity matrix includes the target quantity of parts of each category.

[0061] In the embodiment of the present disclosure, an initial quantity matrix may be generated according to the initial quantities of components of multiple categories. For example, the quantity matrix m may be expressed as m=[m1,m2,...m n ].

[0062] When the target parts are assembled for the first time, the target force matrix can be the initial quantity matrix. When the target parts are assembled for a non-first time, the target quantity matrix is ​​obtained by updating the initial quantity matrix at least once. That is, when the target parts are assembled for the first time successfully, the quantity of the target category parts in the initial quantity matrix is ​​updated to obtain the target quantity matrix for the next assembly of the target parts; after the target parts are assembled for a non-first time successfully, the quantity of the target category parts in the target quantity matrix obtained by the last assembly of the target parts is updated to obtain the target quantity matrix for the next assembly of the target parts.

[0063] Step 206, in the target centroid matrix, the centroid of the target category is updated according to the final position, weight value and target quantity.

[0064] In the embodiment of the present disclosure, the centroid of the target category is updated according to the final position, weight value and number of targets to obtain a target centroid matrix, which can be specifically expressed as the following formula:

[0065] in, C i ′ represents the centroid of the target category parts (when the target parts are assembled for the first time, C i ′ represents the initial centroid of the target category parts), P i Indicates the final position, m i Indicates the target number of components under the target category (when the target component is assembled for the first time, m i represents the initial quantity of components under the target category).

[0066] It should be noted that for flexible assembly, if the six-dimensional mechanical sensor is still subjected to a large force after the final assembly, it may indicate that the component is too tightly fitted or has burrs. Therefore, the update effect of the component on the center of mass should be reduced. Therefore, the weight value can effectively eliminate or reduce the occurrence of such situations to improve the accuracy of the model.

[0067] Step 207, determining the target centroid of the parts of the category with the maximum assembly probability from the target centroid matrix, and determining the initial position of the robot in the next assembly process according to the target centroid.

[0068] In summary, according to the final force value, the maximum force value of the target category parts is determined; according to the final force value and the maximum force value, the force weight value corresponding to the final force value is determined; from the target quantity matrix corresponding to the parts of multiple categories, the target quantity of parts under the target category is obtained; wherein each element in the quantity matrix is ​​used to indicate the target quantity of parts of each category; in the target centroid matrix, the initial centroid of the target category is updated according to the final position, weight value and target quantity, thereby realizing the updating of the centroid of the parts of the target category in the target centroid matrix.

[0069] In order to clearly explain how to determine the target centroid of the parts of the category with the maximum assembly probability from the target centroid matrix in the above embodiment, and determine the initial position of the robot in the next assembly process according to the target centroid, the present disclosure proposes another position adaptive method for flexible assembly technology

[0070] Figure 3 A schematic flow chart of another position adaptation method for flexible assembly technology provided in an embodiment of the present disclosure.

[0071] like Figure 3 As shown, the position adaptive method for flexible assembly technology may include the following steps:

[0072] Step 301, obtaining the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target component.

[0073] Step 302: Based on the final position, determine the target category to which the target component belongs among the set multiple categories.

[0074] Step 303 , updating the mass center of the target category of components in the target mass center matrix of multiple categories of components according to the final position and the final force value.

[0075] The target centroid matrix is ​​generated based on the initial centroid matrices of parts of multiple categories, and each element in the centroid matrix is ​​used to indicate the centroid of each category of parts.

[0076] Step 304 , obtaining target gain matrices and target quantity matrices of components of multiple categories.

[0077] Among them, each element in the gain matrix is ​​used to indicate the assembly times of each category of parts.

[0078] In the embodiment of the present disclosure, an initial gain matrix can be generated according to the number of assembly times of multiple categories of parts. The initial gain matrix can be expressed as G=[t1, t2, ...t n ] T, where all the items in the initial gain matrix are 1; an initial quantity matrix can be generated according to the initial quantities of multiple categories of parts, and the initial quantity matrix m can be expressed as m=[m1,m2,...m n ].

[0079] Step 305 , after the target parts are assembled successfully, the assembly times of the target category in the target gain matrix are updated and the quantity of the parts of the target category in the target quantity matrix is ​​updated.

[0080] It should be noted that after the target parts are successfully assembled, the number of assembly times of the category to which the target parts belong in the target gain matrix can be updated according to the category to which the target parts belong. If the newly assembled parts are of the same type as the parts assembled last time, the gain item of this category is increased by one, and the other gain items remain unchanged. If they are of different categories, the gain item of this category is set to one, and the other items are normalized to one. When the target parts are assembled for the first time, the target gain matrix is ​​the initial gain matrix. When the target parts are not assembled for the first time, the target gain matrix is ​​obtained by updating the initial gain matrix at least once.

[0081] Among them, after the target component is assembled successfully, the target quantity of the component of the category to which the target component belongs in the target quantity matrix is ​​updated once, which can be specifically expressed as the following formula: m i =m i +1.

[0082] Step 306: Generate a probability matrix corresponding to each category of parts based on the target gain matrix and the target quantity matrix.

[0083] Then, the updated quantity matrix is ​​normalized, and the normalized target quantity matrix is ​​multiplied by the target gain matrix to generate the probability matrix of each category, which can be expressed as the following formula:

[0084]

[0085] Where G represents the target gain matrix, m i Indicates the target quantity of each category of parts.

[0086] Step 307, determining the maximum assembly probability according to the probability matrix, and taking the target centroid of the parts of the category corresponding to the maximum assembly probability as the initial position of the robot in the next assembly process.

[0087] It should be noted that as the number of assemblies accumulates, the model is updated and iterated in real time. By performing data analysis on the final position and the final force value fed back by the six-dimensional mechanical sensor, the optimal initial position is determined and fed back to the next transfer, thereby improving assembly efficiency.

[0088] In summary, by obtaining the target gain matrix and target quantity matrix of parts of multiple categories, wherein each element in the gain matrix is ​​used to indicate the assembly times of parts of each category; after the target parts are successfully assembled, the assembly times of the target category in the target gain matrix and the number of parts of the target category in the target quantity matrix are updated, and the probability matrix corresponding to the parts of each category is generated according to the target gain matrix and the target quantity matrix; wherein each element in the probability matrix is ​​used to indicate the assembly probability of the parts of the corresponding category; according to the probability matrix, the maximum assembly probability is determined, and the target center of mass of the parts of the category corresponding to the maximum assembly probability in the target center of mass matrix is ​​used as the initial position of the robot in the next assembly process, thereby, according to the gain matrix and quantity matrix of parts of each category, the probability matrix of the assembly probability of parts of each category can be effectively generated, thereby, according to the target center of mass of the parts of the category with the maximum assembly probability in the probability matrix, the initial position of the robot in the next assembly process can be accurately determined.

[0089] like Figure 4 As shown, in any embodiment of the present disclosure, the position adaptation method for flexible assembly technology can also be implemented based on the following steps:

[0090] 1. Determine the number of centroids n. Determine the number of centroids according to different batches (categories) of parts or different processing techniques;

[0091] 2. Obtain the initial center of mass position C and the maximum force value F of each batch max . Select one from each batch of parts, assemble using the flexible assembly method, record the position P0 where the final robot arm stops after successful assembly, and record the resultant force F of the six-dimensional mechanical sensor after assembly. Set P0 and F of each batch as the initial center of mass and maximum force value. Then form an n×1 center of mass and n×1 maximum force matrix. The center of mass matrix is: C=[C1,C2,...C n ]; the maximum force matrix is: F max =[F1,F2...,F n ]. Record the number m of each batch and form a quantity matrix: m = [m1, m2...m n ];

[0092] 3. Get the category of the latest assembled component (target component). After completing the new assembly, get the current position P i And the final assembly force F. By calculating the current position P i The distance between two points and each centroid is obtained by the distance matrix d = [d1, d2....d n ] because position P iis a six-dimensional position in space, so the six-dimensional Euclidean distance equation is used to obtain the distances in the distance matrix. The distance calculation method is as follows:

[0093]

[0094] Among them, d n Indicates calculation of the current position P i The distance between each centroid, P i,j j represents the current position in each dimension of space, C n,j Represents the center of mass in each dimension of space;

[0095] By obtaining the smallest distance index in the distance matrix, the newly assembled component is assigned to the class indicated by the index;

[0096] i=argmin[d1,d2,...d n ],i∈[1,2,...n];

[0097] 4. Update the centroid C i After completing the classification of the latest assembled parts, use the current final force F and the maximum force in this category to compare using the following formula to determine whether to update the maximum force value F i .

[0098] F i =max(F,F i );

[0099] Then, the centroid of the class is updated using the following formula. i ′ is the centroid of this class before updating. i is the number of batches before updating. λ is the weighting term.

[0100]

[0101]

[0102] Then, update the number of components in this category (target category): m i =m i +1;

[0103] 5. Predict the initial position P of the next assembly. Set the 1×n gain matrix G=[t1,t2,...t n ] T . The initial gain matrix has all items set to 1. If the new assembly point is of the same type as the previous point, the gain item of that type is increased by 1, and the other gain items remain unchanged. If they are of different types, the gain item of that type is set to 1, and the other items are normalized. Then the quantity matrix is ​​normalized and the gain matrix is ​​multiplied to form various probability matrices:

[0104]

[0105] The initial position of the next assembly is the centroid position of the class with the maximum probability in the probability matrix.

[0106] The position adaptation method for flexible assembly technology of the disclosed embodiment obtains the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target parts; based on the final position, determines the target category to which the target parts belong in the set multiple categories; according to the final position and the final force value, updates the center of mass of the parts of the target category in the target center of mass matrix of the parts of the multiple categories; wherein the target center of mass matrix is ​​generated according to the initial center of mass matrix of the parts of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the center of mass of the parts of each category; from the target center of mass matrix, determines the target center of mass of the parts of the category with the maximum assembly probability, and determines the initial position of the robot in the next assembly process according to the target center of mass, thereby, according to the final position after the flexible assembly is completed and the final force value fed back by the six-dimensional mechanical sensor, the robot can obtain a more appropriate initial position for the next assembly process in advance, and can also adapt to different categories of parts, thereby reducing the flexible assembly time and improving the assembly efficiency.

[0107] In order to implement the above embodiments, the present disclosure proposes a position adaptive device for flexible assembly technology.

[0108] Figure 5 A schematic structural diagram of a position adaptive device for flexible assembly technology provided in an embodiment of the present disclosure.

[0109] like Figure 5 As shown, the position adaptive device 500 for flexible assembly technology includes: an acquisition module 510 , a first determination module 520 , an update module 530 and a second determination module 540 .

[0110] Among them, the acquisition module 510 is used to obtain the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target parts; the first determination module 520 is used to determine the target category to which the target parts belong based on the final position; the update module 530 is used to update the center of mass of the parts of the target category in the target center of mass matrix of parts of multiple categories according to the final position and the final force value; wherein the target center of mass matrix is ​​generated based on the initial center of mass matrix of parts of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the center of mass of parts of each category; the second determination module 540 is used to determine the target center of mass of the parts of the category with the maximum assembly probability from the target center of mass matrix, and determine the initial position of the robot in the next assembly process based on the target center of mass.

[0111] As a possible implementation method of the embodiment of the present disclosure, the update module 530 is used to: determine the maximum force value of the target category component according to the final force value; determine the force weight value corresponding to the final force value according to the final force value and the maximum force value; obtain the target quantity of components under the target category from the target quantity matrix corresponding to the components of multiple categories; wherein the target quantity matrix is ​​generated based on the initial quantity matrix of the components of multiple categories, and each element in the target quantity matrix is ​​used to indicate the target quantity of components of each category; in the target centroid matrix, the centroid of the target category is updated according to the final position, weight value and target quantity.

[0112] As a possible implementation method of the embodiment of the present disclosure, the update module 530 is used to: obtain target force matrices corresponding to multiple categories of components, wherein the target force matrix is ​​generated based on the initial force matrix of the multiple categories of components; when the final force value is greater than or equal to the force value of the target category of components in the target force matrix, use the final force value as the maximum force value of the target category of components in the target force matrix; when the final force value is less than the force value of the target category of components in the target force matrix, use the force value of the target category of components in the target force matrix as the maximum force value of the target category.

[0113] As a possible implementation method of the embodiment of the present disclosure, the second determination module 540 is used to obtain target gain matrices and target quantity matrices for multiple categories of parts, wherein the target gain matrix is ​​obtained by updating the initial gain matrix of multiple categories of parts at least once, and each element in the target gain matrix is ​​used to indicate the number of assemblies of each category of parts. The target quantity matrix is ​​generated based on the initial quantity matrix of multiple categories of parts, and each element in the target gain matrix is ​​used to indicate the target quantity of each category of parts; based on the target gain matrix and the target quantity matrix, a probability matrix corresponding to each category of parts is generated; wherein each element in the probability matrix is ​​used to indicate the assembly probability of the corresponding category of parts; based on the probability matrix, the maximum assembly probability is determined, and the target center of mass of the category corresponding to the maximum assembly probability in the target center of mass matrix is ​​used as the initial position of the robot in the next assembly process.

[0114] As a possible implementation method of the embodiment of the present disclosure, the first determination module 520 is used to: obtain the target distance between the final position and the center of mass of each category of parts in the target center of mass matrix; determine the category of the part corresponding to the minimum distance in the target distance, and use the category of the part corresponding to the minimum distance as the target category to which the target part belongs.

[0115] As a possible implementation of the embodiment of the present disclosure, the position adaptive device 500 for flexible assembly technology further includes: an acquisition module, a third determination module and a generation module.

[0116] Among them, the acquisition module is used to use a robot to assemble multiple categories of parts, and after the assembly is successful, obtain the robot's stop position and the force data fed back by the six-dimensional mechanical sensor; the third determination module is used to determine the initial center of mass of multiple categories of parts according to the robot's stop position, and determine the maximum force value of each category of parts according to the force data fed back by the six-dimensional mechanical sensor; the generation module is used to generate an initial center of mass matrix according to the initial center of mass of multiple categories of parts; the generation module is also used to generate an initial force matrix according to the maximum force value of multiple categories of parts.

[0117] As a possible implementation manner of the embodiment of the present disclosure, the generating module is further used to generate an initial quantity matrix according to the initial quantities of parts of multiple categories.

[0118] The position adaptation method for flexible assembly technology of the disclosed embodiment obtains the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target parts; based on the final position, determines the target category to which the target parts belong in the set multiple categories; according to the final position and the final force value, updates the center of mass of the parts of the target category in the target center of mass matrix of the parts of the multiple categories; wherein the target center of mass matrix is ​​generated according to the initial center of mass matrix of the parts of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the center of mass of the parts of each category; from the target center of mass matrix, determines the target center of mass of the parts of the category with the maximum assembly probability, and determines the initial position of the robot in the next assembly process according to the target center of mass, thereby, according to the final position after the flexible assembly is completed and the final force value fed back by the six-dimensional mechanical sensor, the robot can obtain a more appropriate initial position for the next assembly process in advance, and can also adapt to different categories of parts, thereby reducing the flexible assembly time and improving the assembly efficiency.

[0119] In order to implement the above-mentioned embodiments, the present disclosure also 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 so that the at least one processor can execute the position adaptation method for flexible assembly technology described in the embodiments of the present disclosure.

[0120] In order to implement the above embodiments, the present disclosure further proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the position adaptation method for flexible assembly technology described in the embodiments of the present disclosure is implemented.

[0121] In order to implement the above embodiments, the present disclosure further proposes a computer program product. When an instruction processor in the computer program product executes, the position adaptation method for flexible assembly technology described in the above embodiments is implemented.

[0122] In order to implement the above embodiments, the present disclosure also provides an electronic device, such as Figure 6 As shown, Figure 6 is a block diagram of an electronic device for a position adaptive method of flexible assembly technology according to an exemplary embodiment. Figure 6 As shown, the electronic device 600 may include:

[0123] The memory 610 and the processor 620, a bus 630 connecting different components (including the memory 710 and the processor 720), the memory 610 stores a computer program, and when the processor 620 executes the program, the position adaptation method for flexible assembly technology described in the embodiment of the present disclosure is implemented.

[0124] Bus 630 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0125] The electronic device 600 typically includes a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device 600, including volatile and non-volatile media, removable and non-removable media.

[0126] The memory 610 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 640 and / or cache memory 650. The electronic device 600 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 660 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 630 via one or more data medium interfaces. The memory 610 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0127] A program / utility 680 having a set (at least one) of program modules 670 may be stored, for example, in the memory 610, such program modules 670 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 670 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0128] The electronic device 600 may also communicate with one or more external devices 690 (e.g., keyboard, pointing device, display 691, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 692. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter 693. Figure 6 As shown, the network adapter 693 communicates with other modules of the electronic device 600 via the bus 630. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0129] The processor 620 executes various functional applications and data processing by running the programs stored in the memory 610 .

[0130] It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the position adaptation method for flexible assembly technology of the embodiment of the present disclosure, and will not be repeated here.

[0131] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0132] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A position adaptive method for flexible assembly technology, characterized in that: include: Obtain the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target parts; Based on the final position, determining a target category to which the target component belongs among a plurality of set categories; Determine the maximum force value of the target category parts according to the final position, determine the force weight value corresponding to the final force value according to the final force value and the maximum force value, obtain the target number of parts under the target category from the target quantity matrix corresponding to the parts of multiple categories, and update the center of mass of the parts of the target category in the target centroid matrix according to the final position, the force weight value and the target number; wherein the target center of mass matrix is ​​generated according to the initial center of mass matrix of the parts of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the center of mass of the parts of each category, and the target quantity matrix is ​​generated according to the initial quantity matrix of the parts of multiple categories, and each element in the target quantity matrix is ​​used to indicate the target number of parts of each category; The target centroid of the parts of the category with the maximum assembly probability is determined from the target centroid matrix, and the initial position of the robot in the next assembly process is determined according to the target centroid.

2. The method according to claim 1, characterized in that Determining the maximum force value of the target category according to the final force value includes: Obtaining target force matrices corresponding to a plurality of components of the category, wherein the target force matrix is ​​generated according to initial force matrices of the plurality of components of the category; When the final force value is greater than or equal to the force value of the target category component in the target force matrix, the final force value is used as the maximum force value of the target category component in the target force matrix; When the final force value is less than the force value of the target category components in the target force matrix, the force value of the target category components in the target force matrix is ​​used as the maximum force value of the target category.

3. The method according to claim 1, characterized in that Determining the target centroid of the parts of the category with the maximum assembly probability from the target centroid matrix, and determining the initial position of the robot in the next assembly process according to the target centroid, includes: Obtaining a target gain matrix and a target quantity matrix of a plurality of the categories of parts, wherein the target gain matrix is ​​obtained by updating an initial gain matrix of the plurality of the categories of parts at least once, and each element in the target gain matrix is ​​used to indicate the number of assemblies of each category of parts; Generate a probability matrix corresponding to each category of parts according to the target gain matrix and the target quantity matrix; wherein each element in the probability matrix is ​​used to indicate the assembly probability of the corresponding category of parts; According to the probability matrix, the maximum assembly probability is determined, and the target centroid of the component of the category corresponding to the maximum assembly probability in the target centroid matrix is ​​used as the initial position of the robot in the next assembly process.

4. The method according to claim 1, characterized in that: The step of determining, based on the final position, a target category to which the target component belongs among a plurality of set categories comprises: Obtaining a target distance between the final position and the centroid of each category of parts in the target centroid matrix; The category of the component corresponding to the minimum distance in the target distances is determined, and the category of the component corresponding to the minimum distance is used as the target category to which the target component belongs.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: The robot is used to assemble a plurality of parts of the category, and after successful assembly, the stop position of the robot and the force data fed back by the six-dimensional mechanical sensor are obtained; Determine the initial center of mass of a plurality of components of the categories according to the stop position of the robot, and determine the maximum force value of the components of each category according to the force data fed back by the six-dimensional mechanical sensor; Generating the initial centroid matrix according to the initial centroids of the parts of the plurality of categories; An initial force matrix is ​​generated according to the maximum force values ​​of the components of the plurality of categories.

6. The method according to claim 5, characterized in that The method further comprises: The initial quantity matrix is ​​generated according to the initial quantities of the components of the plurality of categories.

7. A position adaptive device for flexible assembly technology, characterized in that: include: An acquisition module is used to obtain the final position of the robot used for assembly and the final force value fed back by the six-dimensional mechanical sensor after the flexible assembly system successfully assembles the target parts; A first determination module, configured to determine, based on the final position, a target category to which the target component belongs among a plurality of set categories; An updating module, used to determine the maximum force value of the target category parts according to the final position, determine the force weight value corresponding to the final force value according to the final force value and the maximum force value, obtain the target number of parts under the target category from the target quantity matrix corresponding to the parts of multiple categories, and update the center of mass of the parts of the target category in the target centroid matrix according to the final position, the force weight value and the target number; wherein the target center of mass matrix is ​​generated according to the initial center of mass matrix of the parts of the multiple categories, and each element in the target center of mass matrix is ​​used to indicate the center of mass of the parts of each category, and the target quantity matrix is ​​generated according to the initial quantity matrix of the parts of multiple categories, and each element in the target quantity matrix is ​​used to indicate the target number of parts of each category; The second determination module is used to determine the target centroid of the parts of the category with the maximum assembly probability from the target centroid matrix, and determine the initial position of the robot in the next assembly process according to the target centroid.

8. An electronic device, characterized in that: include: 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 execute the position adaptation method for flexible assembly technology according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the position adaptation method for flexible assembly technology as described in any one of claims 1 to 6 is implemented.

Images