Visual control method for assembling process of rotating machine

Abstract

The invention relates to the technical field of rotating machine assembly, and discloses a rotating machine assembly process visual control method which comprises the following steps: collecting a part list involved in the rotating machine assembly process and assembly information of each part; generating an assembly tree for each rotating machine based on the part list and the assembly information; a genetic algorithm is adopted, and the assembly tree of each rotating machine is optimized in combination with visual simulation assembly; distributing an assembly line for each rotating machine based on the assembly trees, and performing time alignment on the assembly trees of any group of adjacent assembly lines; dividing a cross-tree assembly group based on the assembly tree of time alignment; and based on an assembly tree and the cross-tree assembly group, synchronous assembly of the rotating machine crossing the assembly line is carried out. The parallel assembly efficiency of the differentiated rotating machines can be improved, the assembly time is shortened, and the assembly cost and the energy consumption are reduced.

Description

Technical Field

[0001] This application relates to the technical field of rotary machine assembly, and particularly to a visual control method for the rotary machine assembly process. Background Art

[0002] The assembly of rotary machines follows certain standard specifications and processes. This standardized method can ensure basic quality requirements, but it often lacks flexibility when faced with specific rotary machines of different models and specifications, as well as diverse customer customization requirements. The traditional static assembly process lacks an effective response mechanism to such variability.

[0003] Generally speaking, rotary machine equipment is mostly customized. When assembling rotary machines with different customization details, there are substantial differences in their assembly details, resulting in significant differences in their assembly processes. There are often differences in the types and sizes of parts among different batches of rotary machine components. For example, for some rotary machines with strict requirements on operating noise from customers, special sound insulation materials and shock absorption components need to be added during assembly; for some rotary machines with high requirements on heat dissipation performance due to the application scenario, the air duct structure needs to be redesigned during assembly, and the arrangement and layout of each component need to be optimized. The above special steps are not general processes in the rotary machine assembly. In the prior art, the parallel assembly of multiple rotary machines needs to be completed by the cooperation of multiple experienced workers, and each worker is responsible for several assembly links with similar processes on one or adjacent production lines. Therefore, the prior art cannot maximize the parallel assembly efficiency of multiple production lines regardless of the differential assembly requirements of rotary machines, and can only perform parallel assembly on rotary machines of the same specification.

[0004] For example, the patent application with the publication number CN113759860A discloses a visual assembly system, an assembly method, equipment and medium. Among them, the visual assembly system includes: an assembly data configuration module, an assembly process integrated control module, and a touch screen display module; wherein, the assembly data configuration module is used to obtain and save assembly data; the assembly process integrated control module is used to provide an operation interface, enabling the user to establish an association relationship between the assembly data and the corresponding assembly process, and display the corresponding assembly data according to the preset assembly process during the assembly process; the display module is used to display the corresponding assembly data according to the content display instruction of the assembly process integrated control module. This technical solution can realize guiding the assembly process in a visual manner during the trial production process, improving the assembly efficiency, and reducing the error rate of assembly operations.

[0005] A patent application with the publication number CN111077867A discloses a method for dynamically simulating the assembly quality of an aero-engine based on digital twins, including: constructing a digital carrier for assembly information based on digital twin technology, obtaining assembly process information through multi-source sensing devices, combining the assembly process mechanism, dynamically simulating the state during the product assembly process, efficiently feeding back the simulation results to the assembly personnel by visualization technology, dynamically adjusting the assembly quality, realizing a closed-loop assembly process in assembly production, achieving the effect of improving the assembly quality of aero-engines, and providing a new dynamic guidance means for the regulation of the product assembly process.

[0006] The above patents all have the problems raised in this background technology: they cannot adapt to the differential assembly requirements of rotating machines to maximize the parallel assembly efficiency of multiple production lines.

[0007] The information disclosed in this background technology section is only intended to increase the understanding of the overall background of this application, and should not be regarded as an admission or an indication in any form that this information constitutes the prior art known to those of ordinary skill in the art. Summary of the Invention

[0008] Based on the above technical problems, this application provides a visualization control method for the assembly process of rotating machines, realizing the parallel assembly control of rotating machines with different assembly specifications to adapt to various differential assembly task requirements.

[0009] To solve the above technical problems, this application provides the following technical solutions:

[0010] A visualization control method for the assembly process of rotating machines includes the following steps:

[0011] Collect the part list involved in the assembly process of the rotating machine and the assembly information of each part;

[0012] Based on the part list and the assembly information, generate an assembly tree for each rotating machine;

[0013] Adopt a genetic algorithm and combine visual simulation assembly to optimize the assembly tree of each rotating machine;

[0014] Based on the assembly tree, allocate an assembly line for each rotating machine, and perform time alignment on the assembly trees of any adjacent set of assembly lines;

[0015] Based on the time-aligned assembly trees, divide the cross-tree assembly groups;

[0016] Based on the assembly tree and the cross-tree assembly groups, perform synchronous assembly of the rotating machines across the assembly lines.

[0017] As a preferred solution of the visualization control method for the assembly process of rotating machines in this application, wherein: the method for generating the assembly tree is as follows:

[0018] S201: Set the root node as the transfer machine and all parts as leaf nodes;

[0019] S202: Find the parent node for each leaf node based on the assembly information; the parent node of any leaf node is the leaf node or the root node corresponding to the assembly position of the part corresponding to the leaf node;

[0020] S203: Connect all nodes according to the parent-child node relationship to generate an assembly tree;

[0021] S204: Check the assembly logic relationship between the parts corresponding to all nodes in each layer of the assembly tree respectively, and adjust the structure of the assembly tree; specifically as follows:

[0022] If there is a sequence of assembly between the parts corresponding to any two nodes in the same layer of the assembly tree, adjust them to adjacent positions and connect them with a dashed line, and the node corresponding to the part with the earlier assembly sequence is on the left, and the node corresponding to the part with the earlier assembly sequence is on the right.

[0023] As a preferred solution of the visualization control method for the transfer machine assembly process described in this application, wherein: the method for optimizing the assembly tree of each transfer machine is as follows:

[0024] S301: Set the population size, crossover probability, and mutation probability, and generate N assembly trees for each transfer machine based on the methods described in S201 - S204, where N is the population size;

[0025] S302: Generate N individuals based on the N assembly trees to form an initial population;

[0026] S303: Calculate the fitness of each individual;

[0027] S304: Perform selection operation, crossover operation, and mutation operation in sequence, and generate the next generation population; among them, the objects of the crossover operation are any pair of chromosomes with the same number in the two individuals participating in the crossover operation;

[0028] S305: Repeat S303 - S304 until the highest fitness in all individuals of the population converges;

[0029] S306: Obtain the assembly tree corresponding to the individual with the highest fitness as the optimization result of the assembly tree of the corresponding transfer machine.

[0030] As a preferred solution of the visualization control method for the transfer machine assembly process described in this application, where: the method for generating the individual based on the assembly tree is as follows: Assume the assembly tree has n layers, then any one of the individuals contains n - 1 chromosomes, numbered chromosome 1, chromosome 2,..., chromosome n - 1 respectively; among them, the i-th chromosome is a one-dimensional array composed of the nodes on the (i + 1)-th layer from top to bottom of the assembly tree, each element in the array corresponds to a node, and the arrangement order of the elements in the array is the nodes on the (i + 1)-th layer sorted from left to right.

[0031] As a preferred solution of the visualization control method for the transfer machine assembly process described in this application, where: the method for calculating the fitness of each individual is as follows:

[0032] Obtain the assembly sequence of each individual. The method is to record the assembly order of each part in the assembly tree corresponding to each individual in sequence from top to bottom and from left to right, and form an assembly sequence;

[0033] Simulate the assembly process of the transfer machine through the digital twin system, and obtain the fitness parameters when assembling the transfer machine according to the assembly sequence of each individual;

[0034] Calculate the assembly benefit score, process optimization score, and resource utilization rate of each individual based on the fitness parameters;

[0035] Calculate the fitness of each individual based on the assembly benefit score, process optimization score, and resource utilization rate.

[0036] As a preferred solution of the visualization control method for the transfer machine assembly process described in this application, where: the time alignment of the assembly trees of any adjacent assembly lines specifically includes:

[0037] Simulate the assembly process of the transfer machine through the digital twin system, and obtain the node features of each node in the assembly tree corresponding to each transfer machine; the node features include part type, assembly tool, and spatial coordinates;

[0038] Based on the node features, calculate the similarity between nodes, and construct a cross-tree association matrix to record the similarity;

[0039] Based on the cross-tree association matrix, perform time alignment on the assembly trees of adjacent assembly lines; specifically including:

[0040] Set a similarity threshold; traverse the cross-tree association matrix, and mark the two nodes corresponding to the elements in the cross-tree association matrix that are greater than the similarity threshold as a similar node pair;

[0041] Mark the layers where the two nodes in each group of similar node pairs are located in the corresponding assembly trees as aligned layers;

[0042] Perform conflict detection on the alignment layers between the assembly trees of adjacent assembly lines; if the conflict detection fails, adjust the alignment layers until the alignment layers between the assembly trees of adjacent assembly lines pass the conflict detection, and complete the time alignment of the assembly trees.

[0043] As a preferred solution of the visualization control method for the turning machine assembly process described in this application, wherein: any group of adjacent assembly lines are two assembly lines adjacent in space; any one assembly line is used to perform the assembly of the corresponding turning machine according to an assembly tree; any one production line is only divided into one group of adjacent assembly lines; the allocation of assembly lines for each turning machine based on the assembly tree specifically includes: if the structures of any two assembly trees are the same, allocate the two assembly trees with the same structure to one group of adjacent assembly lines;

[0044] Any element in the cross-tree association matrix represents the similarity between two nodes from different assembly trees in a group of adjacent assembly lines; let the two assembly trees of adjacent assembly lines be C and D respectively, then the element in the p-th row and q-th column of the cross-tree association matrix represents the similarity between the p-th node in assembly tree C and the q-th node in assembly tree D.

[0045] As a preferred solution of the visualization control method for the turning machine assembly process described in this application, wherein: based on the assembly trees with time alignment, divide the cross-tree assembly groups; specifically including:

[0046] Divide any group of similar node pairs in any alignment layer of the assembly trees with time alignment into a cross-tree assembly group;

[0047] Based on any node in the cross-tree assembly group as the starting point, explore the nodes that can be added to the cross-tree assembly group on the corresponding assembly tree and expand the cross-tree assembly group, specifically including:

[0048] Judge whether any associated node of the starting point meets the constraint conditions for joining the corresponding assembly group; if any associated node meets the constraint conditions, add the associated node to the corresponding assembly group; the associated nodes include the parent node, child node of the starting point, and the nodes in the same layer of the assembly tree as the starting point.

[0049] As a preferred solution of the visualization control method for the turning machine assembly process described in this application, wherein: judging whether the associated node meets the constraint conditions specifically includes: reading the part type, assembly tool, and spatial coordinates of each node in the cross-tree assembly group;

[0050] If the part type of the associated node is the same as that of any node in the cross-tree assembly group, it meets the constraint conditions;

[0051] If the number of assembly tools introduced by the associated node is less than m, and the average distance between the associated node and all nodes in the cross-tree assembly group is less than the preset distance threshold, it meets the constraint conditions.

[0052] As a preferred solution of the visualization control method for the turning machine assembly process described in this application, specifically: based on the assembly tree and the cross-tree assembly group, synchronous assembly of the turning machine across the assembly line is carried out, which specifically includes: obtaining the assembly sequence of the corresponding turning machine based on the assembly tree; performing synchronous assembly of the turning machine across the assembly line according to the part assembly order recorded in the assembly sequence and the cross-tree assembly group; wherein, any cross-tree assembly group shares assembly resources.

[0053] Compared with the prior art, the beneficial effects achieved by this application are as follows:

[0054] This application realizes the dynamic optimization of the assembly process by adjusting the tree structure in real time through intelligent algorithms, and can flexibly change the assembly order and method according to factors such as equipment differences and environmental changes, improving the adaptability and efficiency of the assembly process. Intelligent optimization technologies such as genetic algorithms are used to find the best assembly sequence, reducing the assembly time, cost, and energy consumption.

[0055] The solution of this application can assist the same worker to operate synchronously on the production lines of turning machines of different specifications. Through cross-tree node alignment and grouping, the worker can process similar process nodes on multiple production lines simultaneously, breaking through the limitation in the traditional solution that only turning machines of the same model can be assembled in parallel, dynamically coordinating the assembly rhythm of key nodes of multiple turning machines, avoiding the global progress slowdown caused by the delay of a single production line, and improving the overall assembly coordination efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of this application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0057] Figure 1 is the flowchart of the visualization control method for the turning machine assembly process provided by this application;

[0058] Figure 2 is the flowchart of the optimization method for the assembly tree provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The technical solutions of this application will be described in detail below through the drawings and specific embodiments. It should be understood that the specific features in the embodiments of this application and the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. Without conflict, the technical features in the embodiments of this application and the embodiments can be combined with each other.

[0060] This embodiment introduces a visualization control method for the assembly process of a rotary machine. Refer to Figure 1 , the method includes the following steps:

[0061] Collect the part list involved in the assembly process of the rotary machine and the assembly information of each part;

[0062] The assembly information includes basic part information, assembly simulation animation, 3D model, assembly process operation content, component requirements, and summary of assembly resource requirements;

[0063] Each of the parts is a non - detachable rotary machine component that needs to be assembled; in other words, each of the parts is the smallest unit involved in the assembly process.

[0064] Generate an assembly tree for each rotary machine based on the part list and the assembly information;

[0065] Refer to Figure 2 , the method for generating the assembly tree is as follows:

[0066] S201: Set the root node as the rotary machine, and all parts are set as leaf nodes;

[0067] S202: Find the parent node for each leaf node based on the assembly information; the parent node of any leaf node is the leaf node or the root node corresponding to the assembly position of the part corresponding to the leaf node;

[0068] S203: Connect all nodes according to the parent - child node relationship to generate an assembly tree;

[0069] S204: Check the assembly logic relationship between the parts corresponding to all nodes in each layer of the assembly tree respectively, and adjust the structure of the assembly tree; specifically as follows:

[0070] If there is a sequential assembly order between the parts corresponding to any two nodes in the same layer of the assembly tree, adjust them to adjacent positions and connect them with a dotted line, and the node corresponding to the part with the earlier assembly order is on the left, and the node corresponding to the part with the earlier assembly order is on the right;

[0071] To avoid assembly logic errors when optimizing the assembly order later, it is necessary to ensure that the nodes in each layer of the assembly tree are relatively independent assembly units, and the assembly work for the nodes in the same layer should not interfere with each other; for any layer of nodes that interfere with each other and have an assembly logic order during the assembly process, arrange them adjacent to each other in logical order and connect them with a dotted line. Then, when optimizing the assembly tree later, retain the assembly order connected by the dotted line, thus avoiding assembly logic errors.

[0072] Adopt a genetic algorithm to optimize the assembly tree of each rotary machine in combination with visual simulation assembly;

[0073] The method for optimizing the assembly tree of each transfer machine is as follows:

[0074] S301: Set the population size, crossover probability, and mutation probability, and generate N assembly trees for each transfer machine based on the methods described in S201 - S204, where N is the population size;

[0075] S302: Generate N individuals based on the N assembly trees to form the initial population;

[0076] Assume the assembly tree has n layers, then any one of the individuals contains n - 1 chromosomes, numbered as chromosome 1, chromosome 2,..., chromosome n - 1 respectively; among them, the i - th chromosome is a one - dimensional array composed of the nodes on the (i + 1) - th layer from top to bottom of the assembly tree. Each element in the array corresponds to a node, and the arrangement order of the elements in the array is the nodes on the (i + 1) - th layer sorted from left to right;

[0077] S303: Calculate the fitness of each individual; the method is as follows:

[0078] Obtain the assembly sequence of each individual. The method is to record the assembly order of each part in sequence according to the top - down and left - right order of the assembly tree corresponding to each individual, and form an assembly sequence;

[0079] Simulate the assembly process of the transfer machine through the digital twin system to obtain the fitness parameters when assembling the transfer machine according to the assembly sequence of each individual;

[0080] Calculate the assembly benefit score, process optimization score, and resource utilization rate of each individual based on the fitness parameters;

[0081] Calculate the fitness of each individual based on the assembly benefit score, process optimization score, and resource utilization rate.

[0082] The digital twin model can simulate the real assembly process in real time, including the interactive influence and resource consumption of each link, etc. In this embodiment, the preferred fitness parameters include time benefit score, energy consumption coefficient, redirection ratio, tooling change ratio, interference times, assembly path length, and assembly line utilization rate;

[0083] Furthermore, the preferred calculation formula for fitness in this embodiment is as follows:

[0084] F j = F Bj + α·F Pj + β·F Rj ;

[0085] Among them, F j represents the fitness of the j - th individual, and the value range of j is 1, 2,..., N; F Bjrepresents the assembly benefit score of the j-th individual; F Pj represents the process optimization score of the j-th individual; F Rj represents the resource utilization rate of the j-th individual; α and β are weight coefficients, set according to experience;

[0086] The calculation formula for the above-mentioned assembly benefit score is as follows:

[0087]

[0088] where, T j represents the time benefit score for turning machine assembly according to the assembly sequence represented by the j-th individual, represented by the number of assembled parts completed per unit time; E j represents the energy consumption coefficient for turning machine assembly according to the assembly sequence represented by the j-th individual, represented by the normalized value of energy consumption;

[0089] The calculation formula for the above-mentioned process optimization score is as follows:

[0090]

[0091] where, p j1 represents the redirection ratio for turning machine assembly according to the assembly sequence represented by the j-th individual; that is, the ratio of the number of process rearrangements caused by objective reasons during the assembly process to the total number of assembly processes;

[0092] p j2 represents the tooling change ratio for turning machine assembly according to the assembly sequence represented by the j-th individual; that is, the ratio of the total tooling change time to the total assembly time within the assembly cycle; Tooling change refers to the act of replacing or adjusting the original tooling equipment, tools or jigs.

[0093] p j3 represents the number of interferences during the turning machine assembly process represented by the assembly sequence of the j-th individual, that is, the number of times the phenomenon occurs where two or more components collide or block each other during assembly due to design or positioning errors and cannot be assembled normally.

[0094] The calculation formula for the above-mentioned resource utilization rate is as follows:

[0095]

[0096] where, U j$U_j$ represents the utilization rate of the assembly line for the transfer machine assembly of the assembly sequence represented by the $j$-th individual, which refers to the ratio of the effective working time to the total available time during the assembly process on the assembly line. Among them, the effective working time refers to the time when actual assembly operations are performed on the assembly line, that is, during the period from the start to the stop of the production line, excluding the ineffective time caused by die change, adjustment, and material supply delay, the time when actual production activities are carried out; the total available time refers to the time period during which the assembly line can theoretically operate continuously every day, that is, the total duration available for production on the production line every day after deducting the rest period and unplanned shutdowns.

[0097] R j $L_j$ represents the length of the assembly path for the transfer machine assembly of the assembly sequence represented by the $j$-th individual, which refers to the cumulative moving distance of all parts of the transfer machine during the assembly process.

[0098] S304: Perform selection operation, crossover operation, and mutation operation in sequence, and generate the next generation of population;

[0099] The crossover operation includes single-point crossover and ordered crossover; the objects of the crossover operation are any pair of chromosomes with the same number in the two individuals participating in the crossover operation;

[0100] The mutation operation includes swap mutation, reverse mutation, and adjacent swap mutation;

[0101] Chromosomes with the same number represent nodes from the same layer of different assembly trees; performing the crossover operation only on nodes of the same layer ensures the structural stability of the assembly tree and avoids logical errors in the assembly sequence.

[0102] For swap mutation, randomly select two different positions on the chromosome and swap the elements at these two positions. This may improve the sorting state of the sequence. For reverse mutation, randomly select a continuous subsequence on the chromosome and then reverse the order of this subsequence. For insertion mutation, randomly take out an element from the chromosome and then re-insert it at a random position after it, which is similar to the jumping movement of an element in the sequence. For adjacent swap mutation, randomly select two adjacent elements in the chromosome and swap their positions.

[0103] The method of single-point crossover is as follows: At one or more preset crossover points, part of the sequence of the parental chromosome is swapped to form the offspring chromosome. For example, if there are two chromosomes A and B, and a crossover point p is selected, the offspring chromosome will be composed of the first p elements of A plus the last M - p elements of B, and the first p elements of B plus the last M - p elements of A; M represents the number of elements on the chromosome participating in the crossover.

[0104] The method of ordered crossover is as follows: Select partial subsequences of a pair of parent sequences, keep the order of elements within the subsequences unchanged, and insert them into the corresponding positions of the other parent, so that the offspring sequences after crossover conform to the sorting requirements as much as possible. This crossover method is particularly suitable for sequence optimization problems, ensuring that the offspring sequences generated by crossover still maintain the original relative order of the parents.

[0105] The assembly tree itself covers the assembly constraint information between parts. Performing genetic algorithm optimization on the assembly tree designed in this application is simpler and more efficient than directly performing genetic variation on the assembly sequence and then imposing external conditions for constraint.

[0106] S305: Repeat S303 - S304 until the highest fitness in all individuals of the population converges;

[0107] S306: Obtain the assembly tree corresponding to the individual with the highest fitness as the optimization result of the assembly tree of the corresponding turning machine.

[0108] Allocate assembly lines for each turning machine based on the assembly tree, and perform time alignment on the assembly trees of any group of adjacent assembly lines;

[0109] Any group of adjacent assembly lines are two assembly lines adjacent in space; Any one assembly line is used to perform the assembly of the corresponding turning machine according to an assembly tree; Any one production line is only divided into one group of adjacent assembly lines; The allocation of assembly lines for each turning machine based on the assembly tree specifically includes: If the structures of any two assembly trees are the same, allocate the two assembly trees with the same structure to a group of adjacent assembly lines.

[0110] Giving priority to allocating two assembly trees with the same structure to a group of adjacent assembly lines and then allocating the remaining assembly trees with different structures is conducive to the parallel assembly of the turning machines corresponding to the assembly trees with the same structure on adjacent assembly lines, improving the assembly efficiency.

[0111] The time alignment of the assembly trees of any group of adjacent assembly lines specifically includes:

[0112] Simulate the assembly process of the turning machine through the digital twin system to obtain the node features of each node in the assembly tree corresponding to each turning machine;

[0113] Based on the node features, calculate the similarity between nodes and construct a cross-tree association matrix to record the similarity;

[0114] The node features include part type, assembly tool, and spatial coordinates; For example, the part type is classification labels such as bolts and gears; The assembly tool is the wrench model, hydraulic equipment, etc. required for assembling the corresponding part; The spatial coordinates are obtained based on the digital twin system, and the spatial coordinates are the three-dimensional spatial coordinates of the assembly position of the corresponding part in the assembly workshop.

[0115] The similarity between the computing nodes is calculated based on the corresponding node features of each item of the two nodes. A preferred method for calculating the similarity between nodes in this embodiment is as follows: The basic similarity between any two nodes is 0; if the part types of the two nodes are the same, the similarity is increased by 0.6, otherwise the similarity is increased by 0; if there is one same assembly tool for the two nodes, the similarity is increased by 0.1, and the upper limit of this similarity is 0.3; calculate the normalized Euclidean distance of the spatial coordinates of the two nodes, and adjust the similarity based on the normalized Euclidean distance. The greater the normalized Euclidean distance, the higher the similarity; if the similarity is adjusted based on the time coordinates of the two nodes, the greater the intersection between the time ranges for assembling the corresponding parts of the two nodes, the higher the similarity.

[0116] Any element in the cross-tree association matrix represents the similarity between two nodes from different assembly trees in a group of adjacent assembly lines. Let the two assembly trees of adjacent assembly lines be C and D respectively. Then the element in the p-th row and q-th column of the cross-tree association matrix represents the similarity between the p-th node in assembly tree C and the q-th node in assembly tree D, where p and q are both positive integers.

[0117] Based on the cross-tree association matrix, perform time alignment on the assembly trees of adjacent assembly lines. Specifically, it includes:

[0118] Set a similarity threshold; traverse the cross-tree association matrix, and mark the two nodes corresponding to the elements in the cross-tree association matrix that are greater than the similarity threshold as a similar node pair.

[0119] Mark the layers where the two nodes in each group of similar node pairs are located in the corresponding assembly trees as the aligned layers.

[0120] Perform conflict detection on the aligned layers between the assembly trees of adjacent assembly lines; if the conflict detection fails, adjust the aligned layers until the aligned layers between the assembly trees of adjacent assembly lines pass the conflict detection, and complete the time alignment of the assembly trees.

[0121] A preferred method for conflict detection and adjusting the aligned layers in this embodiment is as follows:

[0122] Connect any group of aligned layers of the two assembly trees with a straight line; if there is an intersection or crossing between the straight lines used to connect the aligned layers, the conflict detection fails. Delete the aligned layers that cause the intersection or crossing between the straight lines until the aligned layers between the assembly trees pass the conflict detection. For example, the third layer in assembly tree C and the third layer and the fourth layer in assembly tree D are both aligned layers. Then the straight lines connecting the third layer in assembly tree C with the third layer and the fourth layer in assembly tree D have an intersection. Delete the aligned layer corresponding to the third layer in assembly tree C and the fourth layer in assembly tree D, and only retain the aligned layer corresponding to the third layer in assembly tree C and the third layer in assembly tree D, so that the aligned layers between assembly trees C and D pass the conflict detection.

[0123] Based on the time-aligned assembly tree, divide the cross-tree assembly groups; specifically including:

[0124] Divide any pair of similar nodes in any alignment layer of the time-aligned assembly tree into a cross-tree assembly group;

[0125] Based on any node in the cross-tree assembly group as the starting point, explore the nodes that can be added to the cross-tree assembly group on the corresponding assembly tree and expand the cross-tree assembly group, specifically including:

[0126] Judge whether any associated node of the starting point satisfies the constraint conditions for joining the corresponding assembly group; if any associated node satisfies the constraint conditions, add the associated node to the corresponding assembly group; the associated nodes include the parent node, child node of the starting point, and the nodes in the same layer of the assembly tree as the starting point;

[0127] Judge whether the associated node satisfies the constraint conditions, specifically including: reading the part type, assembly tool, and spatial coordinates of each node in the cross-tree assembly group;

[0128] If the part type of the associated node is the same as that of any node in the cross-tree assembly group, it satisfies the constraint conditions;

[0129] If the number of assembly tools introduced by the associated node is less than m, and the average distance between the associated node and all nodes in the cross-tree assembly group is less than the preset distance threshold, it satisfies the constraint conditions; m is a positive integer.

[0130] The assembly tools introduced by the associated node are the assembly tools that are not required by all nodes in the cross-tree assembly group among the assembly tools required by the associated node; calculate the Euclidean distance between the associated node and each node in the cross-tree assembly group based on the spatial coordinates and calculate the average value to obtain the average distance between the associated node and all nodes in the cross-tree assembly group. Based on the above constraint conditions, the nodes in the cross-tree assembly group can have unity in assembly tools and operation ranges.

[0131] Based on the assembly tree and the cross-tree assembly group, perform synchronous assembly of the transfer machines across the assembly lines; specifically including:

[0132] Obtain the assembly sequence of the corresponding transfer machine based on the assembly tree; perform synchronous assembly of the transfer machines across the assembly lines according to the part assembly order recorded in the assembly sequence and the cross-tree assembly group; among them, any cross-tree assembly group shares assembly resources, and when assembling

[0133] The assembly resources shared by the cross-tree assembly groups include assembly workers, assembly tools, part libraries, etc.; for fully automated or semi-automated assembly lines, the shared assembly resources also include robotic arms, automated material carts, etc. Any cross-tree assembly group performs continuous assembly as a combination. After completing the assembly of all parts within the cross-tree assembly group, the parts to be assembled outside the assembly group are then assembled. By dividing the cross-tree assembly groups and sharing the assembly resources, the optimization of resource allocation costs between different assembly lines is achieved, the assembly efficiency is improved, and the assembly cost is reduced.

[0134] Preferably, when performing synchronous assembly of the turnaround across assembly lines, visual simulation assembly is synchronously carried out through the digital twin system, and the operation process of each assembly link is displayed in real time, realizing remote monitoring and guiding on-site staff to install according to the correct steps, reducing incorrect operations, and improving the assembly accuracy. By comparing the simulated assembly and the actual assembly progress in real time, the assembly process is monitored, and the delayed links or potential problems are quickly identified, so as to take corresponding measures to ensure the timely completion of the turnaround assembly work.

[0135] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims. All of these are within the protection scope of the present application.

Claims

1. A visual control method for the assembly process of a rotary machine, characterized in that: It includes the following steps: Collect the part list involved in the transfer machine assembly process and the assembly information of each part; Generate an assembly tree for each transfer machine based on the part list and the assembly information; Adopt a genetic algorithm and combine visual simulation assembly to optimize the assembly tree of each transfer machine; Allocate an assembly line for each transfer machine based on the assembly tree, and perform time alignment on the assembly trees of any adjacent pair of assembly lines; Divide the cross-tree assembly groups based on the time-aligned assembly trees; Based on the assembly tree and the cross-tree assembly groups, perform synchronous assembly of the transfer machines across the assembly lines.

2. The visualization control method for the turning machine assembly process according to claim 1, characterized in that: The method for generating the assembly tree is as follows: S201: Set the root node as the transfer machine, and set all parts as leaf nodes; S202: Find the parent node for each leaf node based on the assembly information; the parent node of any leaf node is the leaf node or the root node corresponding to the assembly position of the part corresponding to the leaf node; S203: Connect all nodes according to the parent-child node relationship to generate an assembly tree; S204: Check the assembly logic relationship between the parts corresponding to all nodes in each layer of the assembly tree respectively, and adjust the structure of the assembly tree; specifically as follows: If there is an assembly sequence between the parts corresponding to any two nodes in the same layer of the assembly tree, adjust them to adjacent positions and connect them with a dotted line, and the node corresponding to the part with the earlier assembly sequence is on the left, and the node corresponding to the part with the earlier assembly sequence is on the right.

3. The visualization control method for the turning machine assembly process according to claim 2, characterized in that: The method for optimizing the assembly tree of each transfer machine is as follows: S301: Set the population size, crossover probability, and mutation probability, and generate N assembly trees for each transfer machine based on the methods described in S201 - S204, where N is the population size; S302: Generate N individuals based on the N assembly trees to form an initial population; S303: Calculate the fitness of each individual; S304: Perform selection operation, crossover operation, and mutation operation in sequence, and generate the next generation population; among them, the objects of the crossover operation are any pair of chromosomes with the same number in the two individuals participating in the crossover operation; S305: Repeat S303 - S304 until the highest fitness in all individuals of the population converges; S306: Obtain the assembly tree corresponding to the individual with the highest fitness as the optimization result of the assembly tree of the corresponding transfer machine.

4. The visualization control method for the assembly process of a turning machine according to claim 3, characterized in that: The method for generating the individual based on the assembly tree is as follows: Let the assembly tree have n layers, then any one of the individuals contains n - 1 chromosomes, which are numbered chromosome 1, chromosome 2,..., chromosome n - 1 respectively; among them, the i-th chromosome is a one-dimensional array composed of the nodes in the (i + 1)-th layer from top to bottom of the assembly tree, each element in the array corresponds to a node, and the arrangement order of the elements in the array is the nodes in the (i + 1)-th layer sorted from left to right.

5. The visualization control method for the turning machine assembly process according to claim 4, characterized in that: The method for calculating the fitness of each individual is as follows: Obtain the assembly sequence of each individual. The method is to record the assembly order of each part in sequence according to the top-to-bottom and left-to-right order of the assembly tree corresponding to each individual, and form an assembly sequence; Simulate the assembly process of the transfer machine through the digital twin system to obtain the fitness parameters when assembling the transfer machine according to the assembly sequence of each individual. Calculate the assembly benefit score, process optimization score, and resource utilization rate for each individual based on the fitness parameters. Calculate the fitness of each individual based on the assembly benefit score, process optimization score, and resource utilization rate.

6. The visualization control method for the assembly process of a rotary machine as described in claim 5, characterized in that: The time alignment of the assembly trees for any adjacent pair of assembly lines specifically includes: Simulate the assembly process of the rotating machine through the digital twin system to obtain the node features of each node in the assembly tree corresponding to each rotating machine; the node features include part type, assembly tool, and spatial coordinates. Based on the node features, calculate the similarity between nodes and construct a cross-tree association matrix to record the similarity. Based on the cross-tree association matrix, perform time alignment on the assembly trees of adjacent assembly lines; specifically including: Set a similarity threshold; traverse the cross-tree association matrix, and mark the two nodes corresponding to the elements in the cross-tree association matrix that are greater than the similarity threshold as a pair of similar nodes. Mark the layers where the two nodes in each pair of similar nodes are located in the corresponding assembly trees as aligned layers. Perform conflict detection on the aligned layers between the assembly trees of adjacent assembly lines; if the conflict detection fails, adjust the aligned layers until the aligned layers between the assembly trees of adjacent assembly lines pass the conflict detection, and complete the time alignment of the assembly trees.

7. The visualization control method for the transfer machine assembly process according to claim 6, characterized in that: Any adjacent pair of assembly lines are two assembly lines adjacent in space; any one assembly line is used to perform the assembly of the corresponding rotating machine according to an assembly tree. Any one production line is only divided into one group of adjacent assembly lines; the allocation of assembly lines for each rotating machine based on the assembly tree specifically includes: if the structures of any two assembly trees are the same, allocate the two assembly trees with the same structure to one group of adjacent assembly lines. Any element in the cross-tree association matrix represents the similarity between two nodes from different assembly trees in a group of adjacent assembly lines; let the two assembly trees of the adjacent assembly lines be C and D respectively, then the element in the p-th row and q-th column of the cross-tree association matrix represents the similarity between the p-th node in assembly tree C and the q-th node in assembly tree D.

8. The visualization control method for the turning machine assembly process according to claim 7, characterized in that: Based on the assembly trees with time alignment, divide cross-tree assembly groups; specifically including: Divide any group of similar node pairs in any aligned layer of the assembly trees with time alignment into a cross-tree assembly group. Based on any node in the cross-tree assembly group as the starting point, explore the nodes that can be added to the cross-tree assembly group on the corresponding assembly tree and expand the cross-tree assembly group, specifically including: Judge whether any associated node of the starting point meets the constraint conditions for joining the corresponding assembly group; if any associated node meets the constraint conditions, add the associated node to the corresponding assembly group; the associated nodes include the parent node, child node, and nodes at the same layer as the starting point in the assembly tree.

9. The visualization control method for the assembly process of a turning machine according to claim 8, wherein: Judging whether an associated node meets the constraint conditions specifically includes: reading the part type, assembly tool, and spatial coordinates of each node in the cross-tree assembly group. If the part type of the associated node is the same as that of any node in the cross-tree assembly group, it meets the constraint conditions. If the number of assembly tools introduced by the associated node is less than m, and the average distance between the associated node and all nodes in the cross-tree assembly group is less than the preset distance threshold, it meets the constraint conditions.

10. The visualization control method for the assembly process of a rotary machine as claimed in claim 9, characterized in that: Based on the assembly tree and the cross-tree assembly group, perform synchronous assembly of the transfer machine across assembly lines, specifically including: obtaining the assembly sequence of the corresponding transfer machine based on the assembly tree; performing synchronous assembly of the transfer machine across assembly lines according to the part assembly order recorded in the assembly sequence and the cross-tree assembly group; wherein, any cross-tree assembly group shares assembly resources.

Images