A bridge condition diagnosis method based on data visualization

Abstract

The present invention discloses a bridge condition diagnosis method based on data visualization, which relates to the technical field of condition diagnosis and includes the following steps: obtaining the main girder stiffness values monitored at each monitoring point, judging the fuzzy state of the monitoring point, screening the monitoring points to be analyzed, setting a first mark, calculating the diffusion rate according to the first mark, setting a second mark, calculating the growth rate according to the second mark, judging the damage level, and constructing a condition judgment model. The present invention realizes the safety warning function, can monitor the abnormal conditions of the bridge structure in real time, helps to ensure the safe operation of the bridge and extend its service life, provides scientific basis and guidance for bridge managers and engineers based on the bridge bearing capacity evaluation and damage identification results of big data and artificial intelligence, helps them formulate effective maintenance and repair strategies, analyzes the sensor data of the bridge by using deep learning algorithms, identifies potential damages and structural defects, and improves the accuracy of damage identification.

Description

Technical Field

[0001] The present invention relates to the technical field of condition diagnosis, and particularly relates to a bridge condition diagnosis method based on data visualization. Background Art

[0002] In recent years, bridge detection technology has been developing towards the direction of intelligence. High-precision video equipment is carried by carriers such as unmanned aerial vehicles and robots to detect the appearance of bridge structures, so as to improve the accuracy of data and reduce the influence of subjective factors. By using various sensors and communication devices to continuously measure and record structural responses, timely danger warnings and safety assessments are realized, thereby extending the service life of bridges and guiding the management and maintenance of bridges.

[0003] Currently, in a Chinese invention patent with the publication number of CN112989456B, a bridge performance degradation diagnosis method and system are disclosed. This method constructs a first temperature-displacement similarity factor, and constructs a second temperature-displacement similarity factor by setting the mode of vehicle weight distribution on the bridge, the reference value of strain at the bottom of the beam, the daily operation state of the bridge, the displacement of the expansion joint, the structural temperature, the number of vehicles with a vehicle weight not less than the mode of vehicle weight distribution, and the dynamic strain data at the bottom of the beam, obtains the number of strain peaks, constructs a state degradation factor, and determines the degradation degree of the bridge. However, in the related technology, the monitoring points are not optimized according to the specific driving trajectory of the vehicle and the specific number of times the bridge deck is driven, resulting in a large amount of calculation and being unfavorable for the rapid responsiveness of diagnosis. The state of the bridge is not judged according to the key parameters of the main beam of the bridge deck passed by the vehicle, which is unfavorable for simplifying the judgment process and the flexibility of application, and there are certain limitations. Summary of the Invention

[0004] The technical problem solved by the present invention is that in the related technology, the monitoring points are not optimized according to the specific driving trajectory of the vehicle and the specific number of times the bridge deck is driven, resulting in a large amount of calculation and being unfavorable for the rapid responsiveness of diagnosis. The state of the bridge is not judged according to the key parameters of the main beam of the bridge deck passed by the vehicle, which is unfavorable for simplifying the judgment process and the flexibility of application, and there are certain limitations.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A bridge condition diagnosis method based on data visualization, comprising the following steps:

[0006] Step S100, set the positions of monitoring points, simulation parameters and simulation period and conduct tests;

[0007] Step S200, obtain the main beam stiffness values monitored at each monitoring point, obtain the standard main beam stiffness range according to the bridge type, and obtain the service life and the standard main beam stiffness range according to the bridge code;

[0008] Step S300, preprocess the main girder stiffness value of the monitoring point, and judge the fuzzy state of the monitoring point;

[0009] Step S400, screen the monitoring points to be analyzed according to the fuzzy state, make the first mark on the time point when the initial fuzzy state changes and calculate the diffusion rate, make the second mark on the time point when the initial fuzzy state of the monitoring points to be analyzed changes and calculate the growth rate, judge the damage level according to the growth rate and the diffusion rate, and construct a state judgment model through hierarchical analysis;

[0010] Step S500, make a judgment according to the current data and the state judgment model to obtain the current damage level.

[0011] As a preferred solution of a bridge state diagnosis method based on data visualization according to the present invention, wherein: the method for setting the monitoring points includes:

[0012] Obtain the three-dimensional model of the bridge deck, set the size of the segmentation frame, divide the three-dimensional model into sub-bridge decks, obtain the historical rolling tracks of the sub-bridge decks, set the length, width and height of the selected cuboid, so that there is only one edge of the selected cuboid located on the sub-bridge deck, and the sub-bridge deck is completely distributed in the selected cuboid, take the edge as the origin, and take the directions of the length, width and height as the X-axis, Y-axis and Z-axis to construct a three-dimensional coordinate system, and obtain the three-dimensional coordinates of the rolling track curve;

[0013] Map the historical rolling track into the three-dimensional coordinate system to obtain the rolling track equation, count the number of times the same three-dimensional coordinates appear in the rolling track equation, and record it as the first number;

[0014] Set the first value as the number threshold. When the first number is less than or equal to the first value, delete the corresponding sub-bridge deck. When the first number is greater than the first value, install a stiffness sensor at the three-dimensional coordinates.

[0015] As a preferred solution of a bridge state diagnosis method based on data visualization according to the present invention, wherein: the average vehicle density, average vehicle speed and average vehicle weight are respectively expressed as the average vehicle density, average vehicle speed and average vehicle weight of the entire bridge deck during the operation of the bridge. The vehicle weight includes the weight of the vehicle itself and the weight of the people and objects in the vehicle. The average vehicle density is expressed as the ratio of the number of vehicles on the bridge deck per second to the area of the bridge deck.

[0016] As a preferred solution of a bridge state diagnosis method based on data visualization according to the present invention, wherein: the step S200 includes the following sub-steps:

[0017] Step S201, obtain the bridge code;

[0018] Step S202, retrieve the bridge database, input the bridge code into the bridge database, and match the bridge type, bridge service life, and standard main girder stiffness range of the bridge corresponding to the bridge code;

[0019] The bridge types of the bridge include reinforced concrete slab bridges, reinforced concrete beam bridges, and reinforced concrete arch bridges.

[0020] As a preferred solution of a bridge condition diagnosis method based on data visualization according to the present invention, wherein: the step S300 includes the following sub-steps:

[0021] Step S301, preprocess the main girder stiffness value of the monitoring point, and the preprocessing includes outlier removal processing and missing value filling processing;

[0022] Step S303, judge the fuzzy state of the monitoring point according to the main girder stiffness range, and the fuzzy state includes abnormal response and normal response. The judgment method of the fuzzy state includes:

[0023] Compare the main girder stiffness value with the standard main girder stiffness range. When the main girder stiffness value is distributed within the standard main girder stiffness range, set the fuzzy state to normal response. When the main girder stiffness value is not distributed within the standard main girder stiffness range, set the fuzzy state to abnormal response. When the main girder stiffness value of any monitoring point at any moment is not distributed within the standard main girder stiffness range, judge the fuzzy state as an abnormal state.

[0024] As a preferred solution of a bridge condition diagnosis method based on data visualization according to the present invention, wherein: the screening method for screening the monitoring points to be analyzed according to the fuzzy state includes:

[0025] Obtain the fuzzy state of the monitoring point. When the fuzzy state of the monitoring point is an abnormal state, set the monitoring point as the monitoring point to be analyzed. Otherwise, delete the main girder stiffness value corresponding to the monitoring point.

[0026] As a preferred solution of a bridge condition diagnosis method based on data visualization according to the present invention, wherein: the setting method of the first mark includes:

[0027] Obtain the initial monitoring time points when each fuzzy state changes, sort the initial monitoring time points in chronological order, calculate the time interval between adjacent initial monitoring time points after sorting, set the second value as the time interval threshold, calculate the monitoring point corresponding to the initial monitoring time point with the earliest time order as the first mark of the first color, calculate the sum value of the initial monitoring time point with the earliest time order and the second value, denote it as the second sum value, and set the monitoring points corresponding to the initial monitoring time points before the second sum value as the first marks of the second color;

[0028] Weight the second sum value and the second value to obtain a third sum value, and set the monitoring point corresponding to the initial monitoring time point before the third sum value as the first mark of the third color;

[0029] Repeat the weighting step to obtain the Nth sum value, and set the monitoring point corresponding to the initial monitoring time point before the Nth sum value as the first mark of the Nth color.

[0030] As a preferred solution of a bridge condition diagnosis method based on data visualization according to the present invention, wherein: the calculation method of the diffusion rate includes:

[0031] Statistically calculate the area of the sub-bridge deck corresponding to the first marks of each color, calculate the difference between the areas of the sub-bridge decks corresponding to the first marks of adjacent colors, denote it as the first difference, calculate the ratio of adjacent first differences, calculate the average value of the ratios of each adjacent first difference, denote it as the second average value, and set the second average value as the diffusion rate. The order of the adjacent colors is from the first color to the Nth color.

[0032] As a preferred solution of a bridge condition diagnosis method based on data visualization according to the present invention, wherein: the method for setting the second mark for the monitoring time points when the initial fuzzy state of the same monitoring point to be analyzed changes includes:

[0033] Obtain the main girder stiffness value of any monitoring point to be analyzed, and set the monitoring time point when the initial fuzzy state of the monitoring point to be analyzed changes as the second mark, and the second mark represents the time point when the fuzzy state of the monitoring point first changes from the normal state to the abnormal state;

[0034] The calculation method of the growth rate includes:

[0035] Obtain the monitoring time point when the initial fuzzy state changes and the main girder stiffness values thereafter, calculate the ratio of adjacent main girder stiffness values, and calculate the average value of each ratio of the monitoring point, calculate the average value of the average values of each ratio of each monitoring point, denote it as the first average value, and set the first average value as the growth rate;

[0036] Calculate the sum value of the first average value and the second average value, denote it as the first sum value, and set the third value and the fourth value as the sum value threshold;

[0037] Judge the damage level according to the sum value threshold. The judgment method of the damage level includes:

[0038] When the first sum value is less than the third value, set the damage level as the first level; when the first sum value is greater than or equal to the third value and less than the fourth value, set the damage level as the second level; when the first sum value is greater than or equal to the fourth value, set the damage level as the third level;

[0039] The bridge damage degrees represented by the first level, the second level, and the third level are in an increasing order.

[0040] As a preferred solution of a bridge condition diagnosis method based on data visualization according to the present invention, wherein: taking simulation parameters and bridge service life as the criterion layer, taking the damage level as the target layer, and taking the rules for judging the damage level as the scheme layer, performing hierarchical analysis to obtain the weights of each simulation parameter, constructing a state judgment model according to the weights, obtaining current data, the current data including current simulation parameters and current bridge service life, and judging the current damage level according to the state judgment model;

[0041] The calculation expression of the state judgment level includes:

[0042] ;

[0043] Wherein, is the damage level, is the parameter of the i-th criterion layer, is the coefficient corresponding to the parameter of the i-th criterion layer, is the number of parameters of the criterion layer.

[0044] The beneficial effects of the present invention: realizing the safety warning function, being able to monitor the abnormal conditions of the bridge structure in real time, providing a scientific and reliable basis for bridge disease prevention and control and maintenance and reinforcement decision-making, helping to ensure the safe operation of the bridge and extend its service life, the bridge bearing capacity evaluation and damage identification results based on big data and artificial intelligence providing a scientific basis and guidance for bridge managers and engineers, helping them formulate effective maintenance and repair strategies, and using deep learning algorithms to analyze the sensor data of the bridge to identify potential damages and structural defects, improving the accuracy of damage identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a schematic diagram of the basic process of a bridge condition diagnosis method based on data visualization provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be given in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0047] Embodiment, referring to Figure 1 , which is an embodiment of the present invention, provides a bridge condition diagnosis method based on data visualization. A bridge condition diagnosis method based on data visualization includes the following steps:

[0048] Step S100, set the positions of the monitoring points, simulation parameters and simulation period and conduct tests;

[0049] Step S200, obtain the main girder stiffness values monitored at each monitoring point, obtain the standard main girder stiffness range according to the bridge type, and obtain the service life and standard main girder stiffness range according to the bridge code;

[0050] Step S300, preprocess the main girder stiffness values of the monitoring points and judge the fuzzy state of the monitoring points;

[0051] Step S400, screen the monitoring points to be analyzed according to the fuzzy state, make the first mark on the time point when the initial fuzzy state changes and calculate the diffusion rate, make the second mark on the time point when the initial fuzzy state of the monitoring points to be analyzed changes and calculate the growth rate, judge the damage level according to the growth rate and diffusion rate, and construct a state judgment model through hierarchical analysis;

[0052] Step S500, make a judgment according to the current data and the state judgment model to obtain the current damage level.

[0053] The present invention realizes the safety warning function, can monitor the abnormal conditions of the bridge structure in real time, provides a scientific and reliable basis for the prevention and treatment of bridge diseases and the decision-making of maintenance and reinforcement, helps to ensure the safe operation of the bridge and extend its service life, and provides a scientific basis and guidance for bridge managers and engineers based on the bridge bearing capacity evaluation and damage identification results of big data and artificial intelligence, helps them formulate effective maintenance and repair strategies, analyzes the sensor data of the bridge by using deep learning algorithms, identifies potential damages and structural defects, and improves the accuracy of damage identification.

[0054] The setting method of the monitoring points includes:

[0055] Obtain the three-dimensional model of the bridge deck, set the size of the segmentation frame, divide the three-dimensional model into sub-bridge decks, obtain the historical rolling tracks of the sub-bridge decks, set the length, width and height of the selected cuboid, so that only one edge of the selected cuboid is located on the sub-bridge deck, and the sub-bridge deck is completely distributed in the selected cuboid, construct a three-dimensional coordinate system with the edge as the origin and the directions of the length, width and height as the X-axis, Y-axis and Z-axis, and obtain the three-dimensional coordinates of the rolling track curve;

[0056] Map the historical rolling tracks into the three-dimensional coordinate system to obtain the rolling track equation, count the number of times the same three-dimensional coordinates appear in the rolling track equation, and record it as the first number;

[0057] Set the first value as the number threshold. When the first number is less than or equal to the first value, delete the corresponding sub-bridge deck. When the first number is greater than the first value, install a stiffness sensor at the three-dimensional coordinates.

[0058] In specific implementation, a three-dimensional model of the bridge deck is obtained and the size of the segmentation box is set, and the three-dimensional model is segmented into sub-bridge decks. This method can more accurately locate the monitoring points, improve the accuracy of the monitoring data and the efficiency of the monitoring work. By using the historical rolling tracks and the setting of the three-dimensional coordinate system, the monitoring points are more scientifically arranged to ensure that the monitoring points can cover the key areas, improving the representativeness and practicality of the monitoring data. By counting the number of times the same three-dimensional coordinates appear in the rolling track equation and setting a threshold for the number of times, the sub-bridge decks with fewer occurrences are effectively deleted, reducing redundant data and improving the efficiency of data processing.

[0059] The three-dimensional model of the bridge deck is obtained by using high-precision three-dimensional scanning technology or by constructing the bridge deck based on the design drawings.

[0060] The average vehicle density, average vehicle speed and average vehicle weight are respectively expressed as the average vehicle density, average vehicle speed and average vehicle weight of the entire bridge deck during the operation of the bridge. The vehicle weight includes the weight of the vehicle itself and the weight of the people and objects inside the vehicle. The average vehicle density is expressed as the ratio of the number of vehicles on the bridge deck per second to the area of the bridge deck.

[0061] The step S200 includes the following sub-steps:

[0062] Step S201, obtain the bridge code;

[0063] Step S202, retrieve the bridge database, input the bridge code into the bridge database, and match the bridge type, bridge service life and standard main girder stiffness range of the bridge corresponding to the bridge code;

[0064] The bridge types of the bridge include reinforced concrete slab bridges, reinforced concrete beam bridges and reinforced concrete arch bridges.

[0065] In specific implementation, by accurately obtaining the bridge code and matching the corresponding bridge information, the accuracy of the data such as the bridge type, service life and standard main girder stiffness range obtained is ensured, thereby improving the accuracy of the bridge condition diagnosis. Quickly matching the bridge code with the database information reduces the time for manual query and data processing, and improves the efficiency of the bridge condition diagnosis.

[0066] For example, the bridge code is "XJZ-2024-001", where "XJZ" represents the bridge type, "2024" represents the bridge construction year, and "001" is the serial number of that year. According to the code "XJZ-2024-001", the bridge type is matched as "reinforced concrete beam bridge" in the database, and the service life of the bridge is 15 years. For the "reinforced concrete beam bridge", the standard main girder stiffness range is 1000 kN / m to 1500 kN / m.

[0067] The step S300 includes the following sub-steps:

[0068] Step S301: Preprocess the main girder stiffness value of the monitoring point. The preprocessing includes removing outliers and filling in missing values.

[0069] Step S303: Judge the fuzzy state of the monitoring point according to the main girder stiffness range. The fuzzy state includes abnormal response and normal response. The judgment method of the fuzzy state includes:

[0070] Compare the main girder stiffness value with the standard main girder stiffness range. When the main girder stiffness value is distributed within the standard main girder stiffness range, set the fuzzy state to normal response. When the main girder stiffness value is not distributed within the standard main girder stiffness range, set the fuzzy state to abnormal response. When the main girder stiffness value of any monitoring point at any moment is not distributed within the standard main girder stiffness range, judge the fuzzy state as an abnormal state.

[0071] In specific implementation, by removing outliers and filling in missing values, the preprocessing step improves the quality of the monitoring data, provides a more reliable data basis for subsequent analysis. Accurate outlier processing and missing value filling ensure the authenticity and integrity of the main girder stiffness value, thereby enhancing the accuracy of the monitoring results.

[0072] For example, select monitoring point A. Compare the preprocessed main girder stiffness value with the standard main girder stiffness range. 1200 kN / m and 1500 kN / m belong to normal response, and 1100 kN / m does not belong to the standard main girder stiffness range, so it is judged as an abnormal response. For monitoring point A, since there is an abnormal response (1100 kN / m), the overall fuzzy state is judged as an abnormal state, and further inspection and analysis are required.

[0073] The screening method for screening the monitoring points to be analyzed according to the fuzzy state includes:

[0074] Obtain the fuzzy state of the monitoring point. When the fuzzy state of the monitoring point is an abnormal state, set the monitoring point as the monitoring point to be analyzed. Otherwise, delete the main girder stiffness value corresponding to the monitoring point.

[0075] The setting method of the first mark includes:

[0076] Obtain the initial monitoring time points when each fuzzy state changes. Sort the initial monitoring time points in chronological order. Calculate the time interval between adjacent initial monitoring time points after sorting. Set the second value as the time interval threshold. Set the monitoring point corresponding to the initial monitoring time point with the earliest time order as the first mark of the first color. Calculate the sum value of the initial monitoring time point with the earliest time order and the second value, denoted as the second sum value. Set the monitoring points corresponding to the initial monitoring time points before the second sum value as the first marks of the second color.

[0077] Weight the second sum value and the second value to obtain a third sum value, and set the monitoring point corresponding to the initial monitoring time point before the third sum value as the first mark of the third color;

[0078] Repeat the weighting step to obtain the Nth sum value, and set the monitoring point corresponding to the initial monitoring time point before the Nth sum value as the first mark of the Nth color.

[0079] In specific implementation, by setting the first marks of different colors, the time and location of bridge damage can be more precisely identified and distinguished, the accuracy of damage detection can be improved, the initial monitoring time points are sorted and the time intervals are calculated, the time and speed of damage development are analyzed, providing data support for the time series analysis of bridge damage. Each time point, as well as the time points after weighting of the time points and time intervals, are distributed within the monitoring period. The initial monitoring time points are sorted and the time intervals are calculated, the time and speed of damage development are analyzed, providing data support for the time series analysis of bridge damage. By calculating the time intervals and weighted sum values, the damage development trend is predicted, providing forward-looking guidance for the maintenance and repair of the bridge;

[0080] The calculation method of the diffusion rate includes:

[0081] Statistically calculate the area of the sub-bridge deck corresponding to the first mark of each color, calculate the difference between the areas of the sub-bridge decks corresponding to the first marks of adjacent colors, denoted as the first difference, calculate the ratio of adjacent first differences, calculate the average value of the ratios of each adjacent first difference, denoted as the second average value, and set the second average value as the diffusion rate. The order of the adjacent colors is from the first color to the Nth color.

[0082] The method for setting the second mark for the monitoring time points when the initial fuzzy state of the same monitoring point to be analyzed changes includes:

[0083] Obtain the main beam stiffness value of any monitoring point to be analyzed, and set the second mark for the monitoring time point when the initial fuzzy state of the monitoring point to be analyzed changes. The second mark represents the time point when the fuzzy state of the monitoring point first changes from the normal state to the abnormal state;

[0084] The calculation method of the growth rate includes:

[0085] Obtain the monitoring time points when the initial fuzzy state changes and the main beam stiffness values thereafter, calculate the ratio of adjacent main beam stiffness values, and calculate the average value of each ratio of the monitoring point. Calculate the average value of the average values of each ratio of each monitoring point, denoted as the first average value, and set the first average value as the growth rate;

[0086] Calculate the sum of the first average value and the second average value, denoted as the first sum value, and set the third value and the fourth value as the sum value threshold;

[0087] Judge the damage level according to the sum value threshold. The judgment method of the damage level includes:

[0088] When the first sum value is less than the third value, set the damage level to the first level; when the first sum value is greater than or equal to the third value and less than the fourth value, set the damage level to the second level; when the first sum value is greater than or equal to the fourth value, set the damage level to the third level;

[0089] The first level, the second level and the third level represent the increasing order of the bridge damage degree.

[0090] In specific implementation, count the areas of the sub-bridges corresponding to the first marks of each color. This step involves quantifying the damage states of different parts of the bridge, providing basic data for subsequent analysis. Calculate the difference between the areas of the sub-bridges corresponding to the first marks of adjacent colors, denoted as the first difference, which helps to identify the scale change of damage diffusion. The order of the adjacent colors is from the first color to the Nth color, ensuring the continuity and comprehensiveness of the diffusion rate calculation. Accurately identify the conversion time point of the fuzzy state of the monitoring point from normal to abnormal through the second mark, which helps to detect the starting moment of bridge damage in time and provides a key time node for subsequent damage analysis. The division of the damage level provides a scientific damage degree evaluation method, which helps to formulate targeted maintenance strategies and improve the service life and safety of the bridge.

[0091] For example, the monitoring time point when the initial fuzzy state of monitoring point A changes is TA = 2024−01−01, which is marked as the second mark, indicating the time point when the fuzzy state of monitoring point A first changes from the normal state to the abnormal state. The main beam stiffness value after TA is 1000, and the stiffness value after TA + 30 is 950. The ratio of adjacent main beam stiffness values is 0.95. The average value of each ratio of monitoring point A is 0.950.95, and the average value of each ratio of all monitoring points is also 0.950.95, that is, the growth rate. The first sum value is 1.90, the third value is 1.51, and the fourth value is 2.02. Since the first sum value 1.901.90 is greater than or equal to the third value 1.51.5 and less than the fourth value 2.02, the damage level is set to the second level, indicating medium bridge damage degree.

[0092] Taking the simulation parameters and the service life of the bridge as the criterion layer, the damage level as the target layer, and the rules for judging the damage level as the scheme layer, perform hierarchical analysis to obtain the weights of each simulation parameter. Construct a state judgment model based on the weights, obtain the current data, where the current data includes the current simulation parameters and the current service life of the bridge, and judge the current damage level according to the state judgment model;

[0093] The calculation expression of the state judgment level includes:

[0094] ;

[0095] Among them, is the damage level, is the parameter of the i-th criterion layer, is the coefficient corresponding to the parameter of the i-th criterion layer, is the number of parameters of the criterion layer.

[0096] In specific implementation, hierarchical analysis constructs a pairwise comparison matrix of the criterion layer to the target layer, and the expression of the pairwise comparison matrix is;

[0097] ;

[0098] Among them, is the pairwise comparison matrix, and the pairwise comparison matrix is a 5×5 matrix.

[0099] The present invention realizes the safety warning function, can monitor the abnormal conditions of the bridge structure in real time, provides a scientific and reliable basis for the decision-making of bridge disease prevention and maintenance reinforcement, helps to ensure the safe operation of the bridge and extend its service life. Based on the bridge bearing capacity evaluation and damage identification results of big data and artificial intelligence, it provides scientific basis and guidance for bridge managers and engineers, helps them formulate effective maintenance and repair strategies, uses deep learning algorithms to analyze the sensor data of the bridge, identifies potential damages and structural defects, and improves the accuracy of damage identification.

[0100] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium is implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 functions specified in one block or multiple blocks.

[0101] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that modifications or equivalent replacements of the technical solutions of the present invention, without departing from the spirit and scope of the technical solutions of the present invention, should all be covered by the scope of the claims of the present invention.

Claims

1. A bridge status diagnosis method based on data visualization, characterized in that: The following steps are involved: Step S100, setting the monitoring point location, simulation parameters and simulation cycle and performing testing; Step S200, obtaining the main beam stiffness value monitored at each monitoring point, obtaining the standard main beam stiffness range according to the bridge type, and obtaining the service time and the standard main beam stiffness range according to the bridge code; Step S300, pre-processing the main beam stiffness value of the monitoring point to determine the fuzzy state of the monitoring point; Step S400, selecting the monitoring points to be analyzed according to the fuzzy state, first marking the time point at which the initial fuzzy state changes and calculating the diffusion rate, second marking the time point at which the initial fuzzy state of the monitoring point to be analyzed changes and calculating the growth rate, judging the damage level according to the growth rate and the diffusion rate, and constructing a state judgment model through hierarchical analysis; Step S500, determining the current damage level based on the current data and the state judgment model; The step S300 includes the following sub-steps: Step S301, preprocessing the main beam stiffness value of the monitoring point, wherein the preprocessing includes removing abnormal values ​​and filling missing values; Step S302, judging the fuzzy state of the monitoring point according to the main beam stiffness range, the fuzzy state includes abnormal response and normal response, and the judging method of the fuzzy state includes: Compare the main beam stiffness value with the standard main beam stiffness range. When the main beam stiffness value is distributed within the standard main beam stiffness range, set the fuzzy state to a normal response. When the main beam stiffness value is not distributed within the standard main beam stiffness range, set the fuzzy state to an abnormal response. When the main beam stiffness value at any monitoring point at any time is not distributed within the standard main beam stiffness range, the fuzzy state is judged as an abnormal state. The change of the initial fuzzy state is represented by the change of the detection point to be analyzed from a normal response to an abnormal response; The method for setting the first mark includes: Obtain the initial monitoring time points of each fuzzy state change, sort the initial monitoring time points in chronological order, calculate the time intervals of adjacent initial monitoring time points after sorting, set the second value as the time interval threshold, calculate the monitoring point corresponding to the initial monitoring time point at the front of the time sequence and set it as the first mark of the first color, calculate the sum of the initial monitoring time point at the front of the time sequence and the second value, record it as the second sum value, and set the monitoring point corresponding to the initial monitoring time point before the second sum value as the first mark of the second color; The second sum value and the second value are weighted to obtain a third sum value, and the monitoring point corresponding to the initial monitoring time point before the third sum value is set as a first mark of a third color; The weighted step is repeated to obtain the Nth sum value, and the monitoring point corresponding to the initial monitoring time point before the Nth sum value is set as the first mark of the Nth color; The calculation method of diffusion rate includes: Count the areas of the sub-bridge surfaces corresponding to the first marks of each color, calculate the difference in the areas of the sub-bridge surfaces corresponding to the first marks of adjacent colors, record it as a first difference, calculate the ratio of adjacent first differences, calculate the average of the ratios of each adjacent first difference, record it as a second average, set the second average as the diffusion rate, and the order of the adjacent colors is from the first color to the Nth color; The method for setting a second mark for the monitoring time point at which the initial fuzzy state of the same monitoring point to be analyzed changes includes: Obtaining the main beam stiffness value of any monitoring point to be analyzed, and marking the monitoring time point at which the initial fuzzy state of the monitoring point to be analyzed changes, wherein the second mark represents the time point at which the fuzzy state of the monitoring point changes from a normal state to an abnormal state for the first time; The growth rate calculation method includes: Obtain the main beam stiffness value at and after the monitoring time point when the initial fuzzy state changes, calculate the ratio of adjacent main beam stiffness values, and calculate the average value of each ratio of the monitoring point, calculate the average value of each ratio of each monitoring point, record it as a first average value, and set the first average value as the growth rate; Calculate the sum of the first average value and the second average value, record it as the first sum value, and set the third value and the fourth value as the sum value threshold; The damage level is determined based on the sum value threshold. The damage level determination methods include: When the first sum is less than the third value, the damage level is set to the first level; when the first sum is greater than or equal to the third value and less than the fourth value, the damage level is set to the second level; when the first sum is greater than or equal to the fourth value, the damage level is set to the third level; The first level, second level, and third level represent the degree of bridge damage in increasing order.

2. A bridge status diagnosis method based on data visualization as claimed in claim 1, characterized in that: The method for setting the monitoring points includes: Obtain a three-dimensional model of the bridge deck, set the size of the segmentation frame, segment the three-dimensional model into sub-bridge decks, obtain the historical rolling track of the sub-bridge deck, set the length, width and height of the framed rectangular parallelepiped, so that one and only one corner of the framed rectangular parallelepiped is located on the sub-bridge deck, and the sub-bridge deck is completely distributed in the framed rectangular parallelepiped, take the corner as the origin, take the length direction, width direction and height direction as the X-axis, Y-axis and Z-axis, construct a three-dimensional coordinate system, and obtain the three-dimensional coordinates of the rolling track curve; Mapping the historical rolling track into a three-dimensional coordinate system to obtain a rolling track equation, and counting the number of times the same three-dimensional coordinates appear in the rolling track equation, which is recorded as the first number; The first value is set as the number threshold, when the first number is less than or equal to the first value, the corresponding sub-bridge deck is deleted, and when the first number is greater than the first value, a stiffness sensor is placed at the three-dimensional coordinate.

3. The bridge status diagnosis method based on data visualization according to claim 1, characterized in that: The average vehicle density, average vehicle speed and average vehicle weight are respectively expressed as the average vehicle density, average vehicle speed and average vehicle weight of the entire bridge deck when the bridge is in operation. The vehicle weight includes the weight of the vehicle itself, as well as the weight of people and objects in the vehicle. The average vehicle density is expressed as the ratio of the number of vehicles on the bridge deck per second to the area of ​​the bridge deck.

4. The bridge status diagnosis method based on data visualization according to claim 1, characterized in that: The step S200 includes the following sub-steps: Step S201, obtaining a bridge code; Step S202, calling up a bridge database, inputting the bridge code into the bridge database, and matching the bridge type, bridge service time, and standard main beam stiffness range of the bridge corresponding to the bridge code; The bridge types include reinforced concrete slab bridges, reinforced concrete beam bridges and reinforced concrete soil bridges.

5. The bridge status diagnosis method based on data visualization according to claim 1, characterized in that: The screening methods for screening monitoring points to be analyzed according to the fuzzy state include: The fuzzy state of the monitoring point is obtained. When the fuzzy state of the monitoring point is an abnormal state, the monitoring point is set as a monitoring point to be analyzed. Otherwise, the main beam stiffness value corresponding to the monitoring point is deleted.

6. The bridge status diagnosis method based on data visualization according to claim 1, characterized in that: Taking simulation parameters and bridge service time as the criterion layer, damage level as the target layer, and rules for judging damage level as the solution layer, hierarchical analysis is performed to obtain the weights of various simulation parameters, and a state judgment model is constructed according to the weights to obtain current data, which includes current simulation parameters and current bridge service time, and the current damage level is judged according to the state judgment model; The calculation expressions of the status judgment level include: ； in, is the damage level, is the parameter of the i-th criterion layer, is the coefficient corresponding to the parameter of the i-th criterion layer, is the number of parameters of the criterion layer.

Images