BIM-based bridge construction monitoring method and system

Abstract

The application discloses a bridge construction monitoring method and system based on BIM, and belongs to the technical field of bridge construction. By extracting construction time deviation characteristics and structure response deviation characteristics, a drift index is calculated to evaluate the binding error degree between data and components, and a differentiated processing strategy is implemented based on the drift level. For high-risk data, a similarity score mechanism is introduced, and an intelligent matching algorithm is used to identify the optimal component and complete rebinding. Finally, the accurate data warehousing and dynamic updating of the BIM model state are realized, thereby effectively improving the binding accuracy, risk identification capability and model linkage efficiency of construction monitoring data, and enhancing the intelligent management and decision support level of bridge construction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge construction, in particular to a bridge construction monitoring method and system based on BIM. BACKGROUND

[0002] Bridge construction monitoring based on BIM refers to the use of building information modeling (BIM) technology to digitally, visually and intelligently monitor and manage various construction activities in the bridge construction process. Through BIM model integration of design drawings, construction progress, equipment status and quality detection data, dynamic tracking, problem early warning and collaborative decision-making of the whole construction process are realized, thereby improving construction efficiency and ensuring engineering quality and safety.

[0003] The prior art has the following shortcomings:

[0004] In bridge construction monitoring based on BIM, when real-time data is bound to model components using metadata such as geographic location, timestamp and component ID, data drift may cause component binding errors. Due to the influence of GPS signal blocking, reflection and other factors on the site, the sensor position information may be offset, causing the data to be misbound to adjacent or incorrect bridge components, thereby causing risk warning misjudgment, real risk being ignored, historical data distortion and other serious consequences, affecting engineering safety and decision-making accuracy. SUMMARY

[0005] The purpose of the present application is to provide a bridge construction monitoring method and system based on BIM to solve the problems in the background art.

[0006] In order to achieve the above-mentioned purpose, the present application provides the following technical solution: a bridge construction monitoring method based on BIM, comprising:

[0007] Obtaining real-time sensor data from the bridge construction site, the data including timestamp, component ID, geographic location coordinates and physical response data;

[0008] Extracting data drift related features from the sensor data, including construction time deviation features and structural response deviation features;

[0009] According to the construction time deviation features and structural response deviation features, a drift index is calculated to evaluate the binding error degree between the sensor data and the target component;

[0010] Based on the drift index, the sensor data is divided into three drift levels of high risk, medium risk and low risk, and different drift level data is subjected to differential processing:

[0011] If the drift level is high risk, based on the sensor data and drift index, the similarity score of the target component is calculated, and the target component with the highest similarity score is selected to replace the original binding component;

[0012] The sensor data after binding confirmation is written into the database, and the state information of the corresponding component in the BIM model is updated.

[0013] Preferably, the real-time sensor data from the bridge construction site includes: arranging multiple types of sensors at the components of the bridge structure, and uniquely numbering each sensor or establishing an initial binding relationship with the component ID; the sensors include stress meters, strain gauges, displacement meters, accelerometers, temperature sensors, humidity sensors and GPS positioning modules.

[0014] Preferably, the construction time deviation feature is used to judge the time deviation degree between the time stamp and the construction time plan of the corresponding component in the BIM model, and the extraction method is:

[0015] The construction process dependency graph G(V, E) is constructed, where each node V represents a bridge component or a construction process; the directed edge E represents that each edge (v i →v j ) represents that the component v i is the prerequisite for the construction of v j ; for the target component C t bound by the sensor data, extract its: all direct predecessor nodes P(C t ): must be completed before the construction of C t ; all direct successor nodes S(C t ): can be constructed after C t ; sensor record timestamp T data ; obtain from the BIM construction plan or historical record: predecessor node completion time set: successor node start time set: Define the construction time deviation value ΔT dep , which represents the position deviation degree of the target component in the dependency path, and the expression is: In the formula, is the actual completion time of the i-th predecessor component, is the planned start or actual start time of the j-th successor component.

[0016] Preferably, the structural response deviation feature is used to judge the deviation degree between the physical response data of the sensor and the simulation value of the component or the historical data of the adjacent component, and the extraction method is:

[0017] Let the sensor be in a certain time window t∈[t1,t nresponse data collected in the interior is X={x1, x2,..., xn}; wherein x n represents a stress or strain value, and n is the total number of response data; and the simulation data distribution of the target component is Y={y1, y2,..., ym}; m is the total number of simulation data; X and Y are sorted and normalized to form empirical distribution functions F n m and F X , respectively, and the structural response deviation value W(X, Y) of F Y is calculated, and the expression is as follows: z is an integral variable, representing an arbitrary point in the response value range.

[0018] Preferably, according to the construction time deviation feature and the structural response deviation feature, a drift index is calculated to evaluate the binding error degree between the sensor data and the target component, and specifically includes:

[0019] The construction time deviation value and the structural response deviation value are normalized to be between 0 and 1, and the drift index is calculated according to the normalized construction time deviation value and the structural response deviation value.

[0020] Preferably, based on the drift index, the sensor data is divided into three drift levels of high risk, medium risk and low risk, and different drift level data is subjected to differential processing, specifically including:

[0021] The obtained drift index is compared with gradient standard thresholds, the gradient standard thresholds include a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the drift index is compared with the first standard threshold and the second standard threshold, respectively.

[0022] If the drift index is greater than the second standard threshold, the sensor data is determined as a high-risk drift level, and a binding correction process is triggered.

[0023] If the drift index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the sensor data is determined as a medium-risk drift level, and the data is marked as a confirmation state, which is verified semi-automatically through manual review or in combination with auxiliary information.

[0024] If the drift index is less than the first standard threshold, the sensor data is determined as a low-risk drift level, and it is considered that the binding relationship is reliable, and the binding is automatically completed and included in the BIM model updating process.

[0025] ​Preferably, if the drift level is high risk, a similarity score of the target component is calculated based on the sensor data and the drift index, and the target component with the highest similarity score is selected to replace the original bound component, specifically comprising:

[0026] For the current high-risk drift sensor data, a data feature vector of multiple modalities is constructed All candidate components C in the BIM model i , respectively extract its existing construction time deviation feature and structural response deviation feature, and map it to a component vector Form a standard candidate library d is the total number of components;

[0027] Use a multi-modal embedding model S to map the input vector to a unified embedding space: In the formula, is the multi-modal embedding vector of the current sensor data, is the standard multi-modal embedding vector of the candidate component C i ;

[0028] For each candidate component C i , calculate the vector similarity score S i of the current sensor data: In the formula, is the Euclidean norm of the vector , is the Euclidean norm of the vector ; get the score set of all components, select the component with the highest score, if it is greater than the confidence threshold, replace the original bound component, complete the correction; otherwise, mark the sensor data as low confidence binding, enter the artificial review process.

[0029] The application also provides a bridge construction monitoring system based on BIM, comprising a data acquisition module, a drift feature extraction module, an evaluation module, a classification processing module, a component rebinding module and a BIM model updating module;

[0030] Data acquisition module: obtain real-time sensor data from the bridge construction site, the data including timestamp, component ID, geographic position coordinates and physical response data;

[0031] Drift feature extraction module: extract data drift related features in the sensor data, including construction time deviation feature and structural response deviation feature;

[0032] Evaluation module: calculate the drift index according to the construction time deviation feature and the structural response deviation feature, which is used to evaluate the binding error degree between the sensor data and the target component;

[0033] The hierarchical processing module: based on the drift index, the sensor data is divided into three categories of drift levels: high risk, medium risk and low risk, and different processing is performed on data of different drift levels:

[0034] The component re-binding module: if the drift level is high risk, the similarity score of the target component is calculated based on the sensor data and the drift index, and the target component with the highest similarity score is selected to replace the original bound component;

[0035] The BIM model updating module: the bound sensor data is written into the database, and the state information of the corresponding component in the BIM model is updated.

[0036] In the above technical solution, the technical effects and advantages provided by the present application are:

[0037] 1. The present application introduces construction time deviation characteristics and structural response deviation characteristics, constructs a drift index evaluation mechanism, realizes quantitative evaluation of sensor data and BIM component binding error, breaks through the limitations of existing component ID and geographic location binding, effectively solves the technical problems of component binding error, risk warning misjudgment and monitoring data distortion caused by GPS drift and other problems. Through risk level division and differential processing of sensor data, not only the accuracy of data binding is improved, but also the intelligent identification and dynamic control ability in bridge construction process is enhanced.

[0038] 2. The present application introduces multi-modal embedded matching algorithm, performs component re-identification on high-risk data, establishes a unified embedding space by fusing structure response, time and space information, realizes high-precision component similarity score and binding correction, and ensures the consistency and reliability of monitoring data and BIM model. Combined with the database storage and BIM model state synchronous updating mechanism, a data-driven monitoring closed-loop system is constructed, which significantly improves the intelligent, visual and decision support level of bridge construction monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0040] Figure 1 The method mind map of the present application.

[0041] Figure 2 The system module mind map of the present application. DETAILED DESCRIPTION

[0042] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0043] Embodiment 1, please refer to Figure 1 The BIM-based bridge construction monitoring method described in the embodiment includes:

[0044] Obtaining real-time sensor data from a bridge construction site, the data including a timestamp, a component ID, geographic position coordinates and physical response data;

[0045] Extracting data drift-related features in the sensor data, including construction time deviation features and structural response deviation features;

[0046] According to the construction time deviation features and the structural response deviation features, calculating a drift index for evaluating the binding error degree between the sensor data and the target component;

[0047] Based on the drift index, dividing the sensor data into three drift levels of high risk, medium risk and low risk, and performing differential processing on the data of different drift levels:

[0048] If the drift level is high risk, calculating a similarity score of the target component based on the sensor data and the drift index, and selecting the target component with the highest similarity score to replace the original binding component;

[0049] Writing the sensor data after binding confirmation into a database and updating the state information of the corresponding component in the BIM model.

[0050] Obtaining real-time sensor data from a bridge construction site, specifically including:

[0051] Sensor arrangement and numbering: Pre-installing various types of sensors at key components of the bridge structure (such as bridge piers, main beams, suspension cable anchoring sections, etc.), including but not limited to stress gauges, strain gauges, displacement gauges, accelerometers, temperature sensors, humidity sensors and GPS positioning modules, and uniquely numbering each sensor or establishing an initial binding relationship with the component ID.

[0052] Data field collection definition:

[0053] Each sensor collects data in real time and generates a data packet including the following contents:

[0054] Timestamp: represents the collection time of the data record, accurate to seconds or milliseconds;

[0055] Component ID: represents the component number that the sensor is initially bound or identified (if pre-bound);

[0056] Geographical position coordinates: spatial coordinates provided by GPS or high-precision RTK positioning module, format includes longitude, latitude and optional elevation data;

[0057] Physical response data: according to different sensor types, may include structural stress value, strain value, acceleration value, displacement, temperature, humidity, voltage change and other indicators;

[0058] Data upload and identification packaging: the data is uploaded to the data receiving server or BIM monitoring platform through wired or wireless communication methods (such as LoRa, NB-IoT, 4G / 5G network); Each data packet is attached with a unique data identifier (data UID) for subsequent tracking and error correction processing.

[0059] Data preprocessing and caching mechanism: the uploaded data is preferentially processed in the cache processing area before entering the main processing flow, and the preprocessing operations such as format verification, missing value filling and outlier removal are performed to ensure that the data quality meets the requirements and meets the subsequent component binding calculation requirements.

[0060] Multi-source synchronization and time alignment mechanism: for data packets from different sensors, the system uses a unified time synchronization mechanism (such as based on NTP protocol or local master clock alignment) to ensure a unified time reference when analyzing multiple sensors.

[0061] Construction time deviation feature, used to judge the time deviation degree between the timestamp and the construction time plan of the corresponding component in the BIM model, the extraction method is:

[0062] The bridge construction process is abstracted as a directed acyclic graph (DAG), each node in the graph represents a construction component or process, and each edge represents the construction dependency relationship. By analyzing the sensor data timestamp and the construction completion time of other components in the dependency path, the time deviation degree in the entire construction logic is evaluated to determine whether the binding of the data is reasonable.

[0063] Construction process dependency graph G(V, E) is constructed, where each node V represents a bridge component or construction process, such as piers, beam segments, tower, etc.

[0064] Directed edge E represents each edge (v i →v j ) represents that component v i is the prerequisite for the construction of v j ;

[0065] For the target component C of sensor data binding t Extract its:

[0066] All direct predecessor nodes P(C) t ): Must be in C t Completed before construction;

[0067] All direct successor nodes S(C) t ): In C t Construction can only begin after that.

[0068] Sensor records timestamp T data ;

[0069] Obtain the following from BIM construction plans or historical records: Set of completion times for predecessor nodes: Set of start times for successor nodes:

[0070] Define the construction time deviation value ΔT dep This indicates the degree of deviation of the target component from its position in the dependency path, expressed as: In the formula, Let be the actual completion time of the i-th precursor component. This represents the planned or actual start time of the j-th successor component.

[0071] A larger construction time deviation value indicates that the timestamp of the sensor data deviates further from the construction schedule time window of the target component in the BIM model. This usually indicates a higher degree of binding error between the data and the target component. In other words, the data collected by the sensors is likely to come from other components or construction stages, significantly increasing the risk of misbinding.

[0072] Conversely, if the construction time deviation is close to zero, it indicates that the timestamp of the sensor data closely matches the planned construction time of the target component. In this case, the timing of the binding is highly reasonable, the probability of misbinding is low, and the reliability is high. This feature can serve as one of the key criteria in data drift detection.

[0073] Structural response deviation characteristics are used to determine the degree of deviation between the physical response data of the sensor and the simulated value of the component or the historical data of neighboring components. The extraction method is as follows:

[0074] Suppose that the sensor operates within a certain time window t∈[t1,t2] n The response data collected within the [internal area] is: X = {x1, x2, ..., x} n}; where x n This represents the stress or strain value, where n is the total number of response data.

[0075] The simulation data distribution of the target component is acquired simultaneously, and is Y={y1, y2,..., y m};m is the total number of simulation data;

[0076] X and Y are sorted and normalized respectively to form empirical distribution functions F X 、F Y , and the structural response deviation value W(X, Y) of F z is an integral variable, representing an arbitrary point on the response value domain.

[0077] The greater the structural response deviation value, the more significant the difference between the physical response data currently collected by the sensor and the simulation prediction value of the target component or the historical response value of the adjacent component, indicating that the structural behavior does not meet the expectation, and there may be problems such as sensor misbinding, data drift or component abnormality, and the binding error degree is high.

[0078] On the contrary, the smaller the structural response deviation value, the more consistent the sensor data with the response characteristics of the target component, which meets the structural stress logic and historical law, indicating that the data is more likely to be correctly bound to the target component, and the credibility is high, and the misbinding risk is low.

[0079] According to the construction time deviation characteristics and the structural response deviation characteristics, a drift index is calculated for evaluating the binding error degree between the sensor data and the target component, and specifically includes:

[0080] The construction time deviation value and the structural response deviation value are normalized to be between 0 and 1, and the drift index is calculated according to the normalized construction time deviation value and the structural response deviation value.

[0081] For example, the drift index can be calculated by the following formula, and the calculation expression is: In the formula, F is the drift index, ΔT dep is the construction time deviation value, W(X, Y) is the structural response deviation value, a1 and a2 are weight coefficients of the construction time deviation value and the structural response deviation value (which can be optimized according to experimental experience or machine learning), and a1 and a2 are greater than 0.

[0082] Based on the drift index, the sensor data is divided into three drift levels of high risk, medium risk and low risk, and different drift levels of data are subjected to differential processing, and specifically includes:

[0083] The obtained drift index is compared with gradient standard thresholds, the gradient standard thresholds include a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the drift index is compared with the first standard threshold and the second standard threshold respectively.

[0084] If the drift index is greater than the second standard threshold, the sensor data is determined as a high-risk drift level, triggering a binding rectification process, specifically including recalculating the component matching similarity, reference structure response trend, construction sequence and other features, re-identifying the most likely binding component, and replacing the original binding relationship;

[0085] If the drift index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the sensor data is determined as a medium-risk drift level, and the system marks the data as a confirmation state, which is verified semi-automatically through manual review or in combination with auxiliary information such as video records, personnel operation logs, and construction location information, to confirm the accuracy of the binding component;

[0086] If the drift index is less than the first standard threshold, the sensor data is determined as a low-risk drift level, and the binding relationship is considered reliable, so the binding is automatically completed and included in the BIM model update process for subsequent visual monitoring and risk assessment.

[0087] In the present application, by classifying the drift index, quantitative evaluation and differentiated response of data binding quality are achieved, effectively improving the intelligent level and data reliability of BIM model in bridge construction monitoring.

[0088] If the drift level is high-risk, based on the sensor data and the drift index, the similarity score of the target component is calculated, and the target component with the highest similarity score is selected to replace the original binding component, specifically including:

[0089] For the current high-risk drift sensor data, a data feature vector is constructed by fusing multiple modalities including but not limited to:

[0090] Modality 1: structure response modality;

[0091] Modality 2: time modality;

[0092] Modality 3: spatial modality (sensor geographic location, original binding component coordinates);

[0093] Modality 4: drift index.

[0094] The above data is spliced into a unified high-dimensional feature vector, representing the multi-modality description of the current data to be bound.

[0095] For all candidate components C i in the BIM model, their existing construction time deviation features and structure response deviation features are extracted and mapped into component vectors to form a standard candidate library d is the total number of components;

[0096] Using a pre-trained or online trained multi-modal embedding model S, such as based on Transformer or MLP structure, map the input vectors to a unified embedding space: where, is the multi-modal embedding vector of the current sensor data, is the standard multi-modal embedding vector of the candidate component C i ;

[0097] For each candidate component C i , calculate its vector similarity score S i with the current sensor data (using cosine similarity): where, is the Euclidean norm of the vector , is the Euclidean norm of the vector ; get the score set of all components, select the component with the highest score, if it is greater than the confidence threshold, replace the original binding component, complete the correction; otherwise, mark the sensor data as low confidence binding, enter the artificial review process.

[0098] When the sensor data is confirmed by the binding component through the drift evaluation and similarity matching steps, the system performs data warehousing and BIM model state synchronization update operations, including:

[0099] The sensor data after binding confirmation is packaged as a structured data record, including but not limited to the following fields:

[0100] Sensor unique number (SensorID);

[0101] Data acquisition timestamp (Timestamp);

[0102] Confirm the binding component ID (ComponentID);

[0103] Measurement value (such as stress, strain, displacement, etc.);

[0104] Drift index and binding similarity score (for later tracking);

[0105] Binding confirmation state identifier (such as: automatic binding / correction binding / artificial review).

[0106] This data structure is used as a standard unit for persistent storage.

[0107] The system writes the structured data record to the central construction monitoring database;

[0108] The data is archived in time series, supporting indexing and querying by component, sensor or time range;

[0109] Simultaneously trigger the log recording and the binding history tracking mechanism for later data auditing and traceability analysis.

[0110] The system locates the corresponding component entity in the BIM model based on the confirmed binding component ID, and updates the following information:

[0111] Component state attribute update:

[0112] Update the latest sensor response value;

[0113] Mark the health status of the current component and the data update time;

[0114] If the sensor data triggers the warning threshold, the state can also be marked as "warning" or "abnormal".

[0115] In the three-dimensional BIM visualization interface, the component color is dynamically adjusted according to the binding data state, such as green for normal, yellow for attention, and red for abnormal; Realize the automatic refresh of the real-time monitoring interface.

[0116] If the binding data meets the warning condition, it is automatically transmitted to the risk assessment module; If the data is continuously abnormal, it can trigger component structure performance degradation analysis or operation and maintenance intervention suggestions; All data entry records a unique data ID, which is convenient for subsequent batch processing, model training or fault tracking.

[0117] The embodiment provides a BIM-based bridge construction monitoring method, which collects sensor data from the construction site, extracts construction time deviation features and structure response deviation features, and calculates a drift index for evaluating the binding error degree between the data and the target component; Based on the drift index, the data is divided into three risk levels of high, medium and low, and the high-risk data is subjected to intelligent algorithms such as multi-modal embedding matching for component re-identification and rectification binding; Finally, the data of the confirmed binding is written into the database, and the state information of the corresponding component in the BIM model is updated in real time, realizing accurate binding of construction monitoring data and dynamic linkage of the model, and improving the intelligent perception and safety control level in the bridge construction process.

[0118] Embodiment 2, please refer to Figure 2 The BIM-based bridge construction monitoring system described in the embodiment includes a data acquisition module, a drift feature extraction module, an evaluation module, a hierarchical processing module, a component rebinding module, and a BIM model updating module;

[0119] Data acquisition module: Obtain real-time sensor data from the bridge construction site, which includes timestamp, component ID, geographic location coordinates, and physical response data;

[0120] Drift feature extraction module: extract data drift related features in sensor data, including construction time deviation features and structural response deviation features;

[0121] Evaluation module: calculate drift index according to the construction time deviation features and the structural response deviation features, for evaluating the binding error degree between the sensor data and the target component;

[0122] Hierarchical processing module: based on the drift index, divide the sensor data into three drift levels of high risk, medium risk and low risk, and perform differential processing on data of different drift levels:

[0123] Component rebinding module: if the drift level is high risk, calculate the similarity score of the target component based on the sensor data and the drift index, and select the target component with the highest similarity score to replace the original binding component;

[0124] BIM model updating module: write the binding confirmed sensor data into the database, and update the state information of the corresponding component in the BIM model.

[0125] The above formulas are all dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the nearest real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0126] It should be understood that the term "and / or" herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects, but it can also represent an "and / or" relationship, which can be understood in combination with the context before and after.

[0127] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A BIM-based bridge construction monitoring method, characterized by: The method comprises the following steps: Obtaining real-time sensor data from a bridge construction site, the data including a timestamp, a component ID, geographic location coordinates, and physical response data; Extracting data drift-related features in the sensor data, including construction time deviation features and structural response deviation features; The construction time deviation feature is used to determine the degree of time deviation between the timestamp and the construction time plan of the corresponding component in the BIM model. The extraction method is as follows: construct a construction process dependency graph G(V, E), where node V represents a bridge component or construction process; directed edge E represents each edge Indicates component V i It is V j Prerequisite construction conditions; for target components bound to sensor data Extract all its direct predecessor nodes. : Must be Completed before construction; all direct successor nodes :exist Construction can only begin after that; sensors record timestamps. ; From BIM construction plan or history record: predecessor node completion time set: ; successor node start time set: ; define construction time deviation value , which represents the position deviation degree of the target component in the dependent path, and the expression is: ; In the formula, is the actual completion time of the ith predecessor component, is the planned start or actual start time of the jth successor component; The structural response deviation feature is used for judging the deviation degree between the physical response data of the sensor and the simulation value of the component or the historical data of the adjacent component, and the extraction method is as follows: assuming that the response data collected by the sensor in a certain time window is ; wherein represents a stress or strain value, and n is the total number of response data; meanwhile, the simulation data distribution of the target component is obtained as follows: ; m is the total number of simulation data; X and Y are sorted and normalized respectively to form an empirical distribution function , and the structural response deviation value of is calculated; z is an integral variable, representing an arbitrary point in the response value range; According to the construction time deviation features and the structural response deviation features, a drift index is calculated to evaluate the binding error degree between the sensor data and the target component; The calculation expression of the drift index is: is the drift index, is the construction time deviation value, the weight coefficient of the structure response deviation value, and are all greater than 0. Based on the drift index, the sensor data is divided into three drift levels of high risk, medium risk, and low risk, and different drift levels of data are processed differently: If the drift level is high risk, the similarity score of the target component is calculated based on the sensor data and the drift index, and the target component with the highest similarity score is selected to replace the original binding component; The sensor data after binding confirmation is written into the database, and the state information of the corresponding component in the BIM model is updated.

2. The BIM-based bridge construction monitoring method of claim 1, wherein: Obtaining real-time sensor data from a bridge construction site includes: arranging multiple types of sensors at the components of the bridge structure, and uniquely numbering each sensor or establishing an initial binding relationship with the component ID; the sensors include stress meters, strain gauges, displacement meters, accelerometers, temperature sensors, humidity sensors, and GPS positioning modules.

3. The BIM-based bridge construction monitoring method of claim 1, wherein: According to the construction time deviation features and the structural response deviation features, a drift index is calculated to evaluate the binding error degree between the sensor data and the target component, specifically including: The construction time deviation value and the structural response deviation value are normalized to be between 0 and 1, and the drift index is calculated based on the normalized construction time deviation value and the structural response deviation value.

4. The BIM-based bridge construction monitoring method of claim 3, wherein: Based on the drift index, the sensor data is divided into three drift levels of high risk, medium risk, and low risk, and different drift levels of data are processed differently, specifically including: The obtained drift index is compared with gradient standard thresholds, the gradient standard thresholds include a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, the drift index is compared with the first standard threshold and the second standard threshold respectively; If the drift index is greater than the second standard threshold, the sensor data is determined as high-risk drift level, triggering the binding correction process; If the drift index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the sensor data is determined as medium-risk drift level, and the data is marked as a confirmation state, which is verified semi-automatically through manual review or combined with auxiliary information; If the drift index is less than the first standard threshold, the sensor data is determined as low-risk drift level, and it is considered that the binding relationship is reliable, the binding is automatically completed and is included in the BIM model update process.

5. The BIM-based bridge construction monitoring method of claim 4, wherein: If the drift level is high risk, the similarity score of the target component is calculated based on the sensor data and the drift index, and the target component with the highest similarity score is selected to replace the original binding component, specifically including: For the current high-risk drift of sensor data, a data feature vector is constructed by fusing multiple modalities For all candidate components in the BIM model , respectively extract its existing construction time deviation features and structural response deviation features, and map them to component vectors , form a standard candidate library , d is the total number of components; The input vector is mapped to a unified embedding space using a multi-modal embedding model S: a standard multi-modal embedding vector for the current sensor data, a standard multi-modal embedding vector for the current sensor data, For each candidate component , compute its vector similarity score with the current sensor data : is the Euclidean norm of the vector ; get the score set of all components, select the component with the highest score, if it is greater than the confidence threshold, replace the original binding component, complete the correction; otherwise, mark the sensor data as low-confidence binding, and enter the manual review process.

6. A BIM-based bridge construction monitoring system for implementing the BIM-based bridge construction monitoring method according to any one of claims 1-5, characterized in that: It includes a data acquisition module, a drift feature extraction module, an evaluation module, a grading processing module, a component rebinding module, and a BIM model updating module; Data acquisition module: Obtain real-time sensor data from the bridge construction site, including timestamp, component ID, geographic location coordinates, and physical response data; Drift feature extraction module: Extract data drift-related features from sensor data, including construction time deviation features and structural response deviation features; Evaluation module: Calculate drift index based on construction time deviation features and structural response deviation features to assess the binding error between sensor data and target components; Classification processing module: Based on the drift index, the sensor data is divided into three drift levels: high risk, medium risk, and low risk, and different drift levels of data are processed differently; Component rebinding module: If the drift level is high risk, calculate the similarity score of the target component based on the sensor data and the drift index, and select the target component with the highest similarity score to replace the original binding component; BIM model update module: Write the sensor data after binding confirmation into the database and update the state information of the corresponding component in the BIM model.

Images