Mining mechanical equipment dismounting method and device based on geometric constraint and storage medium

Abstract

The invention discloses a mining mechanical equipment dismounting method and device based on geometric constraints and a storage medium, relates to the field of mining mechanical equipment maintenance, and mainly aims at improving the determination efficiency and the determination accuracy of a dismounting mode of mining machinery. Comprising the steps of obtaining a three-dimensional model of target mining mechanical equipment; determining contact type constraint information and non-contact type constraint information among the parts in the three-dimensional model, and determining constraint strength among the parts based on the contact type constraint information and the non-contact type constraint information; a constraint relation graph is constructed on the basis of all the parts and the constraint strength between all the parts, all the parts serve as all nodes in the constraint relation graph, and the constraint strength serves as the edge between the corresponding adjacent parts; and on the basis of the constraint relation graph, determining a dismounting path of the target mining mechanical equipment, and dismounting the target mining mechanical equipment on the basis of the dismounting path.

Description

Technical Field

[0001] The present invention relates to the field of mine machinery and equipment maintenance, and in particular to a method, device and storage medium for disassembling mine machinery and equipment based on geometric constraints. Background Art

[0002] Due to its complex structure and high-intensity use environment, mining machinery and equipment require frequent disassembly and assembly operations during maintenance.

[0003] Currently, the disassembly and assembly methods of mining machinery are usually planned manually. However, this method is time-consuming and labor-intensive, and due to the varying technical skills of maintenance personnel, errors in disassembly and assembly methods may occur. This can lead to interference and collision between components during the disassembly and assembly process, increasing the difficulty and risk of maintenance and, in severe cases, causing damage to the equipment. Summary of the Invention

[0004] The present invention provides a method, device and storage medium for disassembling mining machinery based on geometric constraints, which mainly aims to improve the efficiency and accuracy of determining the disassembly method of mining machinery.

[0005] According to a first aspect of the present invention, a method for disassembling mining machinery and equipment based on geometric constraints is provided, comprising:

[0006] Obtain a three-dimensional model of the target mining machinery and equipment;

[0007] determining contact constraint information and non-contact constraint information between components in the three-dimensional model, and determining constraint strengths between the components based on the contact constraint information and the non-contact constraint information;

[0008] Based on the constraint strengths between the various components and the various components, a constraint relationship graph is constructed, wherein the various components serve as nodes in the constraint relationship graph, the constraint strengths serve as edges between corresponding adjacent components, and the preset assembly and disassembly priorities serve as directions of the edges;

[0009] Based on the constraint relationship diagram, a disassembly path of the target mining machinery and equipment is determined, and the target mining machinery and equipment is disassembled based on the disassembly path.

[0010] Optionally, the contact constraint information includes the normal contact force and friction torque between the various components, and the non-contact constraint information is the assembly accuracy between the various components;

[0011] The determining the constraint strength between the components based on the contact constraint information and the non-contact constraint information includes:

[0012] The weight coefficients of the normal contact force, the friction torque, and the assembly accuracy are determined respectively. Based on the weight coefficients, the normal contact force, the friction torque, and the assembly accuracy are weightedly summed to obtain the constraint strength between the various components.

[0013] Optionally, before determining the disassembly path of the target mining machinery and equipment based on the constraint relationship graph, the method further includes:

[0014] Determining strongly connected components in the constraint relationship graph, and determining an initial strongly connected subgraph corresponding to each strongly connected component;

[0015] Respectively taking any initial strongly connected subgraph in each of the initial strongly connected subgraphs as a target initial strongly connected subgraph, determining the number of nodes and the number of edges in the target initial strongly connected subgraph, and judging whether the target initial strongly connected subgraph meets a preset condition for subgraph partitioning based on the number of nodes and the number of edges; if so, taking the target initial strongly connected subgraph as the strongly connected subgraph after final partitioning; otherwise, performing subgraph partitioning on the target initial strongly connected subgraph to obtain a strongly connected subgraph after final partitioning;

[0016] Determining a disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes:

[0017] The sub-assembly and disassembly paths corresponding to each of the strongly connected subgraphs are determined respectively, and each of the sub-assembly and disassembly paths is used as the disassembly path of the target mining machinery and equipment.

[0018] Optionally, determining a disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes:

[0019] Determining a set of candidate disassembly paths for the target mining machinery and equipment based on the constraint relationship graph;

[0020] Constructing a hierarchical bounding box for each component of the target mining machinery and equipment respectively, and assembling each of the hierarchical bounding boxes into a hierarchical bounding box tree based on the hierarchical structure of each component of the target mining machinery and equipment;

[0021] Taking any candidate disassembly path in the candidate disassembly path set as a target candidate disassembly path, determining the center point vector and relative direction matrix of each two hierarchical bounding boxes in the target candidate disassembly path on the hierarchical bounding box tree, wherein each two hierarchical bounding boxes contain the hierarchical bounding box of the component to be disassembled;

[0022] Extracting the separation axis of each two bounding boxes based on the center point vector and the relative direction matrix, and determining the projection interval of each two bounding boxes on the separation axis;

[0023] Determine whether the projection intervals of each two hierarchical bounding boxes overlap. If so, remove the target candidate disassembly path from the candidate disassembly path set. Otherwise, retain the target candidate disassembly path and use the candidate disassembly path in the processed candidate disassembly path set as the disassembly path.

[0024] Optionally, determining a disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes:

[0025] Any component other than the starting component and the ending component among the components on the target candidate disassembly path is respectively used as a current component, a starting Euclidean distance between the current component and the starting component is determined, an ending Euclidean distance between the current component and the ending component is determined, and a current constraint strength of the current component is determined;

[0026] Determining an estimated cost of the current component based on the ending Euclidean distance and the current constraint strength, and taking the sum of the estimated cost and the starting Euclidean distance as a reachability evaluation value of the current component;

[0027] The sum of the reachability evaluation values ​​of each current component on the target candidate disassembly path is used as an evaluation parameter of the target candidate disassembly path, and based on the evaluation parameter, a disassembly path of the target mining machinery equipment is selected in each target candidate disassembly path.

[0028] Optionally, determining a disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes:

[0029] Randomly generating an initial population, wherein the initial population contains multiple feasible disassembly paths;

[0030] Determining the number of disassembly steps, the number of tool direction adjustments during the disassembly operation, and the strength of the disassembly constraint for each of the feasible disassembly paths, and determining the fitness of each of the feasible disassembly paths based on the number of disassembly steps, the number of direction adjustments, and the strength of the disassembly constraint;

[0031] A target feasible disassembly path having a fitness greater than a first preset threshold is selected from each of the feasible disassembly paths, partial path segment exchanges are performed on any two target feasible disassembly paths in the target feasible disassembly paths to obtain a cross disassembly path, and components at any two positions on any target feasible disassembly path in the target feasible disassembly paths are exchanged to obtain a variant disassembly path, a new generation population is formed by the target feasible disassembly path, the cross disassembly path, and the variant disassembly path, and the new generation population is used as a new initial population to continue to perform fitness calculation, partial path segment exchange, and component exchange operations until the number of population iterations reaches a preset number, thereby obtaining a final population;

[0032] Determining the ultimate number of disassembly steps, the ultimate number of direction adjustments of the tool during the disassembly operation, and the ultimate disassembly constraint strength of each ultimate disassembly path in the ultimate population, and determining the ultimate fitness of each ultimate disassembly path based on the ultimate number of disassembly steps, the ultimate number of direction adjustments, and the ultimate disassembly constraint strength;

[0033] In each of the ultimate disassembly paths, the ultimate fitness that is greater than a second preset threshold is selected as the disassembly path of the target mining machinery and equipment.

[0034] Optionally, before determining the contact constraint information and non-contact constraint information between the components in the three-dimensional model, the method further includes:

[0035] extracting non-critical assembly features and critical assembly features from the three-dimensional model;

[0036] On the premise of ensuring the geometric integrity and topological continuity of the key assembly features, the non-key assembly features are removed from the three-dimensional model to obtain a simplified three-dimensional model;

[0037] The determining of contact constraint information and non-contact constraint information between components in the three-dimensional model includes:

[0038] Contact constraint information and non-contact constraint information between components in the simplified three-dimensional model are determined.

[0039] According to a second aspect of the present invention, a mining machinery and equipment disassembly device based on geometric constraints is provided, comprising:

[0040] An acquisition unit, used for acquiring a three-dimensional model of target mining machinery and equipment;

[0041] a determining unit, configured to determine contact constraint information and non-contact constraint information between components in the three-dimensional model, and determine constraint strengths between the components based on the contact constraint information and the non-contact constraint information;

[0042] A construction unit, configured to construct a constraint relationship graph based on the constraint strengths between the various components, wherein the various components serve as nodes in the constraint relationship graph and the constraint strengths serve as edges between corresponding adjacent components;

[0043] A disassembly unit is configured to determine a disassembly path of the target mining machinery and equipment based on the constraint relationship diagram, and to disassemble the target mining machinery and equipment based on the disassembly path.

[0044] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the program implements the above-mentioned method for disassembling mining machinery based on geometric constraints.

[0045] According to a fourth aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for disassembling mining machinery based on geometric constraints when executing the program.

[0046] According to the present invention, a method, device, and storage medium for disassembling mining machinery and equipment based on geometric constraints are provided. Compared with the current manually planned disassembly and assembly methods of mining machinery, the present invention uses the geometric constraint relationships of the target mining machinery and equipment to construct a constraint relationship diagram with constraint strength as the edge, and ultimately determines the disassembly path based on the constraint relationship diagram. This can avoid the time-consuming and labor-intensive problem of manually determining the disassembly path, thereby improving the efficiency of determining the disassembly method of mining equipment. The present invention can accurately identify contact constraints and non-contact constraints between parts, ensuring the feasibility and accuracy of the disassembly path. In addition, the present invention determines the disassembly path by conducting a comprehensive analysis of contact constraints and non-contact constraints, which can further improve the accuracy of determining the disassembly path, avoid problems such as collisions with other parts during the disassembly process, and thus avoid equipment damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0048] Figure 1 A flow chart of a method for disassembling mining machinery and equipment based on geometric constraints provided by an embodiment of the present invention is shown;

[0049] Figure 2 A flowchart of another method for disassembling mining machinery and equipment based on geometric constraints provided by an embodiment of the present invention is shown;

[0050] Figure 3 A schematic structural diagram of a mining machinery and equipment disassembly device based on geometric constraints provided by an embodiment of the present invention is shown;

[0051] Figure 4 A schematic structural diagram of another mining machinery and equipment disassembly device based on geometric constraints provided by an embodiment of the present invention is shown;

[0052] Figure 5 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0053] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0054] At present, manual planning of the disassembly and assembly methods of mining machinery is time-consuming and labor-intensive, and due to the uneven technical levels of maintenance personnel, there may be errors in the planning of the disassembly and assembly methods.

[0055] In order to solve the above problems, the embodiment of the present invention provides a method for disassembling mining machinery and equipment based on geometric constraints, such as Figure 1 As shown, the method includes:

[0056] 101. Obtain a three-dimensional model of the target mining machinery and equipment.

[0057] The target mining machinery and equipment may be any machinery and equipment such as a tunnel boring machine, a coal mining machine, a drilling machine, a crusher, etc.

[0058] For an embodiment of the present invention, a three-dimensional model of target mining machinery and equipment is first drawn using three-dimensional drawing software. Then, in order to improve the processing efficiency of the three-dimensional model, the three-dimensional model can be simplified. The specific simplification method includes: extracting non-critical assembly features and critical assembly features in the three-dimensional model; while ensuring the geometric integrity and topological continuity of the critical assembly features, the non-critical assembly features are removed from the three-dimensional model to obtain a simplified three-dimensional model; determining the contact constraint information and non-contact constraint information between each component in the three-dimensional model includes: determining the contact constraint information and non-contact constraint information between each component in the simplified three-dimensional model.

[0059] Among them, non-critical assembly features refer to geometric elements that have little impact on the overall assembly and disassembly process of the target mining machinery and equipment, or do not affect the critical assembly relationship, such as decorative textures on the surface of the equipment, tiny chamfers or fillets, protrusions or depressions of non-load-bearing structures, etc.; critical assembly features refer to geometric elements in the equipment that directly affect the assembly and disassembly process, including mating surfaces, positioning references, the position and size of fasteners (such as bolts and nuts), etc.

[0060] Specifically, non-critical detail features in the three-dimensional model are removed, and a simplified model that reflects key assembly features (such as mating surfaces and positioning datums) is retained. Key assembly features must maintain their original geometric shape and size in the simplified model (i.e., to ensure geometric integrity). For example, the meshing surface of the gear must maintain its precise contour and size to ensure that its relative position and motion relationship with other components can be correctly calculated in the subsequent disassembly path planning; key assembly features must maintain their connection relationship and spatial relationship with other components in the simplified model (i.e., to ensure topological continuity). For example, the position and direction of the bolt hole must remain unchanged to ensure that the disassembly sequence and path of the bolt can be correctly simulated during the disassembly process. Taking a certain model of mining truck gearbox as an example, the original model contains 1,526 parts, and the simplified model contains only 683 parts, the number of geometric elements is reduced by 55%, and the computational complexity is significantly reduced.

[0061] Furthermore, rule-based feature recognition technology automatically extracts assembly information for components in the simplified model, including degrees of freedom, assembly method, and fit type. This technology utilizes a predefined library of assembly feature templates and a pattern matching algorithm to identify the assembly semantics of the components. Component attributes, such as material and mass, are also defined. Coordinate system establishment: A global coordinate system is established using the entire device as a reference. Simultaneously, a local coordinate system is established for each component, and a coordinate transformation matrix is ​​defined to provide a spatial reference for subsequent assembly and disassembly path planning.

[0062] 102. Determine contact constraint information and non-contact constraint information between various components in the three-dimensional model, and determine the constraint strength between various components based on the contact constraint information and the non-contact constraint information.

[0063] Among them, contact constraints refer to the physical contact or direct mechanical connection between components. Contact constraint information includes the normal contact force and friction torque between each component. Non-contact constraints refer to the motion or spatial restrictions that exist although there is no physical contact between components. Non-contact constraint information includes the assembly accuracy between each component.

[0064] In this embodiment of the present invention, a rule-based geometric reasoning method is used to identify contact constraint types between components, such as surface contact and shaft-hole fit. This method utilizes the assembly contact feature ontology, constructs an assembly-oriented geometric constraint semantic model through semantic description and spatial relationship reasoning, and then uses this geometric constraint semantic model to determine contact constraint information, such as normal contact force and friction torque, between each component. Furthermore, this contact constraint information between each component can be determined through finite element analysis. Non-contact constraint information is extracted through collision detection and clearance analysis. A virtual linkage mechanism is used to describe the non-contact constraint relationships between kinematic pairs and incorporated into the geometric constraint semantic model to obtain this non-contact constraint information. Furthermore, the assembly accuracy of the target mining machinery is defined during the design and assembly process, so the non-contact constraint information between each component can be determined by consulting relevant documentation. The constraint strength between each component can then be determined based on this contact and non-contact constraint information. This embodiment of the present invention proposes a multi-level constraint analysis framework to systematically model the geometric constraint relationships of complex equipment. This framework not only considers direct contact constraints (such as surface contact and shaft-hole fit) but also introduces non-contact constraints (such as clearance constraints) to characterize complex assembly relationships. The framework also defines a quantitative constraint strength metric that comprehensively considers normal contact force, assembly accuracy, and friction torque to reflect the relative importance of different constraint types. This framework allows for a comprehensive and accurate characterization of the geometric constraints within the device, providing a foundation for precise disassembly path planning.

[0065] 103. Based on the constraint strengths between each component and each component, a constraint relationship diagram is constructed, wherein each component serves as a node in the constraint relationship diagram, the constraint strength serves as an edge between corresponding adjacent components, and the preset assembly and disassembly priority serves as the direction of the edge.

[0066] The constraint relationship graph is a directed graph, and the preset assembly and disassembly priorities are determined based on actual needs. In this embodiment of the present invention, the components in the three-dimensional model are used as nodes in the constraint relationship graph, and the constraint strengths between the components are used as edges between the nodes in the constraint relationship graph. The direction of the edges can represent the disassembly priority.

[0067] Furthermore, in order to reduce complexity, the constraint relationship graph can also be split before disassembly path planning. Based on this, the method includes: determining the strongly connected components in the constraint relationship graph, and determining the initial strongly connected subgraph corresponding to each strongly connected component; taking any initial strongly connected subgraph in each of the initial strongly connected subgraphs as the target initial strongly connected subgraph, determining the number of nodes and the number of edges in the target initial strongly connected subgraph, and judging whether the target initial strongly connected subgraph meets the preset conditions for subgraph division based on the number of nodes and the number of edges. If so, the target initial strongly connected subgraph is used as the strong connected subgraph after the final division; otherwise, the target initial strongly connected subgraph is subgraph divided to obtain the strong connected subgraph after the final division.

[0068] Specifically, two timestamps (dfn and low) are assigned to each node in the constraint graph, and a stack is initialized to store the node currently being processed. Starting from any unvisited node, a depth-first search traversal is performed. During the traversal, the dfn and low values ​​of the node are updated. When a node's dfn value is found to be equal to its low value, it means that the node and all the nodes above it in the stack constitute a strongly connected component, so that multiple strongly connected components in the constraint graph can be obtained. At this time, these nodes are popped from the stack and marked as a strongly connected component. The strongly connected components of the constraint graph are calculated to obtain the initial strongly connected subgraph set S'=(S1',S2',...,S i '), where the strongly connected subgraph set contains the initial strongly connected subgraph S corresponding to each strongly connected component i ', for each strongly connected subgraph S i ', calculate the number of internal nodes n i and the number of edges m i , if n i ≤ threshold t1, and m i ≤ threshold t2, then S i 'Add to the strongly connected subgraph set S, otherwise recursively i 'Execute the subgraph partitioning operation. The specific partitioning method is as shown above and will not be repeated here. The final partitioned subgraph is added to the set of strongly connected subgraphs S, S = {S1, S2, ..., S n}, the strongly connected subgraph set S contains the strongly connected subgraphs S1, S2, ..., S n. The thresholds t1 and t2 are dynamically adjusted according to the equipment scale and computing resources, and can be set to 50 and 200 respectively. The embodiment of the present invention divides the constraint relationship graph into multiple independent strongly connected subgraphs, each of which corresponds to an independently disassembled module. This can convert the original complex problem into smaller and easier-to-solve subproblems, thereby significantly improving computing efficiency. Taking a certain type of mining truck gearbox as an example, the average number of subgraph nodes after subgraph division can be reduced by 55%, and the optimization solution time can be shortened by 70%.

[0069] 104. Based on the constraint relationship diagram, determine a disassembly path for the target mining machinery and equipment, and disassemble the target mining machinery and equipment based on the disassembly path.

[0070] Among them, the disassembly path can indicate the steps and sequence required for parts to be completely separated from their initial assembly state.

[0071] In the embodiment of the present invention, the sub-disassembly and assembly paths corresponding to each strongly connected subgraph are determined respectively, and each sub-disassembly and assembly path is used as the disassembly path of the target mining machinery and equipment, and finally the disassembly operation is performed on each component on the disassembly path in the direction from the starting point to the end point of the disassembly path. The embodiment of the present invention systematically models the geometric constraint relationship of the equipment, comprehensively considers multi-level constraint factors, constructs a directed graph model with constraint strength as weight, and combines graph theory optimization and hybrid optimization algorithms to automatically generate a global optimal disassembly and assembly sequence, avoiding the time-consuming and labor-intensive problem of manually determining the disassembly method and the problem of determining errors, thereby improving the efficiency and accuracy of determining the disassembly method of mining machinery and equipment. Using this disassembly method to disassemble the equipment can avoid damage to components due to collisions during the disassembly process.

[0072] According to the present invention, a method for disassembling mining machinery and equipment based on geometric constraints is provided. Compared with the current method of manually planning the disassembly and assembly of mining machinery, the present invention uses the geometric constraint relationship of the target mining machinery and equipment to construct a constraint relationship diagram with constraint strength as the edge, and ultimately determines the disassembly path based on the constraint relationship diagram. This can avoid the time-consuming and labor-intensive problem of manually determining the disassembly path, thereby improving the efficiency of determining the disassembly method of mining equipment. The present invention can also accurately identify contact constraints and non-contact constraints between parts, ensuring the feasibility and accuracy of the disassembly path. In addition, the present invention determines the disassembly path through a comprehensive analysis of contact constraints and non-contact constraints, which can further improve the accuracy of determining the disassembly path, avoid problems such as collisions with other parts during the disassembly process, and thus avoid equipment damage.

[0073] Furthermore, in order to better illustrate the above process of planning the disassembly sequence of mining machinery and equipment, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another method for disassembling mining machinery and equipment based on geometric constraints, such as Figure 2 As shown, the method includes:

[0074] 201. Obtain a three-dimensional model of the target mining machinery and equipment.

[0075] 202. Determine contact constraint information and non-contact constraint information between various components in the three-dimensional model, wherein the contact constraint information includes the normal contact force and friction torque between various components, and the non-contact constraint information is the assembly accuracy between various components.

[0076] 203. The weight coefficients of normal contact force, friction torque and assembly accuracy are determined respectively. Based on the weight coefficients, the normal contact force, friction torque and assembly accuracy are weightedly summed to obtain the constraint strength between each component.

[0077] Specifically, the constraint strength C between each component is determined according to the following formula: s :

[0078] C s =α1×F n +α2×P a +α3×T f

[0079] Among them, F n is the normal contact force, P a is the assembly accuracy, T f is the friction torque, α1, α2, α3 are F n 、P a 、T f The corresponding weighted times. Among them, the weight coefficient is set according to actual needs, and the value range of each weight coefficient can be as shown below. It should be noted that the value range of each weight coefficient shown below is only illustrative and does not impose specific limits on the implementation of the present invention.

[0080] 0.4≤α1≤0.6

[0081] 0.2≤α2≤0.4

[0082] 0.1≤α3≤0.3

[0083] 204. Based on the constraint strengths between each component and each component, a constraint relationship diagram is constructed, wherein each component serves as a node in the constraint relationship diagram, the constraint strength serves as an edge between corresponding adjacent components, and the preset assembly and disassembly priority serves as the direction of the edge.

[0084] Specifically, a constraint relationship graph is constructed, with components as nodes and the constraint strengths between components as edges. Based on the results of multi-level constraint analysis, this embodiment of the present invention proposes a directed graph optimization model weighted by constraint strength and designs an efficient graph partitioning algorithm based on strongly connected components. This algorithm decomposes the original complex constraint relationship graph into multiple independent assembly and disassembly units, significantly reducing the complexity of problem solving and improving optimization efficiency.

[0085] 205. Based on the constraint relationship diagram, determine a disassembly path for the target mining machinery and equipment, and disassemble the target mining machinery and equipment based on the disassembly path.

[0086] In one embodiment of the present invention, a method for determining a disassembly path includes: determining a set of candidate disassembly paths for the target mining machinery and equipment based on the constraint relationship graph; constructing a hierarchical bounding box for each component in the target mining machinery and equipment, and assembling each of the hierarchical bounding boxes into a hierarchical bounding box tree based on the hierarchical structure of each component in the target mining machinery and equipment; taking any candidate disassembly path in the set of candidate disassembly paths as a target candidate disassembly path, determining a center point vector and a relative direction matrix of every two hierarchical bounding boxes in the target candidate disassembly path on the hierarchical bounding box tree, wherein every two hierarchical bounding boxes contain a hierarchical bounding box of a component to be disassembled; extracting a separating axis between every two hierarchical bounding boxes based on the center point vector and the relative direction matrix, and determining a projection interval of every two hierarchical bounding boxes on the separating axis; and determining whether the projection intervals of every two hierarchical bounding boxes overlap. If so, the target candidate disassembly path is removed from the set of candidate disassembly paths; otherwise, the target candidate disassembly path is retained, and the candidate disassembly path in the set of candidate disassembly paths is used as the disassembly path.

[0087] Specifically, all feasible paths, i.e., multiple candidate disassembly paths, are generated based on the topological sorting of the constraint relationship graph. For each component, the minimum bounding box B is generated using the AABB (axis-aligned bounding box) or OBB (oriented bounding box) algorithm. i , record the center point C of the bounding box i , semi-axis length L i , direction matrix R i According to the assembly hierarchy of parts, the leaf node is the bounding box of a single part, and the internal node is the result of merging the bounding boxes of its child nodes. The parent-child node relationship is recorded to form a hierarchical bounding box tree T. Each node in the hierarchical bounding box tree T stores the bounding box geometry information and the child node pointer. Based on each candidate disassembly path p and the hierarchical bounding box tree, each step s in the candidate disassembly path p is determined to extract the current part v to be disassembled. i Bounding box B i and the bounding box B of the remaining componentsj , forming a bounding box pair (B i ,B j ), determine the center point vector Among them, C j Bounding box B j The center point of the , and calculate the relative direction matrix Among them, R j Bounding box B j The direction matrix of the center point vector Bounding box B i The three axes and bounding box B j The three axes and their cross product are used as bounding box pairs (B i ,B j ) of the separation axis Then calculate the bounding box B separately i and bounding box B j On the separation axis If the projection intervals on any separating axis overlap, the corresponding candidate disassembly path is determined to be a path that needs to be abandoned. If the projection intervals on all separating axes do not overlap, the corresponding candidate disassembly path is determined to meet the disassembly requirements. This allows determining whether each candidate disassembly path meets the disassembly requirements, and ultimately selects the candidate disassembly path that meets the disassembly requirements as the disassembly path for disassembling the mining machinery. This embodiment of the present invention reduces the complexity of path screening and improves the efficiency of disassembly path determination by constructing a hierarchical bounding box tree of parts and utilizing the branch and bound concept.

[0088] In another embodiment of the present invention, the method of determining the disassembly path also includes: taking any component other than the starting component and the ending component among the components on the target candidate disassembly path as a current component, determining the starting Euclidean distance between the current component and the starting component, determining the ending Euclidean distance between the current component and the ending component, and determining the current constraint strength of the current component; based on the ending Euclidean distance and the current constraint strength, determining the estimated cost of the current component, and taking the sum of the estimated cost and the starting Euclidean distance as the reachability evaluation value of the current component; taking the sum of the reachability evaluation values ​​of each current component on the target candidate disassembly path as the evaluation parameter of the target candidate disassembly path, and selecting the disassembly path of the target mining machinery and equipment in each target candidate disassembly path based on the evaluation parameter.

[0089] Specifically, based on the constraint relationship graph, the constraint strength between the current component and the adjacent components is determined as the current constraint strength. Then, the weight coefficients corresponding to the ending Euclidean distance and the current constraint strength are determined respectively, and based on the weight coefficients, the ending Euclidean distance and the current constraint strength are weighted and summed to obtain an estimated cost, and the sum of the estimated cost and the starting Euclidean distance is used as the accessibility evaluation value of the current component. Thus, according to the above method, the accessibility evaluation values ​​corresponding to all remaining components other than the starting and ending components in each candidate disassembly path can be determined, and the sum of the accessibility evaluation values ​​of each remaining component in each candidate disassembly path is calculated. Finally, the disassembly path with the smallest sum of accessibility evaluation values ​​is selected in each candidate disassembly path as the disassembly path for disassembling the equipment. The embodiment of the present invention uses a reachability analysis method of a heuristic search algorithm, considers the equipment layout and the operable space of the maintenance tools, searches for the optimal reachable disassembly and assembly path, and ensures that the generated disassembly and assembly plan is operable. The algorithm can improve the efficiency of determining the disassembly path by designing a heuristic function that comprehensively considers the Euclidean distance and constraint strength.

[0090] In another embodiment of the present invention, the method of determining the disassembly path also includes: randomly generating an initial population, wherein the initial population includes a plurality of feasible disassembly paths; determining the number of disassembly steps, the number of direction adjustments of the tool during the disassembly operation, and the disassembly constraint strength of each of the feasible disassembly paths, and determining the fitness of each of the feasible disassembly paths based on the number of disassembly steps, the number of direction adjustments, and the disassembly constraint strength; selecting a target feasible disassembly path with a fitness greater than a first preset threshold in each of the feasible disassembly paths, exchanging partial path segments of any two target feasible disassembly paths in the target feasible disassembly paths to obtain a cross disassembly path, and interchanging components at any two positions on any target feasible disassembly path in the target feasible disassembly paths to obtain a variable disassembly path. A different disassembly path is formed by the target feasible disassembly path, the cross disassembly path, and the variant disassembly path to form a new generation population, and the new generation population is used as a new initial population to continue fitness calculation, partial path segment exchange, and parts interchange operations until the number of population iterations reaches a preset number, thereby obtaining an ultimate population; determining the ultimate number of disassembly steps, the ultimate number of direction adjustments of the tool in the disassembly operation, and the ultimate disassembly constraint strength of each ultimate disassembly path in the ultimate population, and determining the ultimate fitness of each ultimate disassembly path based on the ultimate number of disassembly steps, the ultimate number of direction adjustments, and the ultimate disassembly constraint strength; selecting the ultimate fitness of each ultimate disassembly path with an ultimate fitness greater than a second preset threshold in each ultimate disassembly path as the disassembly path of the target mining machinery and equipment.

[0091] Among them, the first preset threshold, the second preset threshold, and the preset number of times are all set according to actual needs.

[0092] Specifically, the embodiment of the present invention can be illustrated by taking each strongly connected subgraph after the constraint relationship graph is divided as an example, and a hybrid optimization algorithm is designed to solve the disassembly and assembly plan for the strongly connected subgraph after the division. The algorithm uses a modified genetic algorithm as a framework, introduces a taboo search strategy for local search, and adopts an adaptive weight adjustment mechanism to balance global exploration and local development. The algorithm process includes: generating a set of feasible disassembly paths based on the topological sorting of the strongly connected subgraph, and randomly extracting N paths from the set of feasible disassembly paths to form an initial population S0. It should be noted that the feasible disassembly path does not have any steps that violate tool dependence or interference constraints, and the disassembly and assembly order of the path covers different component combinations as much as possible. For each path in the initial population S0, the total number of assembly and disassembly steps in the path (number of disassembly steps), the number of tool direction switches during the assembly and disassembly process (number of direction adjustments), and the cumulative value of all constraint strengths in the path (disassembly constraint strength) are determined. The number of disassembly steps, the number of direction adjustments, and the disassembly constraint strength are normalized and weighted summed to obtain the fitness of the corresponding path. Multiple target feasible disassembly paths with fitness greater than the first preset threshold in the initial population S0 are retained to obtain the population S0. select , from population S select Randomly select any two disassembly paths p i and p j , and select two intersection points k1 and k2, swap p i and p j The path segments in the range [k1, k2] generate two cross disassembly paths p i ′ and p′ j For example, if p i :A→B→C→D→E,p j :A→F→G→H→E, intersection k1=2, k2=4, then two cross disassembly paths p are generated i ′: A→B→G→H→E, p′ j :A→F→C→D→E. Further, from the population S select Randomly select a disassembly path p in the , randomly select two positions m and n on the path, exchange the parts at position m and position n, and get the variant disassembly path p'. For example, if p: A→B→C→D→E, the exchange positions are m=2 and n=4, then the variant disassembly path p': A→D→C→B→E. Add the cross disassembly path and the variant disassembly path to the population S select In the new generation population S new , then determine the population S newThe number of disassembly steps in each disassembly path, the number of direction adjustments of the tool in the disassembly operation, and the strength of the disassembly constraint are taken into consideration, and the fitness of each disassembly path is determined based on the number of disassembly steps, the number of direction adjustments, and the strength of the disassembly constraint; a target feasible disassembly path with a fitness greater than a first preset threshold is selected in each disassembly path, and any two target feasible disassembly paths in the target feasible disassembly path are partially exchanged to obtain a cross disassembly path, and parts at any two positions on any target feasible disassembly path in the target feasible disassembly path are exchanged to obtain a variant disassembly path, and a new generation of population is formed by the target feasible disassembly path, the cross disassembly path, and the variant disassembly path. The population is continuously iterated and updated in the above manner. When the number of iterations reaches a certain number, such as 100 times, the iteration is stopped, and the population obtained by the last iteration is used as the ultimate population S z , and perform weighted summation on the ultimate number of disassembly steps, the ultimate number of tool direction adjustments during the disassembly operation, and the ultimate disassembly constraint strength of each path in the ultimate population to obtain the fitness of each path, and select the path with a fitness greater than the second preset threshold as the disassembly path of the mining machinery and equipment. Or for the ultimate population S z For each path in the graph, a tabu search algorithm is used to perform a local search to obtain the local optimal solution. For example, the length of the tabu table is 20% of the number of nodes in the subgraph, and the number of tabu search iterations is 50. During the search process, the weight coefficients of the genetic algorithm and the tabu search algorithm are dynamically adjusted, with the weight being inversely proportional to the current number of iterations to balance global exploration and local development. The embodiments of the present invention determine the disassembly path using a hybrid optimization algorithm, accelerating search convergence while avoiding premature convergence, and obtaining the globally optimal disassembly and assembly solution, thereby improving the efficiency of determining the disassembly path.

[0093] It should be noted that the disassembly path p in the embodiment of the present invention i and p j The number of choices can be determined based on the crossover probability, which represents the proportion of individuals in the population that participate in the crossover operation. For example, the crossover probability can be set to 0.8. Furthermore, the number of disassembly paths p in this embodiment of the present invention can be determined based on the mutation probability, which represents the probability of each individual in the population mutating. For example, the mutation probability can be set to 0.1.

[0094] Furthermore, standardized disassembly and assembly instructions are automatically generated based on the disassembly path of the target mining machinery and equipment. These instructions include detailed instructions for each disassembly and assembly step, a list of required tools, safety precautions, and more. They are also accompanied by extensive 2D schematics and 3D animations, visually presenting key disassembly and assembly steps. 3D Visual Verification: This system integrates the disassembly and assembly plan with a 3D model of the equipment to develop an interactive 3D visualization system. Through visual simulation, the disassembly and assembly process is dynamically simulated, allowing for intuitive assessment of solution feasibility and timely identification and correction of potential interference issues, thereby improving solution quality and reliability.

[0095] For example, consider the disassembly, assembly, and repair of a mining truck transmission. This transmission has a complex structure, and the original 3D model contains 1,526 parts. Model preprocessing involves simplifying the original model while retaining key assembly features. The simplified model contains 683 parts, a 55% reduction compared to the original model. Assembly information is extracted, automatically identifying the assembly relationships and properties of each part. Geometric constraint analysis involves comprehensively considering both contact and non-contact constraints to construct a geometric constraint semantic model. Constraint strengths are quantified to obtain a precise description of the constraint relationships. Constraint graph optimization involves constructing a directed graph model of the constraint relationships based on the constraint analysis results. Using a strongly connected component partitioning algorithm, the original graph is partitioned into 27 independent subgraphs, reducing the average number of subgraph nodes from 308 to 140. Disassembly and assembly path optimization involves solving disassembly and assembly plans for each subgraph using a hybrid optimization algorithm. Through OBB collision detection and reachability analysis, an optimal, interference-free, and operational disassembly and assembly path is obtained. This approach improves computational efficiency and accuracy compared to traditional genetic algorithms. Output and verification: Standardized disassembly and assembly instructions are automatically generated, featuring comprehensive content, rich formats, and strong operability. Through 3D visualization simulation, the feasibility and rationality of the disassembly and assembly plan can be intuitively verified. The visualization system realizes realistic animation simulation of the disassembly and assembly process and supports user interaction.

[0096] According to another method for disassembling mining machinery and equipment based on geometric constraints provided by the present invention, compared with the current method of manually planning the disassembly and assembly of mining machinery, the present invention uses the geometric constraint relationship of the target mining machinery and equipment to construct a constraint relationship diagram with constraint strength as the edge, and finally determines the disassembly path based on the constraint relationship diagram. This can avoid the time-consuming and labor-intensive problem of manually determining the disassembly path, thereby improving the efficiency of determining the disassembly method of mining equipment. The present invention can also accurately identify contact constraints and non-contact constraints between parts, ensuring the feasibility and accuracy of the disassembly path. In addition, the present invention determines the disassembly path by performing a comprehensive analysis of contact constraints and non-contact constraints, which can further improve the accuracy of determining the disassembly path, avoid problems such as collisions with other parts during the disassembly process, and thus avoid equipment damage.

[0097] Further, as Figure 1The specific implementation of the present invention provides a mining machinery and equipment disassembly device based on geometric constraints, such as Figure 3 As shown, the device includes: an acquisition unit 31, a determination unit 32, a construction unit 33, and a disassembly unit 34.

[0098] The acquisition unit 31 may be used to acquire a three-dimensional model of target mining machinery and equipment.

[0099] The determining unit 32 may be configured to determine contact constraint information and non-contact constraint information between components in the three-dimensional model, and determine constraint strengths between components based on the contact constraint information and the non-contact constraint information.

[0100] The construction unit 33 can be used to construct a constraint relationship diagram based on the constraint strengths between each component and each component, wherein the each component serves as each node in the constraint relationship diagram, the constraint strength serves as the edge between corresponding adjacent components, and the preset disassembly and assembly priority serves as the direction of the edge.

[0101] The disassembly unit 34 may be configured to determine a disassembly path for the target mining machinery and equipment based on the constraint relationship diagram, and disassemble the target mining machinery and equipment based on the disassembly path.

[0102] In a specific application scenario, the contact constraint information includes the normal contact force and friction torque between each component, and the non-contact constraint information is the assembly accuracy between each component; in order to determine the constraint strength between each component, the determination unit 32 can be specifically used to respectively determine the weight coefficients of the normal contact force, the friction torque, and the assembly accuracy, and based on the weight coefficients, perform weighted summation on the normal contact force, the friction torque, and the assembly accuracy to obtain the constraint strength between each component.

[0103] In specific application scenarios, in order to split the constraint relationship graph, such as Figure 4 As shown, the device further includes a dividing unit 35.

[0104] The determining unit 32 may also be configured to determine the strongly connected components in the constraint relationship graph and determine an initial strongly connected subgraph corresponding to each strongly connected component.

[0105] The division unit 35 can be used to respectively take any initial strongly connected subgraph in each of the initial strongly connected subgraphs as the target initial strongly connected subgraph, determine the number of nodes and the number of edges in the target initial strongly connected subgraph, and based on the number of nodes and the number of edges, judge whether the target initial strongly connected subgraph meets the preset conditions for subgraph division. If so, the target initial strongly connected subgraph is used as the strongly connected subgraph after the final division. Otherwise, the target initial strongly connected subgraph is subjected to subgraph division to obtain the strongly connected subgraph after the final division.

[0106] The disassembly unit 34 may also be configured to respectively determine a sub-disassembly path corresponding to each of the strongly connected subgraphs, and use each of the sub-disassembly paths as a disassembly path for the target mining machinery and equipment.

[0107] In a specific application scenario, in order to determine the disassembly path of the target mining machinery and equipment, the disassembly unit 34 includes a determination module 341 , a construction module 342 , an extraction module 343 , and a judgment module 344 .

[0108] The determination module 341 may be configured to determine a set of candidate disassembly paths for the target mining machinery and equipment based on the constraint relationship graph.

[0109] The construction module 342 may be configured to construct a hierarchical bounding box for each component in the target mining machinery and equipment, and assemble the hierarchical bounding boxes into a hierarchical bounding box tree based on the hierarchical structure of each component in the target mining machinery and equipment.

[0110] The determination module 341 can also be used to take any candidate disassembly path in the candidate disassembly path set as a target candidate disassembly path, and determine the center point vector and relative direction matrix of each two hierarchical bounding boxes in the target candidate disassembly path on the hierarchical bounding box tree, wherein each two hierarchical bounding boxes contain the hierarchical bounding box of the component to be disassembled.

[0111] The extraction module 343 may be configured to extract the separation axis between each two bounding boxes at each level based on the center point vector and the relative direction matrix, and determine the projection interval of each two bounding boxes at each level on the separation axis.

[0112] The judgment module 344 can be used to determine whether the projection intervals of each two hierarchical bounding boxes overlap. If so, the target candidate disassembly path is removed from the candidate disassembly path set; otherwise, the target candidate disassembly path is retained, and the candidate disassembly path in the processed candidate disassembly path set is used as the disassembly path.

[0113] In a specific application scenario, in order to determine the disassembly path of the target mining machinery and equipment, the determination module 341 can also be used to take any component other than the starting component and the ending component among the components on the target candidate disassembly path as a current component, determine the starting Euclidean distance between the current component and the starting component, determine the ending Euclidean distance between the current component and the ending component, and determine the current constraint strength of the current component.

[0114] The determination module 341 may also be configured to determine an estimated cost of the current component based on the ending Euclidean distance and the current constraint strength, and use the sum of the estimated cost and the starting Euclidean distance as the reachability evaluation value of the current component.

[0115] The extraction module 343 can also be used to use the sum of the reachability evaluation values ​​of each current component on the target candidate disassembly path as an evaluation parameter of the target candidate disassembly path, and select the disassembly path of the target mining machinery equipment in each target candidate disassembly path based on the evaluation parameter.

[0116] In a specific application scenario, in order to determine the disassembly path of the target mining machinery and equipment, the disassembly unit 34 further includes a generation module 345 .

[0117] The generation module 345 can be used to randomly generate an initial population, wherein the initial population includes multiple feasible disassembly paths.

[0118] The determination module 341 can also be used to determine the number of disassembly steps, the number of direction adjustments of the tool during the disassembly operation, and the disassembly constraint strength of each feasible disassembly path, and determine the adaptability of each feasible disassembly path based on the number of disassembly steps, the number of direction adjustments, and the disassembly constraint strength.

[0119] The determination module 341 can also be used to select a target feasible disassembly path with a fitness greater than a first preset threshold value in each of the feasible disassembly paths, exchange partial path segments of any two target feasible disassembly paths in the target feasible disassembly paths to obtain a cross disassembly path, and exchange parts at any two positions on any target feasible disassembly path in the target feasible disassembly paths to obtain a variant disassembly path, and form a new generation population by the target feasible disassembly path, the cross disassembly path, and the variant disassembly path, and use the new generation population as a new initial population to continue to perform fitness calculation, partial path segment exchange, and part interchange operations until the number of population iterations reaches a preset number, and an ultimate population is obtained.

[0120] The determination module 341 can also be used to determine the ultimate number of disassembly steps, the ultimate number of direction adjustments of the tool during the disassembly operation, and the ultimate disassembly constraint strength of each ultimate disassembly path in the ultimate population, and determine the ultimate fitness of each ultimate disassembly path based on the ultimate number of disassembly steps, the ultimate number of direction adjustments, and the ultimate disassembly constraint strength.

[0121] The extraction module 343 may also be configured to select, from each of the ultimate disassembly paths, a final fitness greater than a second preset threshold as the disassembly path for the target mining machinery and equipment.

[0122] In a specific application scenario, in order to simplify the three-dimensional model, the device further includes a simplification unit 36 ​​.

[0123] The simplification unit 36 ​​can be used to extract non-critical assembly features and critical assembly features in the three-dimensional model; while ensuring the geometric integrity and topological continuity of the critical assembly features, the non-critical assembly features are removed from the three-dimensional model to obtain a simplified three-dimensional model.

[0124] The determining unit 32 may also be used to determine contact constraint information and non-contact constraint information between components in the simplified three-dimensional model.

[0125] It should be noted that for other corresponding descriptions of the functional modules involved in the mining machinery and equipment disassembly device based on geometric constraints provided by the embodiment of the present invention, please refer to Figure 1 The corresponding description of the method shown will not be repeated here.

[0126] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which implements the following steps when executed by a processor: obtaining a three-dimensional model of a target mining machinery and equipment; determining contact constraint information and non-contact constraint information between each component in the three-dimensional model, and determining the constraint strength between each component based on the contact constraint information and the non-contact constraint information; constructing a constraint relationship graph based on the constraint strength between each component, wherein each component serves as each node in the constraint relationship graph, and the constraint strength serves as the edge between corresponding adjacent components; determining a disassembly path of the target mining machinery and equipment based on the constraint relationship graph, and disassembling the target mining machinery and equipment based on the disassembly path.

[0127] Based on the above Figure 1 The method shown and Figure 3The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 5 As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43. When the processor 41 executes the program, the following steps are implemented: obtaining a three-dimensional model of a target mining machinery and equipment; determining contact constraint information and non-contact constraint information between various components in the three-dimensional model, and determining the constraint strength between various components based on the contact constraint information and the non-contact constraint information; constructing a constraint relationship graph based on the constraint strength between various components, wherein the various components serve as nodes in the constraint relationship graph, and the constraint strength serves as edges between corresponding adjacent components; determining a disassembly path of the target mining machinery and equipment based on the constraint relationship graph, and disassembling the target mining machinery and equipment based on the disassembly path.

[0128] Through the technical solution of the present invention, a constraint relationship diagram with constraint strength as its edges is constructed based on the geometric constraints of the target mining machinery and equipment. Ultimately, the disassembly path is determined based on the constraint relationship diagram. This can avoid the time-consuming and labor-intensive problem of manually determining the disassembly path, thereby improving the efficiency of determining the disassembly method of mining equipment. The present invention can also accurately identify contact and non-contact constraints between components, ensuring the feasibility and accuracy of the disassembly path. In addition, the present invention can further improve the accuracy of determining the disassembly path by comprehensively analyzing contact and non-contact constraints to determine the disassembly path, avoiding problems such as collisions with other components during the disassembly process, thereby preventing equipment damage.

[0129] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, centralized on a single computing device, or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. In some cases, the steps shown or described can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0130] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for disassembling mining machinery and equipment based on geometric constraints, characterized in that: include: Obtain a three-dimensional model of the target mining machinery and equipment; determining contact constraint information and non-contact constraint information between components in the three-dimensional model, and determining constraint strengths between the components based on the contact constraint information and the non-contact constraint information; Based on the constraint strengths between the various components and the various components, a constraint relationship graph is constructed, wherein the various components serve as nodes in the constraint relationship graph, the constraint strengths serve as edges between corresponding adjacent components, and the preset assembly and disassembly priorities serve as directions of the edges; Based on the constraint relationship diagram, a disassembly path of the target mining machinery and equipment is determined, and the target mining machinery and equipment is disassembled based on the disassembly path.

2. The method according to claim 1, characterized in that The contact constraint information includes the normal contact force and friction torque between the various components, and the non-contact constraint information is the assembly accuracy between the various components; The determining the constraint strength between the components based on the contact constraint information and the non-contact constraint information includes: The weight coefficients of the normal contact force, the friction torque, and the assembly accuracy are determined respectively. Based on the weight coefficients, the normal contact force, the friction torque, and the assembly accuracy are weightedly summed to obtain the constraint strength between the various components.

3. The method according to claim 1, characterized in that Before determining the disassembly path of the target mining machinery and equipment based on the constraint relationship graph, the method further includes: Determining strongly connected components in the constraint relationship graph, and determining an initial strongly connected subgraph corresponding to each strongly connected component; Respectively taking any initial strongly connected subgraph in each of the initial strongly connected subgraphs as a target initial strongly connected subgraph, determining the number of nodes and the number of edges in the target initial strongly connected subgraph, and judging whether the target initial strongly connected subgraph meets a preset condition for subgraph partitioning based on the number of nodes and the number of edges; if so, taking the target initial strongly connected subgraph as the strongly connected subgraph after final partitioning; otherwise, performing subgraph partitioning on the target initial strongly connected subgraph to obtain a strongly connected subgraph after final partitioning; Determining a disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes: The sub-assembly and disassembly paths corresponding to each of the strongly connected subgraphs are determined respectively, and each of the sub-assembly and disassembly paths is used as the disassembly path of the target mining machinery and equipment.

4. The method according to claim 1, wherein The determining of the disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes: Determining a set of candidate disassembly paths for the target mining machinery and equipment based on the constraint relationship graph; Constructing a hierarchical bounding box for each component of the target mining machinery and equipment respectively, and assembling each of the hierarchical bounding boxes into a hierarchical bounding box tree based on the hierarchical structure of each component of the target mining machinery and equipment; Taking any candidate disassembly path in the candidate disassembly path set as a target candidate disassembly path, determining the center point vector and relative direction matrix of each two hierarchical bounding boxes in the target candidate disassembly path on the hierarchical bounding box tree, wherein each two hierarchical bounding boxes contain the hierarchical bounding box of the component to be disassembled; Extracting the separation axis of each two bounding boxes based on the center point vector and the relative direction matrix, and determining the projection interval of each two bounding boxes on the separation axis; Determine whether the projection intervals of each two hierarchical bounding boxes overlap. If so, remove the target candidate disassembly path from the candidate disassembly path set. Otherwise, retain the target candidate disassembly path and use the candidate disassembly path in the processed candidate disassembly path set as the disassembly path.

5. The method according to claim 4, characterized in that The determining of the disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes: Any component other than the starting component and the ending component among the components on the target candidate disassembly path is respectively used as a current component, a starting Euclidean distance between the current component and the starting component is determined, an ending Euclidean distance between the current component and the ending component is determined, and a current constraint strength of the current component is determined; Determining an estimated cost of the current component based on the ending Euclidean distance and the current constraint strength, and taking the sum of the estimated cost and the starting Euclidean distance as a reachability evaluation value of the current component; The sum of the reachability evaluation values ​​of each current component on the target candidate disassembly path is used as an evaluation parameter of the target candidate disassembly path, and based on the evaluation parameter, a disassembly path of the target mining machinery equipment is selected in each target candidate disassembly path.

6. The method according to claim 1, characterized in that The determining of the disassembly path of the target mining machinery and equipment based on the constraint relationship graph includes: Randomly generating an initial population, wherein the initial population contains multiple feasible disassembly paths; Determining the number of disassembly steps, the number of tool direction adjustments during the disassembly operation, and the strength of the disassembly constraint for each of the feasible disassembly paths, and determining the fitness of each of the feasible disassembly paths based on the number of disassembly steps, the number of direction adjustments, and the strength of the disassembly constraint; A target feasible disassembly path having a fitness greater than a first preset threshold is selected from each of the feasible disassembly paths, partial path segment exchanges are performed on any two target feasible disassembly paths in the target feasible disassembly paths to obtain a cross disassembly path, and components at any two positions on any target feasible disassembly path in the target feasible disassembly paths are exchanged to obtain a variant disassembly path, a new generation population is formed by the target feasible disassembly path, the cross disassembly path, and the variant disassembly path, and the new generation population is used as a new initial population to continue to perform fitness calculation, partial path segment exchange, and component exchange operations until the number of population iterations reaches a preset number, thereby obtaining a final population; Determining the ultimate number of disassembly steps, the ultimate number of direction adjustments of the tool during the disassembly operation, and the ultimate disassembly constraint strength of each ultimate disassembly path in the ultimate population, and determining the ultimate fitness of each ultimate disassembly path based on the ultimate number of disassembly steps, the ultimate number of direction adjustments, and the ultimate disassembly constraint strength; In each of the ultimate disassembly paths, the ultimate fitness that is greater than a second preset threshold is selected as the disassembly path of the target mining machinery and equipment.

7. The method according to claim 1, characterized in that Before determining the contact constraint information and the non-contact constraint information between the components in the three-dimensional model, the method further includes: extracting non-critical assembly features and critical assembly features from the three-dimensional model; On the premise of ensuring the geometric integrity and topological continuity of the key assembly features, the non-key assembly features are removed from the three-dimensional model to obtain a simplified three-dimensional model; The determining of contact constraint information and non-contact constraint information between components in the three-dimensional model includes: Contact constraint information and non-contact constraint information between components in the simplified three-dimensional model are determined.

8. A mining machinery and equipment disassembly device based on geometric constraints, characterized in that: include: An acquisition unit, used for acquiring a three-dimensional model of target mining machinery and equipment; a determining unit, configured to determine contact constraint information and non-contact constraint information between components in the three-dimensional model, and determine constraint strengths between the components based on the contact constraint information and the non-contact constraint information; A construction unit, configured to construct a constraint relationship graph based on the constraint strengths between the various components, wherein the various components serve as nodes in the constraint relationship graph and the constraint strengths serve as edges between corresponding adjacent components; A disassembly unit is configured to determine a disassembly path of the target mining machinery and equipment based on the constraint relationship diagram, and to disassemble the target mining machinery and equipment based on the disassembly path.

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

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images