An Automatic Detection and Correction Method for Pipeline Network Conflicts

Abstract

This invention relates to the field of data processing technology and discloses an automatic detection and annotation correction method for pipeline network conflicts. The method includes: collecting pipeline data, identifying pipeline components and environmental components, and establishing a unified data model of the pipeline network; constructing a topology-enhanced pipeline network graph, and simultaneously establishing a standard rule base and an annotation consistency constraint base; calculating the spacing and attribute relationships between nodes and identifying target conflict records; generating a pipeline simulation model to simulate the local pipeline network and comparing it with performance indicators to obtain simulation anomaly areas; verifying annotation attributes and generating annotation anomaly records; obtaining an annotation correction scheme with the optimization objective of reducing annotation modifications and remaining target conflicts; and updating the annotation attributes in the data model and network graph according to the annotation correction scheme. This application reduces the amount of annotation modifications, lowers residual conflicts and performance anomalies, and improves the consistency and accuracy of pipeline network design data.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method for automatic detection and annotation correction of pipeline network conflicts. Background Technology

[0002] With the widespread application of Building Information Modeling (BIM) and computer simulation technologies in building water supply and drainage, HVAC, and industrial piping engineering, the design of piping networks relies on 3D models and computer-based data processing workflows to improve the efficiency of integrated pipeline layout and construction accuracy. In current engineering practice, designers typically create piping models in BIM software and use computer programs for collision detection, icon annotation, and hydraulic or thermal simulations. This allows the geometric relationships, construction positioning information, and operational performance of the piping network to be analyzed and adjusted within the same digital environment.

[0003] However, existing technologies often handle geometric conflict detection, construction positioning annotation, and pipeline network simulation in a fragmented manner, lacking a computer processing flow based on a unified data model that links conflict detection results, simulation performance indicators, and annotation attribute correction. For example, patent CN115130256A discloses a 3D pipeline optimization method based on hierarchical bounding box collision detection, which can identify pipeline collisions in a 3D scene and assist in optimizing spatial layout, but it does not include annotation attributes such as pipe diameter, elevation, and medium in the constraints, nor does it automatically correct the annotations based on simulation results. Patent CN110851956B proposes an automated calculation, annotation, and drawing method for pipeline construction positioning information in construction projects, focusing on quickly generating pipeline elevation, length, and distance annotations to civil engineering components in a building information modeling environment, but it does not verify the consistency of annotation attributes with design specifications, flow rate, pressure drop, and other performance indicators, nor does it automatically eliminate conflicts by treating annotation attributes as variables through multi-objective optimization.

[0004] Therefore, it is necessary to design an automatic detection and annotation correction method for pipeline network conflicts to solve the problems existing in the current technology. Summary of the Invention

[0005] In view of this, the present invention proposes an automatic detection and annotation correction method for pipeline network conflicts, which aims to solve the problems in the prior art where geometric conflict detection, pipeline simulation and annotation verification are separated, and it is impossible to simultaneously detect conflicts, diagnose annotation errors and provide correction solutions under a unified data model.

[0006] This invention proposes an automatic collision detection and annotation correction method for pipeline networks, comprising: Collect pipeline data, identify pipeline components and environmental components based on the pipeline data, and establish a unified data model of the pipeline network; Based on the unified data model of the pipeline network, a topology-enhanced pipeline network graph is constructed with the pipeline components and the environmental components as nodes and the connectivity and proximity relationships as edges. At the same time, a standard rule base and a label consistency constraint base are established. Based on the topology-enhanced pipeline network graph, the spacing and attribute relationships between nodes are calculated, and target conflict records are identified according to the standard rule base. A pipeline simulation model is generated based on the unified data model of the pipeline network. The local pipeline network involved in the target conflict record is simulated. The simulation results are compared with the performance indicators in the standard rule base to obtain the simulation abnormal area. Based on the annotation consistency constraint library and the simulation abnormal area, the annotation attributes of the pipeline components are verified. When the annotation attributes cause both the annotation consistency constraint to be unsatisfied and the simulation result to deviate from the target working condition, an annotation abnormal record is generated. For each of the aforementioned annotation anomaly records, the annotation attribute corresponding to the annotation anomaly record is set as a variable to be optimized, and the specification rule base and annotation consistency constraint base are transformed into constraint conditions. The optimization objective is to reduce the conflict between annotation modification and remaining objectives. An annotation correction scheme is obtained through a multi-objective optimization algorithm. Update the annotation attributes in the unified data model of the pipeline network and the topology-enhanced pipeline network diagram according to the annotation correction scheme.

[0007] Furthermore, when collecting pipeline data, identifying pipeline components and environmental components based on the pipeline data, and establishing a unified data model for the pipeline network, the process includes: Based on drawings and measurement data, the system collects graphic elements and measurement points representing pipelines, unifies spatial coordinates and units for data from different sources, identifies components with fluid transport functions as pipeline components, and identifies building beams, slabs, walls, columns, foundations, and equipment support components as environmental components. Based on the connectivity, attachment, and crossing relationships between graphic elements, the system establishes the association between pipeline components and environmental components, and stores the geometric information, labeling attributes, system information, and association relationships of the pipeline components into the unified data model of the pipeline network according to a unified data structure.

[0008] Furthermore, when constructing a topology-enhanced pipeline network graph based on the unified data model of the pipeline network, and simultaneously establishing a standard rule base and a label consistency constraint base, the process includes: mapping each pipeline component and each environmental component in the unified data model of the pipeline network to a node, mapping the connection relationship representing the flow of the medium to a connected edge, and mapping the relationship representing the crossing relationship, the attachment relationship, or the relationship where the distance is less than a preset proximity threshold to a proximity edge. While establishing the topology-enhanced piping network diagram, the spacing, flow, and pressure requirements for different system types, media types, and temperature levels in the design specifications are compiled into rule entries in the specification rule base. The allowable value combinations between pipe diameter, elevation, and media are compiled into constraint entries in the annotation consistency constraint library.

[0009] Furthermore, when calculating the spacing and attribute relationships between nodes based on the topology-enhanced pipeline network graph, and identifying target conflict records according to the standard rule base, the process includes: The topology-enhanced pipeline network graph is divided into several detection regions, and nodes located in the same detection region or in adjacent detection regions and connected by connecting edges or adjacent edges are combined into candidate node pairs. For each candidate node pair, the minimum clearance is calculated based on the geometric boundaries of the corresponding pipe or environmental component, and the relative positional relationship is determined. At the same time, the system type, medium type, temperature level, and pressure level corresponding to the candidate node pair are read, and the spacing requirements and prohibited contact conditions are retrieved from the specification rule base. When the minimum clearance is less than the spacing requirement or the relative positional relationship violates the prohibited contact condition, the candidate node pair is recorded as a target conflict record, and the conflict type and conflict severity are marked in the target conflict record.

[0010] Furthermore, when generating a pipeline simulation model based on the unified pipeline network data model, the process includes: The simulation nodes and simulation pipe segments are determined based on the connectivity between the pipeline components and the environmental components. The pipe diameter, length, inner wall characteristics, elevation, and medium properties of each simulation pipe segment are used as simulation parameters. The corresponding design conditions, inlet boundary conditions, and outlet boundary conditions are extracted from the standard rule base according to the system type to which the pipeline components belong. The simulation nodes, simulation pipe segments, and boundary conditions are combined to form the pipeline simulation model.

[0011] Furthermore, when comparing the simulation results with the performance metrics in the specified rule base to identify simulation anomaly regions, the following steps are taken: Centered on the node corresponding to each target conflict record, adjacent simulation nodes and adjacent simulation pipe segments are selected within a preset range along the connectivity relationship to form a local simulation subnet. In the pipeline simulation model, the flow distribution, pressure drop distribution, or temperature distribution of the local simulation subnet is calculated. The flow velocity range, pressure drop range, and temperature range corresponding to the local simulation subnet are queried from the standard rule base. The simulation results are compared segment by segment with the ranges in the standard rule base. When the simulation results exceed any range, the corresponding simulation node and simulation pipe segment are divided into simulation abnormal areas.

[0012] Furthermore, when verifying the annotation attributes of the pipeline components and generating annotation anomaly records based on the annotation consistency constraint library and simulation anomaly regions, the process includes: For each simulation anomaly region, the annotation attributes of the pipe components in the simulation anomaly region are selected. The annotation attributes include pipe diameter, elevation, medium type, and pressure rating. The value relationship of the annotation attributes between adjacent pipe components and the matching relationship with the system type are checked according to the annotation consistency constraint library. When the check result does not meet the annotation consistency constraint library and the pipe component with the corresponding annotation attribute is located in the simulation anomaly region, the annotation attribute and the corresponding pipe component are recorded as an annotation anomaly record, and the annotation anomaly record is associated with and stored with the performance index that caused the simulation anomaly.

[0013] Furthermore, for each of the aforementioned annotation anomaly records, the annotation attribute corresponding to the annotation anomaly record is set as a variable to be optimized. When converting the specification rule base and annotation consistency constraint base into constraint conditions, the following steps are included: Starting with the pipe component corresponding to the anomaly record, pipe components that are located within the simulation anomaly region and directly connected to the pipe component are selected along the connectivity and proximity relationships in the topology-enhanced pipe network diagram as the set of pipe components to be optimized. The pipe diameter label, elevation label, medium type label, and pressure level label in the set of pipe components to be optimized are set as variables to be optimized. The spacing requirements, flow rate requirements, and pressure requirements in the specification rule base, as well as the allowed value combination relationships in the label consistency constraint base, are respectively transformed into value range constraints and interrelationship constraints acting on the variables to be optimized, forming a set of local optimization constraints.

[0014] Furthermore, when obtaining a label correction scheme through a multi-objective optimization algorithm with the optimization objective of reducing label modifications and conflicts with remaining targets, the following are included: Multiple candidate annotation correction schemes are generated based on the local optimization constraint set. For each candidate annotation correction scheme, the number of modified annotation attributes, the offset of each annotation attribute relative to the original annotation, the number of remaining target conflict records and the severity of the conflict are counted. The statistical results are combined into a comprehensive evaluation index according to a preset weight. Based on the iterative search algorithm, the annotation correction scheme with the highest comprehensive evaluation index and satisfying all local optimization constraint sets is selected as the final annotation correction scheme.

[0015] Furthermore, when updating the annotation attributes in the unified data model of the pipeline network and the topology-enhanced pipeline network diagram according to the annotation correction scheme, it includes: For each pipeline component to be optimized in the annotation correction scheme, the corrected annotation attributes are written into the unified data model of the pipeline network, and the annotation attributes of the corresponding nodes in the topology-enhanced pipeline network diagram, as well as the simulation parameters and conflict detection parameters determined by the annotation attributes, are updated simultaneously. The nodes affected by the annotation correction and their adjacent nodes within a preset range are marked as nodes to be recalculated. The local simulation subnet where the nodes to be recalculated are located is re-simulated and the target conflict record is identified. The annotation attributes before correction, the annotation attributes after correction, the relevant target conflict records, and the corresponding simulation abnormal areas are stored in the case library.

[0016] Compared with existing technologies, the advantages of this invention are as follows: Based on a unified pipeline network data model and topology-enhanced pipeline network diagram, geometric conflict detection, standard rule verification, simulation performance analysis, and annotation attribute correction are integrated into a closed-loop processing flow. By constraining the spacing and attribute relationships between nodes through a standard rule library and an annotation consistency constraint library, automatic screening and classification of target conflict records are achieved. Then, the pipeline simulation model is used to simulate the working conditions of the local pipeline network involved in the target conflict records. The abnormal simulation areas and annotation consistency verification results are jointly used to determine the abnormal annotation records, avoiding misjudgments and omissions caused by relying solely on geometric relationships or simple rules. The annotation attributes corresponding to the abnormal annotation records are explicitly set as variables to be optimized, and the standard rule library and annotation consistency constraint library are transformed into constraint conditions. With reducing annotation modifications and remaining target conflicts as the joint optimization objectives, a multi-objective optimization algorithm is used to automatically generate annotation correction schemes, and the correction results are written back to the unified pipeline network data model and topology-enhanced pipeline network diagram. This reduces the workload of manual adjustments and the number of repeated modifications while ensuring that design specifications and simulation performance requirements are met, thereby improving the accuracy and consistency of pipeline network design data. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 The flowchart illustrates the automatic detection and annotation correction method for pipeline network conflicts provided in this embodiment of the invention. Detailed Implementation

[0018] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] In the design process of building information modeling (BIM) and computer simulation technologies for building water supply and drainage, HVAC, and industrial pipeline engineering, geometric conflict detection, construction positioning annotation, and pipeline network simulation are handled in a fragmented manner, lacking an automatic linkage mechanism based on a unified data model. This results in the annotation attributes of pipeline components failing to achieve dynamic consistency with design specifications and simulation performance indicators. Specifically, the annotation attributes are not included in the closed-loop verification process of conflict detection results and simulation analysis, leading to a disconnect between design data and the digital environment. This results in reduced overall efficiency and construction accuracy in pipeline network layout, manifesting as a mismatch between annotation information and the interaction requirements of fluid transport functions and building structures, thereby affecting the continuity of design iterations and the reliability of construction positioning.

[0020] For example, in the design of the HVAC piping system for a large commercial complex project, designers used Building Information Modeling (BIM) software to construct a 3D piping model and performed collision detection to identify geometric conflicts between ducts and structural beams. Furthermore, pipe elevation and diameter annotations were automatically generated, but these annotations were not linked to the hydraulic simulation process. When performing local flow and pressure drop simulations on the conflict area, the annotated pipe diameter values ​​caused the simulation results to deviate from the performance specifications stipulated in the design code. However, due to the lack of a linkage verification mechanism between the annotation attributes and the simulation results, the annotation anomalies were not automatically identified and corrected. Consequently, during the construction drawing delivery stage, the inconsistency between the annotation attributes and actual operational requirements became apparent, increasing the complexity of on-site construction coordination and the possibility of design rework. Specifically, the pipe installation positions needed to be repeatedly adjusted to meet performance requirements, and the efficiency of verifying the spatial relationship between construction positioning information and civil engineering components decreased.

[0021] If the aforementioned issues are not addressed, the organic integration of conflict detection results, simulation performance indicators, and annotation attribute corrections will be impossible in pipeline network design, leading to design errors manifesting during the construction phase. Specifically, the persistent inconsistency between annotation attributes and design specifications will prevent the synchronous updating of pipeline component geometric relationships, construction positioning information, and operational performance within a unified data model. This results in frequent engineering changes, construction delays, and decreased pipeline network reliability. Furthermore, the decentralized processing mechanism causes conflict detection to focus solely on geometric spatial relationships while ignoring performance constraints. Simulation analysis cannot drive automatic correction of annotation attributes, ultimately compromising the integrity of design data in the digital environment and impacting the overall project's quality control and delivery efficiency.

[0022] For this, please refer to Figure 1 As shown, this application proposes an automatic detection and annotation correction method for pipeline network conflicts, including: S100: Collect pipeline data, identify pipeline components and environmental components based on the pipeline data, and establish a unified data model of the pipeline network.

[0023] S200: Construct a topology-enhanced pipeline network graph based on the unified data model of pipeline networks, with pipeline components and environmental components as nodes and connectivity and proximity relationships as edges, and establish a standard rule base and a label consistency constraint base.

[0024] S300: Calculates the spacing and attribute relationships between nodes based on the topology-enhanced pipeline network graph, and identifies target conflict records according to the standard rule base.

[0025] S400: Generate a pipeline simulation model based on the unified pipeline network data model, simulate the local pipeline network involved in the target conflict record, compare the simulation results with the performance indicators in the specification rule base, and obtain the simulation anomaly area. Based on the annotation consistency constraint library and the simulation anomaly area, verify the annotation attributes of pipeline components. When the annotation attributes simultaneously cause the annotation consistency constraint to be unsatisfied and the simulation result to deviate from the target working condition, generate an annotation anomaly record.

[0026] S500: For each annotation anomaly record, the annotation attribute corresponding to the annotation anomaly record is set as the variable to be optimized, and the standard rule base and annotation consistency constraint base are transformed into constraint conditions. The goal is to reduce the conflict between annotation modification and remaining objectives. An annotation correction scheme is obtained through a multi-objective optimization algorithm.

[0027] S600: Update the annotation attributes in the unified data model of the pipeline network and the topology-enhanced pipeline network diagram according to the annotation correction scheme.

[0028] This application relates to an automatic detection and annotation correction method for pipeline network conflicts. The unified data model for the pipeline network refers to a data structure used to centrally store pipeline components, environmental components, and their relationships. This model can be implemented using a relational database or a graph database. For example, MySQL can be used to construct tables to store component geometric information and attribute data, or Neo4j can be used to establish a node and relationship model to represent the connectivity and attachment relationships between components. Its main purpose is to provide a unified data foundation to support the conflict detection and simulation process. Specifically, the model construction process can be based on multi-source data input, such as manually entering design parameters or calling external data interfaces to obtain construction information, thereby ensuring data integrity. Furthermore, the topology-enhanced pipeline network graph refers to a graph structure with pipeline components and environmental components as nodes and connectivity and adjacency relationships as edges. This can be implemented using adjacency matrices or graph computation frameworks. For example, the NetworkX library can be used to define node attributes and edge types, or spatial indexing technology can be used to automatically generate adjacent edges. Its main purpose is to quantitatively express the geometric and logical relationships between components, facilitating spacing calculation. In a preferred implementation, the specification rule base and the annotation consistency constraint base refer to collections storing design specification rules and annotation attribute constraints, respectively. The specification rule base can be implemented using XML files, for example, encoding different types of spacing requirements into structured data. The annotation consistency constraint base can be implemented using a rule engine, for example, defining logical combination rules for pipe diameter and medium type, primarily to provide a basis for conflict identification and verification. In practical applications, annotation attribute verification refers to the process of generating anomaly records when annotation attributes simultaneously trigger annotation consistency constraint violations and simulation results deviating from the target working condition. This can be implemented using a logical judgment module, for example, verifying the matching of attribute values ​​with simulation outputs through Boolean expressions, or detecting anomalies based on threshold comparison mechanisms, primarily to accurately locate annotation problems that need correction. Therefore, the multi-objective optimization algorithm refers to a solution method that aims to minimize the amount of annotation modification and the number of remaining conflicts. It can be implemented using genetic algorithms or simulated annealing, for example, applying the NSGA-II algorithm to iteratively search the feasible solution space, or handling constraints through linear programming models, primarily to generate annotation correction schemes that satisfy multi-objective balance. This application uses a unified data model of pipeline networks as the core hub to integrate geometric conflict detection, performance simulation and annotation correction processes into an automatic linkage processing mechanism. This achieves closed-loop processing of conflict detection results, simulation performance indicators and annotation attribute correction, thereby solving the problems in the prior art where the annotation attributes are out of touch with the design specifications and the simulation results cannot drive automatic correction due to the decentralized processing of each link.

[0029] In the pipeline network design process, the data acquisition phase utilizes Building Information Modeling (BIM) drawings and on-site measurement equipment to obtain pipeline graphic elements and measurement point information. Data from different sources undergoes spatial coordinate unification and unit standardization. Components with fluid transport functions are identified as pipeline components, while structural components such as building beams, slabs, and walls are identified as environmental components. A correlation mapping is established based on the connectivity, attachment, and crossing relationships between graphic elements, ultimately forming a unified pipeline network data model containing geometric information, annotation attributes, and system information. Further, this unified data model is converted into a topology-enhanced pipeline network graph, where pipeline components and environmental components serve as nodes. The connection relationships of medium flow constitute connected edges, while crossing, attachment, or distances less than a proximity threshold constitute proximity edges. Simultaneously, the specification rule base integrates spacing, flow rate, and pressure requirements for different system types, while the annotation consistency constraint library stores the permissible combinations of pipe diameter, elevation, and medium. Based on this topology, the minimum clearance and relative positional relationships between nodes are obtained through geometric boundary calculations. Conflict determination is performed by combining the spacing requirements and prohibited contact conditions in the specification rule base. When the minimum clearance is insufficient or the positional relationship violates the rules, a target conflict record is generated. In this process, for the local areas involved in the target conflict records, a unified data model for pipeline networks is used to construct a pipeline simulation model. This model combines parameters such as pipe diameter and length of the simulated pipe segments with the design conditions corresponding to the system type, calculates the flow or pressure drop distribution of the local network, and compares the simulation results with the performance index range in the specification rule base. Pipe segments exceeding the range are marked as simulation anomaly areas. Further, the annotation attribute verification process checks the annotation attributes such as pipe diameter and elevation of pipeline components within the simulation anomaly area through the annotation consistency constraint library. When annotation attributes simultaneously violate the constraint library rules and cause the simulation results to deviate from the target conditions, an annotation anomaly record is generated. For such records, the relevant annotation attributes are set as variables to be optimized. The specification rule base and the annotation consistency constraint library are transformed into value ranges and interrelationship constraints. With the goal of minimizing the amount of annotation modification and remaining conflicts, a multi-objective optimization algorithm is used to search for the optimal correction scheme. Thus, the corrected annotation attributes are written into the unified data model for pipeline networks, and the node attributes in the topology-enhanced pipeline network graph are updated simultaneously. The affected local areas are then re-simulated and conflict detected, achieving closed-loop correction of the data model.

[0030] Taking the water supply and drainage system of a commercial building as an example, during the pipeline data acquisition phase, a DN150 water supply riser and a 300mm×600mm concrete beam were identified, and their crossing relationship was established in a unified data model. When constructing the topology-enhanced pipeline network diagram, the riser and beam were used as nodes, and the crossing relationship was mapped to adjacent edges. The specification rule base stored a minimum spacing requirement of 50mm between the water supply system pipe diameter ≥DN100 and concrete components. Conflict detection calculations showed that the actual minimum clear distance was 35mm, triggering a target conflict record. Subsequently, a local simulation model was generated, and hydraulic calculations were performed using the DN150 pipe diameter parameter. The simulation results showed that the flow velocity exceeded the allowable range of the specification. Combining the annotation consistency constraint library, a logical contradiction was found between the elevation annotation value and adjacent pipe segments. This contradiction simultaneously caused simulation anomalies and constraint violations, thus generating an annotation anomaly record. In the optimization process, the elevation annotation of the riser was set as the variable to be optimized, with constraints including spacing requirements and elevation continuity rules. A multi-objective optimization algorithm output an elevation adjustment scheme, eliminating conflicts while reducing annotation modifications. The final corrected elevation values ​​are updated to the unified data model, the corresponding node attributes in the topology map are updated synchronously, and the affected local networks are re-verified to be conflict-free.

[0031] This technical solution integrates geometric conflict detection, performance simulation, and annotation correction processes through a unified data model, resolving the disconnect between annotation attributes and design specifications caused by fragmented processing in existing technologies. Specifically, the topology-enhanced pipeline network diagram transforms spatial relationships into a computable graph structure, improving conflict detection efficiency. A dual verification mechanism of local simulation and annotation consistency constraints ensures that corrections are triggered only when annotation attributes genuinely impact performance, avoiding over-adjustment. A multi-objective optimization algorithm balances annotation modification volume and conflict elimination effectiveness while minimizing manual intervention, maintaining the consistency of pipeline network design. Thus, the closed-loop processing from data input to automatic correction ensures real-time synchronization between conflict detection and simulation parameters after annotation attribute adjustments, fundamentally eliminating correction lag and consistency issues.

[0032] In some of the embodiments described above in this application, a unified data model for pipeline networks is proposed to integrate pipeline data and support conflict detection and annotation correction. However, in the process of its implementation, the coordinate systems and units of multi-source data are inconsistent, the identification standards of pipeline components and environmental components are ambiguous, and the definition of the relationship between components is incomplete, which leads to deviations in the model data. Consequently, the topology construction, conflict identification and simulation analysis results are unreliable, affecting the accuracy of the overall correction scheme.

[0033] In response, this application further proposes that when collecting pipeline data, identifying pipeline components and environmental components based on the pipeline data, and establishing a unified data model for the pipeline network, the following steps are included: Based on drawings and measurement data, the system collects graphic elements and measurement points representing pipelines, unifies spatial coordinates and units for data from different sources, identifies components with fluid transport functions as pipeline components, and identifies building beams, slabs, walls, columns, foundations, and equipment support components as environmental components. Based on the connectivity, attachment, and crossing relationships between graphic elements, the system establishes the association between pipeline components and environmental components, and stores the geometric information, annotation attributes, system information, and association relationships of pipeline components into the unified data model of the pipeline network according to a unified data structure.

[0034] Among these, drawing data acquisition refers to extracting pipeline geometry and topology information from design documents, which can be achieved using vector graphics exported from CAD or BIM software. Measurement data acquisition refers to obtaining actual spatial location information on site, which can be achieved using point cloud data collected by 3D laser scanning equipment. Its purpose is to ensure dual coverage of design intent and actual site conditions, avoiding the limitations of a single data source. Spatial coordinate unification refers to converting different coordinate systems to a unified engineering benchmark, which can be achieved using coordinate transformation matrices or benchmark point matching algorithms. Unit unification refers to converting different units of measurement to a consistent standard, which can be achieved using batch processing of unit conversion coefficients. Its purpose is to eliminate data heterogeneity and enable direct comparison of geometric information. Pipeline component identification refers to screening fluid transmission elements based on functional attributes, which can be achieved using functional label identification or geometric feature analysis. Its purpose is to ensure the accuracy and uniqueness of pipeline components in fluid transmission logic. Environmental component identification refers to identifying building structures and supporting elements that affect pipeline layout, which can be achieved using building component classification standards or semantic segmentation technology. Its purpose is to comprehensively cover spatial constraint boundaries. Connectivity refers to the connection of media flow paths, which can be identified using endpoint matching algorithms. Attachment relationships refer to physical dependencies, which can be determined using distance thresholds. Traversal relationships refer to spatial penetration relationships, which can be detected using Boolean operations; their purpose is to accurately describe the dynamic spatial logic between components. A unified data structure refers to a standardized data storage format, which can be implemented using relational database table structures or JSON Schema definitions; its purpose is to ensure data consistency and reduce semantic loss during information conversion.

[0035] Specifically, this solution standardizes the data acquisition and processing workflow. First, it integrates drawings and measurement data to ensure data integrity. Then, it eliminates coordinate and unit differences to establish a seamless data environment. Next, it clearly distinguishes between pipe components and environmental components based on their functions. Then, it accurately describes the interaction logic between components through multi-dimensional relationships. Finally, it stores multi-dimensional attributes in a unified structure. This sequential processing mechanism transforms raw data into a structured model after standardization, ensuring a complete mapping of geometric information, functional attributes, and spatial relationships.

[0036] As a specific implementation method, this application is implemented as follows in the pipeline design of an industrial plant: Pipeline graphic elements are extracted from the Revit model, and on-site measurement points are obtained using a 3D laser scanner. The scanned point cloud is converted to the same local coordinate system as the design model and unified to millimeter units. Pipeline structures conveying process fluids are identified as pipeline components, while steel beams, columns, and equipment supports are identified as environmental components. Connectivity is determined by analyzing pipeline endpoint connections, attachment relationships are judged based on the relative positions of components, and crossing relationships are determined using spatial penetration detection. All information is stored in a unified pipeline network data model based on the IFC standard, where the geometric boundaries, diameter markings, system types, and relationships of pipeline components are all stored in a structured manner according to preset fields.

[0037] Through the above technical solutions, this application solves the core problems of inconsistent coordinate units, ambiguous component identification, and missing correlation in multi-source data integration, enabling the unified data model of pipeline network to have data integrity and semantic consistency, thereby improving the accuracy of topology construction, the reliability of conflict identification, and the effectiveness of simulation analysis.

[0038] Specifically, in some of the embodiments described above in this application, it is proposed to construct a topology-enhanced pipeline network graph and establish a standard rule base and a label consistency constraint base to support conflict detection and label correction. However, in the implementation process, the specific mapping method of nodes and edges is unclear, and the establishment of the rule base and constraint base lacks a systematic method, resulting in insufficient detection accuracy and low correction efficiency.

[0039] In response, this application further proposes the following steps for constructing a topology-enhanced pipeline network graph based on a unified pipeline network data model, and simultaneously establishing a standardized rule base and a label consistency constraint base: In the unified data model of the pipeline network, each pipeline component and each environmental component is mapped as a node, the connection relationship representing the flow of the medium is mapped as a connected edge, and the relationship representing the crossing relationship, the attachment relationship, or the relationship where the distance is less than a preset proximity threshold is mapped as a neighboring edge.

[0040] While establishing the topology-enhanced pipeline network diagram, the spacing, flow, and pressure requirements for different system types, media types, and temperature levels in the design specifications are compiled into rule entries in the specification rule base. The allowable value combinations between pipe diameter, elevation, and media are compiled into constraint entries in the annotation consistency constraint library.

[0041] Mapping pipe and environmental components to nodes refers to abstracting physical entities in the pipe network as vertices in graph theory. This can be achieved by determining node positions using spatial coordinates of the component's geometric center or key feature points, aiming to fully incorporate all key elements and avoid omissions during model construction. Mapping connections representing medium flow to connected edges can be understood as transforming physical fluid pathways into directed connections. This can be implemented using logical identifiers or spatial coordinate lines for pipe connection points, aiming to accurately preserve medium flow path information. In practical applications, mapping relationships representing crossing, attachment, or distances less than a preset proximity threshold to neighboring edges specifically involves associating spatially close components as non-functional connections. This can be achieved based on minimum distance calculations of component bounding boxes or spatial topological relationship determination, aiming to quantify geometric constraints and provide objective spatial relationship standards for conflict detection. The rule entries in the specification rule base refer to the parametric and structured storage of design specifications. These can be organized using categorized database tables or hierarchical configuration files, classifying and storing spacing, flow rate, and pressure requirements corresponding to different system types, medium types, and temperature levels. This aims to enable rapid retrieval and dynamic application of specification requirements. The constraint entries in the label consistency constraint library can be understood as a set of logical rules between label attributes. They can be expressed in the form of constraint expressions or truth tables to represent the allowed combinations of pipe diameter, elevation and medium. The purpose is to ensure the inherent logical consistency of label data at the system dimension.

[0042] Specifically, the proposed solution achieves the organic integration of data models and engineering knowledge by simultaneously constructing a topology-enhanced pipeline network graph and a rule base system. Pipeline and environmental components are mapped to nodes to form a basic framework, ensuring the model covers all key entities. Medium flow relationships are mapped to connected edges to preserve fluid dynamics characteristics, providing path information for simulation calculations. Spatial proximity relationships are mapped to adjacent edges to capture geometric constraints, quantifying spatial relationships between components. In this process, the specification rule base transforms design specifications into computable rule entries, enabling conflict detection to dynamically match spacing requirements based on parameters such as system type and medium type. The annotation consistency constraint library solidifies the logical dependencies between annotation attributes, allowing annotation verification to validate the rationality of attribute combinations. This integrated construction mechanism ensures semantic consistency between the topology graph and the rule base, enabling direct application of structured specifications for conflict identification when calculating node spacing and attribute relationships, and anomaly judgment based on logical rules during the annotation verification stage, thus forming a closed-loop data processing flow.

[0043] As a preferred embodiment, the solution of this application is implemented as follows: In the HVAC piping network, duct sections and hot / cold water pipe sections are identified as pipe components, and building beams and walls are identified as environmental components, and mapped as nodes respectively. Duct flange connections or water pipe threaded connections are mapped as connecting edges, and the locations where ducts pass through walls or water pipes are attached to floors are mapped as adjacent edges. Simultaneously, the correspondence between pipe diameter and minimum spacing for air conditioning water systems in design specifications is compiled into a specification rule library. For example, the spacing standards of structural components are dynamically matched based on the pipe diameter range, and the allowed combination logic of pipe diameter, elevation, and medium type (such as chilled water or cooling water) is compiled into a label consistency constraint library.

[0044] Through the above scheme, this application achieves precise mapping rules for nodes and edges, ensuring the integrity and accuracy of the topology-enhanced pipeline network graph. Simultaneously, the establishment of a specification rule base and a label consistency constraint base enables conflict detection to perform dynamic matching based on structured specifications, and label verification to perform automatic verification based on attribute logical relationships, thereby improving the reliability of conflict identification and optimizing the processing efficiency of label correction.

[0045] In practical applications, some of the embodiments described above in this application propose to integrate pipeline network data and design specifications by using topology-enhanced pipeline network graphs and specification rule bases for conflict detection. However, in the implementation process, directly performing global distance calculation and rule retrieval on the entire network will lead to a waste of computing resources, low detection efficiency, and an inability to focus on potential conflict areas, thereby missing local conflict points based on proximity relationships, which affects the real-time performance and comprehensiveness of conflict identification.

[0046] To address this, this application further proposes a method for calculating the spacing and attribute relationships between nodes based on a topology-enhanced pipeline network diagram, and identifying target conflict records according to a regulatory rule base. This includes: dividing the topology-enhanced pipeline network diagram into several detection areas; grouping nodes located in the same detection area or adjacent detection areas connected by connecting edges or adjacent edges into candidate node pairs; for each candidate node pair, calculating the minimum clearance and determining the relative positional relationship based on the geometric boundaries of the corresponding pipeline or environmental components; simultaneously reading the system type, medium type, temperature rating, and pressure rating corresponding to the candidate node pair; and retrieving spacing requirements and prohibited contact conditions from the regulatory rule base. When the minimum clearance is less than the spacing requirement or the relative positional relationship violates the prohibited contact condition, the candidate node pair is recorded as a target conflict record, and the conflict type and severity are marked in the target conflict record.

[0047] The detection area refers to the local spatial units into which the topology-enhanced pipeline network graph is divided. This division can be based on spatial coordinate range or topological connectivity clustering, aiming to narrow the detection range and avoid indiscriminate scanning of irrelevant areas, thereby reducing computational complexity. Candidate node pairs refer to combinations of nodes connected by connected or adjacent edges. These can be nodes located in the same or adjacent detection areas. Their purpose is to intelligently filter out high-probability conflict points and irrelevant node pairs by utilizing the inherent logical or spatial relationships in the topology graph. Minimum clearance refers to the shortest distance between the geometric boundaries of pipeline components or environmental components. This can be achieved by calculating the distance between the bounding boxes or precise geometric bodies of the 3D model, aiming to avoid misjudgments caused by simplified models and ensure the accuracy of spatial conflict assessment. Attributes such as system type and medium type refer to the engineering parameters of the pipeline network. These can be dynamically read from the unified pipeline network data model and matched in real-time with the standard rule base. Their purpose is to adapt to the differentiated standard requirements of different system operating conditions, such as larger spacing for high-temperature media or prohibition of contact for specific media. Target conflict records refer to pairs of nodes identified as violating specifications. They can store conflict type and severity information, with the purpose of recording conflict details in a structured manner.

[0048] Specifically, the proposed solution divides the topology-enhanced pipeline network diagram into local detection units through a region partitioning mechanism, thus narrowing the detection range. Based on this, it utilizes the medium flow relationships represented by connected edges and the spatial proximity relationships represented by adjacent edges to generate candidate node pairs only for node combinations with logical or spatial relationships, avoiding redundant calculations of global node pairs. Subsequently, it accurately calculates the minimum clearance based on the geometric boundaries of components and determines their relative positional relationships. Simultaneously, it dynamically associates the engineering attributes of candidate node pairs with the spacing requirements and prohibited contact conditions in the specification rule base, achieving engineering adaptability for conflict determination. Finally, when insufficient minimum clearance or positional relationship violations are detected, the target conflict record, its type, and severity are structurally recorded, forming a closed-loop detection process. This mechanism, through the synergy of localized processing and intelligent filtering, transforms conflict detection from a coarse-grained global scan to a refined local focus, reducing invalid calculations while ensuring comprehensive coverage of potential conflict points.

[0049] As a preferred embodiment, the solution of this application is implemented as follows: In the pipeline network of a building's water supply and drainage system, the topology-enhanced pipeline network diagram is divided into multiple detection areas according to floor spatial coordinates. For water supply pipelines and building beams connected by connecting edges on the same or adjacent floors, candidate node pairs are formed. Based on the three-dimensional geometric models of the outer wall of the water supply pipeline and the edge of the building beam, the minimum clear distance between them is calculated, and their relative positional relationship is determined. Simultaneously, the system type of this node pair is read from the unified pipeline network data model as domestic water supply system, the medium type as ambient temperature water, and the temperature level as ambient temperature; the corresponding spacing requirements are retrieved from the standard rule base. When the minimum clear distance is less than the threshold required by the standard or the relative positional relationship violates the prohibited contact condition, the node pair is recorded as a target conflict record and marked as insufficient spacing or crossing violation type and high severity.

[0050] Through the above scheme, this application reduces the computational resource consumption of conflict detection, improves detection efficiency, and ensures that local conflict points based on proximity are accurately identified, avoiding omissions caused by global scanning, thereby enhancing the real-time performance and comprehensiveness of conflict identification.

[0051] In the automatic detection and annotation correction method for pipeline network conflicts, when a pipeline simulation model is generated based on the unified data model of the pipeline network to simulate the local pipeline network involved in the target conflict record, the pipeline network has a complex topology and involves the integration of multi-source data. Directly generating the simulation model often leads to fuzzy definitions of simulation nodes and pipe segments, incomplete extraction of key physical parameters, or disconnection between boundary conditions and system type. This results in the simulation results failing to truly reflect the dynamic performance of the pipeline network, thereby affecting the accuracy of identifying abnormal areas in the simulation.

[0052] In this regard, this application further proposes the following steps for generating a pipeline simulation model: determining simulation nodes and simulation pipe segments based on the connectivity between pipeline components and environmental components; using the pipe diameter, length, inner wall characteristics, elevation, and medium properties of each simulation pipe segment as simulation parameters; extracting the corresponding design conditions, inlet boundary conditions, and outlet boundary conditions from the standard rule library according to the system type to which the pipeline components belong; and combining the simulation nodes, simulation pipe segments, and boundary conditions to form a pipeline simulation model.

[0053] Specifically, determining simulation nodes and segments based on the connectivity between pipeline components and environmental components refers to defining key points of the fluid path based on the connection logic between components. This can be implemented using a node-edge model in graph theory, treating pipeline connection points as nodes and connection segments as segments. The aim is to accurately capture the actual fluid path and avoid node omissions or segment breaks due to errors in connection logic. Using the pipe diameter, length, inner wall characteristics, elevation, and medium properties of each simulation segment as simulation parameters means directly using these physical properties for simulation calculations. This can be understood as structured data extracted from a unified data model of the pipeline network, ensuring that parameter inputs are consistent with actual operating conditions. The purpose is to improve the reliability of performance calculations such as flow rate and pressure drop. In practical applications, extracting corresponding design conditions, inlet boundary conditions, and outlet boundary conditions from the code rule base based on the system type of the pipeline component means automatically associating the system type with code requirements. This can be achieved through database queries, such as matching rule entries through system type codes. The purpose is to ensure that boundary conditions comply with the operating standards of different systems such as water supply and drainage, and HVAC, eliminating human-defined deviations. Combining simulation nodes, simulation pipe segments, and boundary conditions to form a pipeline simulation model refers to integrating topology, physical parameters, and boundary conditions. Its purpose is to build a complete simulation environment and provide a basis for local performance analysis.

[0054] Specifically, the proposed solution first precisely divides simulation nodes and pipe segments based on connectivity relationships, ensuring that the topology faithfully reflects the physical connections. Then, key physical parameters are extracted as simulation inputs to guarantee consistency with actual operating conditions. Next, boundary conditions required by specifications are automatically matched according to the system type, eliminating human-defined deviations. Finally, these elements are organically combined to form a complete simulation model, thus providing a reliable foundation for the performance simulation of local pipeline networks. This process systematically integrates topological and attribute information from a unified pipeline network data model, enabling the simulation model to accurately represent the dynamic behavior of the pipeline network and avoiding performance analysis distortion caused by missing parameters or disconnected boundary conditions.

[0055] As a specific implementation method, the solution of this application is implemented as follows: In the piping network of the HVAC system, piping components include ducts and fans, and environmental components include building floors and supporting structures. Based on the connectivity, the fan interface location is determined as a simulation node, and the duct section is determined as a simulation pipe section. The pipe diameter, length, inner wall roughness, elevation, and air medium properties of the simulation pipe section are extracted as simulation parameters. According to the HVAC system type, the design air volume, inlet fan pressure, and outlet exhaust conditions are extracted from the standard rule base as boundary conditions. These elements are combined to form a piping simulation model for pressure drop distribution calculation.

[0056] Through the above technical solutions, this application can generate high-precision pipeline simulation models that truly reflect the dynamic performance of pipeline networks and improve the accuracy of identifying abnormal areas in simulations.

[0057] Specifically, in some embodiments of this application, a pipeline simulation model is proposed for performance simulation. However, in its implementation, the simulation results are not compared with the performance indicators in the specification rule base, making it impossible to accurately locate the abnormal simulation area, which makes it impossible to verify and correct the labeled attributes based on the simulation anomaly.

[0058] In response, this application further proposes to compare the simulation results with the performance indicators in the standard rule base. When obtaining simulation abnormal areas, the following steps are taken: taking the node corresponding to each target conflict record as the center, selecting adjacent simulation nodes and adjacent simulation pipe segments along the connectivity relationship within a preset range to form a local simulation subnet, calculating the flow distribution, pressure drop distribution, or temperature distribution of the local simulation subnet in the pipeline simulation model, querying the flow velocity range, pressure drop range, and temperature range corresponding to the local simulation subnet from the standard rule base, comparing the simulation results with the ranges in the standard rule base segment by segment, and when the simulation results exceed any range, classifying the corresponding simulation node and simulation pipe segment as a simulation abnormal area.

[0059] In practical applications, the node corresponding to the target conflict record refers to the node associated with the conflict point identified during pipeline network conflict detection. It can be a representation of pipeline components or environmental components, introduced to accurately locate the conflict source for targeted analysis. Connectivity can be understood as the connection relationship of media flow between pipeline components, specifically physical or logical connections, used to define the network topology. Specifically, the preset range refers to a pre-defined spatial or logical range, which can be implemented using a fixed distance threshold or a fixed number of hops. Its purpose is to control the size of the local simulation subnet and avoid computational redundancy. In practical applications, the local simulation subnet is specifically a subnet composed of a central node and its adjacent simulation nodes and simulated pipe segments within the preset range. For example, it can be extended to a certain depth based on connectivity, aiming to focus on areas directly related to the conflict and improve analysis efficiency. Flow distribution, pressure drop distribution, or temperature distribution calculations can be understood as performing fluid dynamics or thermodynamic simulations on the local subnet, specifically using numerical solution methods, aimed at obtaining detailed performance data for the local area. Specifically, the specification rule base refers to a database storing performance indicator requirements in design specifications. It can contain flow rate ranges, pressure drop ranges, and temperature ranges corresponding to different system types, introduced to provide an authoritative benchmark for comparison. In practical applications, segment-by-segment comparison refers to individually checking whether the simulation results of each simulation segment in a local simulation subnet exceed the specification range. This can employ threshold comparison algorithms to accurately identify anomalies. The simulation anomaly area can be understood as a localized area where performance indicators exceed the limits, specifically marked as the part requiring correction.

[0060] Specifically, firstly, a local simulation subnet is formed by selecting adjacent simulation nodes and adjacent simulation pipe segments within a preset range along the connectivity relationship, centered on the node corresponding to the target conflict record. This positioning mechanism ensures that the analysis starting point originates from the known conflict point, avoiding redundant calculations in the global simulation. Subsequently, flow distribution, pressure drop distribution, or temperature distribution is calculated for the local simulation subnet in the pipeline simulation model, generating detailed performance data for the local area. Next, the flow velocity range, pressure drop range, and temperature range corresponding to the local simulation subnet are queried from the standard rule base, and a comparison basis is established using predefined systematic design standards. Then, the simulation results are compared segment by segment with the ranges in the standard rule base, achieving refined verification of performance indicators through a segmented checking mechanism. Finally, when the simulation results exceed any range, the corresponding simulation node and simulation pipe segment are divided into simulation abnormal areas, clearly identifying the specific location of performance exceeding the standard, thus providing operable input for attribute verification.

[0061] As a specific implementation method, in the piping network of a HVAC system, for a target conflict record, a local simulation subnet is formed by selecting adjacent simulation nodes and adjacent simulation pipe segments along the connectivity relationship within a preset range, centered on the node corresponding to the conflict point. Pressure drop distribution is calculated for this subnet, and the pressure drop range matching the system type of this subnet is queried from the standard rule base. After comparing the simulation results with the standard range segment by segment, simulation nodes and simulation pipe segments that exceed performance standards are identified and classified as simulation anomaly areas.

[0062] Through the above scheme, this application can accurately locate the abnormal area of ​​the simulation, provide accurate basis for the verification of the labeled attributes, thereby correcting the labeling errors and improving the pertinence of the performance simulation and the accuracy of the conflict handling in the pipeline network design.

[0063] In practical applications, some of the embodiments described above in this application propose to identify abnormal regions based on simulation results to locate pipeline network performance problems. However, in the implementation process, abnormal regions in simulation may be caused by inconsistencies in annotation attributes. However, existing methods lack a verification mechanism to correlate annotation attributes with the annotation consistency constraint library and cannot confirm whether annotation errors directly lead to simulation abnormalities, making it difficult to accurately identify and correct annotation abnormalities.

[0064] In response, this application further proposes a method for verifying the annotation attributes of pipeline components and generating annotation anomaly records based on the annotation consistency constraint library and simulation anomaly regions. This method includes: for each simulation anomaly region, selecting the annotation attributes of pipeline components within the simulation anomaly region, including pipe diameter, elevation, medium type, and pressure rating; checking the value relationships of the annotation attributes between adjacent pipeline components and their matching relationships with the system type based on the annotation consistency constraint library; when the check results do not meet the annotation consistency constraint library and the pipeline component containing the corresponding annotation attribute is located within the simulation anomaly region, recording the annotation attribute and the corresponding pipeline component as an annotation anomaly record, and storing the annotation anomaly record in association with the performance index that caused the simulation anomaly.

[0065] The simulation anomaly area refers to a localized region in the pipeline simulation model where performance indicators exceed the specified range. This can be a set of non-compliant pipe sections identified through calculations of flow distribution, pressure drop distribution, or temperature distribution, aiming to precisely pinpoint the spatial extent of the performance problem. Pipe diameter labeling refers to the labeled value of the pipe diameter, which can be expressed using standard specifications such as DN50, DN100, etc., to define the pipeline's flow capacity. Elevation labeling refers to the labeled value of the pipeline's installation height, which can be expressed as relative or absolute elevation, aiming to determine the pipeline's spatial location. Medium type labeling refers to the type of fluid transported by the pipeline, which can be categorized as water, steam, air, etc., aiming to clarify the fluid characteristics. Pressure rating labeling refers to the design pressure rating of the pipeline, which can be expressed as PN10, PN16, etc., aiming to ensure structural safety. The labeling consistency constraint library is a set of rules storing the allowed combinations of values ​​between pipe diameter, elevation, medium type, and pressure rating. It can be implemented using predefined rule tables or logical expressions, aiming to verify the logical consistency of labeling attributes. Anomaly records are problem records generated when annotated attributes violate constraint rules and are located in anomaly areas. They can contain anomalous attributes, location information, and associated performance metrics, aiming to provide a basis for correction. Performance metric-associated storage refers to the technical means of binding anomalies with specific performance problems. This can be implemented using database indexes or pointer structures, aiming to establish a problem-tracing relationship.

[0066] Specifically, the proposed solution first focuses on the labeling attributes of pipe components within each simulated anomaly region. By selecting key attributes such as pipe diameter, elevation, medium type, and pressure rating, a labeling consistency constraint library is used to check the value relationships between adjacent components and their compatibility with the system type. When a labeling attribute is found to violate constraint rules and is located within the simulated anomaly region, a labeling anomaly record is generated. This dual-condition verification mechanism ensures that a record is only recorded when the labeling error coincides with the performance anomaly space, avoiding misjudgments. Subsequently, the labeling anomaly record is associated with and stored in relation to the specific performance indicators that caused the anomaly, forming a direct causal chain from labeling errors to performance problems. This process achieves precise location of labeling errors and problem tracing.

[0067] As a preferred embodiment, the solution of this application is implemented as follows: When the pipeline simulation model shows that the pressure drop distribution of a certain section of the HVAC water system network exceeds the specification range, the exceeding pipe section is identified as a simulation anomaly area. Subsequently, for the pipe components in this area, their pipe diameter labels, elevation labels, medium type labels, and pressure rating labels are extracted. According to the label consistency constraint library check, it is found that the pipe diameter label of adjacent pipe components suddenly changes from DN80 to DN50, while the constraint library stipulates that the pipe diameter change should be a smooth transition under this system type. At the same time, the pressure rating label PN10 in this area does not match the system requirement of PN16. Since these labeling errors are located in the pressure drop anomaly area, the system records the pipe diameter label and pressure rating label as labeling anomalies and stores them in association with the pressure drop exceeding performance index. In this embodiment, the label consistency constraint library pre-stores the matching rules for the pipe diameter change rate and pressure rating of the HVAC system to ensure that the verification process is accurate and efficient.

[0068] Through the above-described scheme, this application achieves accurate identification and root cause analysis of annotation anomalies. During pipeline network conflict detection, it can distinguish between simulation anomalies caused by annotation errors and normal fluctuations, avoiding misjudgments and redundant processing. The associated storage of annotation anomaly records and performance indicators improves the accuracy and efficiency of conflict resolution, ensuring the compliance of pipeline network design with specifications and the reliability of operation.

[0069] In some of the embodiments described above in this application, it is proposed to generate annotation anomaly records based on the annotation consistency constraint library and the simulation anomaly region. However, in its implementation, the annotation anomaly records are stored in isolation and lack correlation analysis with topological relationships, which makes it impossible to accurately define the local range affected by the anomaly. This may result in the omission of key related components, leading to incomplete correction, or the excessive expansion of the optimization range, introducing redundant calculations, making it difficult to efficiently generate targeted annotation correction schemes.

[0070] In response, this application further proposes that for each anomaly record in the above method, the annotation attribute corresponding to the anomaly record is set as a variable to be optimized, and when converting the specification rule base and annotation consistency constraint base into constraint conditions, the following steps are taken: Starting with the pipe components corresponding to the anomaly records, pipe components that are located within the simulation anomaly region and are directly connected to the pipe components are selected as the set of pipe components to be optimized in the topology-enhanced pipe network diagram along the connectivity and proximity relationships. The pipe diameter, elevation, medium type, and pressure level labels in the set of pipe components to be optimized are set as variables to be optimized. The spacing requirements, flow rate requirements, and pressure requirements in the specification rule base, as well as the allowed value combinations in the label consistency constraint base, are respectively transformed into value range constraints and interrelationship constraints acting on the variables to be optimized, forming a set of local optimization constraints.

[0071] In practical applications, the set of pipeline components to be optimized refers to the local influence range dynamically defined based on topological relationships. This can be achieved using breadth-first search or depth-first search algorithms to avoid computational redundancy in global scanning while ensuring that all potentially influential components related through media flow or spatial proximity are included in the optimization scope. The variables to be optimized can be understood as core annotation attributes that directly affect fluid transport and spatial conflicts. These can include pipe diameter annotations, elevation annotations, media type annotations, and pressure rating annotations, aiming to focus on key factors causing anomalies and avoid ineffective adjustments to irrelevant annotations. Specifically, the set of local optimization constraints refers to quantifying the consistency rules between design specifications and annotations into computable mathematical constraints, which can be implemented using linear inequalities or logical expressions.

[0072] Specifically, the proposed solution starts with the pipe components corresponding to the anomaly records, dynamically selecting local components along connectivity and proximity relationships in the topology-enhanced pipe network graph. Key annotation attributes are set as optimization variables, and standard rules are transformed into local constraints, achieving a seamless transition from anomaly identification to correction execution. First, the local impact range is defined based on the topological location of the anomaly source, ensuring that all potentially impactful components connected through media flow or spatial proximity are included. Second, only core attributes directly affecting performance are focused as variables. Finally, global rules are quantified into locally computable constraints, preserving standard integrity while avoiding excessive restrictions. This topology-driven localization mechanism makes the optimization process highly focused, improving the targeting and computational efficiency of annotation correction.

[0073] As a specific implementation method, the solution of this application is implemented as follows: In the piping network of a heating, ventilation, and air conditioning system, when an abnormal elevation label of a certain section of cold water pipe is detected, causing excessive local pressure drop, starting from the abnormal pipe component, adjacent pipe components that are directly connected within the simulated abnormal area are selected along the connectivity and proximity relationships in the topology-enhanced piping network diagram to form a set of pipe components to be optimized. The pipe diameter label, elevation label, medium type label, and pressure rating label in this set are set as variables to be optimized. The flow requirements, pressure requirements, and allowed value combinations in the specification rule base and the label consistency constraint base are transformed into value range constraints and interrelationship constraints acting on these variables. For example, the pipe diameter label must meet the minimum flow area requirement, and the elevation label must maintain a safe distance from adjacent components. Finally, a set of local optimization constraints is formed for optimization.

[0074] Through the above-mentioned scheme, this application can accurately define the scope of impact of annotation anomalies, avoid omitting key related components or introducing redundant calculations, thereby efficiently generating targeted annotation correction schemes and improving the automation level and calculation efficiency of pipeline network conflict detection and correction.

[0075] In some of the embodiments described above in this application, a multi-objective optimization method is proposed to select a label correction scheme with the goal of reducing label modification and remaining target conflicts. However, in its implementation, how to quantify the engineering cost of label modification and the actual effect of conflict elimination while satisfying local optimization constraints, and efficiently select the optimal solution from the candidate schemes that takes into account minimizing human intervention and maximizing conflict resolution, has become an urgent problem to be solved.

[0076] In response, this application further proposes an optimization scheme for obtaining annotation correction solutions using a multi-objective optimization algorithm, with the goal of reducing annotation modifications and conflicts with remaining objectives. This scheme includes: Multiple candidate annotation correction schemes are generated based on the local optimization constraint set. For each candidate annotation correction scheme, the number of modified annotation attributes, the offset of each annotation attribute relative to the original annotation, the number of remaining target conflict records and the severity of the conflict are counted. The statistical results are combined into a comprehensive evaluation index according to a preset weight. Based on the iterative search algorithm, the annotation correction scheme with the highest comprehensive evaluation index and satisfying all local optimization constraint sets is selected as the final annotation correction scheme.

[0077] In practical applications, the local optimization constraint set refers to the set of constraints transformed from the standard rule base and the annotation consistency constraint base. It can be implemented using a system of mathematical inequalities or a system of logical expressions, aiming to ensure that candidate solutions strictly adhere to design specifications and annotation consistency requirements, thus avoiding invalid solutions. The candidate annotation correction scheme can be understood as a combination of annotation attribute modifications that satisfy the local optimization constraints. It can be implemented using a feasible solution set generated by exhaustive search or an approximate solution set generated by heuristic algorithms, aiming to provide multiple comparable correction options. Specifically, the number of modified annotation attributes refers to the total number of pipe diameter, elevation, medium type, or pressure rating annotations that have changed in the annotation correction scheme. It can be implemented using an integer counter or a weighted counter, aiming to quantify the engineering implementation cost brought about by annotation modifications. The offset of the annotation attribute relative to the original annotation can be understood as the degree of difference between the corrected annotation value and the original value. It can be implemented using an absolute difference calculation module or a classification difference level evaluator, aiming to measure the magnitude of the annotation modification and its impact on construction adjustments. In practical applications, the number and severity of remaining target conflict records within a local area refer to the statistical results of spacing or attribute conflicts between pipeline components and environmental components that still exist after correction. This can be achieved using a conflict counter and a severity rating matrix, with the aim of directly relating the solution to the actual effect of conflict elimination. Specifically, the comprehensive evaluation index refers to the function output that synthesizes multi-dimensional statistical results into a single quantitative score. This can be achieved using a weighted linear combination function or a nonlinear aggregation function, with the aim of transforming multi-objective decision-making into a quantifiable single index comparison. The iterative search algorithm can be understood as a computational method for efficiently exploring the optimal solution in the solution space. It can be implemented using genetic algorithms, simulated annealing algorithms, or particle swarm optimization algorithms, with the aim of quickly converging to the globally optimal or near-optimal solution.

[0078] Specifically, the proposed solution first generates multiple candidate annotation correction schemes based on the local optimization constraint set, ensuring that all candidate schemes meet the design specifications and annotation consistency requirements, thereby constructing a feasible solution space foundation. On this basis, multi-dimensional statistical operations are performed on each candidate scheme: firstly, the number and offset magnitude of modified annotation attributes are statistically analyzed to accurately quantify the engineering implementation cost brought about by annotation modifications; secondly, the number and severity of remaining target conflict records within the local area are statistically analyzed to directly evaluate the actual effect of conflict elimination. Subsequently, the above statistical results are synthesized into a comprehensive evaluation index according to preset weights. The weight configuration flexibly balances the cost of annotation modification and the effect of conflict resolution, transforming multi-objective decision-making into a quantifiable single-index comparison. Finally, based on an iterative search algorithm, the scheme with the highest comprehensive evaluation index and satisfying all constraints is selected from the candidate schemes. The algorithm efficiently explores the characteristics of the solution space, quickly converging to the globally optimal or near-optimal solution, thereby minimizing the disturbance of annotation modifications to the original design and maximizing the integrity of conflict elimination while ensuring specification compliance.

[0079] As a specific implementation method, the solution of this application is implemented as follows: For anomaly records in the HVAC piping network of an industrial plant, the system first generates twenty candidate annotation correction schemes based on the local optimization constraint set. Each scheme satisfies the annotation consistency constraint of pipe diameter and elevation combination, as well as spacing requirements. Next, for each scheme, the number of modified pipe diameter annotations, the elevation annotation offset (represented by classification levels of slight, moderate, or significant offset), and the number and severity level of remaining spacing conflicts in the corrected local piping network are statistically analyzed. Subsequently, the above statistical results are combined into a comprehensive evaluation index according to preset weights, where the annotation modification cost weight is set to 0.4 and the conflict elimination effect weight is set to 0.6. Finally, a genetic algorithm is used to search for the scheme with the highest comprehensive evaluation index among the candidate schemes. After five generations of iteration, the optimal solution is determined. This solution modifies only two elevation annotations with a slight offset, while reducing the remaining number of conflicts to zero, satisfying all constraints.

[0080] Through the above technical solution, this application achieves precise quantification of the engineering cost and conflict elimination effect of annotation modification while satisfying local optimization constraints, avoiding the bias of subjective human judgment. By transforming multi-objective optimization into a quantifiable single-index comparison through a comprehensive evaluation index, the efficiency of selecting modification schemes is improved. Based on an iterative search algorithm, the solution space is efficiently explored and quickly converges to the global optimum, thereby minimizing the disturbance of annotation modification to the original design and maximizing the integrity of conflict elimination while ensuring compliance with design specifications. This solves the technical challenge of selecting the optimal annotation modification scheme that balances minimizing human intervention and maximizing conflict resolution.

[0081] In practical applications, some of the above-described embodiments of this application propose annotation correction schemes to optimize annotation attributes and reduce conflicts. However, in the implementation process, the affected areas are not dynamically verified and systematically recorded after the correction scheme is implemented, which may lead to new simulation anomalies or residual conflicts caused by the correction operation. Furthermore, there is a lack of a traceability mechanism for the correction process, making it impossible to accumulate experience to improve the accuracy of optimization.

[0082] In response, this application further proposes that when updating the annotation attributes in the unified data model of the pipeline network and the topology-enhanced pipeline network diagram according to the annotation correction scheme, the following steps are taken: for each pipeline component to be optimized involved in the annotation correction scheme, the corrected annotation attributes are written into the unified data model of the pipeline network, and the annotation attributes of the corresponding nodes in the topology-enhanced pipeline network diagram, as well as the simulation parameters and conflict detection parameters determined by the annotation attributes, the nodes affected by the annotation correction and their adjacent nodes within a preset range are marked as nodes to be recalculated, the local simulation subnet where the nodes to be recalculated are located is re-simulated and the target conflict record is identified, and the annotation attributes before correction, the annotation attributes after correction, the relevant target conflict records, and the corresponding simulation abnormal areas are stored in the case library.

[0083] The process of writing the corrected annotation attributes into the unified data model of the pipeline network refers to persisting the optimization results to the core data structure. This can be achieved through database transaction commits or file serialization, aiming to ensure strict synchronization between the model data and the optimization results, avoiding analytical biases caused by data lag. Synchronously updating the annotation attributes of corresponding nodes in the topology-enhanced pipeline network graph, as well as the simulation parameters and conflict detection parameters determined by the annotation attributes, can be understood as maintaining the consistency of multi-dimensional data. This can be achieved using an event-driven mechanism or batch update strategy, aiming to ensure that simulation calculations and conflict identification accurately reflect the corrected network state. Marking nodes affected by annotation corrections and their adjacent nodes within a preset range as nodes to be recalculated refers to defining the local impact range of the correction operation. This can be achieved based on graph traversal algorithms, aiming to precisely limit the verification area and avoid computational redundancy caused by global recalculation. Resimulating the local simulation subnet where the nodes to be recalculated are located and identifying target conflict records can be understood as a closed-loop verification of the correction effect. This can be achieved by calling the pipeline simulation engine and conflict detection module, aiming to directly verify the actual effectiveness of the correction scheme. Storing the annotation attributes before correction, the annotation attributes after correction, relevant target conflict records, and corresponding simulation anomaly areas into the case library refers to building a traceable knowledge base, which can be implemented using a structured database, with the aim of accumulating historical correction experience.

[0084] Specifically, the proposed solution writes the corrected annotation attributes into the unified data model of the pipeline network, ensuring data synchronization and providing a reliable foundation for the verification process. Subsequently, the annotation attributes and related parameters in the topology-enhanced pipeline network diagram are updated synchronously to maintain the inherent consistency of the data model, enabling simulation and collision detection to accurately reflect the correction status. Based on the local propagation characteristics of annotation correction, nodes affected by the correction and their neighboring nodes are marked as nodes to be recalculated, limiting the verification scope to improve efficiency. The local simulation subnet is re-simulated and collision identification is performed to directly verify the correction effect and identify new collisions. Finally, the correction process and results are stored in a case library, forming a reusable knowledge system. This sequential execution constitutes a complete closed-loop verification mechanism, both instantly confirming whether abnormal simulation areas have been eliminated and enabling the system to continuously learn through historical data accumulation.

[0085] As a specific implementation method, the solution of this application is implemented as follows: In the implementation of the HVAC piping system, when the annotation correction scheme corrects the pipe diameter annotation of a certain pipe section, the system writes the corrected annotation attributes into the unified data model of the pipe network. The pipe diameter attributes of the corresponding nodes in the topology-enhanced pipe network diagram and the flow velocity parameters determined based on the pipe diameter are updated synchronously. The pipe node and its upstream and downstream adjacent nodes are marked as nodes to be recalculated. Hydraulic simulation is performed on the local pipe network formed by these nodes to check whether the pressure drop distribution is within the allowable range of the specifications. The pipe diameter values ​​before and after correction, relevant target conflict records, and simulation anomaly areas are stored in the case library.

[0086] Through the above scheme, this application ensures real-time dynamic verification after the annotation correction is implemented, avoids new simulation anomalies or residual conflicts caused by the correction operation, and establishes a traceability mechanism by systematically recording the correction process and results, thereby improving the accuracy and efficiency of optimization.

[0087] In the above embodiments, based on a unified pipeline network data model and topology-enhanced pipeline network diagram, geometric conflict detection, specification rule verification, simulation performance analysis, and annotation attribute correction are integrated into a closed-loop processing flow. By constraining the spacing and attribute relationships between nodes through a specification rule base and an annotation consistency constraint base, the screening and classification of target conflict records are achieved. Then, a pipeline simulation model is used to simulate the local pipeline network involved in the target conflict records. The abnormal simulation areas and annotation consistency verification results are jointly used to determine the abnormal annotation records, avoiding misjudgments and omissions caused by relying solely on geometric relationships or simple rules. The annotation attributes corresponding to the abnormal annotation records are explicitly set as variables to be optimized, and the specification rule base and annotation consistency constraint base are transformed into constraint conditions. With reducing annotation modifications and remaining target conflicts as the joint optimization objective, a multi-objective optimization algorithm generates annotation correction schemes, and the correction results are written back to the unified pipeline network data model and topology-enhanced pipeline network diagram. This reduces the workload of manual adjustments and the number of repeated modifications while ensuring that design specifications and simulation performance requirements are met, thereby improving the accuracy and consistency of pipeline network design data.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for automatic detection and annotation correction of pipeline network conflicts, characterized in that, include: Collect pipeline data, identify pipeline components and environmental components based on the pipeline data, and establish a unified data model of the pipeline network; Based on the unified data model of the pipeline network, a topology-enhanced pipeline network graph is constructed with the pipeline components and the environmental components as nodes and the connectivity and proximity relationships as edges. At the same time, a standard rule base and a label consistency constraint base are established. Based on the topology-enhanced pipeline network graph, the spacing and attribute relationships between nodes are calculated, and target conflict records are identified according to the standard rule base. A pipeline simulation model is generated based on the unified data model of the pipeline network. The local pipeline network involved in the target conflict record is simulated. The simulation results are compared with the performance indicators in the standard rule base to obtain the simulation abnormal area. Based on the annotation consistency constraint library and the simulation abnormal area, the annotation attributes of the pipeline components are verified. When the annotation attributes cause both the annotation consistency constraint to be unsatisfied and the simulation result to deviate from the target working condition, an annotation abnormal record is generated. For each of the aforementioned annotation anomaly records, the annotation attribute corresponding to the annotation anomaly record is set as a variable to be optimized, and the specification rule base and annotation consistency constraint base are transformed into constraint conditions. The optimization objective is to reduce the conflict between annotation modification and remaining objectives. An annotation correction scheme is obtained through a multi-objective optimization algorithm. Update the annotation attributes in the unified data model of the pipeline network and the topology-enhanced pipeline network diagram according to the annotation correction scheme.

2. The automatic detection and annotation correction method for pipeline network conflicts according to claim 1, characterized in that, When collecting pipeline data, identifying pipeline components and environmental components based on the pipeline data, and establishing a unified data model for the pipeline network, the process includes: Based on drawings and measurement data, the system collects graphic elements and measurement points representing pipelines, unifies spatial coordinates and units for data from different sources, identifies components with fluid transport functions as pipeline components, and identifies building beams, slabs, walls, columns, foundations, and equipment support components as environmental components. Based on the connectivity, attachment, and crossing relationships between graphic elements, the system establishes the association between pipeline components and environmental components, and stores the geometric information, labeling attributes, system information, and association relationships of the pipeline components into the unified data model of the pipeline network according to a unified data structure.

3. The automatic detection and annotation correction method for pipeline network conflicts according to claim 1, characterized in that, When constructing a topology-enhanced pipeline network graph based on the unified data model of the pipeline network, and simultaneously establishing a standard rule base and a label consistency constraint base, the following steps are taken: mapping each pipeline component and each environmental component in the unified data model of the pipeline network to a node, mapping the connection relationship representing the medium flow to a connected edge, and mapping the relationship representing the crossing relationship, the attachment relationship, or the relationship with a distance less than a preset proximity threshold to a proximity edge. While establishing the topology-enhanced piping network diagram, the spacing, flow, and pressure requirements for different system types, media types, and temperature levels in the design specifications are compiled into rule entries in the specification rule base. The allowable value combinations between pipe diameter, elevation, and media are compiled into constraint entries in the annotation consistency constraint library.

4. The automatic detection and annotation correction method for pipeline network conflicts according to claim 3, characterized in that, When calculating the spacing and attribute relationships between nodes based on the topology-enhanced pipeline network graph, and identifying target conflict records according to the standard rule base, the process includes: The topology-enhanced pipeline network graph is divided into several detection regions, and nodes located in the same detection region or in adjacent detection regions and connected by connecting edges or adjacent edges are combined into candidate node pairs. For each candidate node pair, the minimum clearance is calculated based on the geometric boundaries of the corresponding pipe or environmental component, and the relative positional relationship is determined. At the same time, the system type, medium type, temperature level, and pressure level corresponding to the candidate node pair are read, and the spacing requirements and prohibited contact conditions are retrieved from the specification rule base. When the minimum clearance is less than the spacing requirement or the relative positional relationship violates the prohibited contact condition, the candidate node pair is recorded as a target conflict record, and the conflict type and conflict severity are marked in the target conflict record.

5. The automatic detection and annotation correction method for pipeline network conflicts according to claim 1, characterized in that, When generating a pipeline simulation model based on the unified pipeline network data model, the following steps are included: The simulation nodes and simulation pipe segments are determined based on the connectivity between the pipeline components and the environmental components. The pipe diameter, length, inner wall characteristics, elevation, and medium properties of each simulation pipe segment are used as simulation parameters. The corresponding design conditions, inlet boundary conditions, and outlet boundary conditions are extracted from the standard rule base according to the system type to which the pipeline components belong. The simulation nodes, simulation pipe segments, and boundary conditions are combined to form the pipeline simulation model.

6. The automatic detection and annotation correction method for pipeline network conflicts according to claim 5, characterized in that, When comparing the simulation results with the performance metrics in the specified rule base to identify simulation anomaly regions, the following steps are taken: Centered on the node corresponding to each target conflict record, adjacent simulation nodes and adjacent simulation pipe segments are selected within a preset range along the connectivity relationship to form a local simulation subnet. In the pipeline simulation model, the flow distribution, pressure drop distribution, or temperature distribution of the local simulation subnet is calculated. The flow velocity range, pressure drop range, and temperature range corresponding to the local simulation subnet are queried from the standard rule base. The simulation results are compared segment by segment with the ranges in the standard rule base. When the simulation results exceed any range, the corresponding simulation node and simulation pipe segment are divided into simulation abnormal areas.

7. The automatic detection and annotation correction method for pipeline network conflicts according to claim 6, characterized in that, When validating the annotation attributes of the pipeline components and generating annotation anomaly records based on the annotation consistency constraint library and simulation anomaly regions, the process includes: For each simulation anomaly region, the annotation attributes of the pipe components in the simulation anomaly region are selected. The annotation attributes include pipe diameter, elevation, medium type, and pressure rating. The value relationship of the annotation attributes between adjacent pipe components and the matching relationship with the system type are checked according to the annotation consistency constraint library. When the check result does not meet the annotation consistency constraint library and the pipe component with the corresponding annotation attribute is located in the simulation anomaly region, the annotation attribute and the corresponding pipe component are recorded as an annotation anomaly record, and the annotation anomaly record is associated with and stored with the performance index that caused the simulation anomaly.

8. The automatic detection and annotation correction method for pipeline network conflicts according to claim 7, characterized in that, For each of the aforementioned annotation anomaly records, the annotation attribute corresponding to the annotation anomaly record is set as a variable to be optimized. When converting the specification rule base and annotation consistency constraint base into constraint conditions, the process includes: Starting with the pipe component corresponding to the anomaly record, pipe components that are located within the simulation anomaly region and directly connected to the pipe component are selected along the connectivity and proximity relationships in the topology-enhanced pipe network diagram as the set of pipe components to be optimized. The pipe diameter label, elevation label, medium type label, and pressure level label in the set of pipe components to be optimized are set as variables to be optimized. The spacing requirements, flow rate requirements, and pressure requirements in the specification rule base, as well as the allowed value combination relationships in the label consistency constraint base, are respectively transformed into value range constraints and interrelationship constraints acting on the variables to be optimized, forming a set of local optimization constraints.

9. The automatic detection and annotation correction method for pipeline network conflicts according to claim 8, characterized in that, When obtaining a label correction scheme using a multi-objective optimization algorithm with the optimization objective of reducing label modifications and conflicts with remaining targets, the following are included: Multiple candidate annotation correction schemes are generated based on the local optimization constraint set. For each candidate annotation correction scheme, the number of modified annotation attributes, the offset of each annotation attribute relative to the original annotation, the number of remaining target conflict records and the severity of the conflict are counted. The statistical results are combined into a comprehensive evaluation index according to a preset weight. Based on the iterative search algorithm, the annotation correction scheme with the highest comprehensive evaluation index and satisfying all local optimization constraint sets is selected as the final annotation correction scheme.

10. The automatic detection and annotation correction method for pipeline network conflicts according to claim 9, characterized in that, When updating the annotation attributes in the unified data model of the pipeline network and the topology-enhanced pipeline network diagram according to the annotation correction scheme, the following are included: For each pipeline component to be optimized in the annotation correction scheme, the corrected annotation attributes are written into the unified data model of the pipeline network, and the annotation attributes of the corresponding nodes in the topology-enhanced pipeline network diagram, as well as the simulation parameters and conflict detection parameters determined by the annotation attributes, are updated simultaneously. The nodes affected by the annotation correction and their adjacent nodes within a preset range are marked as nodes to be recalculated. The local simulation subnet where the nodes to be recalculated are located is re-simulated and the target conflict record is identified. The annotation attributes before correction, the annotation attributes after correction, the relevant target conflict records, and the corresponding simulation abnormal areas are stored in the case library.

Images