Control management system based on steel structure raw material use limit

Abstract

The invention discloses a control management system based on a steel structure raw material use limit, and the system comprises a limit obtaining module which is used for obtaining a raw material use limit and a raw material quantitative limit of a current sub-component; the local sub-graph representation module is used for extracting a local sub-graph of the current sub-component in the assembly dependence path graph according to the raw material use limit and the raw material quantitative limit of the current sub-component and generating embedded representation of the local sub-graph; the abnormal use path output module is used for inputting the embedded representation of the local sub-graph into an abnormal path identification model and outputting an abnormal dependency path corresponding to the current sub-component in the assembly dependency path graph; according to the method, the abnormal path identification model is constructed, so that the aggregation state identification of the abnormal use amount in the assembly path and the analysis of the abnormal trend conduction are realized, and the identification precision and the structure positioning capability of the raw material use abnormality in the graph structure are enhanced.

Description

Technical Field

[0001] The present invention relates to a control and management system, in particular to a control and management system based on the usage quota of steel structure raw materials. Background Art

[0002] During steel structure construction, the amount of raw materials used directly impacts structural safety and cost control. To this end, project management typically involves quantitatively controlling the raw material usage of components, combined with threshold judgments to identify anomalies. Patent publication number CN109992800A discloses a management method for a steel structure project management system, addressing issues such as untimely information acquisition, asymmetric communication, and poor coordination among project management parties involved in steel structure projects.

[0003] However, existing systems for controlling and managing raw material usage quotas generally have the following problems: first, they easily overlook the assembly sequence and structural dependencies between components, making it difficult to determine whether anomalies are structural problems in the assembly chain; second, they are unable to identify "tolerable errors" that are within the threshold range but have deviated from the trend. Such errors may become a hidden danger of accumulated structural anomalies; and third, it is difficult to identify whether anomalies form coherent paths or clustered areas in the structure as a whole, thereby limiting the accuracy of anomaly location and intervention. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a control and management system based on the usage quota of steel structure raw materials, which solves the technical problems raised in the background technology by constructing an assembly dependency path diagram and performing anomaly recognition modeling on it.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] A control and management system based on the usage quota of steel structure raw materials, the management system includes:

[0007] The quota acquisition module is used to obtain the raw material usage quota and raw material quantitative quota of the current sub-component;

[0008] The local subgraph representation module is used to extract the local subgraph of the current subcomponent in the assembly dependency path graph based on the raw material usage quota and raw material quantitative quota of the current subcomponent, and generate an embedded representation of the local subgraph;

[0009] The abnormal usage path output module is used to input the embedded representation of the local subgraph into the abnormal path recognition model and output the abnormal dependency path corresponding to the current subcomponent in the assembly dependency path graph.

[0010] In some specific embodiments, the modeling steps of the abnormal path identification model include:

[0011] S1. Construct an assembly dependency path diagram of several sub-components in the steel structure;

[0012] The assembly dependency path graph includes a number of sub-component nodes with assembly dependency relationships; the assembly dependency relationships include: path numbers and node numbers in each path number;

[0013] S2. Anchoring a node to be determined from a plurality of sub-component nodes of the assembly dependency path graph;

[0014] S3. Determine abnormality of the raw material usage of the node to be determined;

[0015] S4. If the raw material usage of the node to be determined is normal, proceed to the next node to be determined along the assembly dependency path diagram according to the assembly dependency relationship to perform abnormality determination;

[0016] S5. If the node to be determined is an abnormal usage, obtain the abnormal dependency path from the assembly dependency path graph and encode the abnormal dependency path into an abnormal path vector;

[0017] S6. intercepting a local subgraph of the node corresponding to the abnormal usage and its N preceding adjacent nodes, and extracting an embedded representation of the local subgraph;

[0018] S7. The embedded representation of the local subgraph is used as the input of the supervised model, and the abnormal path vector is used as the target variable. After iterative training, an abnormal path recognition model is generated.

[0019] In some specific embodiments, constructing an assembly dependency path diagram of several sub-components in a steel structure includes:

[0020] S1-1. Obtain the component types involved in the steel structure of the project;

[0021] S1-2. Disassemble the steel structure in the project into several sub-components according to the types of components involved;

[0022] S1-3, allocating predefined assembly dependencies among several sub-components;

[0023] S1-4, define each subcomponent as a component node of the graph structure, and define the assembly dependency as a directed edge between the component nodes;

[0024] S1-5. Connect any two adjacent component nodes that have assembly dependencies according to the directed edges between the component nodes until all assembly dependencies are connected;

[0025] S1-6. Define the overall structure of component nodes and their directed edges as the assembly dependency path graph of sub-components.

[0026] In some specific embodiments, abnormality determination of raw material usage of a node to be determined includes:

[0027] S3-1. Obtain the raw material quota and raw material usage quota of the node to be determined

[0028] S3-2. Calculate the real-time error between the raw material usage quota and the raw material quantitative quota of the node to be determined;

[0029] S3-3, placing the real-time rated error into a threshold range, and determining that the real-time rated error is within the threshold range error position;

[0030] S3-4, determine the amount of raw materials based on the error position;

[0031] S3-5. If the error position is within the threshold range, the raw material usage of the node to be determined is output as normal usage;

[0032] S3-6. If the error position is outside the threshold range, the raw material usage of the node to be determined is output as abnormal usage.

[0033] In some specific embodiments, if the node to be determined is an abnormal usage, obtaining the abnormal dependency path from the assembly dependency path graph includes:

[0034] S5-1. Based on the assembly dependency relationship, in the assembly dependency path graph, with the abnormal usage as the center, advance M subsequent adjacent nodes backward;

[0035] S5-2, performing abnormality determination on the M subsequent adjacent nodes;

[0036] S5-3. If the raw material usage of the M subsequent adjacent nodes is determined to have at least two abnormal usages, extract the assembly dependency path between the two abnormal usages;

[0037] S5-4, determining the assembly dependency relationship of the assembly dependency path between the two abnormal usages;

[0038] S5-5. If an upstream and downstream assembly dependency relationship exists on the assembly dependency path between the two abnormal usages, the abnormal usage and the dependency path with the upstream and downstream assembly dependency relationship are exported as the abnormal dependency path.

[0039] In some specific embodiments, performing abnormality determination on M subsequent adjacent nodes includes:

[0040] S5-2-1. Obtain the raw material quota and raw material usage quota of M subsequent adjacent nodes;

[0041] S5-2-2. Calculate the real-time credit errors of M subsequent adjacent nodes;

[0042] S5-2-3. Determine the error positions of the M subsequent adjacent nodes whose real-time credit errors are within a threshold range, and obtain M error positions;

[0043] S5-2-4. Generate a raw material usage determination for the corresponding subsequent adjacent nodes based on the M error positions.

[0044] In some specific embodiments, extracting the embedding vector of the local subgraph includes:

[0045] S6-1, determining an assembly dependency feature of a preceding adjacent node in the local subgraph according to a path number and a node sequence number of the preceding adjacent node in the local subgraph;

[0046] S6-2, determining an error accumulation characteristic of a preceding adjacent node in the local subgraph based on the real-time amount error of the preceding adjacent node in the local subgraph;

[0047] S6-3. The local subgraph with assembly dependency features and error accumulation features is used as the input of the graph neural network. After node feature aggregation, the embedding vector of the local subgraph is obtained.

[0048] In some specific embodiments, the step of obtaining the assembly dependency features of the N preceding adjacent nodes includes:

[0049] A6-1. Define each preceding adjacent node as an intermediate node of the assembly-dependent feature;

[0050] A6-2. Obtain the path number of the intermediate node;

[0051] A6-3. Obtain the previous node and the next node adjacent to the intermediate node according to the path number of the intermediate node;

[0052] A6-4. Obtain the node sequence numbers of the previous node and the next node;

[0053] A6-5 concatenates the path number of the intermediate node, the node sequence numbers of the previous node, and the next node to obtain the position number of the previous adjacent node in the assembly dependency path graph;

[0054] A6-6. Encode the position number into a one-hot vector and generate assembly dependency features of N preceding adjacent nodes.

[0055] In some specific embodiments, the step of acquiring the error accumulation features of the N preceding adjacent nodes includes:

[0056] B6-1. Obtain the real-time rated errors of N preceding adjacent nodes;

[0057] B6-2. Normalize the real-time rated errors of N preceding adjacent nodes to generate N normalized errors;

[0058] B6-3. Encode the N normalized errors into a one-hot vector to generate the error accumulation features of the N preceding adjacent nodes.

[0059] In some specific embodiments, an abnormal path recognition model is generated after iterative training, including:

[0060] Get the embedding representation of the local subgraph of the current batch and input it into the supervised learning model;

[0061] Perform forward propagation on the embedded representation of the local subgraph of the current batch and output the corresponding abnormal path prediction vector;

[0062] Calculate the mean square error loss between the abnormal path prediction vector and the abnormal path vector;

[0063] Back propagation is performed based on the mean squared error loss to update the model parameters, and iterations are continued until the mean squared error loss converges.

[0064] The present invention provides a control and management system based on the usage quota of steel structure raw materials, which has the following beneficial effects:

[0065] The present invention constructs an abnormal path recognition model and uses the assembly dependency structure of a local subgraph as the input representation of the model. By jointly encoding the structural position and error accumulation characteristics, it identifies the potential causes of abnormal nodes in their preceding structures. At the same time, it determines whether there are multiple abnormal nodes in the subsequent adjacent paths that constitute a directed path with upstream and downstream assembly dependencies, thereby realizing the recognition of the aggregation state of abnormal usage in the assembly path and the analysis of abnormal trend transmission, thereby enhancing the recognition accuracy and structural positioning capability of raw material usage anomalies in the graph structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a structural block diagram of the control and management system based on the steel structure raw material usage quota of the present invention;

[0067] Figure 2 This is a schematic diagram of the management process of the control and management system based on the steel structure raw material usage quota of the present invention;

[0068] Figure 3 Schematic diagram of the modeling process of the abnormal path identification model of the present invention;

[0069] Figure 4 This is a schematic diagram of the export process of the abnormal dependency path described in the present invention. DETAILED DESCRIPTION

[0070] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0071] Example 1: Please refer to Figures 1 to 2 The present invention provides a control and management system based on the usage quota of steel structure raw materials, the management system comprising:

[0072] The quota acquisition module is used to obtain the raw material usage quota and raw material quantitative quota of the current sub-component;

[0073] The local subgraph representation module is used to extract the local subgraph of the current subcomponent in the assembly dependency path graph based on the raw material usage quota and raw material quantitative quota of the current subcomponent, and generate an embedded representation of the local subgraph;

[0074] The abnormal usage path output module is used to input the embedded representation of the local subgraph into the abnormal path recognition model and output the abnormal dependency path corresponding to the current subcomponent in the assembly dependency path graph.

[0075] It should be noted that the assembly dependency path diagram refers to a directed graph structure constructed based on the assembly sequence, connection logic, or mechanical dependency relationships of components in steel structure design. Each node in the diagram represents a subcomponent, and the edges represent the assembly dependency or construction sequence between components. This diagram is used to express the upstream and downstream relationships of "who depends on whom" in the structure;

[0076] An abnormal dependency path is one or more directed paths in the assembly dependency path graph consisting of component nodes identified as having abnormal usage. This path is used to reveal whether there is a structural propagation trend in the abnormal use of raw materials.

[0077] This embodiment extracts an embedded representation of a local subgraph based on the difference between raw material usage quotas and raw material quantitative quotas, and inputs this embedded representation into an abnormal path identification model for inference. This allows for the identification of abnormal subcomponent usage paths within the structural constraints of the assembly dependency path graph. This effectively integrates the assembly dependency relationships between subcomponents and accurately locates abnormal dependency paths consisting of abnormal nodes, thereby improving the ability to perceive abnormal raw material usage trends in steel structures.

[0078] Example 2: See Figures 3 and 4 The technical solution of this embodiment 2 is different from that of embodiment 1 in that it discloses the modeling steps of the abnormal path identification model described in embodiment 1, and the modeling steps include:

[0079] S1. Construct an assembly dependency path diagram of several sub-components in the steel structure;

[0080] The assembly dependency path graph includes a number of sub-component nodes with assembly dependency relationships; the assembly dependency relationships include: path numbers and node numbers in each path number;

[0081] Among them, the quantitative quota of raw materials represents the theoretical total amount of materials estimated for the sub-component under standard assembly conditions based on the design drawings or budget list; while the raw material usage quota represents the real-time recorded amount of raw materials consumed by the sub-component during the actual construction process.

[0082] S2. Anchoring a node to be determined from a plurality of sub-component nodes of the assembly dependency path graph;

[0083] S3. Determine abnormality of the raw material usage of the node to be determined;

[0084] S4. If the raw material usage of the node to be determined is normal, proceed to the next node to be determined along the assembly dependency path diagram according to the assembly dependency relationship to perform abnormality determination;

[0085] S5. If the node to be determined is an abnormal usage, obtain the abnormal dependency path from the assembly dependency path graph and encode the abnormal dependency path into an abnormal path vector;

[0086] It should be noted that the abnormal path vector is used to characterize the path structure formed by the sub-component nodes identified as abnormal usage in the assembly dependency path graph. The path is a node sequence with a directed dependency relationship, and its encoding method is: extract the corresponding node numbers according to the order of appearance of the nodes in the path, and perform position encoding in combination with their position index in the path, or perform one-hot encoding, embedded encoding or tensor splicing operations on the ordered node sequence to form a fixed-dimensional path vector representation.

[0087] S6. intercepting a local subgraph of the node corresponding to the abnormal usage and its N preceding adjacent nodes, and extracting an embedded representation of the local subgraph;

[0088] S7. The embedded representation of the local subgraph is used as the input of the supervised model, and the abnormal path vector is used as the target variable. After iterative training, an abnormal path recognition model is generated.

[0089] This embodiment implements supervised modeling of the abnormal path identification model by performing node-by-node abnormality judgment on the raw material usage of component nodes in the assembly dependency path graph, extracting the abnormal dependency path as the target variable, and embedding the local subgraph contained in the previous dependency relationship as input.

[0090] Specifically in this embodiment, step S1 further includes:

[0091] S1-1. Obtain the component types involved in the steel structure of the project;

[0092] Specifically, component type refers to the different component categories divided according to the steel structure design drawings, including but not limited to main beams, secondary beams, columns, node plates, support rods, connectors, etc. Component type is usually associated with its structural function, stress characteristics and installation location.

[0093] S1-2. Disassemble the steel structure in the project into several sub-components according to the types of components involved;

[0094] Specifically, several subcomponents refer to the smallest assembly units after further refinement of various components according to the structural division principle. Each subcomponent can be independently represented as a node in the graph structure, with clear assembly start and end relationships and raw material usage information.

[0095] S1-3, allocating predefined assembly dependencies among several sub-components;

[0096] It should be noted that predefined assembly dependencies refer to the pre-defined assembly order relationships between components based on the assembly sequence, node connection logic, and construction process rules in the steel structure design drawings. These relationships are expressed through path numbers and node numbers in the graph structure. The path number identifies a complete assembly path, while the node number indicates the assembly order of the subcomponent within the corresponding path. Together, they clarify the assembly dependencies of the subcomponents within the overall assembly structure.

[0097] S1-4, define each subcomponent as a component node of the graph structure, and define the assembly dependency as a directed edge between the component nodes;

[0098] S1-5. Connect any two adjacent component nodes that have assembly dependencies according to the directed edges between the component nodes until all assembly dependencies are connected;

[0099] S1-6. Define the overall structure of component nodes and their directed edges as the assembly dependency path graph of sub-components.

[0100] This embodiment obtains the component type and decomposes it into several sub-components, assigns predefined assembly dependencies between the sub-components, and uses path numbers and node numbers to identify the dependencies. On this basis, an assembly dependency path graph is constructed with sub-components as nodes and assembly dependencies as directed edges, thereby achieving a structured expression of assembly relationships in steel structures.

[0101] Specifically in this embodiment, step S3 further includes:

[0102] S3-1. Obtain the raw material quota and raw material usage quota of the node to be determined

[0103] S3-2. Calculate the real-time error between the raw material usage quota and the raw material quantitative quota of the node to be determined;

[0104] S3-3, placing the real-time rated error into a threshold range, and determining that the real-time rated error is within the threshold range error position;

[0105] S3-4, determine the amount of raw materials based on the error position;

[0106] S3-5. If the error position is within the threshold range, the raw material usage of the node to be determined is output as normal usage;

[0107] S3-6. If the error position is outside the threshold range, the raw material usage of the node to be determined is output as abnormal usage.

[0108] This embodiment obtains the raw material quantitative quota and raw material usage quota of the node to be determined, calculates the real-time quota error, compares the error with the threshold range, and outputs the normal or abnormal state of the raw material usage based on the error position, thereby realizing the determination of the raw material usage of the node to be determined.

[0109] Specifically in this embodiment, step S5 further includes:

[0110] S5-1. Based on the assembly dependency relationship, in the assembly dependency path graph, with the abnormal usage as the center, advance M subsequent adjacent nodes backward;

[0111] S5-2, performing abnormality determination on the M subsequent adjacent nodes;

[0112] S5-3. If the raw material usage of the M subsequent adjacent nodes is determined to have at least two abnormal usages, extract the assembly dependency path between the two abnormal usages;

[0113] S5-4, determining the assembly dependency relationship of the assembly dependency path between the two abnormal usages;

[0114] S5-5. If an upstream and downstream assembly dependency relationship exists on the assembly dependency path between the two abnormal usages, the abnormal usage and the dependency path with the upstream and downstream assembly dependency relationship are exported as the abnormal dependency path.

[0115] This embodiment establishes a directed path screening mechanism for local assembly areas by centering the abnormal usage node in the assembly dependency path graph, combining forward tracing back to preceding adjacent nodes and backward tracing back to succeeding adjacent nodes. By determining anomalies in succeeding adjacent nodes, the assembly dependency path between at least two abnormal nodes is extracted, and further determination is made as to whether there are clear upstream and downstream assembly dependencies within the path, thereby identifying structural relationships between abnormal usage components.

[0116] Furthermore, the step S5-2 further includes:

[0117] S5-2-1. Obtain the raw material quota and raw material usage quota of M subsequent adjacent nodes;

[0118] S5-2-2. Calculate the real-time credit errors of M subsequent adjacent nodes;

[0119] S5-2-3. Determine the error positions of the M subsequent adjacent nodes whose real-time credit errors are within a threshold range, and obtain M error positions;

[0120] S5-2-4. Generate a raw material usage determination for the corresponding subsequent adjacent nodes based on the M error positions.

[0121] This embodiment obtains the raw material quantitative quotas and raw material usage quotas of M subsequent adjacent nodes, calculates the corresponding real-time quota errors, and determines the abnormal state of the errors based on their position within the threshold range, thereby realizing item-by-item usage determination of the subsequent adjacent nodes on the structural path.

[0122] Specifically in this embodiment, step S6 further includes:

[0123] S6-1, determining an assembly dependency feature of a preceding adjacent node in the local subgraph according to a path number and a node sequence number of the preceding adjacent node in the local subgraph;

[0124] S6-2, determining an error accumulation characteristic of a preceding adjacent node in the local subgraph based on the real-time amount error of the preceding adjacent node in the local subgraph;

[0125] S6-3. The local subgraph with assembly dependency features and error accumulation features is used as the input of the graph neural network. After node feature aggregation, the embedding vector of the local subgraph is obtained.

[0126] This example extracts the path number and node sequence number of the preceding adjacent node in a local subgraph as assembly dependency features, combines them with the node's real-time quota error to form an error accumulation feature. After establishing directed connections between nodes in the graph structure, the local subgraph with these features is used as the input of a graph neural network to aggregate node features and generate an embedding vector for the local subgraph. This method achieves a fusion expression of structural position information and raw material usage status, enabling the local subgraph to jointly represent assembly dependency relationships and error distribution.

[0127] Specifically in this embodiment, the step of obtaining the assembly-dependent feature includes:

[0128] A6-1. Define each preceding adjacent node as an intermediate node of the assembly-dependent feature;

[0129] A6-2. Obtain the path number of the intermediate node;

[0130] A6-3. Obtain the previous node and the next node adjacent to the intermediate node according to the path number of the intermediate node;

[0131] A6-4. Obtain the node sequence numbers of the previous node and the next node;

[0132] A6-5 concatenates the path number of the intermediate node, the node sequence numbers of the previous node, and the next node to obtain the position number of the previous adjacent node in the assembly dependency path graph;

[0133] Exemplarily, the position number is used to uniquely identify the structural position relationship of the preceding adjacent node in the assembly dependency path graph to express its upstream and downstream dependency relationship in the assembly path;

[0134] A6-6. Encode the position number into a one-hot vector and generate assembly dependency features of N preceding adjacent nodes.

[0135] This embodiment uses each preceding adjacent node as an intermediate node, generates a structural position number based on the path number and the node sequence numbers of the preceding and following adjacent nodes, and encodes the position number as a one-hot vector to obtain the assembly dependency feature of the preceding adjacent node. This assembly dependency feature is used to represent the structural position relationship of the node in the assembly dependency path graph, enabling the node input to distinguish and express the upstream and downstream dependency relationships in the assembly path.

[0136] Specifically in this embodiment, the step of obtaining the error accumulation feature includes:

[0137] B6-1. Obtain the real-time rated errors of N preceding adjacent nodes;

[0138] B6-2. Normalize the real-time rated errors of N preceding adjacent nodes to generate N normalized errors;

[0139] B6-3. Encode the N normalized errors into a one-hot vector to generate the error accumulation features of the N preceding adjacent nodes.

[0140] This example constructs an error accumulation feature to represent the intensity of error fluctuation by obtaining the real-time credit limit errors of N preceding adjacent nodes, normalizing them, and encoding them into a one-hot vector. This feature uses a unified numerical representation to characterize the status of each node under raw material usage deviations, enabling the local subgraph to represent a relatively tolerant level of input features.

[0141] In this embodiment, the training steps of the abnormal path identification model include:

[0142] Get the embedding representation of the local subgraph of the current batch and input it into the supervised learning model;

[0143] Perform forward propagation on the embedded representation of the local subgraph of the current batch and output the corresponding abnormal path prediction vector;

[0144] Calculate the mean square error loss between the abnormal path prediction vector and the abnormal path vector;

[0145] Back propagation is performed based on the mean squared error loss to update the model parameters, and iterations are continued until the mean squared error loss converges.

[0146] In this embodiment, the abnormal path identification model uses the abnormal usage node as the identification starting point. Based on its previous adjacent structure in the assembly dependency path graph, it intercepts a local subgraph and generates an embedded representation as the model input. This local subgraph only selects the previous adjacent nodes of the abnormal node. The reason for this is that in the assembly logic of steel structures, the assembly sequence of subcomponents is reflected as a directed propagation path of structural dependencies. If the current node has an abnormal raw material usage, the material usage of the previous assembly node may not have triggered the abnormal threshold, but there is already an error accumulation or deviation trend. Although this trend itself is within the "tolerance range", once it enters the subsequent structural assembly chain, its tolerance characteristics may be the prerequisite for the occurrence of structural abnormalities in the subsequent path. Therefore, by introducing the "error accumulation feature", the model can model the state of the previous component that has not triggered the threshold but may have abnormality inducement, and pre-establish the semantic space of upstream and downstream abnormal transmission at the input end.

[0147] The model's output design also reflects assembly logic constraints. The output goal is to ensure that, in the adjacent structure immediately following the current abnormal node, there are at least two nodes identified as having abnormal usage, and that these two abnormal nodes must satisfy a clear upstream and downstream assembly dependency relationship. This means that the model focuses not only on whether an anomaly exists, but also on whether these anomalies structurally form a continuous assembly chain. Only when multiple abnormal nodes have assembly path connectivity can they be judged to constitute an abnormal dependency path. This path-level structural identification effectively distinguishes between isolated error triggers and systematic assembly anomaly trends, enhancing the model's ability to structurally identify areas where anomalies cluster.

[0148] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means.

[0149] The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0150] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative, and for example, multiple units or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0151] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A control and management system based on the usage quota of steel structure raw materials, characterized by: The management system includes: The quota acquisition module is used to obtain the raw material usage quota and raw material quantitative quota of the current sub-component; The local subgraph representation module is used to extract the local subgraph of the current subcomponent in the assembly dependency path graph based on the raw material usage quota and raw material quantitative quota of the current subcomponent, and generate an embedded representation of the local subgraph; The abnormal usage path output module is used to input the embedded representation of the local subgraph into the abnormal path recognition model and output the abnormal dependency path corresponding to the current subcomponent in the assembly dependency path graph.

2. The control and management system based on the steel structure raw material usage quota according to claim 1 is characterized in that: The modeling steps of the abnormal path identification model include: S1. Construct an assembly dependency path diagram of several sub-components in the steel structure; The assembly dependency path graph includes a number of sub-component nodes with assembly dependency relationships; the assembly dependency relationships include: path numbers and node numbers in each path number; S2. Anchoring a node to be determined from a plurality of sub-component nodes of the assembly dependency path graph; S3. Determine abnormality of the raw material usage of the node to be determined; S4. If the raw material usage of the node to be determined is normal, proceed to the next node to be determined along the assembly dependency path diagram according to the assembly dependency relationship to perform abnormality determination; S5. If the node to be determined is an abnormal usage, obtain the abnormal dependency path from the assembly dependency path graph and encode the abnormal dependency path into an abnormal path vector; S6. intercepting a local subgraph of the node corresponding to the abnormal usage and its N preceding adjacent nodes, and extracting an embedded representation of the local subgraph; S7. The embedded representation of the local subgraph is used as the input of the supervised model, and the abnormal path vector is used as the target variable. After iterative training, an abnormal path recognition model is generated.

3. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: Construct an assembly dependency path diagram for several sub-components in a steel structure, including: S1-1. Obtain the component types involved in the steel structure of the project; S1-2. Disassemble the steel structure in the project into several sub-components according to the types of components involved; S1-3, allocating predefined assembly dependencies among several sub-components; S1-4, define each subcomponent as a component node of the graph structure, and define the assembly dependency as a directed edge between the component nodes; S1-5. Connect any two adjacent component nodes that have assembly dependencies according to the directed edges between the component nodes until all assembly dependencies are connected; S1-6. Define the overall structure of component nodes and their directed edges as the assembly dependency path graph of sub-components.

4. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: Perform abnormal determination on the raw material usage of the node to be determined, including: S3-1. Obtain the raw material quota and raw material usage quota of the node to be determined S3-2. Calculate the real-time error between the raw material usage quota and the raw material quantitative quota of the node to be determined; S3-3, placing the real-time rated error into a threshold range, and determining that the real-time rated error is within the threshold range error position; S3-4, determine the amount of raw materials based on the error position; S3-5. If the error position is within the threshold range, the raw material usage of the node to be determined is output as normal usage; S3-6. If the error position is outside the threshold range, the raw material usage of the node to be determined is output as abnormal usage.

5. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: If the node to be determined is an abnormal usage, the abnormal dependency path is obtained from the assembly dependency path graph, including: S5-1. Based on the assembly dependency relationship, in the assembly dependency path graph, with the abnormal usage as the center, advance M subsequent adjacent nodes backward; S5-2, performing abnormality determination on the M subsequent adjacent nodes; S5-3. If the raw material usage of the M subsequent adjacent nodes is determined to have at least two abnormal usages, extract the assembly dependency path between the two abnormal usages; S5-4, determining the assembly dependency relationship of the assembly dependency path between the two abnormal usages; S5-5. If an upstream and downstream assembly dependency relationship exists on the assembly dependency path between the two abnormal usages, the abnormal usage and the dependency path with the upstream and downstream assembly dependency relationship are exported as the abnormal dependency path.

6. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: Perform abnormality determination on the M subsequent adjacent nodes, including: S5-2-1. Obtain the raw material quota and raw material usage quota of M subsequent adjacent nodes; S5-2-2. Calculate the real-time credit errors of M subsequent adjacent nodes; S5-2-3. Determine the error positions of the M subsequent adjacent nodes whose real-time credit errors are within a threshold range, and obtain M error positions; S5-2-4. Generate a raw material usage determination for the corresponding subsequent adjacent nodes based on the M error positions.

7. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: Extract the embedding vector of the local subgraph, including: S6-1, determining an assembly dependency feature of a preceding adjacent node in the local subgraph according to a path number and a node sequence number of the preceding adjacent node in the local subgraph; S6-2, determining an error accumulation characteristic of a preceding adjacent node in the local subgraph based on the real-time amount error of the preceding adjacent node in the local subgraph; S6-3. The local subgraph with assembly dependency features and error accumulation features is used as the input of the graph neural network. After node feature aggregation, the embedding vector of the local subgraph is obtained.

8. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: The step of obtaining the assembly dependency features of the N preceding adjacent nodes includes: A6-1. Define each preceding adjacent node as an intermediate node of the assembly-dependent feature; A6-2. Obtain the path number of the intermediate node; A6-3. Obtain the previous node and the next node adjacent to the intermediate node according to the path number of the intermediate node; A6-4. Obtain the node sequence numbers of the previous node and the next node; A6-5 concatenates the path number of the intermediate node, the node sequence numbers of the previous node, and the next node to obtain the position number of the previous adjacent node in the assembly dependency path graph; A6-6. Encode the position number into a one-hot vector and generate assembly dependency features of N preceding adjacent nodes.

9. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: The step of acquiring the error accumulation features of the N preceding adjacent nodes includes: B6-1. Obtain the real-time rated errors of N preceding adjacent nodes; B6-2. Normalize the real-time rated errors of N preceding adjacent nodes to generate N normalized errors; B6-3. Encode the N normalized errors into a one-hot vector to generate the error accumulation features of the N preceding adjacent nodes.

10. The control and management method based on the steel structure raw material usage quota according to claim 2 is characterized in that: After iterative training, an abnormal path recognition model is generated, including: Get the embedding representation of the local subgraph of the current batch and input it into the supervised learning model; Perform forward propagation on the embedded representation of the local subgraph of the current batch and output the corresponding abnormal path prediction vector; Calculate the mean square error loss between the abnormal path prediction vector and the abnormal path vector; Back propagation is performed based on the mean squared error loss to update the model parameters, and iterations are continued until the mean squared error loss converges.

Images