Bridge construction monitoring system based on Internet of Things

Abstract

The invention belongs to the technical field of bridge construction monitoring, and discloses a bridge construction monitoring system based on the Internet of Things. The system comprises a prediction analysis early warning module, a control strategy generation module, a construction quality scheduling module and a visual decision support module, and is characterized in that multi-stage preprocessing is performed on a first processing data set to obtain a second processing data set, the second processing data set is analyzed to obtain a risk early warning report, and on the basis of the risk early warning report, a control strategy is generated; the method comprises the steps of generating a first processing data set, generating a strategy control report, performing conversion and execution sequence processing on the strategy control report to obtain a system instruction set, processing a second processing data set, a risk early warning report and the system instruction set, and providing support for manual decision making and instruction issuing based on a visual panel. The method has the remarkable advantages of being high in original data integration capacity, good in risk active prediction effect and high in control response efficiency.

Description

Technical Field

[0001] This invention relates to the field of bridge construction monitoring technology, and more specifically, to a bridge construction monitoring system based on the Internet of Things. Background Technology

[0002] A bridge construction monitoring system is a system that uses a series of technical means to monitor, analyze, and provide feedback on the bridge's structural condition, construction environment, and key process parameters in real time during the bridge construction process. It is mainly used to ensure the safety and controllability of the construction process and to ensure that the completed bridge's alignment and internal force state meet the design requirements.

[0003] However, traditional bridge construction monitoring systems suffer from several shortcomings. First, they often rely on independent sensors for data acquisition, resulting in inconsistent data formats and asynchronous timing. This isolation creates "data silos," making it difficult for staff to accurately assess the bridge's structural condition during construction and posing safety risks. Second, traditional systems primarily offer data display and threshold alarms, lacking the ability to predict potential and trending risks. This leads to a reactive approach to risk management during construction. Third, even when risks are identified, control relies heavily on manual intervention, which is time-consuming and hinders rapid risk mitigation, impacting construction quality and speed. Therefore, effectively addressing the issues of data fragmentation, passive risk decision-making, and heavy reliance on manual control in traditional systems is a critical challenge for current bridge construction monitoring systems.

[0004] In view of this, the present invention proposes a bridge construction monitoring system based on the Internet of Things to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution, including:

[0006] The multi-source sensor data acquisition module is used to acquire raw data based on sensor networks to obtain raw datasets;

[0007] Furthermore, the steps for acquiring raw data based on sensor networks include:

[0008] S1.1: Based on the preset acquisition frequency and according to the sensor network, the original electrical signals are acquired to obtain the first original dataset;

[0009] S1.2: Convert the original electrical signals in the first original dataset into engineering unit values ​​to obtain the second original dataset. The specific formula for the conversion is as follows:

[0010] ;

[0011] Obtain engineering unit value ,in, and The calibration coefficients for the sensor. This represents the value of the original electrical signal;

[0012] S1.3: Add system timestamps and sensor IDs to all data items in the second original dataset to obtain the original dataset;

[0013] S1.4: Output the raw dataset to the edge gateway transmission module;

[0014] The edge gateway transmission module is used to process the original dataset to obtain the first processed dataset;

[0015] Further, the steps for processing the original dataset include:

[0016] S2.1: Store the original dataset in the database;

[0017] S2.2: The original dataset in the database is filtered using moving average filtering to obtain the filtered dataset. The specific calculation formula for moving average filtering is as follows:

[0018] ;

[0019] Get the current time point Filtered engineering unit value ,in, For the size of the filter window, For time points The unit value of the project;

[0020] S2.3: Use data standardization to detect outliers in all data items of the filtered dataset. When the absolute value of the detected value is greater than 3, the data item is marked as suspicious data, thus obtaining the inspection dataset. The specific formula for the data standardization method is:

[0021] ;

[0022] Obtain the detection value ,in, This is the average of the filtered engineering unit values ​​within a preset time window. The standard deviation of the filtered engineering unit values ​​within a preset time window;

[0023] S2.4: Compress the inspection dataset using a lossless compression algorithm, and encrypt the compressed inspection dataset using the AES encryption algorithm to obtain the first processed dataset;

[0024] S2.5: Output the first processed dataset to the data fusion and cleaning module;

[0025] The data fusion and cleaning module is used to perform multi-level preprocessing on the first processed dataset to obtain the second processed dataset.

[0026] Furthermore, the steps of performing multi-level preprocessing on the first processing dataset include:

[0027] S3.1: Decrypt and decompress the first processed data, and extract the sensor ID1, timestamp, and filtered engineering unit value within a preset time window from the decrypted and decompressed first processed dataset to obtain the dataset to be processed;

[0028] S3.2: Use linear interpolation to synchronize the filtered engineering unit values ​​within a preset time window in the dataset to be processed, resulting in a synchronized dataset. The specific calculation formula for linear interpolation is as follows:

[0029] ;

[0030] Obtain the synchronous filter value ,in, For the target time point, and For two adjacent timestamps, and The filtered engineering unit value within a preset time window corresponding to two adjacent timestamps;

[0031] S3.3: Calculate the quartiles of all sensors in the synchronized dataset, in order to and As a benchmark, when the synchronization filter value is greater than or less than When the range is reached, synchronous filter values ​​that are out of range are removed to obtain a cleaned dataset;

[0032] S3.4: Using a weighted average fusion algorithm, the synchronous filter values ​​of all sensors for the same physical quantity in the cleaned dataset are fused to obtain a fused dataset. The specific calculation formula for the weighted average fusion algorithm is as follows:

[0033] ;

[0034] Obtain the data fusion value ,in, For the number of sensors, For the first The weighting coefficients of each sensor For the first Synchronous filter values ​​for each sensor;

[0035] S3.5: Calculate the confidence score for all data items in the fused dataset, and aggregate them to obtain the confidence dataset. The specific formula for calculating the confidence score is as follows:

[0036] ;

[0037] Receive confidence score ;

[0038] S3.6: Pack the timestamp, sensor type, fused dataset, and confidence dataset to obtain the second processing dataset;

[0039] S3.7: Output the second processed dataset to the predictive analysis and early warning module;

[0040] The predictive analysis and early warning module is used to analyze the second processing dataset and generate a risk warning report;

[0041] Furthermore, the steps for analyzing the second processed dataset include:

[0042] S4.1: Read the second processing dataset and perform feature extraction to obtain feature vectors;

[0043] S4.2: Input the feature vector into the pre-trained long short-term memory network model and output the future prediction value;

[0044] S4.3: Based on future forecasts and safety thresholds, calculate the risk index and probability of occurrence to obtain the risk index value and probability of occurrence value. The specific formula set for calculation is as follows:

[0045] ;

[0046] Obtain risk indicator value and probability of occurrence ,in, For future time points Future forecasts As a safety threshold, This is the scaling factor;

[0047] S4.4: Based on the risk indicator value and the probability of occurrence value, a low-risk warning is generated when the risk indicator value is less than 5% and the probability of occurrence value is less than 0.3; a medium-risk warning is generated when the risk indicator value is greater than or equal to 5% and less than 10%, or the probability of occurrence value is greater than or equal to 0.3 and less than 0.7; and a high-risk warning is generated when the risk indicator value is greater than or equal to 10% or the probability of occurrence value is greater than or equal to 0.7.

[0048] S4.5: Package the risk type, risk level, future forecast value, risk indicator value, and probability of occurrence value to obtain a risk warning report;

[0049] S4.6: Output the risk warning report to the control strategy generation module;

[0050] The control strategy generation module is used to generate strategy control reports based on risk warning reports;

[0051] Furthermore, the steps for generating a strategy control report based on the risk warning report include:

[0052] S5.1: Based on the risk type and risk level in the risk warning report, and by matching it with the predefined strategy rule base in the database, an adjustment strategy report is obtained;

[0053] S5.2: Optimize the strategy parameters in the adjustment strategy report using a multi-objective optimization algorithm, and solve it using linear programming to obtain the second adjustment strategy report. The objective function of the multi-objective optimization algorithm is:

[0054] ;

[0055] in, To maximize the function, and These are the weighting coefficients. To apply the future forecasts after adjusting the strategy report, Cost of strategy application;

[0056] S5.3: Package the second adjustment strategy report, the predicted risk reduction rate, and the usage conditions to obtain the strategy control report;

[0057] S5.4: Output the strategy control report to the construction quality scheduling module;

[0058] The construction quality scheduling module is used to convert strategy control reports and process their execution order to obtain a system instruction set.

[0059] Furthermore, the steps for transforming the policy control report and performing execution sequence processing include:

[0060] S6.1: Read the policy control report and parse the second adjustment policy report in the policy control report;

[0061] The analysis includes breaking down the second adjustment strategy report into a specific sequence of system instructions to obtain an adjustment instruction set;

[0062] S6.2: Based on the construction plan and construction time, prioritize the adjustment instruction set to obtain the priority instruction set. The specific calculation formula for the prioritization is as follows:

[0063] ;

[0064] Obtain priority data ,in, and As a weighting factor, As for the risk urgency factor, Time urgency factor;

[0065] S6.3: Pack the priority instruction set and instruction execution time to obtain the system instruction set;

[0066] S6.4: Output the system instruction set to the visualization decision support module;

[0067] The visualization decision support module is used to process the second processing dataset, risk warning reports and system instruction sets, and provides support for manual decision-making and instruction issuance based on the visualization panel;

[0068] Furthermore, the steps of processing the second processing dataset, risk warning reports, and system instruction sets, and providing support for human decision-making and instruction issuance based on a visualization panel, include:

[0069] S7.1: Based on the second processing dataset, and using the BIM model, the bridge status is visualized and rendered, and the rendering results are displayed through a visualization panel;

[0070] Based on the risk level in the risk warning report, color rendering is performed using color coding, and the color rendering results are displayed through a visualization panel;

[0071] The system instruction set is displayed in list format;

[0072] S7.2: Based on the visual panel, administrators can view and process risk warning reports and system command sets, including confirmation, rejection, and modification;

[0073] When the administrator's processing result is confirmation or modification, the instruction status of the system instruction set is changed to confirmed or modified, and sent to the target control device;

[0074] When the administrator's decision is rejection, the rejection reason text is manually entered and output to the control policy generator for rule update;

[0075] S7.3: Monitor the operation records in step S7.2 to obtain the decision operation log, and store the decision operation log in the database. The operation record includes the system instruction set, instruction status, administrator ID, operation timestamp and execution result.

[0076] Furthermore, S1: Collect raw data based on sensor networks to obtain the raw dataset;

[0077] S2: Process the original dataset to obtain the first processed dataset;

[0078] S3: Perform multi-level preprocessing on the first processing dataset to obtain the second processing dataset;

[0079] S4: Analyze the second processing dataset to obtain a risk warning report;

[0080] S5: Generate strategy control reports based on risk warning reports;

[0081] S6: Transform and execute the policy control report to obtain the system instruction set;

[0082] S7: Processes the second processing dataset, risk warning reports, and system instruction sets, and provides support for human decision-making and instruction issuance based on a visualization panel.

[0083] The technical effects and advantages of the IoT-based bridge construction monitoring system of this invention are as follows:

[0084] This invention acquires raw data based on a sensor network to obtain a raw dataset. This raw dataset is then processed to obtain a first processed dataset. Multi-level preprocessing of the first processed dataset yields a second processed dataset. Analysis of the second processed dataset generates a risk warning report. Based on the risk warning report, a strategy control report is generated. The strategy control report undergoes transformation and execution sequence processing to obtain a system instruction set. The second processed dataset, the risk warning report, and the system instruction set are processed, and a visual panel provides support for human decision-making and instruction issuance. This allows the system to integrate and unify complex raw data through the collaborative work of a multi-source sensor data acquisition module, an edge gateway transmission module, and a data fusion and cleaning module. This invention completely solves the "data silo" problem existing in traditional systems, providing a real and reliable data foundation for the system. In addition, by predicting data trends and identifying risks, this invention effectively transforms the passive response of traditional systems into proactive early warning, greatly improving the foresight and safety assurance of construction safety. Finally, through the collaborative operation of the control strategy generation module, construction quality scheduling module, and visualization decision support module, the early warning report is automatically converted into a specific and executable set of system instructions, and rapid review and execution by human and machine collaboration are realized, thereby greatly improving the construction quality and speed of the bridge construction process. Overall, this invention has significant advantages such as strong raw data integration capabilities, good proactive risk prediction effect, and high control response efficiency. Attached Figure Description

[0085] Figure 1 This is a schematic diagram of the Internet of Things-based bridge construction monitoring system of the present invention;

[0086] Figure 2 This is a schematic diagram of the Internet of Things-based bridge construction monitoring method of the present invention. Detailed Implementation

[0087] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0088] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0089] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0090] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0091] In practice, the server-side equipment deployed in an IoT-based bridge construction monitoring system may consist of one or more devices. This IoT-based bridge construction monitoring system can be implemented as: a business instance, a virtual machine, or hardware devices. For example, the IoT-based bridge construction monitoring system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, this IoT-based bridge construction monitoring system can be understood as software deployed on a cloud node, used to provide IoT-based bridge construction monitoring to various user terminals. Alternatively, the IoT-based bridge construction monitoring system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Or, the IoT-based bridge construction monitoring system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide IoT-based bridge construction monitoring to various user terminals.

[0092] In terms of implementation, the IoT-based bridge construction monitoring system and the user terminal are mutually compatible. That is, if the IoT-based bridge construction monitoring system is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the IoT-based bridge construction monitoring system is implemented as a website, then the user terminal is implemented as a webpage; or if the IoT-based bridge construction monitoring system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0093] like Figure 1 The figure shown is a system architecture diagram of a bridge construction monitoring system based on the Internet of Things provided in an embodiment of the present invention.

[0094] The IoT-based bridge construction monitoring system described in this invention can be hosted on a cloud server. In terms of implementation, it can function as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the IoT-based bridge construction monitoring system may include a raw traffic data acquisition module, a metadata generation module, a data storage management module, a data feature extraction module, a feature vector anomaly detection module, a threat alarm analysis module, and a threat alarm response execution module. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0095] In this embodiment of the invention, in the IoT-based bridge construction monitoring system, each of the above modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. For example, the sharing and evaluation module can call the same information collection module to obtain information collected by that module. Based on the above characteristics, in the IoT-based bridge construction monitoring system provided by this embodiment of the invention, without modifying the program code, the applicable scope of the IoT-based bridge construction monitoring system architecture can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the IoT-based bridge construction monitoring system. In practical applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0096] Example 1

[0097] Please see Figure 1 As shown in this embodiment, the bridge construction monitoring system based on the Internet of Things includes:

[0098] The multi-source sensor data acquisition module is used to acquire raw data based on the sensor network to obtain the raw dataset;

[0099] Furthermore, the steps for acquiring raw data based on sensor networks include:

[0100] S1.1: Based on the preset acquisition frequency and according to the sensor network, the original electrical signals are acquired to obtain the first original dataset;

[0101] It should be explained that the preset acquisition frequency refers to the data reading frequency set according to the requirements, such as once per second; the sensor network refers to, for example, a sensor network composed of strain sensors, displacement sensors, and temperature sensors.

[0102] S1.2: Convert the original electrical signals in the first original dataset into engineering unit values ​​to obtain the second original dataset. The specific formula for the conversion is as follows:

[0103] ;

[0104] Obtain engineering unit value ,in, and The calibration coefficients for the sensor. This represents the value of the original electrical signal;

[0105] It should be explained that converting the raw electrical signals in the first raw dataset into engineering unit values ​​means, for example, converting voltage values ​​into temperature values ​​in degrees Celsius.

[0106] S1.3: Add system timestamps and sensor IDs to all data items in the second original dataset to obtain the original dataset;

[0107] S1.4: Output the raw dataset to the edge gateway transmission module;

[0108] The edge gateway transmission module is used to process the original dataset to obtain a first processed dataset;

[0109] Further steps in processing the original dataset include:

[0110] S2.1: Store the original dataset in the database;

[0111] S2.2: The original dataset in the database is filtered using moving average filtering to obtain the filtered dataset. The specific calculation formula for moving average filtering is as follows:

[0112] ;

[0113] Get the current time point Filtered engineering unit value ,in, For the size of the filter window, For time points The unit value of the project;

[0114] S2.3: Use data standardization to detect outliers in all data items of the filtered dataset. When the absolute value of the detected value is greater than 3, the data item is marked as suspicious data, thus obtaining the inspection dataset. The specific formula for the data standardization method is:

[0115] ;

[0116] Obtain the detection value ,in, This is the average of the filtered engineering unit values ​​within a preset time window. The standard deviation of the filtered engineering unit values ​​within a preset time window;

[0117] It should be explained that the preset time window refers to the recent data of the filtered engineering unit value, such as the past minute;

[0118] S2.4: Compress the inspection dataset using a lossless compression algorithm, and encrypt the compressed inspection dataset using the AES encryption algorithm to obtain the first processed dataset;

[0119] S2.5: Output the first processed dataset to the data fusion and cleaning module;

[0120] The data fusion and cleaning module is used to perform multi-level preprocessing on the first processed dataset to obtain the second processed dataset;

[0121] Furthermore, the steps of performing multi-level preprocessing on the first processing dataset include:

[0122] S3.1: Decrypt and decompress the first processed data, and extract the sensor ID1, timestamp, and filtered engineering unit value within a preset time window from the decrypted and decompressed first processed dataset to obtain the dataset to be processed;

[0123] S3.2: Use linear interpolation to synchronize the filtered engineering unit values ​​within a preset time window in the dataset to be processed, resulting in a synchronized dataset. The specific calculation formula for linear interpolation is as follows:

[0124] ;

[0125] Obtain the synchronous filter value ,in, For the target time point, and For two adjacent timestamps, and The filtered engineering unit value within a preset time window corresponding to two adjacent timestamps;

[0126] It should be explained that the synchronization filter value refers to the filtered engineering unit value within a preset time window after time synchronization;

[0127] S3.3: Calculate the quartiles of all sensors in the synchronized dataset, in order to and As a benchmark, when the synchronization filter value is greater than or less than When the range is reached, synchronous filter values ​​that are out of range are removed to obtain a cleaned dataset;

[0128] It should be explained that quartiles refer to arranging all the synchronization filter values ​​of a single sensor and obtaining them separately. The quartiles are the data points that occupy the 25th percentile in a sequence. The quartiles are the data points that occupy the 75th percentile position in a permutation sequence;

[0129] S3.4: Using a weighted average fusion algorithm, the synchronous filter values ​​of all sensors for the same physical quantity in the cleaned dataset are fused to obtain a fused dataset. The specific calculation formula for the weighted average fusion algorithm is as follows:

[0130] ;

[0131] Obtain the data fusion value ,in, For the number of sensors, For the first The weighting coefficients of each sensor For the first Synchronous filter values ​​for each sensor;

[0132] It needs to be explained that the same physical quantity refers to, for example, the strain value and temperature value of a bridge;

[0133] S3.5: Calculate the confidence score for all data items in the fused dataset, and aggregate them to obtain the confidence dataset. The specific formula for calculating the confidence score is as follows:

[0134] ;

[0135] Receive confidence score ;

[0136] It should be explained that the confidence score ranges from 0 to 1, with a higher confidence score indicating higher reliability.

[0137] S3.6: Pack the timestamp, sensor type, fused dataset, and confidence dataset to obtain the second processing dataset;

[0138] S3.7: Output the second processed dataset to the predictive analysis and early warning module;

[0139] The predictive analysis and early warning module is used to analyze the second processing dataset and obtain a risk warning report;

[0140] Further steps in analyzing the second processed dataset include:

[0141] S4.1: Read the second processing dataset and perform feature extraction to obtain feature vectors;

[0142] It should be explained that feature extraction refers to, for example, the moving average of strain values ​​and the slope of the trend;

[0143] S4.2: Input the feature vector into the pre-trained long short-term memory network model and output the future prediction value;

[0144] S4.3: Based on future forecasts and safety thresholds, calculate the risk index and probability of occurrence to obtain the risk index value and probability of occurrence value. The specific formula set for calculation is as follows:

[0145] ;

[0146] Obtain risk indicator value and probability of occurrence ,in, For future time points Future forecasts As a safety threshold, This is the scaling factor;

[0147] It should be explained that the safety threshold is manually set and entered into the system;

[0148] S4.4: Based on the risk indicator value and the probability of occurrence value, a low-risk warning is generated when the risk indicator value is less than 5% and the probability of occurrence value is less than 0.3; a medium-risk warning is generated when the risk indicator value is greater than or equal to 5% and less than 10%, or the probability of occurrence value is greater than or equal to 0.3 and less than 0.7; and a high-risk warning is generated when the risk indicator value is greater than or equal to 10% or the probability of occurrence value is greater than or equal to 0.7.

[0149] S4.5: Package the risk type, risk level, future forecast value, risk indicator value, and probability of occurrence value to obtain a risk warning report;

[0150] S4.6: Output the risk warning report to the control strategy generation module;

[0151] The control strategy generation module is used to generate a strategy control report based on the risk warning report;

[0152] Furthermore, the steps for generating a strategy control report based on the risk warning report include:

[0153] S5.1: Based on the risk type and risk level in the risk warning report, and by matching it with the predefined strategy rule base in the database, an adjustment strategy report is obtained;

[0154] It should be explained that the predefined strategy rule base is in IF-THEN format, for example, IF Risk Type = "Strain Exceeds Limits" AND Risk Level = "High Risk Warning" THEN Strategy = "Adjust Tensioning Sequence";

[0155] S5.2: Optimize the strategy parameters in the adjustment strategy report using a multi-objective optimization algorithm, and solve it using linear programming to obtain the second adjustment strategy report. The objective function of the multi-objective optimization algorithm is:

[0156] ;

[0157] in, To maximize the function, and These are the weighting coefficients. To apply the future forecasts after adjusting the strategy report, Cost of strategy application;

[0158] S5.3: Package the second adjustment strategy report, the predicted risk reduction rate, and the usage conditions to obtain the strategy control report;

[0159] It should be explained that the predicted risk reduction rate is calculated based on the future predicted value after applying the adjustment strategy report and the future predicted value in step S4.2;

[0160] S5.4: Output the strategy control report to the construction quality scheduling module;

[0161] The construction quality scheduling module is used to convert the strategy control report and process the execution order to obtain the system instruction set;

[0162] Furthermore, the steps for transforming the policy control report and processing it according to the execution sequence include:

[0163] S6.1: Read the policy control report and parse the second adjustment policy report in the policy control report;

[0164] The analysis includes breaking down the second adjustment strategy report into a specific sequence of system instructions to obtain an adjustment instruction set;

[0165] It should be explained that breaking down the second adjustment strategy report into a specific system instruction sequence means, for example, when the second adjustment strategy report is to adjust the tensioning sequence, the specific system instruction sequence includes: the first instruction: "Pause the current tensioning equipment", the second instruction: "Load the new tensioning scheme", and the third instruction: "Start the tensioning equipment", and each instruction includes the action, parameters and target control equipment;

[0166] S6.2: Based on the construction plan and construction time, prioritize the adjustment instruction set to obtain the priority instruction set. The specific calculation formula for the prioritization is as follows:

[0167] ;

[0168] Obtain priority data ,in, and As a weighting factor, As for the risk urgency factor, Time urgency factor;

[0169] S6.3: Pack the priority instruction set and instruction execution time to obtain the system instruction set;

[0170] S6.4: Output the system instruction set to the visualization decision support module;

[0171] The visualization decision support module is used to process the second processing dataset, risk warning report and system instruction set, and to provide support for manual decision-making and instruction issuance based on the visualization panel;

[0172] Further steps include processing the second dataset, risk warning reports, and system instruction sets, and providing support for human decision-making and instruction issuance based on a visualization panel, including:

[0173] S7.1: Based on the second processing dataset, and using the BIM model, the bridge status is visualized and rendered, and the rendering results are displayed through a visualization panel;

[0174] Based on the risk level in the risk warning report, color rendering is performed using color coding, and the color rendering results are displayed through a visualization panel;

[0175] It needs to be explained that color rendering refers to, for example, high-risk warnings being displayed in red;

[0176] The system instruction set is displayed in list format;

[0177] S7.2: Based on the visual panel, administrators can view and process risk warning reports and system command sets, including confirmation, rejection, and modification;

[0178] When the administrator's processing result is confirmation or modification, the instruction status of the system instruction set is changed to confirmed or modified, and sent to the target control device;

[0179] When the administrator's decision is rejection, the rejection reason text is manually entered and output to the control policy generator for rule update;

[0180] S7.3: Monitor the operation records in step S7.2 to obtain the decision operation log, and store the decision operation log in the database. The operation record includes the system instruction set, instruction status, administrator ID, operation timestamp and execution result.

[0181] In this embodiment, the beneficial effects are as follows: raw data is collected based on a sensor network to obtain a raw dataset; the raw dataset is processed to obtain a first processed dataset; the first processed dataset undergoes multi-level preprocessing to obtain a second processed dataset; the second processed dataset is analyzed to obtain a risk warning report; based on the risk warning report, a strategy control report is generated; the strategy control report is transformed and its execution order is processed to obtain a system instruction set; the second processed dataset, the risk warning report, and the system instruction set are processed, and a visualization panel is used to support manual decision-making and instruction issuance. This enables the system to integrate and unify complex raw data through the collaborative work of the multi-source sensor data acquisition module, the edge gateway transmission module, and the data fusion and cleaning module. This invention completely solves the "data silo" problem in traditional systems, providing a reliable data foundation for the system. Furthermore, by predicting data trends and identifying risks, it effectively transforms the passive response of traditional systems into proactive early warning, significantly improving the foresight and safety assurance of construction safety. Finally, through the collaborative operation of the control strategy generation module, construction quality scheduling module, and visualization decision support module, early warning reports are automatically converted into specific, executable system instruction sets, enabling rapid review and execution through human-machine collaboration. This greatly improves the construction quality and speed of bridge construction. Overall, this invention has significant advantages in terms of strong raw data integration capabilities, effective proactive risk prediction, and high control response efficiency.

[0182] Example 2

[0183] Please see Figure 2 As shown, the parts not described in detail in this embodiment are described in Embodiment 1. A bridge construction monitoring method based on the Internet of Things is provided. The method includes: S1: collecting raw data based on a sensor network to obtain a raw dataset;

[0184] S2: Process the original dataset to obtain the first processed dataset;

[0185] S3: Perform multi-level preprocessing on the first processing dataset to obtain the second processing dataset;

[0186] S4: Analyze the second processing dataset to obtain a risk warning report;

[0187] S5: Generate strategy control reports based on risk warning reports;

[0188] S6: Transform and execute the policy control report to obtain the system instruction set;

[0189] S7: Processes the second processing dataset, risk warning reports, and system instruction sets, and provides support for human decision-making and instruction issuance based on a visualization panel.

[0190] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the present invention.

Claims

1. A bridge construction monitoring system based on Internet of Things, characterized in that, The system comprises a predictive analysis early warning module, a control strategy generation module, a construction quality scheduling module and a visual decision support module, wherein: The predictive analysis early warning module is configured to analyze the second processed data set to obtain a risk early warning report; The control strategy generation module is configured to generate a strategy control report based on the risk early warning report; The construction quality scheduling module is configured to convert the strategy control report and perform sequence processing to obtain a system instruction set; The visual decision support module is configured to process the second processed data set, the risk early warning report and the system instruction set, and provide support for manual decision-making and instruction issuing based on a visual panel.

2. The bridge construction monitoring system based on Internet of Things according to claim 1, wherein, The system further comprises a multi-source sensing data acquisition module, an edge gateway transmission module and a data fusion cleaning module, wherein: The multi-source sensing data acquisition module is configured to acquire raw data based on a sensor network to obtain a raw data set; The edge gateway transmission module is configured to process the raw data set to obtain a first processed data set; The data fusion cleaning module is configured to perform multi-level preprocessing on the first processed data set to obtain a second processed data set.

3. The bridge construction monitoring system based on Internet of Things according to claim 2, characterized in that, The step of acquiring raw data based on a sensor network comprises: S1.1: acquiring raw electrical signals based on a preset acquisition frequency and according to the sensor network to obtain a first raw data set; S1.2: converting the raw electrical signals in the first raw data set into engineering unit values to obtain a second raw data set; S1.3: adding system timestamps and sensor IDs to all data items in the second raw data set to obtain a raw data set; S1.4: outputting the raw data set to the edge gateway transmission module.

4. The bridge construction monitoring system based on Internet of Things according to claim 2, wherein, The step of processing the raw data set comprises: S2.1: storing the raw data set in a database; S2.2: filtering the raw data set in the database using a moving average filter to obtain a filtered data set; S2.3: detecting outliers in all data items in the filtered data set using a data standardization method, and when the absolute value of the detected value is greater than 3, marking the data item quality flag as suspicious data to obtain a checked data set; S2.4: compressing the checked data set using a lossless compression algorithm, and encrypting the compressed checked data set using an AES encryption algorithm to obtain a first processed data set; S2.5: outputting the first processed data set to the data fusion cleaning module.

5. The bridge construction monitoring system based on Internet of Things as claimed in claim 2 wherein, The step of performing multi-level preprocessing on the first processed data set comprises: S3.1: decrypting and decompressing the first processed data set, and extracting the sensor ID1, timestamp and filtered engineering unit values within a preset time window from the decrypted and decompressed first processed data set to obtain a to-be-processed data set; S3.2: synchronizing the filtered engineering unit values within the preset time window in the to-be-processed data set using a linear interpolation method to obtain a synchronized data set; S3.3: Calculate the quartiles of all sensors in the synchronization dataset to and as a reference, when the synchronization filter value is greater or less than range, the synchronization filter value that exceeds the range is rejected, and the cleaning dataset is obtained; S3.4: fusing the synchronized filtered values of all sensors of the same physical quantity in the cleaned data set using a weighted average fusion algorithm to obtain a fused data set; S3.5: Confidence score calculation is performed on all data items in the fusion dataset, and the set is obtained, to obtain a confidence dataset; S3.6: The timestamp, sensor type, fusion dataset and confidence dataset are packaged to obtain a second processing dataset; S3.7: The second processing dataset is output to the prediction analysis and early warning module. 6.The Internet of Things based bridge construction monitoring system as claimed in claim 1, wherein, The steps of analyzing the second processing dataset include: S4.1: Read the second processing dataset and perform feature extraction to obtain a feature vector; S4.2: The feature vector is input into a pre-trained long short-term memory network model to output a future prediction value; S4.3: Based on the future prediction value and the safety threshold, the risk index and the occurrence probability are calculated respectively to obtain the risk index value and the occurrence probability value; S4.4: Based on the risk index value and the occurrence probability value, when the risk index value is less than 5% and the occurrence probability value is less than 0.3, a low-risk warning is generated, when the risk index value is greater than or equal to 5% and less than 10%, or the occurrence probability value is greater than or equal to 0.3 and less than 0.7, a medium-risk warning is generated, and when the risk index value is greater than or equal to 10% or the occurrence probability value is greater than or equal to 0.7, a high-risk warning is generated; S4.5: The risk type, risk level, future prediction value, risk index value and occurrence probability value are packaged to obtain a risk warning report; S4.6: The risk warning report is output to the control strategy generation module. 7.The Internet of Things based bridge construction monitoring system as claimed in claim 1, wherein, Based on the risk warning report, the steps of generating a strategy control report include: S5.1: Based on the risk type and risk level in the risk warning report, and according to the pre-defined strategy rule library in the database, the adjustment strategy report is matched to obtain an adjustment strategy report; S5.2: The strategy parameters in the adjustment strategy report are optimized using a multi-objective optimization algorithm, and linear programming is used for solution to obtain a second adjustment strategy report; S5.3: The second adjustment strategy report, the predicted risk reduction rate and the use conditions are packaged to obtain a strategy control report; S5.4: The strategy control report is output to the construction quality scheduling module.

8. The bridge construction monitoring system based on Internet of Things according to claim 1, wherein, The steps of converting the strategy control report and performing sequence processing include: S6.1: Read the strategy control report and analyze the second adjustment strategy report in the strategy control report; The analysis includes decomposing the second adjustment strategy report into a specific system instruction sequence to obtain an adjustment instruction set; S6.2: Based on the construction plan and construction time, the adjustment instruction set is prioritized to obtain a priority instruction set; S6.3: The priority instruction set and the instruction execution time are packaged to obtain a system instruction set; S6.4: The system instruction set is output to the visual decision support module. 9.The Internet of Things based bridge construction monitoring system as claimed in claim 1, wherein, The steps of processing the second processing dataset, the risk warning report and the system instruction set, and providing support for manual decision-making and instruction issuance based on the visual panel include: S7.1: Based on the second processing dataset, the bridge state is visualized and rendered using the BIM model, and the rendering result is displayed through the visual panel; Based on the risk level in the risk warning report, color rendering is performed using color coding, and the color rendering result is displayed through the visual panel; The system instruction set is displayed in list form; S7.2: Based on the visual panel, administrators can view and process risk warning reports and system command sets, including confirmation, rejection, and modification; When the administrator's processing result is confirmation or modification, the instruction status of the system instruction set is changed to confirmed or modified, and sent to the target control device; When the administrator's decision is rejection, the rejection reason text is manually entered and output to the control policy generator for rule update; S7.3: Monitor the operation records in step S7.2 to obtain the decision operation log, and store the decision operation log in the database. The operation record includes the system instruction set, instruction status, administrator ID, operation timestamp and execution result.

10. The bridge construction monitoring method based on the Internet of Things is realized according to the bridge construction monitoring system based on the Internet of Things in any one of claims 1-9, characterized in that, The work includes the following steps: S1: Collect raw data based on sensor networks to obtain the raw dataset; S2: Process the original dataset to obtain the first processed dataset; S3: Perform multi-level preprocessing on the first processing dataset to obtain the second processing dataset; S4: Analyze the second processing dataset to obtain a risk warning report; S5: Generate strategy control reports based on risk warning reports; S6: Transform and execute the policy control report to obtain the system instruction set; S7: Processes the second processing dataset, risk warning reports, and system instruction sets, and provides support for human decision-making and instruction issuance based on a visualization panel.

Images