BIM-based digital acceptance management system for construction quality of water conservancy projects

Abstract

The application relates to the technical field of water conservancy engineering quality management, in particular to a water conservancy engineering construction quality digital acceptance management system based on BIM, which is used for solving the problem that the prior art cannot fuse BIM and OWL ontology, it is difficult to realize semantic modeling of quality control points and time attribute and multi-source data association, BIM model information cannot be dynamically updated and intelligent construction suggestions cannot be generated, and the intelligentization, precision and automation level of water conservancy engineering construction quality control is reduced; the water conservancy engineering construction quality digital acceptance management system based on BIM fuses BIM and OWL ontology through a water conservancy component quality intelligent control module, realizes semantic modeling of quality control points and time attribute and multi-source data association, dynamically updates BIM model information and generates intelligent construction suggestions, and the intelligentization, precision and automation level of water conservancy engineering construction quality control is significantly improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of water conservancy engineering quality management, in particular to a water conservancy engineering construction quality digital acceptance management system based on BIM. BACKGROUND

[0002] The traditional water conservancy engineering acceptance field has been subject to multiple technical bottlenecks for a long time. The scattered data system leads to the dispersion of design, construction and acceptance information. The manual comparison of drawings and measured data is low in efficiency and easy to introduce errors. The construction quality change is difficult to update to the acceptance model in real time, causing the deviation between the model and the entity, and affecting the accuracy and reliability of the results.

[0003] The patent application with the publication number CN118657415A discloses a water conservancy engineering construction quality digital acceptance management platform. The application analyzes and processes the excavation accuracy, stability and water seepage drainage qualification of earthwork projects to obtain the quality qualification of the earthwork projects and performs early warning. The layout qualification and the pouring qualification of concrete are analyzed to obtain the quality qualification of the foundation project and perform early warning. The application analyzes the excavation accuracy, stability and water seepage drainage qualification of earthwork projects to obtain the quality qualification of the earthwork projects, avoids the intervention of manual operation, reduces the generation of data errors, and thus improves the acceptance qualification of the earthwork projects. The layout qualification and the pouring qualification of concrete are analyzed to obtain the quality qualification of the foundation project. The data in the foundation project are intelligently analyzed to improve the acceptance qualification of the foundation project.

[0004] However, the above-mentioned reference patent analyzes the construction parameters of earthwork, foundation and steel frame intelligently to realize accurate evaluation of the quality qualification, reduce manual errors, improve the project acceptance qualification rate and construction quality and efficiency, but cannot integrate BIM and OWL ontology, is difficult to realize semantic modeling of the quality control points and the temporal attributes and correlation of multi-source data, cannot dynamically update the BIM model information and generate intelligent construction suggestions, and reduces the intelligent, accurate and automatic level of water conservancy engineering construction quality control. At the same time, it cannot construct a quantifiable and interpretable acceptance strategy parameter adjustment model, is difficult to realize dynamic optimization of the detection frequency, detection point arrangement and judgment threshold, cannot promote the transformation of acceptance from static fixation to dynamic accuracy, and reduces the acceptance efficiency, pertinence and engineering quality guarantee level.

[0005] Therefore, the application proposes a water conservancy engineering construction quality digital acceptance management system based on BIM in view of the above-mentioned problems. SUMMARY

[0006] The application aims to provide a BIM-based digital acceptance management system for construction quality of water conservancy projects, solve the problem that the prior art cannot integrate BIM and OWL ontology, it is difficult to realize semantic modeling of quality control points and temporal attributes and association of multi-source data, it is unable to dynamically update BIM model information and generate intelligent construction suggestions, and the intelligent, accurate and automatic level of construction quality control of water conservancy projects is reduced; meanwhile, it is unable to construct a quantifiable and interpretable acceptance strategy parameter adjustment model, it is difficult to realize dynamic optimization of detection frequency, detection point arrangement and determination threshold, it is unable to promote the transformation of acceptance from static fixation to dynamic precision, and the efficiency, pertinence and engineering quality guarantee level of acceptance are reduced.

[0007] The application aims to provide a BIM-based digital acceptance management system for construction quality of water conservancy projects, solve the problem that the prior art cannot integrate BIM and OWL ontology, it is difficult to realize semantic modeling of quality control points and temporal attributes and association of multi-source data, it is unable to dynamically update BIM model information and generate intelligent construction suggestions, and the intelligent, accurate and automatic level of construction quality control of water conservancy projects is reduced; meanwhile, it is unable to construct a quantifiable and interpretable acceptance strategy parameter adjustment model, it is difficult to realize dynamic optimization of detection frequency, detection point arrangement and determination threshold, it is unable to promote the transformation of acceptance from static fixation to dynamic precision, and the efficiency, pertinence and engineering quality guarantee level of acceptance are reduced.

[0008] The BIM-based digital acceptance management system for construction quality of water conservancy projects comprises:

[0009] The data acquisition and processing module is used for acquiring multi-source sensing data arranged at various automatic monitoring points in the construction process of water conservancy projects, and pre-processing the acquired multi-source sensing data.

[0010] The water conservancy component quality intelligent control module is used for constructing an OWL ontology to express quality control points and temporal attributes based on a BIM model, fusing the pre-processed multi-source sensing data, predicting component quality states by using a graph neural network and a multi-task learning method, dynamically updating BIM model information and generating construction optimization suggestions.

[0011] The water conservancy project acceptance execution module is used for automatically generating an acceptance task according to a construction progress, a component quality state and a dynamic acceptance strategy, comparing sensing data and specification standards by using a rule engine, and generating and archiving a digital acceptance report.

[0012] The water conservancy quality traceability control module is used for constructing a quality event graph based on a BIM component, associating abnormal data, early warning information and acceptance results, executing a problem disposal process and performing defect clustering analysis.

[0013] The water conservancy acceptance strategy optimization module is used for integrating a construction progress, environmental conditions, material states and historical acceptance data based on a BIM model, constructing an acceptance strategy parameter adjustment model, and dynamically generating a detection frequency, a detection point spatial arrangement scheme and a key index determination threshold.

[0014] As a preferred embodiment of the application, the process that the water conservancy component quality intelligent control module constructs an OWL ontology to express quality control points and temporal attributes based on a BIM model and fuses the pre-processed multi-source sensing data comprises:

[0015] extracting unique identifiers, types, spatial locations and material properties of structural units from the BIM model, creating a construction structural unit class instance for each structural unit, creating one or more quality control point class instances for each construction structural unit class instance, and creating quality state instances for each quality control point class instance at different time points;

[0016] obtaining pre-processed multi-source perception data, extracting pre-processed multi-source perception data related to each quality control point class instance, and aggregating data by time point;

[0017] creating a graph structure with node types of construction structural unit classes and quality control point classes, using the generated feature vectors as input features of quality control point class nodes, and outputting the graph structure as input of a graph neural network.

[0018] As a preferred embodiment of the present application, the process of predicting the quality state of the water conservancy component by the water conservancy component quality intelligent control module using the graph neural network and the multi-task learning method includes:

[0019] extracting unique identifiers of all structural components from the BIM model, creating a graph node for each component to form a node set V={v i};

[0020] analyzing the physical connection relationship between components in the BIM model, adding an edge between the corresponding nodes v i and v j if there is a physical connection between component A and component B, and forming an edge set E={(v i ,v j )};

[0021] for each component c i , obtaining the historical data of all quality control points thereof, and calculating the time-weighted average of the data as the feature vector f i of the node;

[0022] setting the network layer to 3 layers, updating the node features using the propagation rule, inputting the initial node features for three-layer graph convolution operation, and finally outputting the embedding representation z i of each component;

[0023] inputting the embedding representation z i of each node into two independent fully connected layers, performing forward propagation on each component corresponding node using the trained model, and respectively obtaining the classification result and the quality degradation degree prediction value.

[0024] As a preferred embodiment of the present application, the process of dynamically updating the BIM model information and generating construction optimization suggestions by the water conservancy component quality intelligent control module includes:

[0025] Obtaining an embedding representation z of each structural component i Obtaining an embedding representation z of each structural component i Inputting the classification head, and outputting a state corresponding to the maximum probability as a prediction result;

[0026] Obtaining an embedding representation z of each structural component i Inputting the regression head, and outputting a value as a component quality comprehensive score;

[0027] Adding the loss value of the classification task and the loss value of the regression task according to weights to obtain a joint loss function, creating an attribute hasPredictedStatus, and writing the predicted quality state into the ontology instance of the corresponding component, and creating an attribute predictedAt and writing the current time of the system in the format of xsd:dateTime;

[0028] Writing the updated OWL ontology data into the quality attribute field of the BIM model, inputting three pieces of data: the predicted quality state of the component, the construction stage number and the predicted quality state of the adjacent component;

[0029] According to a preset rule table, one instruction is generated for each component, and if multiple rules match, the instruction with the highest priority is taken;

[0030] Creating an attribute hasConstructionAdvice, writing the generated construction operation instruction into the ontology instance of the corresponding component, and inserting a record into the scheduling system interface table, and after the insertion operation is completed, the database transaction is committed.

[0031] As a preferred embodiment of the present application, the process of automatically generating an acceptance task by the water conservancy project acceptance execution module according to the construction progress, the component quality state and the dynamic acceptance strategy comprises:

[0032] Reading the current time of the system, and obtaining the planned completion ratio and the actual completion ratio corresponding to the current time from the construction plan data table;

[0033] Subtracting the planned completion ratio from the actual completion ratio to obtain a construction progress deviation value, reading a progress tolerance threshold, taking the absolute value of the construction progress deviation value, and determining whether the construction progress state is normal by comparing the absolute value with the progress tolerance threshold;

[0034] Reading the unique identifier of the first structural component from the component list, and obtaining all quality indicator detection values of the component from the quality monitoring system;

[0035] Multiplying the detection value of each quality indicator by the weight value corresponding thereto, adding all the product results to obtain a quality comprehensive score of the component, reading a quality score qualified benchmark value, and determining whether the component quality state meets the acceptance prerequisite by comparing the quality comprehensive score with the quality score qualified benchmark value;

[0036] checking whether the construction progress state is normal and whether the component quality state meets the acceptance prerequisite, creating a new record, and writing the record into an acceptance task table;

[0037] reading a unique identifier of a next structural component from a component list, and repeating all operations starting from obtaining a detection value from a quality monitoring system if there are still unprocessed components in the component list.

[0038] As a preferred embodiment of the present application, the process in which the water conservancy project acceptance execution module compares the perception data with the specification standard and generates a digital acceptance report by using a rule engine includes:

[0039] obtaining a component unique identifier, a quality index detection value list, a construction progress deviation value and a quality comprehensive score as input data, querying minimum allowable values and maximum allowable values of each quality index from a specification standard database according to the component unique identifier;

[0040] calling a rule engine, outputting a judgment result of each quality index by the rule engine, creating a digital acceptance report data structure, and serializing the report data structure into a structured data format.

[0041] As a preferred embodiment of the present application, the process in which the water conservancy quality traceability control module constructs a quality event graph based on a BIM component, and correlates abnormal data, early warning information and acceptance results includes:

[0042] reading unique identifiers, types, spatial positions and material attributes of all structural components from a BIM model, and creating a component node for each structural component;

[0043] generating an abnormal data record when a sensor monitors that temperature, stress or displacement data exceeds a preset threshold value, performing a corresponding operation for processing when the abnormal data meets a preset early warning rule, and performing a corresponding operation for processing when an event is rectified;

[0044] performing an acceptance when the rectification is completed, performing a corresponding operation for processing, and writing all nodes and edges into a graph database to form a quality event graph.

[0045] As a preferred embodiment of the present application, the process in which the water conservancy quality traceability control module executes a problem disposal process and performs defect clustering analysis includes:

[0046] reading current states of all structural components from a component state table, performing a corresponding state update process for each structural component, reading all historical defect records from a quality event graph, and performing a corresponding operation for processing for each defect record;

[0047] Set the number of clusters K, use the K-means algorithm to calculate the normalized feature sample set iteratively, output the clustering result, and write the clustering result into the defect analysis result table.

[0048] As a preferred embodiment of the present application, the process of the water acceptance strategy optimization module integrating construction progress, environmental conditions, material state and historical acceptance data based on the BIM model and constructing an acceptance strategy parameter adjustment model includes:

[0049] Reading the integrated component dataset from the BIM model, standardizing the construction progress state, and generating a construction progress state standardized value;

[0050] Standardizing the temperature, humidity and wind speed in the environmental conditions respectively, and generating an environmental comprehensive index;

[0051] Structuring the material state to generate a material state comprehensive score, and processing the historical acceptance data to generate a historical acceptance index;

[0052] Taking the construction progress state standardized value, the environmental comprehensive index, the material state comprehensive score and the historical acceptance index as four input features, reading the historical acceptance frequency adjustment value from the acceptance execution record as the model output label;

[0053] Defining the structure of the acceptance strategy parameter adjustment model, and using the least squares method to perform regression analysis on the input feature matrix and the output label vector;

[0054] Writing the model structure information into the model metadata table, and associating the model parameters and the model structure information through the model number.

[0055] As a preferred embodiment of the present application, the process of the water acceptance strategy optimization module dynamically generating detection frequency, detection point spatial arrangement scheme and key indicator judgment threshold value includes:

[0056] Obtaining a detection task trigger signal, reading the current construction completion ratio from the progress management system, reading the reference detection frequency from the system configuration table, and obtaining the current detection frequency through a series of processes;

[0057] Generating a detection frequency parameter, reading the geometric center coordinates of the component to be detected from the BIM model, reading the risk level of the component to be detected from the risk level table, and determining the number of detection points according to the risk level;

[0058] Taking the geometric center as the reference, generating a detection point spatial arrangement scheme on the surface of the component in a symmetrical distribution manner;

[0059] Reading the initial judgment threshold value of the key indicator from the design specification library, and calculating the material correction term;

[0060] Read the environmental condition influence coefficient from the system configuration table, read the current environmental condition from the environmental monitoring system, obtain the environmental correction term by calculation, add the initial judgment threshold, the material correction term and the environmental correction term to obtain the key indicator judgment threshold at the current time;

[0061] Generate the key indicator judgment threshold parameter, generate the detection task scheme data packet, and write the detection task scheme data packet into the detection task configuration table.

[0062] Compared with the prior art, the advantages of the present application are:

[0063] (1) In the present application, the quality intelligent control module of the water conservancy component fuses BIM and OWL ontology, realizes semantic modeling of quality control points and temporal attributes and multi-source data association, constructs a structured knowledge graph, uses graph neural networks and multi-task learning, combines component topological relations and time sequence features, synchronously predicts quality state and degradation degree, dynamically updates BIM model information and generates intelligent construction suggestions, forms a 'perception-analysis-decision-feedback' closed loop, and significantly improves the intelligentization, precision and automation level of water conservancy construction quality control;

[0064] (2) In the present application, the water conservancy acceptance strategy optimization module integrates construction progress, environment, materials and historical data, constructs a quantifiable and interpretable acceptance strategy parameter adjustment model, realizes dynamic optimization of detection frequency, detection point arrangement and judgment threshold, improves the scientificity and adaptability of acceptance resource configuration in a data-driven manner, enhances the response capability to complex working conditions, and the output optimization strategy effectively supports the intelligent decision of the water conservancy engineering acceptance execution module, promotes the transformation of acceptance from static fixed to dynamic precision, and significantly improves the acceptance efficiency, pertinence and engineering quality guarantee level. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 The system block diagram of the first embodiment in the present application;

[0066] Figure 2 The system block diagram of the second embodiment in the present application. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application; obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments; based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor are within the protection scope of the present application.

[0068] Embodiment one: as Figure 1As shown, the BIM-based digital acceptance management system for water conservancy construction quality presented by the application comprises:

[0069] The data acquisition and processing module is used for acquiring multi-source perception data arranged at various automatic monitoring points in the water conservancy construction process, the multi-source perception data comprising horizontal displacement of a cofferdam horizontal displacement monitoring point, vertical displacement of a soil and rock cofferdam vertical displacement monitoring point, wind speed of an aerial work wind speed monitoring point, internal temperature of a concrete temperature control monitoring point, strain of a concrete member strain monitoring point, water level elevation of a groundwater level observation well and real-time compressive strength of a concrete strength maturity monitoring point, and the multi-source perception data is preprocessed, the preprocessing operation comprising data cleaning, data calibration, time alignment and data format standardization.

[0070] The multi-source monitoring data such as displacement, wind speed, temperature and strain are automatically acquired and integrated by the data acquisition and processing module, and are preprocessed such as cleaning, calibration, time alignment and standardization, so that the data quality and real-time performance are significantly improved, the construction state is comprehensively perceived, and abnormal rapid early warning is realized; the standardized and modular design supports intelligent analysis and system expansion, reduces manual cost and error, guarantees data traceability, and provides solid support for safe, quality and intelligent management of water conservancy construction.

[0071] The water conservancy member quality intelligent control module constructs an OWL ontology to express quality control points and temporal attributes based on a BIM model, fuses the preprocessed multi-source perception data, predicts the member quality state by using a graph neural network and a multi-task learning method, dynamically updates BIM model information and generates construction optimization suggestions;

[0072] The process that the water conservancy member quality intelligent control module constructs an OWL ontology to express quality control points and temporal attributes based on a BIM model and fuses the preprocessed multi-source perception data comprises:

[0073] The unique identifier, type, spatial position and material attribute of a structural unit are extracted from the BIM model, a construction structural unit class instance is created for each structural unit;

[0074] A construction structural unit class is created for describing members in the project, and a quality control point class is created for describing quality monitoring positions or detection indexes attached to the members;

[0075] A member contains quality control point attribute is created, the action object of which is set to be the construction structural unit class, and the value range of which is the quality control point class;

[0076] A quality state attribute is created, the action object of which is set to be the quality control point class, and the value range of which is qualified, unqualified and re-inspection required;

[0077] A state time attribute is created, the action object of which is set to be the quality state, and the data type of which is date and time format.

[0078] create a previous state attribute, set its action object as the quality state instance, and set its value range as the quality state instance;

[0079] create a next state attribute, set its action object as the quality state instance, and set its value range as the quality state instance;

[0080] create one or more quality control point class instances for each construction structure unit class instance, and for each quality control point class instance, use the component contains quality control point attribute to associate the construction structure unit class instance to which it belongs;

[0081] create quality state instances for each quality control point class instance at different time points, each quality state instance is associated with a quality state value and a state time value, and multiple quality state instances of the same quality control point class instance are arranged in ascending order of state time value;

[0082] use the previous state attribute to connect the next state with the previous state, and use the next state attribute to connect the previous state with the next state, the first quality state instance is not set with the previous state attribute, and the last quality state instance is not set with the next state attribute;

[0083] obtain preprocessed multi-source sensing data, for each quality control point class instance, extract the preprocessed multi-source sensing data related to it, aggregate the data by time point, and combine the temperature, humidity, stress, strain, water content, material batch number, and construction process code at the same timestamp into a feature vector;

[0084] the vector contains eight elements, the first to fifth elements are temperature, humidity, stress, strain, and water content, the sixth element is the material batch number, the seventh element is the construction process code, and the eighth element is the timestamp code, missing values are filled with 0, and the feature vector is associated with the corresponding quality state instance;

[0085] create a graph structure, the node types are construction structure unit class and quality control point class, and add nodes: each construction structure unit class instance and quality control point class instance corresponds to a graph node;

[0086] add edges: for each component contains quality control point attribute, add an edge from the construction structure unit class node to the quality control point class node;

[0087] for each previous state attribute, add an edge from the previous quality state instance to the current quality state instance;

[0088] for each next state attribute, add an edge from the current quality state instance to the next quality state instance;

[0089] The generated feature vector is taken as an input feature of the quality control point class node, and the output graph structure is taken as an input of the graph neural network;

[0090] The process of predicting the quality state of the component by the water conservancy component quality intelligent control module using the graph neural network and the multi-task learning method includes:

[0091] All unique identifiers of the structural components are extracted from the BIM model, a graph node is created for each component to form a node set V={v i} where each node v i corresponds to a component c i ;

[0092] The physical connection relationship between the components in the BIM model is analyzed, and if there is a physical connection between component A and component B, an edge is added between the corresponding nodes v i and v j to form an edge set E={(v i ,v j )};

[0093] For each component c i , the historical data of all quality control points thereof are obtained, and the time-weighted average value of the data is calculated as the feature vector f i of the node, and the time weight is calculated using a decay factor, and the decay factor is equal to 0.95;

[0094] The graph G=(V,E) is constructed using the node set V and the edge set E, and the adjacency matrix A is added to the loop to obtain where I is the unit matrix, and the degree matrix D is calculated ;

[0095] The number of network layers is set to 3 layers, and the node features are updated by using a propagation rule, which is represented by the following formula:

[0096] where z is the node feature matrix of the lth layer, is the weight matrix of the lth layer, is the ReLU activation function;

[0097] The initial node feature z is input to perform three-layer graph convolution operation, and finally the embedding representation z i of each component is output.

[0098] The embedding representation z i of each node is input to two independent fully connected layers:

[0099] The first fully connected layer is used for classification task, and the output dimension is 3;

[0100] The second fully connected layer is used for the regression task, outputting a single value;

[0101] The trained model is used to perform forward propagation on the nodes corresponding to each component to obtain the classification results and the predicted value of the quality degradation.

[0102] The process by which the intelligent quality control module for hydraulic components dynamically updates BIM model information and generates construction optimization suggestions includes:

[0103] Obtain the embedded representation z of each structural component i As input data for the prediction task, the embedded representation z i Input the classification head, which is a fully connected neural network with an output dimension of 3, corresponding to three states: qualified, unqualified, and needing re-inspection. Output the probability distribution and take the state with the highest probability as the prediction result. During the training phase, the binary cross-entropy loss function is used to calculate the classification error.

[0104] The embedding representation z i The input regression head is a fully connected neural network with an output dimension of 1. The output value is scaled to the [0,100] range after Sigmoid transformation and is used as the comprehensive score of component quality. During the training phase, the mean squared error loss function is used to calculate the regression error.

[0105] The loss values ​​from the classification task and the regression task are added together by weights to obtain the joint loss function:

[0106] ;

[0107] in For classifying losses, To regress the loss, The classification loss weight is set to 1.0. The regression loss weight is set to 0.5.

[0108] Create the property hasPredictedStatus to write the predicted quality status to the corresponding component's ontology instance; create the property predictedAt to write the current system time in xsd:dateTime format.

[0109] Write the updated OWL ontology data into the quality attribute field of the BIM model. After the update operation is completed, the predicted state field value of the corresponding component in the BIM model will be the latest written value.

[0110] Input three data items: the predicted quality status of the component, the construction stage number, and the predicted quality status of adjacent components;

[0111] Matching is performed based on a preset rule table:

[0112] If the predicted quality status is unqualified, output the instruction PauseAndInspect;

[0113] If the predicted quality status is reinspection needed and the construction phase number is greater than 5, output the instruction StrengthenSupport;

[0114] If the adjacent component status is unqualified, output the instruction AdjustCuringCondition;

[0115] If the predicted quality status is unqualified and the adjacent component status is reinspection needed, output the instruction ReplanConstructionSequence;

[0116] Each component generates an instruction, and if multiple rules match, the one with the highest priority is taken;

[0117] Create an attribute hasConstructionAdvice and write the generated construction operation instruction to the ontology instance corresponding to the component;

[0118] Insert a record into the scheduling system interface table, including the following fields: component ID, operation instruction, and generation time, and after the insertion operation is completed, the database transaction is committed;

[0119] Through the water conservancy component quality intelligent control module, BIM and OWL ontology are integrated to realize semantic modeling of quality control points and temporal attributes and multi-source data association, and a structured knowledge graph is constructed; using graph neural networks and multi-task learning, combined with component topological relationships and temporal features, the quality state and degradation degree are simultaneously predicted; through dynamic updating of BIM model information and generation of intelligent construction suggestions, a "perception-analysis-decision-feedback" closed loop is formed, significantly improving the intelligent, precise, and automated level of water conservancy construction quality control.

[0120] The water conservancy project acceptance execution module is used to automatically generate acceptance tasks according to the construction progress, component quality status, and dynamic acceptance strategy, and to generate and archive digital acceptance reports by comparing sensing data and specification standards using a rule engine;

[0121] The process of automatically generating acceptance tasks by the water conservancy project acceptance execution module according to the construction progress, component quality status, and dynamic acceptance strategy includes:

[0122] Read the current time of the system, query the planned completion ratio and actual completion ratio corresponding to the current time from the construction plan data table;

[0123] Subtract the actual completion ratio from the planned completion ratio to get the construction progress deviation value, read the progress tolerance threshold, take the absolute value of the construction progress deviation value, and compare the absolute value with the progress tolerance threshold:

[0124] If the absolute value is greater than the progress tolerance threshold, record the construction progress state as abnormal, and if the absolute value is less than or equal to the progress tolerance threshold, record the construction progress state as normal.

[0125] Read the unique identifier of the first structural component from the component list, obtain all quality indicator detection values of the component from the quality monitoring system according to the component unique identifier, and read the weight values corresponding to each quality indicator from the quality weight configuration table;

[0126] Multiply the detection value of each quality indicator by its corresponding weight value, add all the product results to obtain the quality comprehensive score of the component, read the quality score qualified reference value, and compare the quality comprehensive score with the quality score qualified reference value:

[0127] If the quality comprehensive score is greater than or equal to the quality score qualified reference value, record the component quality state as meeting the acceptance prerequisite, and if the quality comprehensive score is less than the quality score qualified reference value, record the component quality state as not meeting the acceptance prerequisite;

[0128] Check whether the construction progress state is normal and the component quality state is the acceptance prerequisite:

[0129] If both are yes, enter the task generation process, and if either is no, skip the task generation and continue processing the next component;

[0130] Create a new record and write it into the acceptance task table, fill in the unique identifier of the current component in the new record, fill in the current system time in the new record, and fill in the task state in the new record, whose value is to be executed;

[0131] Read the unique identifier of the next structural component from the component list, and if there are still unprocessed components in the component list, repeat all operations starting from obtaining the detection value from the quality monitoring system, and if all components in the component list have been processed;

[0132] The process of the water conservancy project acceptance execution module comparing the perception data with the specification standard and generating a digital acceptance report using the rule engine includes:

[0133] Obtain the component unique identifier, quality indicator detection value list, construction progress deviation value, and quality comprehensive score as input data, and query the minimum allowable value and maximum allowable value of each quality indicator from the specification standard database according to the component unique identifier;

[0134] Call the rule engine, and the input content is: quality indicator detection value, minimum allowable value, and maximum allowable value;

[0135] The rule engine performs the following decision logic: if the detection value is less than the minimum allowable value, the output decision result is not in compliance, if the detection value is greater than the maximum allowable value, the output decision result is not in compliance, if the detection value is greater than or equal to the minimum allowable value and less than or equal to the maximum allowable value, the output decision result is in compliance;

[0136] The rule engine outputs the decision result of each quality indicator;

[0137] The rule engine counts the decision results: if there is at least one indicator whose decision result is not in compliance, the output component acceptance conclusion is not in compliance with the acceptance standard, if all indicators have decision results in compliance, the output component acceptance conclusion is in compliance with the acceptance standard;

[0138] Create a digital acceptance report data structure, fill in the component unique identifier, component acceptance conclusion, quality comprehensive score and construction progress deviation value in the report;

[0139] For each quality indicator, the following operations are performed:

[0140] If the detection value is greater than the maximum allowable value, calculate the positive deviation value by subtracting the maximum allowable value from the detection value, fill in the report, if the detection value is less than the minimum allowable value, calculate the negative deviation value by subtracting the minimum allowable value from the detection value, fill in the report, if the detection value is within the allowable range, fill in the deviation value 0;

[0141] Serialize the report data structure into a structured data format, generate a file name, write the serialized data into a file named with the file name, and transfer the file to the specified storage path of the digital archive system;

[0142] Through the water conservancy project acceptance execution module, the construction progress, component quality state and dynamic acceptance strategy are integrated, the intelligent triggering and automatic generation of acceptance tasks are realized, and the timeliness and pertinence of acceptance are improved; Based on the rule engine, automatically compare multi-source sensing data with standard specifications, accurately determine the compliance of indicators and overall acceptance conclusion, and ensure objective and consistent evaluation; Support the automatic generation and archiving of digital acceptance reports, the structure is clear and traceable, significantly improve the efficiency and standardization level of acceptance, and promote the digitalization and intelligentization transformation of water conservancy project acceptance.

[0143] The water quality traceability control module is based on BIM components to build a quality event graph, associate abnormal data, early warning information and acceptance results, execute problem handling processes and perform defect clustering analysis;

[0144] The process of the water quality traceability control module based on BIM components to build a quality event graph, associate abnormal data, early warning information and acceptance results includes:

[0145] Read the unique identifier, type, spatial location and material properties of all structural components from the BIM model, create a component node for each structural component, mark the node type as "component", and fill in the unique identifier, type, spatial location and material properties in the component node;

[0146] When the sensor monitors that the temperature, stress or displacement data exceeds the preset threshold, an abnormal data record is generated, and the abnormal data record is associated with the component node of the corresponding component, and the association type is "monitoring abnormality";

[0147] When the abnormal data meets the preset warning rule, the following operations are performed: read the unique identifier of the component associated with the abnormal data, determine the event type: if it is the first occurrence, the event type is one of crack, deformation or shedding, according to the rule matching classification code, create an event node, mark the node type as "event", fill in the classification code, event type and occurrence time in the event node, add a directed edge, the starting point is the component node, and the ending point is the event node, the edge type is marked as "occurrence", create a warning information, including component unique identifier, event classification code, trigger time and warning level, associate the warning information with the event node, and the association type is "trigger warning";

[0148] When the event is rectified, the following operations are performed: read the classification code and occurrence time of the event node, record the start time of rectification, add a directed edge, the starting point is the component node, and the ending point is the event node, and the edge type is marked as "rectification";

[0149] When the rectification is completed and the acceptance is performed, the following operations are performed: create an acceptance record, fill in the component unique identifier, event classification code, acceptance time and acceptance conclusion in the acceptance record, and the acceptance conclusion is "pass" or "fail", associate the acceptance record with the component node, and the association type is "acceptance result", and associate the acceptance record with the event node, and the association type is "acceptance result";

[0150] Write all nodes and edges into a graph database to form a quality event graph;

[0151] The process of executing the problem handling process and defect clustering analysis by the water quality traceability control module includes:

[0152] Read the current state of all structural components from the component state table, and perform the following state update process for each structural component:

[0153] Read whether the component has associated quality events, if not associated, keep the state as normal, if first associated quality events and the current state is normal, update the state to be evaluated, read whether the component has generated warning information, if it has been generated and the current state is to be evaluated, update the state to warning, read whether the component has added edges of type "rectification", if it has been added and the current state is in warning, update the state to rectification, read whether the component has associated acceptance records, if the acceptance conclusion is passed and the current state is in rectification, update the state to have been accepted, verify the state transition path: if the state jumps from to be evaluated to rectification, mark it as abnormal transition, if the state backtracks from accepted to rectification, mark it as illegal operation, all legal transitions only allow to proceed in the direction of normal→to be evaluated→warning→rectification→accepted, write the updated state back to the component state table;

[0154] Read all historical defect records from the quality event graph, and perform the following operations on each defect record:

[0155] Extract the defect category, which takes one of the values of crack, deformation or shedding, extract the component type, extract the spatial coordinates X, Y, Z, extract the occurrence time, convert it to the number of hours since January 1, 1970, extract the severity level, which takes an integer value from 1 to 5;

[0156] Organize each defect record into a feature sample, and perform standardization processing on all feature samples:

[0157] Z-score standardization is used for numerical fields, and one-hot encoding is performed for category fields;

[0158] Set the number of clusters K to 5, and use the K-means algorithm to iteratively calculate the standardized feature sample set:

[0159] Randomly initialize K cluster centers, assign each sample to the nearest cluster center, recalculate the center of each cluster, repeat the assignment and update until the cluster centers no longer change significantly or the maximum number of iterations is reached;

[0160] Output the clustering result, label each defect record with the cluster number it belongs to, and write the clustering result to the defect analysis result table;

[0161] The quality event graph integrating abnormal data, warning information and acceptance results is constructed through the water quality traceability management module, realizing the full-chain visual traceability of quality problems; clear state transition rules are defined to automatically execute problem handling processes and check operation compliance, ensuring that the management process is standardized and orderly; combined with defect multi-dimensional feature clustering analysis, the distribution law and potential association of quality problems are mined, supporting the transition from passive response to active prevention, significantly improving the systematicness, intelligence and decision-making scientific level of water conservancy engineering quality management.

[0162] Embodiment two: the technical scheme of the embodiment of the application is different from that of embodiment one in that

[0163] As shown in the figure, the water acceptance strategy optimization module integrates the construction progress, environmental conditions, material state and historical acceptance data based on the BIM model, constructs an acceptance strategy parameter adjustment model, dynamically generates detection frequency, detection point spatial arrangement scheme and key indicator judgment threshold, and outputs the optimized strategy to the water conservancy project acceptance execution module for guiding the execution of dynamic acceptance tasks. Figure 2 The process of the water acceptance strategy optimization module integrating the construction progress, environmental conditions, material state and historical acceptance data based on the BIM model and constructing the acceptance strategy parameter adjustment model includes:

[0164] Reading the integrated component data set from the BIM model, the data set containing the construction progress state, environmental conditions, material state and historical acceptance data of each component, standardizing the construction progress state, and converting the original value into a dimensionless value using the mean and standard deviation of the historical data;

[0165] Standardizing the temperature, humidity and wind speed in the environmental conditions respectively, then calculating the arithmetic mean of the three, and generating an environmental comprehensive index;

[0166] Structural processing of material state: converting material arrival time to material age, comparing average temperature during storage with standard storage temperature to calculate temperature deviation, comparing average humidity during storage with standard storage humidity to calculate humidity deviation, mapping material batch number to historical quality score of the batch, and weighted sum of age, temperature deviation, humidity deviation and quality score to generate a material state comprehensive score, and standardizing the comprehensive score;

[0167] Processing of historical acceptance data: reading the number of acceptance passes and total number of acceptance of the same type of component in historical projects, calculating the acceptance pass rate, and standardizing the pass rate to generate a historical acceptance index;

[0168] Taking the construction progress state standardized value, environmental comprehensive index, material state comprehensive score and historical acceptance index as four input features, reading the historical acceptance frequency adjustment value from the acceptance execution record as the model output label, and normalizing the output label to make it in a unified numerical range;

[0169] Defining the structure of the acceptance strategy parameter adjustment model: the model type is a linear regression model, the input is four features, and the output is an acceptance frequency adjustment coefficient;

[0170]

[0171] ​The input feature matrix and output label vector are analyzed by using the least square method to obtain four regression coefficients, which correspond to the influence weights of construction progress state, environmental condition, material state and historical acceptance data, and the four regression coefficients are written into the model parameter table;

[0172] The model structure information is written into the model metadata table, including the model type, input feature name and output variable name, the model parameters are associated with the model structure information through the model number, and the model state is set to built;

[0173] The process of dynamically generating detection frequency, detection point spatial arrangement scheme and key indicator judgment threshold by water conservancy acceptance strategy optimization module includes:

[0174] Get the detection task trigger signal, read the current construction completion ratio from the progress management system, read the reference detection frequency from the system configuration table, read the frequency adjustment coefficient from the system configuration table, use the inverse function of the standard normal distribution to transform the current construction completion ratio, multiply the transformation result by the frequency adjustment coefficient, add the product result to the reference detection frequency to get the current detection frequency, and the detection frequency generation model is represented by the following formula:

[0175] Where f(t) is the detection frequency at the current time, μ is the reference detection frequency, σ is the frequency adjustment coefficient, is the inverse function of the standard normal distribution, and R(t) is the current construction completion ratio;

[0176] Generate detection frequency parameters, parameter value is the calculation result, read the geometric center coordinates of the detected component from the BIM model, read the risk level of the detected component from the risk level table, and determine the number of detection points according to the risk level: risk level 1, number 1, risk level 2, number 2, risk level 3, number 3, risk level 4, number 4, risk level 5, number 5;

[0177] Take the geometric center as the reference, generate detection point positions on the component surface in a symmetrical distribution manner, generate unique identifiers and three-dimensional space coordinates for each detection point, generate a detection point spatial arrangement scheme, which contains the identifiers and coordinates of all detection points, and bind the detection point spatial arrangement scheme with the component unique identifier;

[0178] Read the initial judgment threshold of the key indicator from the design specification library, read the material state influence coefficient from the system configuration table, read the current material state from the material management system, calculate the deviation value of the material state from the standard state, multiply the material state influence coefficient and the material state deviation value to get the material correction term;

[0179] The environmental condition influence coefficient is read from the system configuration table, the current environmental condition is read from the environmental monitoring system, the deviation value from the ideal state is calculated, the environmental condition influence coefficient is multiplied by the environmental condition deviation value to obtain the environmental correction term, the initial judgment threshold, the material correction term and the environmental correction term are added to obtain the key indicator judgment threshold at the current time, and the judgment threshold dynamic adjustment model is represented by the following formula:

[0180] wherein is the judgment threshold at the current time, is the initial judgment threshold, is the material state influence coefficient, is the deviation value of the material state from the standard state, is the environmental condition influence coefficient, is the deviation value of the environmental condition from the ideal state.

[0181] The key indicator judgment threshold parameter is generated, the parameter value is the calculation result, the detection task scheme data packet is generated, the data packet includes: the detection frequency parameter, the detection point space arrangement scheme and the key indicator judgment threshold parameter, the detection task scheme data packet is written into the detection task configuration table, and the scheme state is marked as generated;

[0182] The construction progress, environment, material and historical data are integrated through the water conservancy acceptance strategy optimization module, a quantifiable and interpretable acceptance strategy parameter adjustment model is constructed, the dynamic optimization of the detection frequency, the detection point arrangement and the judgment threshold is realized, in a data-driven manner, the scientificity and adaptability of the acceptance resource configuration are improved, and the response capability to complex working conditions is enhanced; the output optimization strategy effectively supports the intelligent decision of the water conservancy engineering acceptance execution module, promotes the transformation of acceptance from static fixation to dynamic precision, and significantly improves the acceptance efficiency, the pertinence and the engineering quality guarantee level.

[0183] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any skilled person in the art can make equivalent replacement or change according to the technical scheme and the improvement concept of the present application within the technical range disclosed by the present application, which should be covered in the protection scope of the present application.

Claims

1. A BIM-based digital acceptance management system for water conservancy project construction quality, characterized in that: include: The data acquisition and processing module is used to collect multi-source sensing data from various automated monitoring points deployed during the construction of water conservancy projects, and to preprocess the collected multi-source sensing data. The intelligent quality control module for hydraulic components uses an OWL ontology built on a BIM model to express quality control points and temporal attributes. It integrates pre-processed multi-source perception data, uses graph neural networks and multi-task learning methods to predict the quality status of components, dynamically updates BIM model information, and generates construction optimization suggestions. The water conservancy project acceptance execution module is used to automatically generate acceptance tasks based on construction progress, component quality status and dynamic acceptance strategies. It uses a rule engine to compare perceived data with standards and specifications to generate and archive digital acceptance reports. The water conservancy quality traceability and control module constructs a quality event map based on BIM components, associates abnormal data, early warning information and acceptance results, executes the problem handling process and performs defect clustering analysis. The water conservancy acceptance strategy optimization module integrates construction progress, environmental conditions, material status, and historical acceptance data based on the BIM model to construct an acceptance strategy parameter adjustment model, dynamically generating inspection frequency, inspection point spatial layout scheme, and key indicator judgment thresholds.

2. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 1, characterized in that, The process by which the intelligent quality control module for hydraulic components constructs an OWL ontology based on the BIM model to express quality control points and temporal attributes, and integrates preprocessed multi-source sensing data, includes: Extract the unique identifier, type, spatial location, and material properties of structural units from the BIM model, and create a construction structural unit class instance for each structural unit; Create one or more quality control point class instances for each construction structure unit class instance. For each quality control point class instance, use components to contain quality control point attributes. Create quality status instances for each quality control point class instance at different time points. Obtain the preprocessed multi-source sensing data, extract the preprocessed multi-source sensing data related to each quality control point instance, and aggregate the data by time point; Create a graph structure with node types of construction structure unit class and quality control point class. Use the generated feature vector as the input feature of the quality control point class node, and use the output graph structure as the input of the graph neural network.

3. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 2, characterized in that, The process by which the intelligent quality control module for hydraulic components predicts the quality status of components using graph neural networks and multi-task learning methods includes: Extract unique identifiers for all structural components from the BIM model, and create a graph node for each component, forming a node set V={v i }; Analyze the physical connections between components in the BIM model. If there is a physical connection between component A and component B, then at the corresponding node v i and v j Add an edge between them to form the edge set E={(v i ,v j )}; For each component c i Obtain historical data for all quality control points, and calculate the time-weighted average of these data as the feature vector f for this node. i ; The network has three layers. Each layer updates node features using a propagation rule. The initial node features are input and subjected to a three-layer graph convolution operation. The final output is the embedding representation z of each component. i ; The embedding representation of each node z i The input is fed into two independent fully connected layers, and the trained model is used to perform forward propagation on the nodes corresponding to each component to obtain the classification results and the predicted value of the quality degradation degree, respectively.

4. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 3, characterized in that, The process by which the intelligent quality control module for hydraulic components dynamically updates BIM model information and generates construction optimization suggestions includes: Obtain the embedded representation z of each structural component i , embedding representation z i Input the classification header, output the state corresponding to the highest probability as the prediction result, and embed the representation z. i Input the regression head, and output the value as the overall quality score of the component; The loss values ​​of the classification task and the regression task are added together by weight to obtain the joint loss function. An attribute hasPredictedStatus is created to write the predicted quality status into the ontology instance of the corresponding component. An attribute predictedAt is created to write the current system time in xsd:dateTime format. Write the updated OWL ontology data into the quality attribute field of the BIM model, and input three data items: the predicted quality status of the component, the construction stage number, and the predicted quality status of adjacent components. Matching is performed according to a preset rule table. Each component generates one instruction. If multiple rules match, the one with the highest priority is selected. Create the attribute hasConstructionAdvice, write the generated construction operation instructions into the corresponding component's ontology instance, insert a record into the scheduling system interface table, and commit the database transaction after the insertion operation is completed.

5. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 1, characterized in that, The process by which the water conservancy project acceptance execution module automatically generates acceptance tasks based on construction progress, component quality status, and dynamic acceptance strategies includes: Read the current system time and retrieve the planned completion rate and actual completion rate corresponding to the current time from the construction plan data table; Subtract the planned completion percentage from the actual completion percentage to obtain the construction progress deviation value. Read the progress tolerance threshold, take the absolute value of the construction progress deviation value, and determine whether the construction progress status is normal by comparing the absolute value with the progress tolerance threshold. Read the unique identifier of the first structural component from the component list, and obtain all quality index test values ​​of the component from the quality monitoring system based on the component's unique identifier; The measured value of each quality indicator is multiplied by its corresponding weight value, and all the product results are added together to obtain the overall quality score of the component. The quality score pass benchmark value is read, and the overall quality score is compared with the quality score pass benchmark value to determine whether the quality status of the component meets the acceptance conditions. Check whether the construction progress status is normal and whether the component quality status meets the acceptance requirements. Create a new record and write it into the acceptance task table. Read the unique identifier of the next structural component from the component list. If there are still unprocessed components in the component list, repeat all operations starting from obtaining the detection value from the quality monitoring system.

6. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 5, characterized in that, The process by which the water conservancy project acceptance execution module uses a rule engine to compare perceived data with standards and specifications and generates a digital acceptance report includes: The system obtains the component's unique identifier, a list of quality indicator test values, construction progress deviation values, and comprehensive quality score as input data. Based on the component's unique identifier, it queries the minimum and maximum allowable values ​​for each quality indicator from the standard database. The rules engine is invoked, and it outputs the judgment results for each quality indicator, creating a digital acceptance report data structure and serializing the report data structure into a structured data format.

7. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 1, characterized in that, The water conservancy quality traceability and control module constructs a quality event map based on BIM components, and the process of linking abnormal data, early warning information and acceptance results includes: Read the unique identifiers, types, spatial locations, and material properties of all structural components from the BIM model, and create a component node for each structural component; When the sensor detects that the temperature, stress or displacement data exceeds the preset threshold, an abnormal data record is generated. When the abnormal data meets the preset warning rules, corresponding operations are performed for processing. When the event is rectified, corresponding operations are performed for processing. When the rectification is completed and acceptance is carried out, the corresponding operations are performed to process the data, and all nodes and edges are written into the graph database to form a quality event graph.

8. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 7, characterized in that, The process by which the water conservancy quality traceability and control module executes the problem handling procedure and performs defect clustering analysis includes: Read the current status of all structural components from the component status table, execute the corresponding status update process for each structural component, read all historical defect records from the quality event graph, and perform corresponding operations to process each defect record. Set the number of clusters K, use the K-means algorithm to iteratively calculate the standardized feature sample set, output the clustering results, and write the clustering results into the defect analysis result table.

9. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 1, characterized in that, The process by which the water conservancy acceptance strategy optimization module integrates construction progress, environmental conditions, material status, and historical acceptance data based on the BIM model and constructs an acceptance strategy parameter adjustment model includes: Read the integrated component dataset from the BIM model, standardize the construction progress status, and generate standardized construction progress status values. Temperature, humidity, and wind speed in environmental conditions are standardized to generate comprehensive environmental indicators. The material condition is structured to generate a comprehensive material condition score, and historical acceptance data is processed to generate historical acceptance indicators. The standardized value of construction progress status, comprehensive environmental index, comprehensive score of material status, and historical acceptance index are used as four input features. The historical acceptance frequency adjustment value is read from the acceptance execution record and used as the model output label. Define the acceptance strategy parameters to adjust the model structure, and use the least squares method to perform regression analysis on the input feature matrix and the output label vector; Write the model structure information into the model metadata table, and establish a relationship between the model parameters and the model structure information through the model number.

10. The BIM-based digital acceptance management system for water conservancy project construction quality according to claim 9, characterized in that, The process by which the water conservancy acceptance strategy optimization module dynamically generates the detection frequency, the spatial layout plan of detection points, and the judgment thresholds for key indicators includes: The system acquires the detection task trigger signal, reads the current construction completion percentage from the progress management system, reads the baseline detection frequency from the system configuration table, and obtains the current detection frequency through a series of processes. Generate inspection frequency parameters, read the geometric center coordinates of the component to be inspected from the BIM model, read the risk level of the component to be inspected from the risk level table, and determine the number of inspection points based on the risk level; Based on the geometric center, the locations of detection points are generated on the surface of the component in a symmetrical manner. A unique identifier and three-dimensional spatial coordinates are generated for each detection point, and a spatial arrangement scheme for the detection points is generated. The initial judgment thresholds of key indicators are read from the design specification library, the material state influence coefficient is read from the system configuration table, the current material state is read from the material management system, and the material correction items are calculated. The environmental condition influence coefficient is read from the system configuration table, the current environmental conditions are read from the environmental monitoring system, the environmental correction item is calculated, and the initial judgment threshold, material correction item, and environmental correction item are added together to obtain the current key indicator judgment threshold. Generate key indicator judgment threshold parameters, generate detection task plan data package, and write the detection task plan data package into the detection task configuration table.

Images