Bridge construction safety intelligent monitoring method and system

Abstract

The present invention relates to the technical field of construction progress monitoring, specifically to a method and system for intelligently monitoring bridge construction safety. The method comprises the following steps: acquiring main beam structure and construction equipment data through sensors, calculating dynamic responses using a mutual information algorithm and generating disturbance response time series data, constructing a disturbance path and extracting path offset angles and jump frequencies, acquiring main beam offset angles and disturbance frequencies and marking abnormal time periods, generating a main beam component offset map, analyzing abnormal areas of pier components, and generating a bridge construction monitoring view. In the present invention, distributed sensors synchronously collect state data, extract disturbance response amplitudes and reconstruct time series, fit path directions and jump frequencies, capture displacement offsets and unstable behaviors, identify imbalance risk areas, and construct a visual layer for dynamic updates, thereby improving monitoring accuracy and early warning efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of construction progress monitoring, and in particular to a method and system for intelligently monitoring bridge construction safety. Background Art

[0002] The field of construction progress monitoring technology encompasses the real-time monitoring and management of the progress of various tasks during the execution of a construction project. This primarily involves data collection, information transmission, and real-time feedback from the construction site through various means and equipment. The core aspects of construction progress monitoring technology include the development of construction plans, progress tracking, the allocation of construction resources, and the early warning and adjustment of delays. To ensure the smooth progress of construction projects, construction progress monitoring technology requires the ability to accurately capture the usage of various resources during the construction process and provide real-time feedback to the management platform, enabling timely correction and optimization of any issues.

[0003] The intelligent bridge construction safety monitoring method and system refers to a safety monitoring system specifically designed for bridge construction, including real-time safety monitoring technology for bridge construction sites. Specifically, it involves using sensors and monitoring equipment to collect various safety data during the construction process in real time, including personnel location, equipment status, and environmental changes, to ensure that the safety situation at the construction site is immediately reflected. By establishing monitoring points, data collection, and information transmission paths, comprehensive monitoring and management of various safety parameters at the construction site are achieved. Furthermore, based on the collected data, the system can issue alarms for abnormal situations, providing real-time protection for construction safety.

[0004] Existing technologies rely on conventional sensors and monitoring equipment to collect and transmit on-site status data. However, most systems are limited to static data acquisition and status threshold assessment, making it difficult to continuously track and analyze dynamic changes during the construction process. Data collection fails to fully capture the dynamic evolution of disturbance behavior, resulting in a lack of quantitative analysis of deviation trends and jump anomalies. In complex environments with frequent construction equipment movement and drastic changes in main beam status, traditional systems often only provide static feedback after a problem occurs. They lack the ability to model and proactively identify the evolving behavior, resulting in delayed anomaly warnings and difficulty in effectively activating on-site risk response mechanisms. For example, when a main beam exhibits transient nonlinear deviation during hoisting, conventional systems, due to limitations in data acquisition frequency and data linkage mechanisms, may not be able to capture the sudden change in real time, missing the warning window and compromising the real-time and accuracy of overall safety control. Existing technologies still have significant shortcomings in dynamic data analysis capabilities, structural behavior trend modeling, and spatial risk expression, making them difficult to meet the needs of intelligent monitoring in complex construction environments. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present invention provide a bridge construction safety intelligent monitoring method and system. The technical solution is as follows:

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a bridge construction safety intelligent monitoring method, comprising the following steps:

[0007] S1: Distributed sensors are used to obtain the physical state data of the main beam structure and the action state data of the bridge construction equipment, which are aligned by time nodes. The dynamic response amplitude of the main beam during construction is calculated using the mutual information algorithm to generate disturbance response time series data.

[0008] The dynamic response amplitude is the displacement data generated by the main beam during the hoisting operation. The influence of the equipment action on the main beam response is calculated by the mutual information method, and the actual response amplitude of the main beam to the construction action is calculated in combination with the structural state synchronization data.

[0009] S2: Obtain the continuous displacement changes of the disturbance response time series data to construct a disturbance path segment set, classify it through a support vector machine model and extract the path offset angle and jump frequency to generate a disturbance path change sequence;

[0010] S3: Based on the disturbance path variation sequence, the continuous offset angles and disturbance jump frequencies of the main beam during the hoisting construction process are obtained and an offset angle sequence is constructed. The angular offset trends of the offset angle sequences of the trajectory segments in multiple time periods are calculated and abnormal time periods are marked to generate an offset map of the main beam components.

[0011] S4: Based on the main beam component offset map, the jump time and offset angle changes of adjacent pier components are obtained and the differences are calculated respectively, the areas with abnormal bridge component positions are screened, and the imbalance response identification results are generated;

[0012] S5: Construct visual layer coordinates using the imbalance response identification results and the disturbance response time series data, and mark the risk level of the bridge main beam on the map to generate a smart monitoring view for bridge construction.

[0013] As a further solution of the present invention, the disturbance response time series data specifically refers to the dynamic response amplitude of the main beam and the disturbance jump frequency. The disturbance path change sequence includes the path direction offset angle, jump frequency, and offset angle sequence. The main beam component offset map specifically refers to the offset angle change trend, abnormal time period marking, and main beam component offset map. The imbalance response identification result specifically refers to the offset angle difference, abnormal area identification, and area screening result. The bridge construction intelligent monitoring view includes component number, coordinate position, risk level marking, and main beam component response level distribution.

[0014] As a further solution of the present invention, the step S1 is specifically as follows:

[0015] S101: Obtain structural physical status data of the bridge main beam and motion status data of the construction equipment through distributed sensors, align them with time nodes, and generate synchronized data of the main beam and equipment status;

[0016] S102: Based on the main beam and equipment status synchronization data, quantitatively analyze the relationship between the construction equipment movement and the main beam response, calculate the impact of the equipment movement on the main beam response through a mutual information algorithm, and generate equipment impact coefficient data;

[0017] S103: Calculate the dynamic response amplitude of the main beam during the construction process based on the equipment influence coefficient data and the main beam and equipment status synchronization data, and generate disturbance response time series data.

[0018] As a further solution of the present invention, the influence degree of the device action on the main beam response is calculated by the mutual information algorithm. , using the formula:

[0019] ;

[0020] in, Indicates the Class device actions and The main beam response is The joint probability under the level, Indicates the Class device action The probability of the level, Indicates the The main beam response is The probability of the level, Indicates that the equipment action and the main beam response are in the The absolute value of the probability difference under the level, The total number of levels.

[0021] As a further solution of the present invention, the step S2 is specifically as follows:

[0022] S201: Based on the disturbance response time series data, extract adjacent displacement point pairs at equal time intervals, construct a set of path displacement vectors in a two-dimensional coordinate system, calculate the length and direction angle value of each vector segment respectively, and arrange them to generate a displacement path segment sequence;

[0023] S202: Obtaining the path direction angle and timestamp in the displacement path segment sequence and performing training, calculating the angle change feature value, classifying the path jump behavior through a support vector machine model, and generating a path jump frequency interval.

[0024] S203: Based on the displacement path segment sequence and the path jump frequency interval, the path direction offset angle and frequency value in each segment are used as feature vectors, and a change combination sequence composed of the disturbance direction offset angle and jump frequency of each segment is output to obtain a disturbance path variation sequence.

[0025] As a further solution of the present invention, the angle change characteristic value is calculated , using the formula:

[0026] ;

[0027] in: Representative The direction angle of the path segment, Representative The direction angle of the path segment, Representative The velocity weight corresponding to the segment path segment, and Representing the With the timestamp, Represents the angles of all path segments and their average angle The sum of the absolute values ​​of the differences, Representative The direction angle of the path segment, represents the arithmetic mean of all path direction angles, Indicates the total number of path segments.

[0028] As a further solution of the present invention, the step S3 is specifically as follows:

[0029] S301: Acquire continuous offset angle and disturbance jump frequency data of the main beam during the hoisting construction process, construct a main beam offset angle sequence, and compare and analyze it with the disturbance path variation sequence to generate a main beam offset angle sequence;

[0030] S302: Based on the main beam offset angle sequence, calculating the angle offset trends of track segments in multiple time periods, quantifying the angle change trends through a time series analysis method and marking abnormal time periods in the angle changes, thereby generating track segment offset trends;

[0031] S303: Based on the deviation trend of the track section, a deviation map of the main beam component is drawn, the deviation characteristics of multiple time periods are displayed, and areas with abnormal changes are marked to generate a deviation map of the main beam component.

[0032] As a further solution of the present invention, the step S4 is specifically as follows:

[0033] S401: obtaining jump time and offset angle change data of adjacent pier components based on the main beam component offset map, calculating offset angle differences of adjacent components, and preliminarily screening the change trend to generate offset angle difference data;

[0034] S402: Based on the offset angle difference data, the jump time difference and the offset angle difference are combined and classified using an interval aggregation method to screen the abnormal area position and generate an offset angle abnormal area identification result;

[0035] S403: Based on the identification result of the abnormal deviation angle area, the identified area is mapped to the main beam component deviation map for matching, and the response mapping calculation and integration are performed in combination with the deviation shape and difference range in the map to generate the imbalance response identification result.

[0036] As a further solution of the present invention, the step S5 is specifically as follows:

[0037] S501: Based on the imbalance response identification result and the disturbance response time series data, a matching mapping is performed, and the offset characteristic value is mapped to the same time node of the disturbance response using a time series comparison method. The response mutation positions of multiple components in the corresponding time period are extracted and integrated to generate the main beam component response mapping coordinates;

[0038] S502: projecting the main beam component response mapping coordinates into a two-dimensional visual layer coordinate system, constructing a bridge component distribution map by overlaying according to layer numbers, classifying and marking component coordinate points by color, and generating a component layer response level distribution result;

[0039] S503: Based on the component layer response level distribution result, the response levels of multiple main beam components are marked on the layer with the bridge main beam area as the index, and the information graphics are integrated by combining the known component function numbers to generate a smart monitoring view for bridge construction.

[0040] In another aspect, a bridge construction safety intelligent monitoring system is provided, which is applied to a bridge construction safety intelligent monitoring method, and includes:

[0041] The response analysis module uses distributed sensors to obtain the physical state data of the main beam structure and the action state data of the bridge construction equipment, aligning them by time nodes. It then uses the mutual information algorithm to calculate the dynamic response amplitude of the main beam during construction, generates disturbance response time series data, and transmits it to the change fitting module.

[0042] The dynamic response amplitude is the displacement data generated by the main beam during the hoisting operation. The influence of the equipment action on the main beam response is calculated by the mutual information method, and the actual response amplitude of the main beam to the construction action is calculated in combination with the structural state synchronization data.

[0043] A change fitting module obtains the continuous displacement change of the disturbance response time series data to construct a disturbance path segment set, extracts the path direction offset angle and jump frequency through fitting using a support vector machine model, generates a disturbance path change sequence, and transmits it to a trend analysis module;

[0044] A trend analysis module, based on the disturbance path variation sequence, obtains the continuous offset angles and disturbance jump frequencies of the main beam during the hoisting construction process and constructs an offset angle sequence. The module calculates the angular offset trends of the offset angle sequence in multiple time period trajectory segments and marks abnormal time periods. The module generates a main beam component offset map and transmits it to the imbalance identification module.

[0045] An imbalance identification module, based on the main beam component offset map, obtains the jump time and offset angle changes of adjacent pier components and calculates the difference respectively, screens the areas with abnormal bridge component positions, generates imbalance response identification results and transmits them to the monitoring visualization module;

[0046] The monitoring visualization module constructs a visual layer coordinate using the imbalance response identification result and the disturbance response time series data, and marks the risk level of the bridge main beam on the map to generate an intelligent monitoring view for bridge construction.

[0047] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0048] In construction progress and safety monitoring, distributed sensors are used to synchronously collect the physical states of the main beam structure and equipment movements. The mutual information algorithm is then used to extract the dynamic response amplitude under construction disturbances, effectively reconstructing the time series of structural response behavior. By modeling the continuous displacement changes in the response time series and fitting the path direction and jump frequency, the construction disturbance path is made continuous and quantifiable, enhancing the data interpretation dimension and the ability to identify spatial trajectories. Furthermore, the path change trends are integrated into the angular change sequence within the trajectory segments, effectively capturing the displacement direction deviations and unstable jump behaviors of the main beam at different time periods, enhancing the time sensitivity of abnormal displacements and the accuracy of trend judgment. Furthermore, a combined operation of the jump time difference between adjacent components and the change in offset angle is introduced to identify the spatial distribution of imbalance states between components and accurately locate risk areas. A visual layer is constructed by combining offset behavior and disturbance characteristics, enabling intuitive presentation and dynamic updating of risk levels, effectively improving monitoring accuracy and early warning efficiency. Each link operates collaboratively through multi-source data fusion, spatial behavior modeling, and visualization, bringing significant gains in improving the precision of main beam structure monitoring, the ability to identify dynamic construction anomalies, and the intuitive expression of risk levels, effectively supporting efficient and safe management and control during the bridge construction phase. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0051] Figure 2 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0053] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0054] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0055] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0056] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0057] See also Figure 1 The present invention provides a technical solution, a bridge construction safety intelligent monitoring method, comprising the following steps:

[0058] S1: Distributed sensors are used to obtain the physical state data of the main beam structure and the action state data of the bridge construction equipment, which are aligned by time nodes. The dynamic response amplitude of the main beam during construction is calculated using the mutual information algorithm to generate disturbance response time series data.

[0059] The dynamic response amplitude is the displacement data generated by the main beam during the lifting operation. The mutual information method is used to calculate the impact of the equipment movement on the main beam response. The actual response amplitude of the main beam to the construction action is calculated in combination with the synchronous data of the structural state.

[0060] S2: Obtain the continuous displacement changes of the disturbance response time series data to construct a set of disturbance path segments, classify them through the support vector machine model, extract the path offset angle and jump frequency, and generate a sequence of disturbance path changes;

[0061] S3: Based on the disturbance path variation sequence, the continuous offset angles of the main beam during the hoisting construction process and the disturbance jump frequency are obtained and the offset angle sequence is constructed. The angular offset trend of the offset angle sequence of multiple time segment trajectory sections is calculated and the abnormal time periods are marked to generate the main beam component offset map;

[0062] S4: Based on the main beam component offset map, the jump time and offset angle changes of adjacent pier components are obtained and the differences are calculated respectively. The areas with abnormal bridge component positions are screened to generate the imbalance response identification results;

[0063] S5: Construct visual layer coordinates based on the imbalance response identification results and disturbance response time series data, mark the risk level of the bridge main beam on the map, and generate an intelligent monitoring view for bridge construction.

[0064] The disturbance response time series data specifically includes the dynamic response amplitude of the main beam and the disturbance jump frequency. The disturbance path change sequence includes the path direction offset angle, jump frequency, and offset angle sequence. The main beam component offset map specifically refers to the offset angle change trend, abnormal time period marking, and main beam component offset map. The imbalance response identification result specifically includes the offset angle difference, abnormal area identification, and area screening results. The intelligent monitoring view of bridge construction includes component number, coordinate position, risk level marking, and main beam component response level distribution.

[0065] See also Figure 1 , the steps of S1 are as follows:

[0066] S101: Obtain structural physical status data of the bridge main beam and motion status data of the construction equipment through distributed sensors, align the time nodes, and generate synchronization data of the main beam and equipment status;

[0067] During the cantilever construction phase of the bridge's pier #6, 12 strain sensors (with longitudinal spacing of 2m), 8 inclinometers (located at segment joints), and 3 GNSS displacement monitoring points (midspan and quarter span) were deployed, collecting data at a 1Hz frequency. The construction equipment coding system wrote action parameters such as the tower crane's rotation angle (0-360° divided into 36 segments) and pumping pressure (0-10MPa divided into 5 levels) into the equipment status register. The sensor clock and the equipment controller clock were aligned using the NTP time server. When the tower crane was performing concrete hoisting of segment #3, main beam strain data (sampling value range: 82-107με), inclination data (-0.12° to +0.15°), and equipment action logs were extracted from the first 5 minutes to the last 10 minutes of the period. A synchronization data packet was generated, consisting of a four-tuple consisting of a timestamp, equipment action code, sensor code, and numerical value. The time alignment deviation of the sample data was controlled within ±50ms.

[0068] S102: Based on the synchronized data of the main beam and equipment status, the relationship between the construction equipment movement and the main beam response is quantitatively analyzed. The influence of the equipment movement on the main beam response is calculated using a mutual information algorithm to generate equipment influence coefficient data.

[0069] Based on the synchronization data of the main beam and equipment status, the monitoring data of the equipment action type number i=1 (tower crane lifting) and the main beam response number j=3 (mid-span vertical displacement) are extracted, and the tower crane lifting weight is divided into 5 levels. Indicates the tower crane lifting action (equipment type coding rules: 1-tower crane, 2-pump truck, 3-tensioning equipment, equipment type coding rules correspond to subscript symbols ), Indicates the vertical displacement of the main beam mid-span (response type coding rules: 1-strain, 2-inclination, 3-displacement, the response type coding rules correspond to the subscript symbol ), According to the Highway Bridge Construction Monitoring Specifications, the data is divided into 5 levels: By counting the number of times the crane action and displacement response are at level k in 100 sets of synchronous data, if k=4 and the joint occurs 12 times, then , By counting the number of times the crane is at level k alone, including 18 times when k=4, then , By counting the number of times the displacement is at level k, if k=4, it occurs 15 times, then , obtain the above data from Table 1 and substitute it into the formula , take k=4 levels for single-level calculation: , , , cumulative calculation of all levels: According to the Technical Standard for Structural Health Monitoring Systems GB / T38206-2019, the threshold value of the equipment impact coefficient is set. Calculated value , it is determined that the lifting action of the tower crane has a significant impact on the mid-span displacement.

[0070] Table 1 Calculation table of mutual information between tower crane lifting and mid-span displacement

[0071]

[0072] S103: Calculate the dynamic response amplitude of the main beam during the construction process based on the equipment influence coefficient data and the main beam and equipment status synchronization data, and generate disturbance response time series data;

[0073] Take the equipment influence coefficient As the weight coefficient, when the tower crane continuously performs a 20-ton lifting operation between 10:15 and 10:30, the main beam mid-span displacement monitoring value sequence [4.2, 5.1, 5.8, 6.3, 6.7] mm is extracted during this period to calculate the dynamic response amplitude. , generate the time series data point set {(10:15, 0.418×0.0), (10:18, 0.418×0.9), (10:21, 0.418×1.6), (10:24, 0.418×2.1), (10:27, 0.418×2.5)}. The multipliers (0.9, 1.6, 2.1, 2.5) in the time series data point set are based on the displacement value of 4.2 mm at the first monitoring moment 10:15. The displacement value at each subsequent moment is subtracted from the baseline value to obtain the relative displacement change. The difference between the 5.1mm value at 10:18 and the baseline value is 0.9mm, the difference between the 5.8mm value at 10:21 is 1.6mm, the difference between the 6.3mm value at 10:24 is 2.1mm, and the difference between the 6.7mm value at 10:21 is 2.5mm. The maximum amplitude value of 1.045 completely corresponds to the time window of the tower crane's full-load working condition. When the value exceeds the preset threshold of 0.8, a warning signal is triggered.

[0074] See also Figure 1 , the steps of S2 are as follows:

[0075] S201: Based on the disturbance response time series data, adjacent displacement point pairs are extracted at equal time intervals to construct a set of path displacement vectors in a two-dimensional coordinate system. The length and direction angle values ​​of each vector segment are calculated and arranged to generate a displacement path segment sequence;

[0076] Based on the disturbance response time series data, the displacement monitoring points with 5-minute intervals in the period of 10:00-10:30 are extracted to construct a displacement vector set. The coordinates of the time point t=10:00 (0, 0) and the coordinates of the time point t=10:05 (2.3, 1.5) are taken to calculate the vector length , direction angle ,The generated sequence is arranged in chronological order.,As shown in Table 2, the data of the 1st and 2nd periods,are formed after continuous processing of 6 periods, including a,displacement path segment sequence with vector length [2.76, 3.15, 3.89, 4.12, 3.45, 2.98] mm and angle [33.2°, 41.5°, 52.1°, 58.3°, 49.7°, 38.4°].

[0077] Table 2 Example of displacement vector calculation table

[0078]

[0079] S202: Obtain the path direction angle and timestamp in the displacement path segment sequence and perform training, calculate the angle change feature value, classify the path jump behavior through the support vector machine model, and generate the path jump frequency interval.

[0080] When r=2 in the path segment sequence and , Representative The direction angle of the path segment, and Derived from the GNSS displacement monitoring system, Representative Direction angle of each path segment, timestamp 、 (Time difference ), , according to the tower crane moving speed according to Calculation (refer to "Crane Safety Regulations" GB / T6067-2010), Represents the speed weight coefficient, which is calculated by the crane moving speed v and the reference speed 1.5. Representative The velocity weight corresponding to the segment path segment, and Representing the With the timestamp, , represents the arithmetic mean of all path direction angles, Represents the angles of all path segments and their average angle The absolute value of the difference is summed by calculating the average angle of the 6 periods: - , the direction angles of the six time periods are obtained from Table 2, Representative The direction angle of each path segment is calculated by calculating the absolute deviation item by item: , is the arithmetic mean of all path direction angles, 、 、 The direction angles of the three time periods obtained from Table 2 are substituted into the formula and the calculation process is: According to the Code for Vibration Control of Building Structures JGJ / T441-2019, the jump judgment threshold is set ,when The path jump is determined when r=2, 3, 4, and 6 in the 6 time periods, triggering the jump, generating a frequency range of [2-4 times / hour].

[0081] S203: Based on the displacement path segment sequence and the path jump frequency interval, the path direction offset angle and frequency value in each segment are used as feature vectors, and a change combination sequence consisting of the disturbance direction offset angle and jump frequency of each segment is output to obtain a disturbance path variation sequence;

[0082] Take the direction deviation angle when r=2 With a jump frequency of 2 times / hour, r represents the path segment, and constructs the feature vector [0.183, 2]. The four time periods are processed in sequence. According to the direction angle data in Table 2, the formula is substituted into , Representative The direction angle of the path segment, and Derived from the GNSS displacement monitoring system, Representative Direction angle of each path segment, timestamp 、 (Time difference ), , according to the tower crane moving speed according to Calculation (refer to "Crane Safety Regulations" GB / T6067-2010), Represents the speed weight coefficient, which is calculated by the crane moving speed v and the reference speed 1.5. Representative The velocity weight corresponding to the segment path segment, and Representing the With the timestamp, , represents the arithmetic mean of all path direction angles, Represents the angles of all path segments and their average angle The absolute value of the difference is summed by calculating the average angle of the 6 periods: - , the direction angles of the 6 time periods are obtained from Table 2, r=3 period, θ3 , r=4 period, Δθ4 , and obtain the change combination sequence [(0.183, 2), ( ,2),( ,4)].

[0083] See also Figure 1 , the specific steps of S3 are:

[0084] S301: Acquire continuous offset angle and disturbance jump frequency data of the main beam during the hoisting construction process, construct a main beam offset angle sequence, and compare and analyze it with the disturbance path variation sequence to generate a main beam offset angle sequence;

[0085] Based on the output perturbation path variation sequence [(0.183, 2), ( ,2),( ,4)], extract the monitoring data of the mid-span displacement of the main beam during the period of 10:00-10:20, collect the three-dimensional coordinates at a frequency of 1Hz through the GNSS positioning system, calculate the average offset angle per minute, take the coordinates at 10:05 (2.3, 1.5) and the coordinates at 10:06 (2.7, 1.9), and calculate the offset angle , 10:00-10:01 , 10:10-10:11 , calculated in sequence, the offset angle of the period 10:10-10:16 is 48.6, and the offset angle of the period 10:20-10:21 is 44.7. The offset angle sequence is generated by continuous processing for 20 minutes [33.2, 45.0, 47.8, 52.1, 49.3, 44.7]°. After time alignment with the disturbance path change sequence, the path change of the period 10:10-10:15 is compared. The corresponding offset angle is 52.1°, and the deviation value is The error is less than the tolerance threshold of 2°, and the calibrated main beam offset angle sequence [33.2, 45.0, 47.8, 51.2, 48.6, 44.7]° is generated, as shown in Table 3 for the first 6 minutes of data.

[0086] Table 3 Comparison of offset angle calibration

[0087]

[0088] S302: Based on the main beam offset angle sequence, calculate the angle offset trend of the track segments in multiple time periods, quantify the angle change trend through time series analysis method and mark the abnormal time periods in the angle change, and generate track segment offset trend and abnormal time period data;

[0089] Take the offset angle sequence data from 10:00-10:30, divide it into 5-minute time windows, calculate the displacement angle by GNSS coordinate difference, and use the sampling rule to calculate the displacement angle of adjacent coordinates once per minute. Collect the data from 10:00-10:05: 33.2°, 34.5°, 36.1°, 37.8°, 39.2°, and from 10:05-10:10: 45.0°, 44.7°, 46.2°, 45.8°, 44.6°. Calculate the angle mean of the first window (10:00-10:05). , standard deviation , the mean of the second window (10:05-10:10) , standard deviation , set the abnormal threshold , when three consecutive data points exceed the threshold, an anomaly is marked. The data of 10:18-10:23 period are detected as 51.2°, 52.8°, 53.6°, 54.9°, 55.1°, 54.8°, and the angle mean is calculated. for , standard deviation for , [51.2, 53.6, 55.1]° all exceed , generating the abnormal time period [10:18, 10:23].

[0090] S303: Based on the deviation trend of the track section, a deviation map of the main beam component is drawn, which displays the deviation characteristics of multiple time periods and marks the areas with abnormal changes, thereby generating a deviation map of the main beam component;

[0091] Based on the trajectory segment offset trend data, the offset angle sequence of the 10:00-10:30 period was imported into the BIM model, and the color spectrum mapping rules were set: blue (less than 40°), green (40-50°), yellow (50-55°), and red (greater than 55°). A three-dimensional offset map was generated, and the red area was marked in the 10:18-10:23 period, corresponding to the coordinate points (15.2, 22.3, 0) to (16.8, 24.1, 0). The output map file included 6 abnormal areas, and the maximum offset of 55.1° occurred at the 3# segment hoisting operation position at 10:21.

[0092] See also Figure 1 , the steps of S4 are as follows:

[0093] S401: Based on the main beam component offset map, the jump time and offset angle change data of adjacent pier components are obtained, the offset angle difference of adjacent components is calculated, and the change trend is preliminarily screened to generate offset angle difference data;

[0094] Based on the six abnormal areas marked in the main beam component offset map, the offset angle data of adjacent piers (Pier 5# and Pier 6#) during the period of 10:15-10:25 were extracted. The offset angle sequence of Pier 5# was [51.2, 53.6, 55.1]°, and that of Pier 6# was [49.8, 50.3, 51.7]°. The offset angle difference per minute was calculated: , 10:20 , set the difference threshold to 2.5° (according to the displacement angle difference limit of adjacent piers in the "Highway Bridge Design Code" JTGD60-2015), filter the data points with 3.4°>2.5°, and generate the difference sequence [1.4, 2.1, 3.4]°, as shown in Table 4 for the first three groups of data.

[0095] Table 4 Differences of offset angles of adjacent piers

[0096]

[0097] S402: Based on the offset angle difference data, the jump time difference and the offset angle difference are combined and classified using an interval aggregation method to screen the abnormal area position and generate an offset angle abnormal area identification result;

[0098] The three groups of over-limit data (differences of 3.4°, 2.9°, and 3.1°) in the 10:15-10:25 period in Table 4 were aggregated into intervals of 5 minutes and the average difference was calculated. , set the aggregation threshold to 2.8°, and determine it as an abnormal area when the average difference is greater than 2.8° and the time difference is ≤ 5 minutes. The 3# segment of pier 5# (coordinate X=15.2, Y=22.3) to the 2# segment of pier 6# (coordinate X=16.8, Y=24.1) are identified as abnormal areas, and the identification results including 3 abnormal grids are generated.

[0099] S403: Based on the identification result of the abnormal deviation angle area, the identified area is mapped to the main beam component deviation map for matching, and the response mapping calculation and integration are performed based on the deviation shape and difference range in the map to generate the imbalance response identification result;

[0100] Map the coordinates of the abnormal area [(15.2, 22.3), (16.8, 24.1)] to the offset map, and extract the offset morphological parameters of the area during the period of 10:20-10:25: Maximum curvature 0.15 / m, The average difference is 3.13°, and the response value is set ,when When the system is judged as unbalanced, an imbalance response identification result including three red warning areas is generated.

[0101] See also Figure 1 , the specific steps of S5 are:

[0102] S501: Based on the imbalance response identification results and the disturbance response time series data, a matching mapping is performed, and the offset characteristic value is mapped to the same time node of the disturbance response using a time series comparison method. The response mutation positions of multiple components in the corresponding time period are extracted and integrated to generate the main beam component response mapping coordinates;

[0103] Based on the three red warning areas (coordinate range X=15.2-16.8, Y=22.3-24.1) in the output imbalance response identification results, the GNSS positioning data of each minute during the period of 10:20-10:25 was extracted. The coordinates of the warning area (15.6, 23.2) were timestamped with the tower crane lifting weight of 25 tons in the same period (corresponding to load level 5 in the disturbance response data). The displacement of the main beam mid-span suddenly increased from 8.1mm to 9.8mm (the mutation threshold was set to 8.5mm). The displacement points at 10:22 (15.6, 23.2, 9.8) and the adjacent segment points (16.1, 23.8, 8.9) were extracted to construct the response vector, and the vector length was calculated. , direction angle , extract the displacement point (16.5, 24.3, 10.5) at 10:24 and the adjacent segment point (16.1, 23.8, 8.9) to construct the response vector, and calculate the vector length at the same time , integrating the 6 mutation points to generate the coordinate set [(15.6, 23.2), (16.1, 23.8), (16.5, 24.3)], as shown in Table 5 for the first 3 groups of data.

[0104] Table 5 Response mapping coordinate table

[0105]

[0106] S502: Calling the main beam component response mapping coordinates to project them into a two-dimensional visual layer coordinate system, constructing a bridge component distribution map by overlaying layer numbers, classifying and marking component coordinate points with colors, and generating a component layer response level distribution result;

[0107] Import the coordinates in Table 5 into the BIM model, set the layer coordinate system origin (0, 0) to correspond to the starting point of the bridge centerline, map the coordinate (15.6, 23.2) to the layer grid (156, 232), define the response level color coding: green (displacement <8 mm), yellow (8-10 mm), and red (>10 mm), fill the coordinate (156, 232) with red, and calculate the grid within a radius of 500 m, including 3 yellow grids (displacement 9.2-9.7 mm) and 1 red grid. Overlay the tower crane position layer L1025 according to layer number L2030 to generate a distribution result including 12 color-coded grids.

[0108] S503: Based on the component layer response level distribution results, the response levels of multiple main beam components are marked on the layer with the bridge main beam area as the index. The information graphics are integrated into the partitions based on the known component function numbers to generate a smart monitoring view for bridge construction.

[0109] Locate the main beam area in the distribution results (layer X=150-170, Y=200-250), extract the three red grids in the L2030 layer (corresponding to displacements of 10.1-10.5mm), associate them with component numbers G-5-3 (3# segment of 5# pier) and G-6-2 (2# segment of 6# pier), mark them with red warning signs in the smart monitoring view, and integrate wind speed sensor data (8.2m / s) and hoisting load data (25 tons). The dynamic parameter panel is a visualization module that updates data in real time or periodically. It contains six dynamic parameter panels: main beam displacement monitoring (10.1-10.5mm), wind speed monitoring (8.2m / s), hoisting load monitoring (25 tons), component response level (red warning), pier settlement data (requires association with G-5-3 / G-6-2), and structural stress distribution (based on red grid analysis). A monitoring view file in PDF format is generated, including the six dynamic parameter panels.

[0110] See also Figure 2 A bridge construction safety intelligent monitoring system is provided. The bridge construction safety intelligent monitoring system is used to implement the above-mentioned bridge construction safety intelligent monitoring method. The system includes:

[0111] The response analysis module uses distributed sensors to obtain the physical state data of the main beam structure and the action state data of the bridge construction equipment, aligning them by time nodes. It then uses the mutual information algorithm to calculate the dynamic response amplitude of the main beam during construction, generates disturbance response time series data, and transmits it to the change fitting module.

[0112] The dynamic response amplitude is the displacement data generated by the main beam during the lifting operation. The mutual information method is used to calculate the impact of the equipment movement on the main beam response. The actual response amplitude of the main beam to the construction action is calculated in combination with the synchronous data of the structural state.

[0113] The change fitting module obtains the continuous displacement changes of the disturbance response time series data to construct a set of disturbance path segments. The support vector machine model is used for fitting to extract the path direction offset angle and jump frequency, and a disturbance path change sequence is generated and passed to the trend analysis module.

[0114] The trend analysis module obtains the continuous offset angles and disturbance jump frequencies of the main beam during the lifting construction process based on the disturbance path variation sequence and constructs an offset angle sequence. It calculates the angular offset trends of the offset angle sequence in multiple time period trajectory segments and marks the abnormal time periods. It generates a main beam component offset map and transmits it to the imbalance identification module.

[0115] The imbalance identification module, based on the main beam component offset map, obtains the jump time and offset angle changes of adjacent pier components and calculates the difference respectively, screens areas with abnormal bridge component positions, generates imbalance response identification results, and transmits them to the monitoring visualization module;

[0116] The monitoring visualization module constructs visual layer coordinates through the imbalance response identification results and disturbance response time series data, and marks the risk level of the bridge main beam on the map to generate an intelligent monitoring view for bridge construction.

[0117] It should be understood that the term "and / or" as used herein simply describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the related objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0118] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0119] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0121] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0123] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0125] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A bridge construction safety intelligent monitoring method, characterized in that: The method comprises: S1: Distributed sensors are used to obtain the physical state data of the main beam structure and the action state data of the bridge construction equipment, which are aligned by time nodes. The dynamic response amplitude of the main beam during construction is calculated using the mutual information algorithm to generate disturbance response time series data. The dynamic response amplitude is the displacement data generated by the main beam during the hoisting operation. The influence of the equipment action on the main beam response is calculated by the mutual information method, and the actual response amplitude of the main beam to the construction action is calculated in combination with the structural state synchronization data. S2: Obtain the continuous displacement changes of the disturbance response time series data to construct a disturbance path set and extract the path offset angle, input the support vector machine model to classify the path jump behavior and analyze the jump frequency, and generate a disturbance path change sequence; S3: Based on the disturbance path variation sequence, the continuous offset angles and disturbance jump frequencies of the main beam during the hoisting construction process are obtained and an offset angle sequence is constructed. The angular offset trends of the offset angle sequences of the trajectory segments in multiple time periods are calculated and abnormal time periods are marked to generate an offset map of the main beam components. S4: Based on the main beam component offset map, the jump time and offset angle changes of adjacent pier components are obtained and the differences are calculated respectively, the areas with abnormal bridge component positions are screened, and the imbalance response identification results are generated; S5: Construct a visual graph layer using the imbalance response identification result and the disturbance response time series data, mark the risk level of the bridge main beam, and generate an intelligent monitoring view for bridge construction.

2. The bridge construction safety intelligent monitoring method according to claim 1 is characterized in that: The disturbance response time series data specifically includes the dynamic response amplitude of the main beam and the disturbance jump frequency. The disturbance path change sequence includes the path direction offset angle, jump frequency, and offset angle sequence. The main beam component offset map specifically refers to the offset angle change trend, abnormal time period marking, and main beam component offset map. The imbalance response identification result specifically includes the offset angle difference, abnormal area identification, and area screening result. The bridge construction intelligent monitoring view includes component number, coordinate position, risk level marking, and main beam component response level distribution.

3. The bridge construction safety intelligent monitoring method according to claim 1 is characterized in that: The steps of S1 are specifically as follows: S101: Obtain structural physical status data of the bridge main beam and motion status data of the construction equipment through distributed sensors, align them with time nodes, and generate synchronized data of the main beam and equipment status; S102: Based on the main beam and equipment status synchronization data, quantitatively analyze the relationship between the construction equipment movement and the main beam response, calculate the impact of the equipment movement on the main beam response through a mutual information algorithm, and generate equipment impact coefficient data; S103: Calculate the dynamic response amplitude of the main beam during the construction process based on the equipment influence coefficient data and the main beam and equipment status synchronization data, and generate disturbance response time series data.

4. The bridge construction safety intelligent monitoring method according to claim 3 is characterized in that: The mutual information algorithm is used to calculate the degree of influence of the equipment action on the main beam response , using the formula: ； in, Indicates the Class device actions and The main beam response is The joint probability under the level, Indicates the Class device action The probability of the level, Indicates the The main beam response is The probability of the level, Indicates that the equipment action and the main beam response are in the The absolute value of the probability difference under the level, The total number of levels.

5. The bridge construction safety intelligent monitoring method according to claim 1 is characterized in that: The steps of S2 are specifically as follows: S201: Based on the disturbance response time series data, extract adjacent displacement point pairs at equal time intervals, construct a set of path displacement vectors in a two-dimensional coordinate system, calculate the length and direction angle value of each vector segment respectively, and arrange them to generate a displacement path segment sequence; S202: Obtaining the path direction angle and timestamp in the displacement path segment sequence and performing training, calculating the angle change feature value, classifying the path jump behavior through a support vector machine model, and generating a path jump frequency interval; S203: Based on the displacement path segment sequence and the path jump frequency interval, the path direction offset angle and frequency value in each segment are used as feature vectors, and a change combination sequence composed of the disturbance direction offset angle and jump frequency of each segment is output to obtain a disturbance path variation sequence.

6. The bridge construction safety intelligent monitoring method according to claim 5 is characterized in that: The calculation angle change characteristic value , using the formula: ， in: Representative The direction angle of the path segment, Representative The direction angle of the path segment, Representative The velocity weight corresponding to the segment path segment, and Representing the With the timestamp, Represents the angles of all path segments and their average angle The sum of the absolute values ​​of the differences, Representative The direction angle of the path segment, represents the arithmetic mean of all path direction angles, Indicates the total number of path segments.

7. The bridge construction safety intelligent monitoring method according to claim 1 is characterized in that: The steps of S3 are specifically as follows: S301: Acquire continuous offset angle and disturbance jump frequency data of the main beam during the hoisting construction process, construct a main beam offset angle sequence, and compare and analyze it with the disturbance path variation sequence to generate a main beam offset angle sequence; S302: Based on the main beam offset angle sequence, calculating the angle offset trends of track segments in multiple time periods, quantifying the angle change trends through a time series analysis method and marking abnormal time periods in the angle changes, thereby generating track segment offset trends; S303: Based on the deviation trend of the track section, a deviation map of the main beam component is drawn, the deviation characteristics of multiple time periods are displayed, and areas with abnormal changes are marked to generate a deviation map of the main beam component.

8. The bridge construction safety intelligent monitoring method according to claim 1 is characterized in that: The steps of S4 are specifically as follows: S401: obtaining jump time and offset angle change data of adjacent pier components based on the main beam component offset map, calculating offset angle differences of adjacent components, and preliminarily screening the change trend to generate offset angle difference data; S402: Based on the offset angle difference data, the jump time difference and the offset angle difference are combined and classified using an interval aggregation method to screen the abnormal area position and generate an offset angle abnormal area identification result; S403: Based on the identification result of the abnormal deviation angle area, the identified area is mapped to the main beam component deviation map for matching, and the response mapping calculation and integration are performed in combination with the deviation shape and difference range in the map to generate the imbalance response identification result.

9. The bridge construction safety intelligent monitoring method according to claim 1 is characterized in that: The steps of S5 are specifically as follows: S501: Based on the imbalance response identification result and the disturbance response time series data, a matching mapping is performed, and the offset characteristic value is mapped to the same time node of the disturbance response using a time series comparison method. The response mutation positions of multiple components in the corresponding time period are extracted and integrated to generate the main beam component response mapping coordinates; S502: projecting the main beam component response mapping coordinates into a two-dimensional visual layer coordinate system, constructing a bridge component distribution map by overlaying according to layer numbers, classifying and marking component coordinate points by color, and generating a component layer response level distribution result; S503: Based on the component layer response level distribution result, the response levels of multiple main beam components are marked on the layer with the bridge main beam area as the index, and the information graphics are integrated by combining the known component function numbers to generate a smart monitoring view for bridge construction.

10. A bridge construction safety intelligent monitoring system, characterized in that: The system is used to implement the bridge construction safety intelligent monitoring method according to any one of claims 1 to 9, and the system includes: The response analysis module uses distributed sensors to obtain the physical state data of the main beam structure and the action state data of the bridge construction equipment, aligning them by time nodes. It then uses the mutual information algorithm to calculate the dynamic response amplitude of the main beam during construction, generates disturbance response time series data, and transmits it to the change fitting module. The dynamic response amplitude is the displacement data generated by the main beam during the hoisting operation. The influence of the equipment action on the main beam response is calculated by the mutual information method, and the actual response amplitude of the main beam to the construction action is calculated in combination with the structural state synchronization data. A change fitting module obtains the continuous displacement change of the disturbance response time series data to construct a disturbance path segment set, extracts the path direction offset angle and jump frequency through fitting using a support vector machine model, generates a disturbance path change sequence, and transmits it to a trend analysis module; A trend analysis module, based on the disturbance path variation sequence, obtains the continuous offset angles and disturbance jump frequencies of the main beam during the hoisting construction process and constructs an offset angle sequence. The module calculates the angular offset trends of the offset angle sequence in multiple time period trajectory segments and marks abnormal time periods. The module generates a main beam component offset map and transmits it to the imbalance identification module. An imbalance identification module, based on the main beam component offset map, obtains the jump time and offset angle changes of adjacent pier components and calculates the difference respectively, screens the areas with abnormal bridge component positions, generates imbalance response identification results and transmits them to the monitoring visualization module; The monitoring visualization module constructs a visual layer coordinate using the imbalance response identification result and the disturbance response time series data, and marks the risk level of the bridge main beam on the map to generate an intelligent monitoring view for bridge construction.

Images