Intelligent analysis method for welding seam layout of complex pipeline structure based on graph neural network

Abstract

The invention discloses a graph neural network-based complex pipeline structure welding seam layout intelligent analysis method. The method comprises the following steps of S1, obtaining a three-dimensional model construction graph structure; s2, predicting a weld joint score through a graph neural network; s3, constructing a candidate weld map to execute a reward and punishment type Steiner tree; s4, generating a construction dependency graph and executing a minimum feedback arc set; s5, constructing a residual conflict graph to calculate a conflict feedback coefficient; s6, adjusting the prize value and the weight; s7, executing the Steiner tree algorithm again; and S8, judging whether a constraint is met or not and outputting a final scheme. Linkage optimization of weld joint intelligent layout and construction scheduling is achieved, and constructability and the intelligent level under a complex structure are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of graph neural networks, and particularly to an intelligent analysis method for weld layout of complex pipeline structures based on graph neural networks. Background Art

[0002] Complex pipeline structures are widely used in major engineering fields such as petrochemical, power, nuclear energy, shipbuilding, and ocean engineering. Their spatial configurations usually have characteristics such as high three-dimensional coupling, dense pipe segment intersections, and numerous support nodes. During the pipeline manufacturing and installation processes, the layout and construction sequence of welds not only directly affect the connection strength, structural stability, and service safety, but also have a significant impact on the construction period, welding process complexity, and maintenance cost. Therefore, how to complete a reasonable, implementable, and schedulable weld layout and construction sequence planning on the premise of meeting the structural performance requirements has become one of the key issues in the intelligent analysis of engineering drawings.

[0003] In the prior art, the weld layout and path analysis methods are mainly divided into three categories: structural expert rule method, geometric optimization method, and graph model optimization method. The expert rule method relies on manual experience for initial weld point selection and path arrangement, with low efficiency, poor consistency, and difficulty in dealing with large-scale structures. The geometric optimization method usually conducts spatial analysis and path traversal based on a CAD model. Although it can automatically generate some reachable paths, it cannot consider engineering semantic factors such as connection importance and structural redundancy, and the layout is often disjointed from the overall process optimization. The graph modeling method developed in recent years has to some extent made up for the above deficiencies and can abstract the complex pipeline structure into a topological graph composed of nodes and edges, and realize preliminary structural visualization analysis and layout optimization by introducing graph neural networks and path optimization algorithms.

[0004] Existing graph modeling methods generally use static graph neural networks to encode the pipeline structure, and use node features (such as spatial position, pipe diameter, connection type) to score the importance of weld points, and then select the weld positions. However, such methods usually do not consider the logical dependencies between welding sequences. For example, some welds must be completed after other welds, or there are occlusion and reachability problems when constructing certain paths in a specific direction. In addition, during the layout graph generation process, the node selection strategy often only depends on score sorting, ignoring the cost of the connection path and the overall connectivity of the structure, which easily leads to local important nodes being isolated or high-cost weld connections being preferentially selected, affecting the overall constructability and stability.

[0005] In terms of path planning, existing research mostly uses graph theory methods such as the shortest path and minimum spanning tree for optimization. However, it lacks the comprehensive modeling of the dual factors of weld "reward value" and connection "cost", and cannot effectively balance the structural importance and welding difficulty. On this basis, the introduction of constraint optimization algorithms such as Steiner tree can alleviate the path redundancy problem to a certain extent. However, the node selection logic lacking the support of a reward and punishment mechanism is still prone to problems such as high reward and low connectivity or high connection and low benefit, especially in complex multi-redundant node distribution scenarios, where the generated results are unstable and difficult to generalize.

[0006] On the other hand, there is a clear logical sequence dependence in the weld construction process, that is, some weld nodes must be welded before other nodes. If there is a directed loop in the generated path graph, it will directly lead to construction logic conflicts. However, most existing methods use static sequence planning or rely on manual adjustment by engineers, lacking a systematic directed acyclic graph generation strategy. Although some research has introduced the minimum feedback arc set algorithm for loop elimination, its path selection process is mostly based on a single structural cost or graph topology weight, and fails to combine the weld importance score or structural centrality factor, resulting in the eliminated paths not being optimal, easily destroying structural redundancy or generating unreasonable sequences.

[0007] In addition, existing weld planning methods are generally one-way processes, that is, the weld layout and construction sequence are deduced from structural analysis, lacking feedback control ability and unable to use the conflict information in the sequence graph to reverse-correct the weld node reward value or path cost. The absence of a feedback adjustment module makes the method insensitive to engineering uncontrollable factors such as welding conflicts, structural occlusion, and sequence adjustment, and the generated solutions lack robustness. In the multi-round iterative optimization process, existing technologies also lack a scientific termination strategy judgment standard, making it difficult to effectively control the convergence and stability of the layout results, or there is a risk of resource waste and overfitting.

[0008] In summary, existing weld layout and construction sequence planning technologies still have significant deficiencies in aspects such as graph modeling accuracy, node path evaluation mechanism, sequence graph generation logic, feedback adjustment ability, and iterative convergence control. Especially when facing complex pipeline scenarios with high structural complexity, high redundant connections, and high construction dependence, there is an urgent need for a new intelligent weld analysis method that integrates graph neural network prediction, reward and punishment graph selection, conflict feedback adjustment, and multi-strategy termination control to improve the layout rationality, path reachability, and scheduling controllability of the system.

[0009] Therefore, how to provide an intelligent analysis method for weld layout of complex pipeline structures based on graph neural networks is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0010] One purpose of the present invention is to propose an intelligent analysis method for weld layout of complex pipeline structures based on graph neural network. The present invention comprehensively uses graph neural network modeling, reward-penalty Steiner tree optimization algorithm, minimum feedback arc set elimination mechanism and conflict feedback adjustment strategy to construct an iterative optimization system of structure-sequence dual graph linkage, and describes in detail the whole process control logic from weld prediction, path selection to construction sequence optimization, which has the advantages of high structural strength, strong construction accessibility, reasonable process sequence and strong feedback adjustment ability.

[0011] According to an embodiment of the present invention, a method for intelligent analysis of weld layout of a complex pipeline structure based on a graph neural network comprises the following steps: S1. Obtain the three-dimensional model data of the complex pipeline structure and construct a graph structure; S2. Input the graph structure into the graph neural network model, extract node features, generate the weld layout probability score of each node, and obtain the weld prediction graph; S3. Based on the weld prediction graph, a weighted candidate weld graph is constructed, node scores are mapped to bonus values, edge attributes are mapped to welding costs, and a reward-penalty Steiner tree algorithm is introduced. A greedy strategy is adopted to generate a weld layout subgraph. S4, constructing a directed dependency graph of weld construction based on the weld layout subgraph, using the minimum feedback arc set algorithm to eliminate loops in the graph, and generating a directed acyclic graph of construction sequence; S5. construct a residual conflict graph based on the removed edges of the construction sequence directed acyclic graph, count the participation frequency of the conflict nodes, and calculate the conflict feedback information; S6. adjusting the reward value of the corresponding node in the weighted candidate weld diagram according to the conflict feedback coefficient, and adjusting the weight of the conflicting node in the weld selection; S7, re-inputting the updated reward value into the reward-penalty Steiner tree algorithm, and iteratively generating a new weld layout subgraph; S8. Repeat S4 to S7, classify the iterative result strategies, until the structural strength and construction sequence non-cyclic constraints are met, and output the final weld layout diagram.

[0012] Optionally, it is characterized in that S2 specifically includes: inputting the graph structure into the graph neural network model, assigning a node attribute vector containing spatial coordinates, structural type and load-bearing level to each node, assigning an edge attribute vector containing connection length, connection angle, welding accessibility and material heterogeneity to each edge, the graph neural network model performs graph convolution processing of no less than three layers of graph convolution layers on the above attribute vectors, extracts features from the node attribute vectors in turn, scores each node through a classifier, generates a weld layout probability score corresponding to each node, and forms a weld prediction map.

[0013] Optionally, it is characterized in that S3 specifically includes: S31. Construct a weighted candidate weld map according to the weld prediction map; S32. For each node in the weighted candidate weld map, set its reward value to , where represents the weld layout probability score output by the node in the graph neural network. The weld layout probability score is calculated by the graph neural network based on the spatial position of the node, the type of pipeline structure, and its bearing capacity characteristics. The higher the node score, the more this node needs to be preferentially selected; S33. For each edge , set the cost function of the edge , and the cost function is calculated considering the following factors: ; where represents the connection length of the welding path, represents the connection angle, represents the welding accessibility coefficient, represents the material heterogeneity coefficient, , , , are preset weighted coefficients; S34. Input the reward value of the node and the cost of the edge into the reward and punishment Steiner tree algorithm, and use the greedy strategy for iterative screening. The goal of the reward and punishment Steiner tree algorithm is to select a subgraph that contains the optimal weld nodes and the shortest welding path to minimize the objective function which is: ; where represents the set of selected weld nodes, represents the set of selected weld paths. The first item represents the total cost of the selected path, and the second item is the penalty term for unselected nodes. By minimizing the objective function, the reward and punishment Steiner tree algorithm can select important weld nodes while optimizing the welding path, reduce the penalty for unselected nodes, and generate an optimized subgraph of the weld layout.

[0014] Optionally, it is characterized in that the greedy strategy adopted by the reward and punishment Steiner tree algorithm in S34 specifically includes: S341. Define the joint evaluation function of the reward and punishment Steiner tree algorithm for selecting the optimal combination of nodes and edges, where: ; Among them, is the minimum connection distance between the node and the currently selected node set, is the adjustment coefficient, which controls the balance between the path cost and the structural connectivity; S342. In each round of selection, from the set of unselected nodes, calculate the evaluation function value of each node and its connecting edge , select the node with the maximum evaluation function value and its corresponding connecting edge, add the node to the selected node set, and add the edge to the selected edge set; S343. Whenever a new node is selected, update the reward values of all unselected nodes. The specific update formula is: ; Among them, is the reward value of the unselected node, is the updated reward value of the unselected node, is the attenuation factor, is the node 's degree, is the number of currently selected nodes; S344. Through iteration, execute the above node selection and reward value update steps, select the optimal node in each round and update the path cost until the objective function reaches the minimum value; S345. When the objective function reaches the minimum or reaches the preset number of iterations, the algorithm terminates, and outputs the optimized weld layout subgraph, which contains the optimal weld nodes and the shortest welding path.

[0015] Optionally, it is characterized in that the S4 specifically includes: S41. Construct a weld construction dependency digraph based on the weld layout subgraph generated by the reward and punishment Steiner tree algorithm; S42. Perform loop detection on the dependency digraph to obtain all the feedback edge sets that form a closed loop; S43. For each feedback edge, calculate the static feedback weight , and the static feedback weight is jointly defined based on the structural path cost and the weld importance difference as: ; Among them, , are the reward values of the two updated nodes respectively, , is the weighting coefficient; S44. Adopt the minimum feedback arc set algorithm, and select the edge set with the minimum total cost for deletion according to the static feedback weight to obtain an acyclic weld sequence graph.

[0016] Optionally, it is characterized in that S44 specifically includes: S441. Based on the set of feedback edges existing in the dependency directed graph, combined with the connection density of the weld nodes connected by each edge in the original structure diagram, the position hierarchy in the graph, and the key degree in the process path, calculate the path importance score to measure the structural and technological value of the dependency edge in the overall welding logic; S442. Define the comprehensive cost function of the feedback edge according to the basic structure weight of the feedback edge, the node reward value difference, the path importance, and the sequential tension index between nodes , specifically as follows: ; Wherein, is the path importance score, comprehensively considering the connection degree and centrality of the node in the structure diagram, is the technological dependency tension between node pairs, reflecting the impact of sequential changes on the stability of the construction process, is the geometric distance of the node in the structure diagram, , is the adjustment parameter; S443. Select a group of edges with the minimum sum of the comprehensive cost function from the feedback edge set as the optimal feedback arc set, and after deletion, output an acyclic weld sequence diagram.

[0017] Optionally, it is characterized in that after the optimization of the feedback arc set of the acyclic weld sequence diagram in S5, it is further fused with the construction reachability diagram to construct a directed acyclic graph of the construction sequence. Among them, the construction reachability diagram is generated based on the operation space layout, the equipment reach range, the spatial hierarchy of the weld nodes, and the occlusion relationship between adjacent components. All physically executable paths are retained during the graph fusion process, and the directed edges conflicting with the actual construction path are deleted.

[0018] Optionally, it is characterized in that S5 specifically includes: S51. Construct a residual conflict graph according to the difference set between the directed acyclic graph of the construction sequence and the directed dependency graph of the weld construction; S52. Count the number of feedback edges involved when each node is used as the starting point or the ending point in the residual conflict graph, and calculate its node conflict frequency coefficient , defined as: ; Wherein, represents the number of feedback edges associated with the node , is the degree value of this node in the weld layout subgraph, and is normalized; For each edge in the feedback edge set , calculate its path dynamic conflict intensity , which is defined as: ; Among them, is the static feedback weight, is the conflict weight adjustment coefficient, representing the amplification factor of the node conflict degree on the path conflict cost; S54. Use the node conflict frequency coefficient and the path dynamic conflict intensity as conflict feedback information to guide the adaptive adjustment of the reward value function and the cost function .

[0019] Optionally, it is characterized in that the S6 specifically includes: adaptively adjusting the reward value function according to the node conflict feedback coefficient to generate the reward value function after conflict response, which is defined as: ; Among them, is the reward value weakening factor, is the non-linear control index; Replace the original reward value with the updated reward value , update the node attributes in the weighted candidate weld map, and adjust the evaluation function of the greedy strategy in the reward and punishment Steiner tree algorithm.

[0020] Optionally, it is characterized in that the S8 strategy classification has four types, and any one of the four strategies is satisfied to terminate the iteration. Specifically, it includes: Strategy I, acyclicity sufficient satisfaction strategy: The construction sequence diagram generated in the current round is a directed acyclic graph, and all node conflict frequency coefficients derived from the residual conflict graph all satisfy , where is the node conflict threshold; Strategy II, structural strength constraint strategy: All connection paths in the current weld layout subgraph satisfy the minimum connected redundancy defined in the structural mechanics model, that is: ; Among them, represents the shortest equivalent redundant path number of the node in the structure diagram; Strategy III, structural change convergence strategy: The structural difference degree between the current layout diagram and the previous round layout diagram satisfies: ; Among them, is the structural convergence threshold, represents the symmetric difference, is the round node set, is the round node set, is the round edge set, is the round edge set, represents the number of elements; Strategy IV, maximum round limit strategy: If the iteration round reaches the preset maximum round upper limit , the iteration is forced to terminate.

[0021] The beneficial effects of the present invention are: (1) The present invention proposes a graph neural network modeling and weld prediction method for complex pipeline structures, which can automatically extract component connection relationships and node features, generate a high-confidence weld layout probability map, avoid the limitations of relying on artificial rules or geometric heuristic strategies for weld selection in traditional methods, and improve the accuracy and intelligence level of weld point selection.

[0022] (2) By introducing the reward and punishment Steiner tree algorithm, the present invention jointly models the structural importance (reward value) of nodes and the engineering cost (penalty) of connection paths, realizes the optimal selection of weld subgraphs under the global structural connectivity constraint, effectively solves the problem of the disconnection between node selection and path planning in the prior art, and dynamically adjusts the reward value and cost through a feedback adjustment mechanism to achieve iterative coupling optimization between the layout graph and the construction sequence graph.

[0023] (3) The present invention further combines the minimum feedback arc set algorithm to construct a directed acyclic graph of the construction sequence, and proposes a feedback adjustment strategy driven by a residual conflict graph to construct a closed-loop of collaborative optimization of the structure-sequence dual graph. At the same time, a structural difference convergence criterion, process connectivity control, and maximum round tolerance mechanism are introduced to ensure that the entire method has adaptive, controllable, and convergent optimization performance on the basis of meeting structural strength and constructability, and significantly improve the engineering feasibility and robustness of the solution. Description of the Drawings

[0024] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings: Figure 1 is the overall flowchart of the intelligent analysis method for weld layout of complex pipeline structures based on graph neural network proposed by the present invention; Figure 2Flowchart of node-path selection for the reward-punishment Steiner tree based on the greedy strategy proposed by the present invention; Figure 3 Multi-round iterative optimization process and structural difference convergence judgment diagram for the intelligent analysis method of weld layout of complex pipeline structures based on graph neural networks proposed by the present invention. Detailed implementation manners

[0025] Now, the present invention will be further described in detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0026] Refer to Figures 1-3 , the intelligent analysis method of weld layout of complex pipeline structures based on graph neural networks includes the following steps: S1. Obtain the three-dimensional model data of the complex pipeline structure and construct a graph structure; S2. Input the graph structure into the graph neural network model, extract node features, generate the weld layout probability scores of each node, and obtain a weld prediction graph; S3. Based on the weld prediction graph, construct a weighted candidate weld graph, map the node scores to reward values, map the edge attributes to welding costs, introduce the reward-punishment Steiner tree algorithm, and adopt the greedy strategy to generate a weld layout sub-graph; S4. Based on the weld layout sub-graph, construct a directed dependence graph for weld construction, and use the minimum feedback arc set algorithm to eliminate the loops in the graph to generate a directed acyclic graph of construction sequence; S5. Based on the removed edges of the directed acyclic graph of construction sequence, construct a residual conflict graph, count the participation frequencies of conflict nodes, and calculate conflict feedback information; S6. Adjust the reward values of the corresponding nodes in the weighted candidate weld graph according to the conflict feedback coefficient, and adjust the weights of conflict nodes in weld selection; S7. Re-input the updated reward values into the reward-punishment Steiner tree algorithm, and iteratively generate a new weld layout sub-graph; S8. Repeat steps S4 to S7, classify the iterative results, until the structural strength and acyclic construction sequence constraints are satisfied, and output the final weld layout graph.

[0027] The present invention innovatively realizes the deep coupling optimization of weld layout and construction scheduling by constructing a complete closed-loop process from three-dimensional modeling, graph neural network prediction, weld selection to construction sequence scheduling. Compared with the problems of mutual separation of weld analysis, path planning and process sequencing in the prior art, the present invention unifies the scheduling structure logic and spatial process information on the basis of the same graph modeling, and has the advantages of accurate prediction, efficient layout, feasible scheduling and strong convergence, significantly improving the intelligent weld analysis ability under complex pipeline structures.

[0028] In this embodiment, it is characterized in that S2 specifically includes: inputting the graph structure into the graph neural network model, allocating a node attribute vector including spatial coordinates, structure type, and load level to each node, allocating an edge attribute vector including connection length, connection angle, welding accessibility, and material heterogeneity to each edge, performing graph convolution processing on the above attribute vectors through at least three graph convolution layers in the graph neural network model, sequentially extracting features from the node attribute vectors, scoring each node through a classifier, generating the weld layout probability score corresponding to each node, and forming a weld prediction graph.

[0029] The present invention realizes in-depth feature extraction of complex pipeline nodes at the spatial, structural, and technological levels by introducing multi-dimensional attribute vectors for each node and edge in the graph structure and performing at least three graph convolution processes in the graph neural network. Compared with the traditional weld scoring method that uses only single geometric or connection information, the graph neural model of the present invention captures the semantic, topological, and structural context of the welding points more comprehensively, provides a high-quality prediction basis for subsequent reward value setting and subgraph selection, and improves the intelligence and credibility of weld recognition.

[0030] In this embodiment, it is characterized in that S3 specifically includes: S31. Construct a weighted candidate weld graph according to the weld prediction graph; S32. For each node in the weighted candidate weld graph , set its reward value as , represents the weld layout probability score output by the node in the graph neural network. The weld layout probability score is calculated by the graph neural network based on the spatial position of the node, the pipeline structure type, and its load level characteristics. The higher the node score, the more it indicates that the node needs to be preferentially selected; S33. For each edge , set the cost function of the edge . The cost function is calculated considering the following factors: ; Wherein, represents the connection length of the welding path, represents the connection angle, represents the welding accessibility coefficient, represents the material heterogeneity coefficient, , , , is a preset weighting coefficient; S34. Compare the reward value of the node with the cost Input into the reward and punishment Steiner tree algorithm, and use the greedy strategy for iterative screening. The goal of the reward and punishment Steiner tree algorithm is to select a subgraph that contains the optimal weld nodes and the shortest welding path to minimize the objective function which is: ; wherein, represents the set of selected weld nodes, represents the set of selected weld paths, and the first item represents the total cost of the selected path, and the second item is the penalty term for unselected nodes. By minimizing the objective function, the reward and punishment Steiner tree algorithm can select important weld nodes while optimizing the welding path, reduce the penalty of unselected nodes, and generate an optimized subgraph of the weld layout.

[0031] Based on the weld prediction graph, the present invention constructs a weighted candidate weld graph, maps the node scores to reward values, and maps the edge attributes to welding costs. The layout subgraph generation is realized through the reward and punishment Steiner tree algorithm, which solves the problem of the disconnection between weld point selection and path optimization in the prior art. By jointly modeling nodes and paths into the objective function and performing joint optimization, the present invention can minimize the welding path cost on the premise of ensuring the coverage of weld importance, and generate a weld layout scheme with a more stable structure and better weldability.

[0032] In this embodiment, it is characterized in that the reward and punishment Steiner tree algorithm of S34 adopts the greedy strategy specifically including: S341. Define the joint evaluation function of the reward and punishment Steiner tree algorithm for selecting the optimal combination of nodes and edges, wherein: ; wherein, is the minimum connection distance between node and the currently selected node set, is the adjustment coefficient to control the balance between path cost and structural connectivity; S342. In each round of selection, calculate the evaluation function value of each node and its connecting edge from the set of unselected nodes, select the node with the maximum evaluation function value and its corresponding connecting edge, add the node to the selected node set, and add the edge to the selected edge set; S343. Whenever a new node is selected, update the reward values of all unselected nodes. The specific update formula is: ; wherein, is the reward value of the unselected node, is the reward value for the updated unselected node, is the attenuation factor, is the node degree, is the number of currently selected nodes; S344. Through iteration, perform the above node selection and reward value update steps, select the optimal node in each round and update the path cost until the objective function reaches the minimum value; S345. When the objective function reaches the minimum or reaches the preset number of iterations, the algorithm terminates, and the optimized weld layout subgraph is output. This subgraph contains the optimal weld nodes and the shortest welding path.

[0033] The present invention introduces a greedy strategy based on node-edge combination into the reward and punishment Steiner tree algorithm. By jointly using the scoring function to balance the node reward value, edge cost, and connectivity distance, the optimal node expansion is realized round by round. At the same time, a reward value attenuation mechanism is constructed to avoid repeated selection of high-score nodes and ensure the overall rationality of the structure. Compared with the non-feedback and single-point drive strategies in the existing algorithms, the present invention provides a more intelligent node screening and path construction method, making the layout process highly dynamic, self-adaptive, and locally optimal controllable.

[0034] In this embodiment, it is characterized in that the said S4 specifically includes: S41. Construct a weld construction dependency digraph based on the weld layout subgraph generated by the reward and punishment Steiner tree algorithm; S42. Perform loop detection on the dependency digraph to obtain all sets of feedback edges that form a closed loop; S43. For each feedback edge, calculate the static feedback weight , and the static feedback weight is jointly defined based on the structural path cost and the difference in weld importance as: ; where, , are respectively the reward values of the two updated nodes, , is the weighting coefficient; S44. Adopt the minimum feedback arc set algorithm, and select the edge set with the minimum total cost for deletion according to the static feedback weight to obtain an acyclic weld sequence graph.

[0035] The present invention constructs a construction dependency graph based on the weld layout sub-graph, and through the feedback edge weight function, synthesizes the structural cost and the difference in weld bonus values to guide the minimum feedback arc set algorithm for loop elimination. This method breaks through the problems in traditional DAG construction that rely on static graph topology information and lack node semantic modeling, can more accurately identify the process logic conflict paths, improve the optimality of the directed dependency graph and the practicality of the welding process graph, and provide a theoretical guarantee for subsequent scheduling generation.

[0036] In this embodiment, it is characterized in that the S44 specifically includes: S441. Based on the set of feedback edges existing in the dependency directed graph, combined with the connection density of the weld nodes connected by each edge in the original structure diagram, the position hierarchy in the graph, and the key degree in the process path, calculate the path importance score, which is used to measure the structural and technological value of the dependency edge in the overall welding logic; S442. Define the comprehensive cost function of the feedback edge according to the basic structure weight of the feedback edge, the difference in node bonus values, the path importance, and the sequential tension index between nodes , specifically as follows: ; Wherein, is the path importance score, which synthesizes the connection degree and centrality of the node in the structure diagram, is the technological dependency tension between node pairs, which reflects the impact of sequential changes on the stability of the construction process, is the geometric distance of the node in the structure diagram, , is the adjustment parameter; S443. Select a group of edges with the minimum sum of the comprehensive cost function from the feedback edge set as the optimal feedback arc set, and delete it and output an acyclic weld sequence diagram.

[0037] The present invention defines a comprehensive cost function by introducing factors such as path importance, sequential tension, and structural hierarchy for the feedback edge, accurately measures the influence degree of each edge on the overall construction logic, and adopts a weighted strategy to select the optimal feedback arc set. Compared with the existing method that uses a single structure weight or static path length as the basis for loop resolution, the present invention incorporates structural semantics, weld strategy, and technological tension into the optimization scope, realizes a more scientific acyclic reconstruction of the dependency graph, and effectively prevents the destruction of process logic caused by incorrect edge deletion.

[0038] In this embodiment, it is characterized in that after the optimization of the feedback arc set, the acyclic weld sequence diagram in S5 is further fused with the construction reachability diagram to construct a directed acyclic graph of the construction sequence. Among them, the construction reachability diagram is generated based on the operation space layout, the reachable range of equipment, the spatial hierarchy of weld nodes, and the occlusion relationship between adjacent components. During the graph fusion process, all physically executable paths are retained, and the directed edges conflicting with the actual construction path are deleted.

[0039] The present invention fuses the weld sequence diagram with the construction reachability diagram, comprehensively considers the space layout, the operation range of equipment, and the weld occlusion relationship, screens and retains the physically feasible paths, and generates a directed acyclic graph of the construction sequence. This mechanism enables the system to transition from "theoretically feasible sequence" to "engineerable implementation", avoids the problem that the graph structure is logically correct but the on-site construction is unreachable, significantly enhances the executability, reliability, and engineering adaptability of the weld scheduling diagram, and improves the feasibility of the system in actual projects.

[0040] In this embodiment, it is characterized in that S5 specifically includes: S51. Construct a residual conflict graph according to the difference set between the directed acyclic graph of the construction sequence and the directed dependency graph of the weld construction; S52. Count the number of feedback edges involved in each node as the starting point or the ending point in the residual conflict graph, and calculate its node conflict frequency coefficient , defined as: ; Among them, represents the number of feedback edges associated with the node , is the degree value of this node in the weld layout subgraph, and is normalized; S53. For each edge in the feedback edge set, calculate its path dynamic conflict intensity , which is defined as: ; Among them, is the static feedback weight, is the conflict weight adjustment coefficient, representing the amplification factor of the node conflict degree on the path conflict cost; S54. Use the node conflict frequency coefficient and the path dynamic conflict intensity as conflict feedback information to guide the adaptive adjustment of the reward value function and the cost function .

[0041] The present invention introduces a residual conflict graph to explicitly model the conflict between sequential dependence and structural prediction, and constructs a node conflict frequency coefficient and a path conflict intensity function to provide accurate quantitative indicators for subsequent reward value and cost adjustment. Compared with the "unaware" conflict feedback in traditional weld optimization, the present invention realizes a closed-loop mapping mechanism for sequential-structural conflict feedback, which helps to accurately identify key conflict regions and nodes, thereby improving the convergence efficiency, conflict suppression ability and overall stability of the optimization system.

[0042] In this embodiment, it is characterized in that the S6 specifically includes: Adapting the reward value function according to the node conflict feedback coefficient to generate a reward value function after conflict response , defined as: ; where is a reward value weakening factor, is a non-linear control exponent; Replacing the original reward value with the updated reward value , updating the node attributes in the weighted candidate weld graph, and adjusting the evaluation function of the greedy strategy in the reward-punishment Steiner tree algorithm.

[0043] The present invention adjusts the node reward value according to the conflict feedback coefficient, introduces a non-linear attenuation function to control the amplitude of the reward value update, and realizes the intelligent dynamic adjustment of the node selection weight. By updating the evaluation function in the greedy strategy, the present invention realizes a conflict-oriented controllable feedback mechanism. Compared with the traditional single-score-driven node evaluation method, this mechanism significantly improves the system's response ability and learning ability to conflict regions, enhances the algorithm's precision control and feedback adaptation ability, and provides a solid foundation for iterative optimization.

[0044] In this embodiment, it is characterized in that the S8 strategy classification has four types, and the iteration is terminated as long as any one of the four strategies is satisfied. Specifically, it includes: Strategy I, the acyclicity fully satisfied strategy: the construction sequence graph generated in the current round is a directed acyclic graph, and all node conflict frequency coefficients derived from the residual conflict graph all satisfy , where is the node conflict threshold; Strategy II, the structural strength constraint strategy: all connection paths in the current weld layout subgraph satisfy the minimum connected redundancy defined in the structural mechanics model, that is: ; where represents the number of the shortest equivalent redundant paths of the node in the structure diagram; Strategy III, Structural Change Convergence Strategy: The structural difference degree between the current layout diagram and the previous-round layout diagram satisfies: ; wherein, is the structural convergence threshold, represents the symmetric difference, is the node set of the th round, is the node set of the th round, is the edge set of the th round, is the edge set of the th round, represents the number of elements; Strategy IV, Maximum Round Limit Strategy: If the iteration round reaches the preset maximum round upper limit , the iteration is forced to terminate.

[0045] The present invention proposes four types of termination strategies including full satisfaction of acyclicity, structural strength constraint, structural change convergence, and maximum round number control, which are used to judge the reasonable termination timing of feedback iteration. This strategy set takes into account process legality, structural stability, and algorithm efficiency. Compared with the termination mechanisms using fixed rounds or single error indicators in the prior art, it has stronger precision control and flexible adjustment capabilities, significantly improving the controllability, robustness, and engineering practicability of the weld optimization process.

[0046] Example 1: To verify the feasibility and performance advantages of the present invention in actual engineering scenarios, the method of the present invention is applied to the weld construction of the high-pressure ring network pipeline in the second-phase project of a coastal natural gas liquefaction and treatment base. The core pipe network layout structure of this project is complex, the total length of the overall pipeline exceeds 4.3 kilometers, involving 17 large flange connection sections and nearly a hundred multi-branch intersection nodes, and there are a series of practical problems such as high weld task density, serious pipe segment occlusion, and complex construction paths. Traditional weld layout planning methods have repeatedly encountered problems such as layout fragmentation, serious path redundancy, and construction sequence conflicts in this project, seriously affecting the continuity of the welding process and the construction rhythm.

[0047] In this project, the technical team first obtained a complex pipeline structure model exported by a three-dimensional laser scanning and modeling system, and used the method of the present invention to perform graph structure conversion on this model. In the converted graph structure, each node corresponds to a potential weld point, the node attributes cover spatial coordinates, pipe section types, and load-bearing grades, and the edge attributes reflect the welding connection length, angle, accessibility, and material heterogeneity. Subsequently, the graph structure was input into the constructed graph neural network model for feature extraction and weld score prediction. 82 weld nodes with engineering weldability value were successfully identified, and their layout probability scores were given, forming a preliminary weld prediction graph.

[0048] Based on the prediction graph, the method of the present invention further constructed a weighted candidate weld graph, and applied the reward-punishment Steiner tree algorithm combined with the reward-value - cost joint scoring strategy to dynamically screen weld nodes and paths. Through this algorithm, the system preferentially retained nodes with critical structural positions, high reward values, and low path costs, and fully considered construction connection risks and welding tensions in the cost function. Different from the traditional shortest path method, the present invention introduced a feedback adjustment mechanism in the node selection process, and adaptively adjusted the reward value based on path-dependent tension and conflict feedback, thus avoiding occlusion conflicts and welding sequence conflicts that occurred in the early selection.

[0049] During the optimization process, the system went through 2 rounds of conflict feedback adjustment iterations, automatically eliminated 3 redundant connection paths that caused construction occlusion and sequence chaos, and finally output a weld layout plan with a structural stability score of 91.2, and constructed an acyclic construction sequence graph. During the process of the construction unit verifying the plan, the proposed layout and scheduling graph was determined by the on-site welding team as "no need to adjust the sequence again and has direct constructability", and was successfully applied to the welding subsystems of the 3rd and 4th modules of the project and achieved efficient implementation.

[0050] In the comparative experiment, the technical team also used the traditional graph optimization module in a well-known industrial software to analyze the weld layout in the same scenario. Although the initial weld graph can be quickly output under this method, its prediction accuracy is less than 85%. There are multiple loops in the final sequence graph, and it is necessary to manually adjust the sequence logic about 8 times on-site. The average scheduling planning time is 17 seconds more than that of the method of the present invention, and the structural connection stability score is less than 70 points, which affects the continuous scheduling of the subsequent process path and the construction rhythm.

[0051] The specific experimental data are sorted out in the following table, clearly reflecting the advantages of the present invention in key indicators such as weld node recognition accuracy, optimization convergence speed, and construction scheduling feasibility: Table 1: Performance comparison data between the method of the present invention and the traditional method in the actual engineering scenario ; According to the indicators listed in Table 1, it can be clearly seen that the method of the present invention has significant advantages over the traditional graph optimization method in multiple key dimensions.

[0052] First of all, in terms of the accuracy of weld joint identification, the method of the present invention correctly predicted 78 out of a total of 82 weld joints, and the prediction accuracy rate reached 95.12%. While the traditional method only identified 65 accurate joints, with an accuracy rate of 83.33%. This shows that the graph neural network model constructed by the present invention has stronger learning and expression capabilities in the node attribute extraction and scoring links, can effectively identify high-value weld points, and avoid the omission or misjudgment of key welds.

[0053] Secondly, in terms of the optimization of the construction path, the total number of paths generated by the method of the present invention is 136, which is less than the 143 paths of the traditional method, and the number of feedback conflicts has decreased significantly, from 12 times to only 3 times. It shows that through the combination of the reward and punishment Steiner tree algorithm and the feedback adjustment mechanism, redundant paths and logical conflicts between paths are effectively avoided, and the overall simplicity and logical consistency of the layout structure are improved.

[0054] In terms of optimization efficiency, the average layout optimization time of the method of the present invention is 26.4 seconds, which is shortened by more than 39.7% compared with the 43.8 seconds of the traditional method. This not only improves the operation efficiency of the optimization process, but also reduces the resource cost of deployment and operation in large-scale industrial projects. At the same time, the constructability rate of the layout plan has increased from 87.4% to 98.6%, fully reflecting the comprehensive ability of the present invention in considering physical accessibility, structural occlusion and process sequence consistency.

[0055] In addition, from the perspective of the final scheduling results, the sequential graph generated by the traditional method has loops and needs to be adjusted manually, and its structural stability score is only 68.7. While the sequential graph generated by the present invention is a directed acyclic structure, and the structural stability score is as high as 91.2, indicating that it is more in line with the engineering structure connection logic and on-site welding process requirements. In terms of feedback convergence, the method of the present invention only needs 2 rounds of iteration to complete the optimization, while the traditional method requires at least 5 rounds, further verifying the accelerating effect of the feedback adjustment module on conflict correction and iterative convergence.

[0056] In summary, the present invention is significantly superior to the prior art in many aspects such as weld joint prediction, path optimization, conflict adjustment, convergence efficiency and structural stability, and has extremely high engineering feasibility, system intelligence and on-site adaptability. It is an innovative method with practical value and technical prospects in the field of intelligent analysis of welds and construction scheduling for complex pipeline structures.

[0057] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, shall be covered by the protection scope of the present invention.

Claims

1. An intelligent analysis method for weld layout of complex pipeline structures based on graph neural network, characterized in that: The steps include: S1. Obtain the three-dimensional model data of the complex pipeline structure and construct a graph structure; S2. Input the graph structure into the graph neural network model, extract node features, generate the weld layout probability score of each node, and obtain the weld prediction graph; S3. Based on the weld prediction graph, a weighted candidate weld graph is constructed, node scores are mapped to bonus values, edge attributes are mapped to welding costs, and a reward-penalty Steiner tree algorithm is introduced. A greedy strategy is adopted to generate a weld layout subgraph. S4, constructing a directed dependency graph of weld construction based on the weld layout subgraph, using the minimum feedback arc set algorithm to eliminate loops in the graph, and generating a directed acyclic graph of construction sequence; S5. construct a residual conflict graph based on the removed edges of the construction sequence directed acyclic graph, count the participation frequency of the conflict nodes, and calculate the conflict feedback information; S6. adjusting the reward value of the corresponding node in the weighted candidate weld diagram according to the conflict feedback coefficient, and adjusting the weight of the conflicting node in the weld selection; S7, re-inputting the updated reward value into the reward-penalty Steiner tree algorithm, and iteratively generating a new weld layout subgraph; S8. Repeat S4 to S7, classify the iterative result strategies, until the structural strength and construction sequence non-cyclic constraints are met, and output the final weld layout diagram.

2. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 1 is characterized in that: The S2 specifically includes: inputting the graph structure into the graph neural network model, assigning a node attribute vector including spatial coordinates, structural type and load-bearing level to each node, assigning an edge attribute vector including connection length, connection angle, welding accessibility and material heterogeneity to each edge, the graph neural network model performs graph convolution processing of no less than three layers of graph convolution layers on the above attribute vectors, extracts features from the node attribute vectors in turn, scores each node through a classifier, generates a weld layout probability score corresponding to each node, and forms a weld prediction map.

3. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 1 is characterized in that: The S3 specifically includes: S31, constructing a weighted candidate weld map according to the weld prediction map; S32, for each node in the weighted candidate weld diagram , set its reward value to , Representation Node The weld placement probability score output in the graph neural network is calculated by the graph neural network based on the spatial position of the node, the pipeline structure type and its load-bearing grade characteristics. The higher the node score, the more priority the node needs to be selected. S33, for each side , set the cost function of the edge ,The cost function is calculated as a weighted fusion of the connection length of the welding path, the connection angle, the welding accessibility coefficient, and the material heterogeneity coefficient; S34. The reward value of the node The cost of the edge The input is fed into the reward-penalty Steiner tree algorithm, and the greedy strategy is used for iterative screening. The goal of the reward-penalty Steiner tree algorithm is to select a subgraph that contains the optimal weld nodes and the shortest welding path to minimize the objective function for: ； in, Represents the selected weld node set, Represents the selected weld path collection.

4. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 3 is characterized in that: The reward-penalty Steiner tree algorithm of S34 adopts a greedy strategy, specifically including: S341. Define the joint evaluation function of the reward-penalty Steiner tree algorithm , used to select the optimal combination of nodes and edges; S342. In each round of selection, the evaluation function value of each node and its connecting edge is calculated from the set of unselected nodes. , select the node with the maximum evaluation function value and its corresponding connecting edge, add the node to the selected node set, and add the edge to the selected edge set; S343. Whenever a new node is selected, the reward values ​​of all unselected nodes are updated. The specific update formula is: ； in, is the reward value of the unselected node, is the reward value of the updated unselected node, is the attenuation factor, For Node The degree, is the number of currently selected nodes; S344, through iteration, execute the above node selection and reward value update steps, select the best node and update the path cost in each round, until the objective function Reach a minimum value; S345. When the objective function reaches the minimum or reaches the preset number of iterations, the algorithm terminates and outputs the optimized weld layout subgraph, which contains the optimal weld nodes and the shortest welding path.

5. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 1 is characterized in that: The S4 specifically includes: S41, constructing a weld construction dependency directed graph based on the weld layout subgraph generated by the reward-penalty Steiner tree algorithm; S42, performing loop detection on the dependency directed graph to obtain a set of all feedback edges constituting a closed loop; S43. For each feedback edge, calculate the static feedback weight , the static feedback weight is defined based on the joint structure path cost and weld importance difference as: ； in, , are the updated rewards of the two nodes respectively, , is the weighting coefficient; S44, using the minimum feedback arc set algorithm, based on the static feedback weight The edge set with the smallest total cost is selected for deletion to obtain a weld sequence graph without a cycle.

6. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 5 is characterized in that: The S44 specifically includes: S441. Based on the feedback edge set existing in the dependency directed graph, the path importance score is calculated in combination with the connection density of the weld nodes connected by each edge in the original structure graph, the position level in the graph, and the criticality in the process path, so as to measure the structural and process value of the dependency edge in the overall welding logic; S442. Define the comprehensive cost function of the feedback edge based on the basic structural weight of the feedback edge, the node reward difference, the path importance, and the sequential tension index between nodes. , as follows: ； in, Score the importance of the path, integrating the connectivity and centrality of the node in the structure graph. is the process dependency tension between node pairs, reflecting the impact of sequence changes on the stability of the construction process. is an exponential function, is the geometric distance of the node in the structure graph, , To adjust the parameters; S443. Select comprehensive cost function from feedback edge set The set of edges with the smallest sum is taken as the optimal feedback arc set, which is deleted to output a weld sequence diagram without loops.

7. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 1 is characterized in that: The acyclic weld sequence graph in S5 is further fused with the construction accessibility graph after the feedback arc set optimization is completed to construct a directed acyclic graph of the construction sequence, wherein the construction accessibility graph is generated based on the layout of the working space, the reachable range of the equipment, the spatial hierarchy of the weld nodes, and the occlusion relationship of adjacent components. During the graph fusion process, all physically executable paths are retained, and directed edges that conflict with the actual construction paths are deleted.

8. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 1 is characterized in that: The S5 specifically includes: S51, constructing a residual conflict graph according to the difference set of the construction sequence directed acyclic graph and the weld construction directed dependency graph; S52. Statistics of each node The number of feedback edges involved as the starting point or end point in the residual conflict graph, and the node conflict frequency coefficient is calculated ; S53, for each edge in the feedback edge set , calculate the dynamic conflict intensity of its path , defined as: ； in, is the static feedback weight, is the conflict weight adjustment coefficient, which represents the amplification factor of the node conflict degree on the path conflict cost; S54, node conflict frequency coefficient Dynamic conflict strength of paths As conflict feedback information, guide the reward function With the cost function Adaptive adjustment.

9. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 1 is characterized in that: S6 specifically includes: adjusting the reward function according to the node conflict feedback coefficient Make adaptive adjustments to generate reward functions after conflict response , defined as: ； in, is the reward weakening factor, is the nonlinear control index; The updated reward value Replace the original reward value , update the node attributes in the weighted candidate weld graph, and adjust the evaluation function of the greedy strategy in the reward-penalty Steiner tree algorithm.

10. The intelligent analysis method for weld layout of complex pipeline structure based on graph neural network according to claim 1 is characterized in that: There are four types of S8 strategies. If any one of the four strategies is met, the iteration is terminated, including: Strategy I, acyclicity fully satisfies the strategy: the construction sequence graph generated in the current round is a directed acyclic graph, and the conflict frequency coefficients of all nodes derived from the residual conflict graph are All meet ,in, is the node conflict threshold; Strategy II, structural strength constraint strategy: All connection paths in the current weld layout subgraph satisfy the minimum connectivity redundancy defined in the structural mechanics model. ,Right now: ； in, Indicates the number of shortest equivalent redundant paths of a node in the structure graph; Strategy III, structural change convergence strategy: the structural difference between the current layout and the previous layout satisfy: ； in is the structural convergence threshold, represents the symmetric difference, For the Wheel node set, For the Wheel node set, For the Wheel side collection, For the Wheel side collection, Indicates the number of elements; Strategy IV, maximum round limit strategy: If the iteration round Reached the preset maximum round limit , the iteration is forced to terminate.

Images