Bridge collapse identification method and system based on vehicle mobile terminal sensing data

Abstract

The application relates to a bridge collapse identification method and system based on vehicle mobile terminal sensing data, and belongs to the technical field of bridge safety monitoring. The method comprises the following steps: in the case that a target vehicle is determined to be located on a bridge section based on relative positions, monitoring driving acceleration of the target vehicle according to IMU data of a vehicle mobile terminal; in the case that a mutation occurs in vertical acceleration in the driving acceleration of the target vehicle, judging whether the target vehicle appears a bridge falling state caused by bridge collapse based on the vertical acceleration and synthetic lateral acceleration; if the target vehicle appears the bridge falling state caused by bridge collapse, obtaining jerk of the vertical acceleration, and determining bridge falling time information of the target vehicle based on the jerk; and based on the bridge falling time information of the target vehicle and falling heights of multiple vehicles when falling off the bridge, adjusting the credibility of the bridge collapse based on the falling heights of the multiple vehicles when falling off the bridge, so as to improve the determination accuracy and credibility of the bridge collapse state.

Description

Technical Field

[0001] This invention relates to the field of bridge safety monitoring technology, and in particular to a method and system for identifying bridge deck collapse based on vehicle mobile terminal sensing data. Background Technology

[0002] With social development, various types of bridges have been built throughout the country. Bridges play a vital role in transportation. Quickly determining the extent and height of a collapse is crucial for rescue deployment, cause investigation, and traffic control. Summary of the Invention

[0003] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a bridge deck collapse identification method and system based on vehicle mobile terminal perception data, which solves the technical problem of identifying the height of bridge deck collapse.

[0004] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0005] The first aspect of this invention provides a method for identifying bridge deck collapse based on vehicle mobile terminal sensing data.

[0006] The bridge deck collapse identification method based on vehicle mobile terminal sensing data proposed in this embodiment of the invention includes:

[0007] The relative position between the target vehicle and the bridge / road section is determined based on the positioning data of the vehicle's mobile terminal.

[0008] When the target vehicle is located on a bridge section based on the relative position, the vehicle's acceleration is monitored based on the IMU data of the vehicle's mobile terminal. If there is a sudden change in the vertical acceleration of the target vehicle, the vehicle is judged to be in a state of falling off the bridge due to the collapse of the bridge deck based on the vertical acceleration and the combined lateral acceleration.

[0009] If the target vehicle falls off the bridge due to the collapse of the bridge deck, and multiple vehicles fall off the bridge in succession within a predetermined time, the time information of the fall of multiple vehicles when they fall off the bridge in succession is obtained based on the jerk of the vertical acceleration of the multiple vehicles.

[0010] Based on the time information of the multiple vehicles falling off the bridge in succession, the fall height of the multiple vehicles when they fell off the bridge is determined, and the credibility of the bridge collapse is adjusted based on the fall height of the multiple vehicles when they fell off the bridge.

[0011] In some instances, adjusting the credibility of the bridge collapse based on the fall height of the multiple vehicles includes:

[0012] Based on the fall height of the multiple vehicles when they fell off the bridge, determine the variance of the fall height of the multiple vehicles when they fell off the bridge;

[0013] The credibility of the bridge collapse is adjusted based on the variance of the fall height of the multiple vehicles when they fell off the bridge.

[0014] In some instances, the bridge fall time information includes the start time of the vehicle falling off the bridge and the end time of the vehicle falling off the bridge.

[0015] The method of obtaining the bridge fall time information when multiple vehicles fall off the bridge consecutively based on the jerk in the vertical acceleration of multiple vehicles includes:

[0016] Based on the jerk in the vertical acceleration of multiple vehicles, the start and end times of the consecutive falls off the bridge are obtained; among them...

[0017] When the vertical acceleration suddenly changes, and the acceleration first shows a negative pulse whose absolute value exceeds the absolute value of the negative threshold, the time point at which the acceleration first shows the negative pulse is determined as the starting time of the target vehicle falling off the bridge.

[0018] After the initial bridge fall time, if the vertical acceleration undergoes a reverse abrupt change, and the acceleration first shows a positive pulse whose absolute value exceeds the absolute value of the positive threshold, the time point at which the acceleration first shows the positive pulse is determined as the termination time of the target vehicle's bridge fall.

[0019] In some instances, determining the fall height of the multiple vehicles based on the fall time information during the consecutive falls includes:

[0020] Obtain the vertical initial velocity corresponding to the initial time of the fall when the multiple vehicles fall off the bridge;

[0021] Integrate the vertical acceleration of the multiple vehicles when they fall off the bridge by the time of the initial fall and the time of the final fall, and sum the initial vertical velocities to obtain the integral velocity of each vehicle when it falls off the bridge.

[0022] The fall height of each vehicle is obtained by integrating the initial fall time and the final fall time based on the integral speed of each vehicle.

[0023] In some instances, determining whether the target vehicle is in a bridge-falling state due to bridge deck collapse based on the vertical acceleration and the combined lateral acceleration includes:

[0024] If the sudden change in the vertical acceleration of the target vehicle lasts for a duration longer than a predetermined duration, and the minimum absolute value of the vertical acceleration within the predetermined duration is greater than a predetermined threshold, then it is determined that the target vehicle has fallen off the bridge, and based on the synthetic lateral acceleration, it is determined whether the target vehicle has fallen off the bridge due to the collapse of the bridge deck.

[0025] In some instances, determining whether the target vehicle is in a bridge-falling state due to bridge deck collapse based on the synthesized lateral acceleration includes:

[0026] If the modulus of the synthetic lateral acceleration exceeds the predetermined modulus value within the predetermined time period, it is determined that the target vehicle has experienced a lateral collision, and the target vehicle is determined to have fallen off the bridge as a lateral collision and bridge fall state.

[0027] If the modulus of the synthesized lateral acceleration is less than or equal to the predetermined modulus value within the predetermined time period, then it is determined that the target vehicle has fallen off the bridge due to the collapse of the bridge deck.

[0028] In some instances, the method includes:

[0029] If the confidence level is greater than a predetermined value, the collapse height of the bridge deck is determined by weighted averaging of the fall heights of multiple vehicles that meet the confidence level.

[0030] A second aspect of this invention provides a bridge collapse identification system based on vehicle mobile terminal sensing data, comprising:

[0031] The vehicle location monitoring module is used to determine the relative position between the target vehicle and the bridge section based on the positioning data of the vehicle mobile terminal.

[0032] The vehicle acceleration monitoring module is used to monitor the vehicle acceleration based on the IMU data of the vehicle mobile terminal when the target vehicle is determined to be located on a bridge section based on the relative position.

[0033] The bridge fall monitoring module is used to determine whether the target vehicle is in a bridge fall state due to bridge collapse when the vertical acceleration in the vehicle's acceleration changes abruptly, based on the vertical acceleration and the combined lateral acceleration.

[0034] The bridge fall time determination module is used to obtain the bridge fall time information of multiple vehicles falling into the bridge in succession within a predetermined time if the target vehicle falls into the bridge due to the collapse of the bridge surface. This is based on the jerk of the vertical acceleration of the multiple vehicles.

[0035] The bridge collapse identification module is used to determine the fall height of the multiple vehicles when they fall off the bridge, based on the fall time information of the multiple vehicles falling off the bridge in succession, and to adjust the credibility of the bridge collapse based on the fall height of the multiple vehicles falling off the bridge.

[0036] A third aspect of the present invention provides a computer-readable storage medium storing a bridge collapse identification program based on vehicle mobile terminal sensing data. When the bridge collapse identification program based on vehicle mobile terminal sensing data is executed by a processor, it implements the bridge collapse identification method based on vehicle mobile terminal sensing data described in the first aspect above.

[0037] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a bridge collapse identification program based on vehicle mobile terminal sensing data stored in the memory and executable on the processor. When the processor executes the bridge collapse identification program based on vehicle mobile terminal sensing data, it implements the bridge collapse identification method based on vehicle mobile terminal sensing data described in the first aspect above.

[0038] This invention discloses a bridge collapse identification method based on vehicle mobile terminal sensing data, comprising: determining the relative position between a target vehicle and a bridge section based on the positioning data of the vehicle mobile terminal; when the target vehicle is determined to be located on the bridge section based on the relative position, monitoring the vehicle's acceleration based on the IMU data of the vehicle mobile terminal, and determining whether the target vehicle is in a state of falling off the bridge due to bridge collapse based on the vertical acceleration and the combined lateral acceleration when a sudden change occurs in the vertical acceleration of the target vehicle; if the target vehicle is in a state of falling off the bridge due to bridge collapse, and multiple vehicles fall off the bridge consecutively within a predetermined time, obtaining the fall time information of the multiple vehicles falling off the bridge consecutively based on the jerk of the vertical acceleration of the multiple vehicles; determining the fall height of the multiple vehicles falling off the bridge based on the fall time information of the multiple vehicles falling off the bridge, and adjusting the credibility of the bridge collapse based on the fall height of the multiple vehicles falling off the bridge. In this application, by using the positioning data and IMU data of the vehicle's mobile terminal, after determining that a vehicle has fallen off the bridge due to a bridge collapse, the time information of the target vehicle's fall can be determined by accelerating the vehicle. Based on the time information of the target vehicle's fall, the fall height of multiple vehicles when they fall off the bridge is determined, and the credibility of the bridge collapse is adjusted based on the fall height of multiple vehicles when they fall off the bridge, thereby improving the accuracy and credibility of determining the bridge collapse status. Attached Figure Description

[0039] Figure 1 A flowchart of a bridge deck collapse identification method based on vehicle mobile terminal sensing data provided in an embodiment of the present invention;

[0040] Figure 2This invention provides a bridge deck collapse identification process based on vehicle mobile terminal sensing data. Figure 1 ;

[0041] Figure 3 This invention provides a bridge deck collapse identification process based on vehicle mobile terminal sensing data. Figure 2 ;

[0042] Figure 4 This is a schematic diagram of the bridge collapse recognition system based on vehicle mobile terminal sensing data provided in an embodiment of the present invention. Detailed Implementation

[0043] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] The bridge collapse identification method based on vehicle mobile terminal sensing data proposed in this invention addresses the issue of bridge collapse height. By using the vehicle mobile terminal's positioning data and IMU data, after a vehicle falls from the bridge due to a collapse, the method can determine the time of the vehicle's fall by accelerating the vehicle. Based on this fall time information, the method can determine the fall height of multiple vehicles falling from the bridge and adjust the reliability of the bridge collapse assessment, thereby improving the accuracy and reliability of determining the bridge collapse status.

[0045] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0046] Figure 1 This is a flowchart illustrating a bridge deck collapse identification method based on vehicle mobile terminal sensing data, provided as an embodiment of the present invention. Figure 1 As shown in the embodiment of the present invention, the bridge deck collapse identification method based on vehicle mobile terminal perception data includes:

[0047] Step 100: Determine the relative position between the target vehicle and the bridge section based on the positioning data of the vehicle mobile terminal;

[0048] Step 110: If the target vehicle is located on a bridge section based on the relative position, monitor the vehicle's acceleration according to the IMU data of the vehicle's mobile terminal. If there is a sudden change in the vertical acceleration of the target vehicle, determine whether the target vehicle is in a state of falling off the bridge due to the collapse of the bridge deck based on the vertical acceleration and the combined lateral acceleration.

[0049] Step 120: If the target vehicle falls off the bridge due to the collapse of the bridge deck, and multiple vehicles fall off the bridge in succession within a predetermined time, the time information of the fall of multiple vehicles when they fall off the bridge in succession is obtained based on the jerk of the vertical acceleration of the multiple vehicles.

[0050] Step 130: Based on the time information of the multiple vehicles falling off the bridge in succession, determine the fall height of the multiple vehicles when they fall off the bridge, and adjust the credibility of the bridge collapse based on the fall height of the multiple vehicles when they fall off the bridge.

[0051] In this exemplary embodiment, the positioning data of the vehicle mobile terminal may include GPS (Global Positioning System) data and electronic maps. Determining the relative position between the target vehicle and the bridge section based on the positioning data of the vehicle mobile terminal includes determining the relative position between the target vehicle and the bridge section based on the GPS data and electronic maps of the vehicle mobile terminal.

[0052] In this exemplary embodiment, real-time GPS data of the vehicle's movement can be obtained through the vehicle-mounted GPS and IMU modules. Combined with GPS output, vehicle speed, and electronic map, the location of the vehicle and the bridge section can be comprehensively determined.

[0053] If the target vehicle is located on a bridge section, the vehicle's real-time acceleration data is collected using an onboard IMU, and the characteristics of vertical acceleration changes are analyzed. When the vehicle's vertical acceleration drops sharply, the time information of the vehicle falling off the bridge is extracted.

[0054] In this application, by using the positioning data and IMU data of the vehicle's mobile terminal, after determining that a vehicle has fallen off the bridge due to a bridge collapse, the time information of the target vehicle's fall can be determined by accelerating the vehicle. Based on the time information of the target vehicle's fall, the fall height of multiple vehicles when they fall off the bridge is determined, and the credibility of the bridge collapse is adjusted based on the fall height of multiple vehicles when they fall off the bridge, thereby improving the accuracy and credibility of determining the bridge collapse status.

[0055] In some instances, adjusting the credibility of the bridge collapse based on the fall height of the multiple vehicles includes:

[0056] Based on the fall height of the multiple vehicles when they fell off the bridge, determine the variance of the fall height of the multiple vehicles when they fell off the bridge;

[0057] The credibility of the bridge collapse is adjusted based on the variance of the fall height of the multiple vehicles when they fell off the bridge.

[0058] In this exemplary embodiment, adjusting the credibility of the bridge collapse based on the variance of the fall height of the multiple vehicles when they fell off the bridge includes:

[0059] The smaller the variance of the fall height when multiple vehicles fall off a bridge, the higher the reliability of controlling bridge collapse.

[0060] The greater the variance in the fall height of multiple vehicles when they fall off the bridge, the lower the reliability of controlling the bridge collapse.

[0061] The smaller the variance of the fall height when multiple vehicles fall off a bridge, the higher the reliability of controlling for bridge collapse, indicating a higher degree of confidence in the bridge collapse scenario. Conversely, the larger the variance of the fall height when multiple vehicles fall off a bridge, the lower the reliability of controlling for bridge collapse, indicating a lower degree of confidence in the bridge collapse scenario.

[0062] In some instances, the bridge fall time information includes the start time of the vehicle falling off the bridge and the end time of the vehicle falling off the bridge.

[0063] The method of obtaining the bridge fall time information when multiple vehicles fall off the bridge consecutively based on the jerk in the vertical acceleration of multiple vehicles includes:

[0064] Based on the jerk in the vertical acceleration of multiple vehicles, the start and end times of the consecutive falls off the bridge are obtained; among them...

[0065] When the vertical acceleration suddenly changes, and the acceleration first shows a negative pulse whose absolute value exceeds the absolute value of the negative threshold, the time point at which the acceleration first shows the negative pulse is determined as the starting time of the target vehicle falling off the bridge.

[0066] After the initial bridge fall time, if the vertical acceleration undergoes a reverse abrupt change, and the acceleration first shows a positive pulse whose absolute value exceeds the absolute value of the positive threshold, the time point at which the acceleration first shows the positive pulse is determined as the termination time of the target vehicle's bridge fall.

[0067] In this exemplary embodiment, longitudinal acceleration is extracted in the vehicle body coordinate system. (Direction of vehicle movement) and lateral acceleration Through longitudinal acceleration (Direction of vehicle movement) and lateral acceleration , synthesizing lateral acceleration.

[0068] In this exemplary embodiment, raw sensor data packets, including raw GNSS (Global Navigation Satellite System) observations, raw IMU (accelerometer, gyroscope) data, and high-precision timestamps, can be recorded at an extremely high sampling rate (e.g., sampling rate ≥ 100 Hz) for a period of time before and after the event trigger point (e.g., 10 seconds before and after).

[0069] In this exemplary embodiment, data packets (including a vehicle's unique identifier) ​​can be asynchronously uploaded to a cloud data processing center via a cellular network, a vehicle-to-everything (V2X) network, or any available communication link. If the network is temporarily interrupted, the data will be persistently stored locally and retransmitted once the connection is restored.

[0070] The cloud platform receives raw data uploaded from multiple mobile devices and vehicles, and then performs standardized preprocessing.

[0071] 1. Filtering and noise reduction: A low-pass filter is used to smooth the raw acceleration data and suppress high-frequency noise;

[0072] 2. Sensor Fusion and Coordinate Transformation: Based on Kalman filtering or complementary filtering algorithms, GNSS, accelerometer, and gyroscope data are fused to accurately calculate the vehicle's attitude (pitch, roll, and yaw angles) at each moment. Using this attitude matrix, the acceleration data is precisely transformed from the vehicle coordinate system to the geodetic-northeast coordinate system, obtaining a clean and directionally accurate vertical acceleration component. .

[0073] In this exemplary embodiment, the preprocessed The data is numerically differentiated to calculate its jerk. Before calculating the normal jerk, the original a_z(t) data can be low-pass filtered (e.g., cutoff frequency 20Hz) to suppress high-frequency noise, because differentiation will amplify the noise and affect the accuracy of the result.

[0074] In this exemplary embodiment, at the instant the bridge deck collapses, the supporting force disappears, and the vertical acceleration undergoes a step abrupt change from 0 to -g. This abrupt change corresponds to... A very large negative pulse. The system searches for... The point at which the free fall begins is determined by the first occurrence of the negative threshold m. This refers to the initial time when the target vehicle began to fall off the bridge. At the moment of impact with the ground, the vehicle's speed decreases sharply, and its vertical acceleration undergoes a drastic and reverse change. A very large positive impulse. The system searches for... The point at which the positive threshold n is first exceeded is used to determine the impact moment. This refers to the time at which the target vehicle will fall off the bridge.

[0075] Among them, the thresholds m and n need to be determined through a large number of experiments or high-precision simulation data. The absolute values ​​of the thresholds m and n are much higher than the acceleration values ​​generated by normal driving or bumps.

[0076] In some instances, determining the fall height of the multiple vehicles based on the fall time information during the consecutive falls includes:

[0077] Obtain the vertical initial velocity corresponding to the initial time of the fall when the multiple vehicles fall off the bridge;

[0078] Integrate the vertical acceleration of the multiple vehicles when they fall off the bridge by the time of the initial fall and the time of the final fall, and sum the initial vertical velocities to obtain the integral velocity of each vehicle when it falls off the bridge.

[0079] The fall height of each vehicle is obtained by integrating the initial fall time and the final fall time based on the integral speed of each vehicle.

[0080] In this exemplary embodiment, considering the effects of air resistance, lift, and changes in vehicle attitude during the fall, the normal acceleration... It is not always -g. Numerical integration methods (such as the trapezoidal rule or Runge-Kutta method) are used to perform two integrations to improve computational accuracy.

[0081] The velocity is obtained by integrating once. :

[0082] ;

[0083] in for The vertical initial velocity at time t can be obtained by integration. Estimate the acceleration of the previous instant.

[0084] The height of the bridge deck collapse was obtained by integrating the displacement twice. : ;

[0085] exist absolute value of displacement at time t This is the calculated fall height of the vehicle. .

[0086] In some instances, determining whether the target vehicle is in a bridge-falling state due to bridge deck collapse based on the vertical acceleration and the combined lateral acceleration includes:

[0087] If the sudden change in the vertical acceleration of the target vehicle lasts for a duration longer than a predetermined duration, and the minimum absolute value of the vertical acceleration within the predetermined duration is greater than a predetermined threshold, then it is determined that the target vehicle has fallen off the bridge, and based on the synthetic lateral acceleration, it is determined whether the target vehicle has fallen off the bridge due to the collapse of the bridge deck.

[0088] In this exemplary embodiment, a suspected bicycle fall warning is triggered when a sudden drop in vertical acceleration is detected and the following conditions are met:

[0089] , where g is the nominal value of gravitational acceleration (9.8 m / s²). This is a tolerance threshold set based on a specific sensor noise level. The value can be taken as 0.4 ± 0.2 g. That is, the minimum absolute value of the vertical acceleration within the predetermined time period is greater than the predetermined threshold.

[0090] Duration of the above-mentioned abnormal mutations ( (This is the minimum duration threshold used to filter out disturbances such as sudden, severe jolts).

[0091] In some instances, determining whether the target vehicle is in a bridge-falling state due to bridge deck collapse based on the synthesized lateral acceleration includes:

[0092] If the modulus of the synthetic lateral acceleration exceeds the predetermined modulus value within the predetermined time period, it is determined that the target vehicle has experienced a lateral collision, and the target vehicle is determined to have fallen off the bridge as a lateral collision and bridge fall state.

[0093] If the modulus of the synthesized lateral acceleration is less than or equal to the predetermined modulus value within the predetermined time period, then it is determined that the target vehicle has fallen off the bridge due to the collapse of the bridge deck.

[0094] In this exemplary embodiment, to distinguish whether the fall was caused by a vehicle colliding with the guardrail or by the overall collapse of the bridge deck, the system rewinds 5 seconds before the suspected fall event occurred. High-frequency IMU data.

[0095] For example, 1. Data extraction: Extract longitudinal acceleration in the vehicle body coordinate system. (Direction of vehicle movement) and lateral acceleration (Perpendicular to the direction of movement).

[0096] 2. Feature Calculation: Calculate the composite lateral acceleration modulus of the vehicle during this time period. :

[0097] .

[0098] 3. Pattern discrimination: Set an empirical threshold. (Typically, the value is between 3 and 5). If at any point during the backtracking period, the following condition is met: If the signal is clear, it indicates that the vehicle experienced extremely violent lateral movement (such as a violent collision with a guardrail or loss of control rollover). The system determines the event as a single-vehicle or multi-vehicle continuous accident caused by a collision and rules out the possibility of bridge collapse. Otherwise, it confirms that the entire bridge collapsed, resulting in a synchronous, continuous, collision-free single / multi-vehicle fall event.

[0099] Figure 2 This invention provides a bridge deck collapse identification process based on vehicle mobile terminal sensing data. Figure 1 .like Figure 2 As shown, the bridge deck collapse identification process based on vehicle mobile terminal perception data includes:

[0100] Step 20: Onboard sensors collect data in real time;

[0101] Step 21: Determine whether the vehicle is located on a bridge section based on the collected data;

[0102] Step 22: If the vehicles are located on a bridge section, monitor the normal acceleration (vertical acceleration) in real time and calculate the convergence of the falling times of multiple vehicles;

[0103] Step 23: Determine whether the conditions for a suspected multi-vehicle collision are met.

[0104] Step 24: Determine if there is a drastic step change in lateral acceleration. If there is a drastic step change in lateral acceleration, bridge deck collapse is ruled out. If there is no drastic step change in lateral acceleration, bridge deck collapse is determined.

[0105] Step 25: Trigger data recording and asynchronously upload to the cloud;

[0106] Step 26: Cloud data preprocessing and height calculation;

[0107] Step 27: Output the estimated collapse height.

[0108] In some instances, the method includes:

[0109] If the confidence level is greater than a predetermined value, the collapse height of the bridge deck is determined by weighted averaging of the fall heights of multiple vehicles that meet the confidence level.

[0110] In this exemplary embodiment, the step of taking a weighted average of the multiple initial bridge deck collapse heights to obtain the bridge deck collapse height includes:

[0111] Obtain the falling posture of multiple target vehicles when they fall onto the ground or water surface;

[0112] Based on the fall posture of each target vehicle, the weighting weight of each target vehicle is determined;

[0113] The bridge deck collapse height is obtained by performing a weighted average calculation based on multiple initial bridge deck collapse heights and the weighted weights of each target vehicle.

[0114] In this exemplary embodiment, in a multi-vehicle fall event, the system receives fall height calculation results from multiple mobile devices (such as mobile phones, in-vehicle smart terminals) and / or multiple vehicles within the same vehicle, constituting a set of height estimates. , ,..., } (K is the total number of data sources); where, This represents the estimated fall height of the Kth vehicle. The optimal estimate is generated using the following fusion strategy:

[0115] a) Data preprocessing and weight assignment: Assign a confidence weight to each data source i. This weight can be adjusted based on time confidence, sensor accuracy, data quality indicators, and device attitude. For example, the weighted averaging of multiple initial bridge deck collapse heights to obtain the bridge deck collapse height includes:

[0116] Based on the group's average fall time The deviation is used to determine the weighting of each target vehicle.

[0117] The bridge deck collapse height is obtained by performing a weighted average calculation based on multiple initial bridge deck collapse heights and the weighted weights of each target vehicle.

[0118] Among them, the average fall time of the group The smaller the deviation of a vehicle, the higher the reliability of its data and the higher its weight, because this indicates that it is closer to the starting point of the collapse.

[0119] Among them, high-end IMUs (such as automotive-grade IMUs) have a higher weight than consumer-grade smartphone IMUs.

[0120] The step of taking a weighted average of multiple initial bridge deck collapse heights to obtain the bridge deck collapse height includes:

[0121] The weighting of each target vehicle is determined based on the signal-to-noise ratio, the variance of acceleration during free fall, and the confidence level of the start and end point identification.

[0122] The bridge deck collapse height is obtained by performing a weighted average calculation based on multiple initial bridge deck collapse heights and the weighted weights of each target vehicle.

[0123] Among them, the signal-to-noise ratio, the variance of acceleration during free fall, and the confidence level for identifying the start and end points are calculated, and the higher the quality, the greater the weight.

[0124] Among these factors, the more stable the device's attitude during the fall, the more reliable the transformed a_z(t) is, and the higher its weight. (For example:) The specific function form can be determined during system calibration.

[0125] b) Outlier Removal: Before weighted averaging, statistical methods are used to remove height values ​​that significantly deviate from the group. In consecutive fall events, these outliers usually originate from a vehicle hitting an obstacle during the fall or from severe data distortion. Removing these outliers can greatly improve the consistency and purity of the overall data.

[0126] c) Weighted fusion: The effective height estimates after cleaning are weighted and averaged to obtain the final collapse height estimate. :

[0127] The confidence level is based on data fusion of the target vehicle. Let be the estimated fall height of the i-th vehicle.

[0128] d) Uncertainty Quantification: Calculate the weighted standard deviation or confidence interval of the final result. This indicator is closely related to the number of data sources K and the weight of each data source, and is output to the rescue unit as a core indicator for assessing the reliability of this altitude measurement.

[0129] Figure 3 This invention provides a bridge deck collapse identification process based on vehicle mobile terminal sensing data. Figure 2 .like Figure 3 As shown, the bridge deck collapse identification process based on vehicle mobile terminal perception data includes:

[0130] Step 30: Receive sensor data from multiple devices and vehicles;

[0131] Step 31: Cloud data preprocessing and coordinate transformation;

[0132] Step 32: Calculate the jerk to identify the start and end times of the vehicle's fall;

[0133] Step 33: Integrate the acceleration twice to find the displacement;

[0134] Step 34: Calculate the set of fall heights for each fallen vehicle;

[0135] Step 35: Multi-source data fusion, weighted average / outlier removal;

[0136] Step 36: Output the final height and uncertainty assessment.

[0137] This invention provides a bridge collapse identification system based on vehicle mobile terminal sensing data. Figure 4 This is a schematic diagram of the bridge collapse recognition system based on vehicle mobile terminal sensing data provided in an embodiment of the present invention. Figure 4 As shown, it includes:

[0138] The vehicle location monitoring module 40 is used to determine the relative position between the target vehicle and the bridge section based on the positioning data of the vehicle mobile terminal.

[0139] The vehicle acceleration monitoring module 41 is used to monitor the vehicle acceleration based on the IMU data of the vehicle mobile terminal when the target vehicle is determined to be located on a bridge section based on the relative position.

[0140] The bridge fall monitoring module 42 is used to determine whether the target vehicle is in a bridge fall state due to bridge collapse based on the vertical acceleration and the combined lateral acceleration when the vertical acceleration of the target vehicle changes abruptly.

[0141] The bridge fall time determination module 43 is used to obtain the bridge fall time information of multiple vehicles falling into the bridge in succession within a predetermined time if the target vehicle falls into the bridge due to the collapse of the bridge surface.

[0142] The bridge collapse identification module 44 is used to determine the fall height of the multiple vehicles when they fall off the bridge based on the fall time information of the multiple vehicles falling off the bridge in succession, and to adjust the credibility of the bridge collapse based on the fall height of the multiple vehicles falling off the bridge.

[0143] In this exemplary embodiment, the positioning data of the vehicle mobile terminal may include GPS (Global Positioning System) data and electronic maps. Determining the relative position between the target vehicle and the bridge section based on the positioning data of the vehicle mobile terminal includes determining the relative position between the target vehicle and the bridge section based on the GPS data and electronic maps of the vehicle mobile terminal.

[0144] In this exemplary embodiment, real-time GPS data of the vehicle's movement can be obtained through the vehicle-mounted GPS and IMU modules. Combined with GPS output, vehicle speed, and electronic map, the location of the vehicle and the bridge section can be comprehensively determined.

[0145] If the target vehicle is located on a bridge section, the vehicle's real-time acceleration data is collected using an onboard IMU, and the characteristics of vertical acceleration changes are analyzed. When the vehicle's vertical acceleration drops sharply, the time information of the vehicle falling off the bridge is extracted.

[0146] In this application, by using the positioning data and IMU data of the vehicle's mobile terminal, after determining that a vehicle has fallen off the bridge due to a bridge collapse, the time information of the target vehicle's fall can be determined by accelerating the vehicle. Based on the time information of the target vehicle's fall, the fall height of multiple vehicles when they fall off the bridge is determined, and the credibility of the bridge collapse is adjusted based on the fall height of multiple vehicles when they fall off the bridge, thereby improving the accuracy and credibility of determining the bridge collapse status.

[0147] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0148] This invention provides a computer-readable storage medium storing a bridge collapse identification program based on vehicle mobile terminal sensing data. When the bridge collapse identification program based on vehicle mobile terminal sensing data is executed by a processor, it implements the bridge collapse identification method based on vehicle mobile terminal sensing data described in the above embodiments.

[0149] This invention provides an electronic device, including a memory, a processor, and a bridge collapse identification program based on vehicle mobile terminal perception data stored in the memory and executable on the processor. When the processor executes the bridge collapse identification program based on vehicle mobile terminal perception data, it implements the bridge collapse identification method based on vehicle mobile terminal perception data described in the above embodiments.

[0150] In the description of this invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0151] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0152] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first and second features are in direct contact, or that they are in indirect contact through an intermediate medium. Furthermore, "above," "over," or "on top" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," or "beneath" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0153] In the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0154] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make modifications, alterations, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A bridge deck collapse identification method based on vehicle mobile terminal perception data, characterized in that, The method comprises the following steps: determining the relative position between the target vehicle and the bridge section based on the positioning data of the vehicle mobile terminal; monitoring the driving acceleration of the target vehicle according to the IMU data of the vehicle mobile terminal in the case that the target vehicle is determined to be located on the bridge section based on the relative position, and judging whether the target vehicle appears the falling-off state due to the collapse of the bridge deck based on the vertical acceleration and the synthetic lateral acceleration in the case that the vertical acceleration in the driving acceleration of the target vehicle appears a sudden change; if the target vehicle appears the falling-off state due to the collapse of the bridge deck, obtaining the falling-off time information of the continuous falling-off of multiple vehicles based on the jerk in the vertical acceleration of the multiple vehicles in the case that the continuous falling-off of multiple vehicles appears within a predetermined time; determining the falling height of the multiple vehicles in the case of falling-off based on the falling-off time information of the multiple vehicles in the case of continuous falling-off, and adjusting the credibility of the collapse of the bridge deck based on the falling height of the multiple vehicles in the case of falling-off; the smaller the variance value of the falling height of the multiple vehicles in the case of falling-off, the higher the credibility of the collapse of the bridge deck; the larger the variance value of the falling height of the multiple vehicles in the case of falling-off, the lower the credibility of the collapse of the bridge deck; the adjusting of the credibility of the collapse of the bridge deck based on the falling height of the multiple vehicles in the case of falling-off comprises: determining the variance value of the falling height of the multiple vehicles in the case of falling-off based on the falling height of the multiple vehicles in the case of falling-off; adjusting the credibility of the collapse of the bridge deck based on the variance value of the falling height of the multiple vehicles in the case of falling-off; the falling-off time information comprises the starting falling-off time of the vehicle falling-off and the ending falling-off time of the vehicle falling-off; the obtaining of the falling-off time information of the continuous falling-off of multiple vehicles based on the jerk in the vertical acceleration of the multiple vehicles comprises: obtaining the starting falling-off time and the ending falling-off time of the continuous falling-off of multiple vehicles based on the jerk in the vertical acceleration of the multiple vehicles; wherein, in the case that the vertical acceleration appears a sudden change, when the jerk first appears a negative pulse with an absolute value exceeding a negative threshold absolute value, the time point at which the jerk first appears the negative pulse is determined as the starting falling-off time of the target vehicle falling-off; after the starting falling-off time, when the vertical acceleration appears a reverse sudden change and the jerk first appears a positive pulse with an absolute value exceeding a positive threshold absolute value, the time point at which the jerk first appears the positive pulse is determined as the ending falling-off time of the target vehicle falling-off. 2.The bridge deck collapse identification method based on vehicle mobile terminal sensing data according to claim 1, wherein, the determination of the falling height of the multiple vehicles in the case of falling-off based on the falling-off time information of the multiple vehicles in the case of continuous falling-off comprises: obtaining the vertical initial speed corresponding to the starting falling-off time of the multiple vehicles in the case of falling-off; integrating the vertical acceleration of the multiple vehicles in the case of falling-off in the starting falling-off time and the ending falling-off time, and accumulating the vertical initial speed to obtain the integral speed of each vehicle in the case of falling-off of the multiple vehicles; integrating the integral speed of each vehicle in the starting falling-off time and the ending falling-off time to obtain the falling height of each vehicle. 3.The bridge deck collapse recognition method based on vehicle mobile terminal sensing data according to claim 1, wherein, the judgment of whether the target vehicle appears the falling-off state due to the collapse of the bridge deck based on the vertical acceleration and the synthetic lateral acceleration comprises: If the mutation duration of the vertical acceleration of the target vehicle is greater than a predetermined duration, and the minimum value of the absolute value of the vertical acceleration in the predetermined duration is greater than a predetermined threshold, it is determined that the target vehicle is in a bridge collapse state, and whether the target vehicle is in a bridge collapse state due to bridge collapse is determined based on the synthetic lateral acceleration. 4.The bridge deck collapse identification method based on vehicle mobile terminal sensing data according to claim 3, wherein, The determination of whether the target vehicle is in a bridge collapse state due to bridge collapse based on the synthetic lateral acceleration comprises: If the modulus of the synthetic lateral acceleration in the predetermined duration is greater than a predetermined modulus value, it is determined that the target vehicle is in a lateral collision, and it is determined that the target vehicle is in a bridge collapse state due to vehicle lateral collision; If the modulus of the synthetic lateral acceleration in the predetermined duration is less than or equal to a predetermined modulus value, it is determined that the target vehicle is in a bridge collapse state due to bridge collapse. 5.The bridge deck collapse recognition method based on vehicle mobile terminal sensing data according to claim 1, wherein, The method comprises: In the case where the credibility is greater than a predetermined value, the falling height of the multiple vehicles that meet the credibility is weighted and averaged to determine the collapse height of the bridge collapse. 6.A bridge deck collapse identification system based on vehicle mobile terminal perception data, characterized by, Comprise: A vehicle position monitoring module for determining the relative position between the target vehicle and the bridge section based on the positioning data of the vehicle mobile terminal; A driving acceleration monitoring module for monitoring the driving acceleration of the target vehicle according to the IMU data of the vehicle mobile terminal based on the determination that the target vehicle is located on the bridge section based on the relative position; A bridge collapse state monitoring module for determining whether the target vehicle is in a bridge collapse state due to bridge collapse based on the vertical acceleration and the synthetic lateral acceleration in the case where the vertical acceleration in the driving acceleration of the target vehicle is mutated; A bridge collapse time determination module for acquiring bridge collapse time information of multiple vehicles in continuous bridge collapse based on the jerk in the vertical acceleration of the multiple vehicles in the case where the target vehicle is in a bridge collapse state due to bridge collapse and multiple vehicles are in continuous bridge collapse within a predetermined time; A bridge collapse identification module for determining the falling height of the multiple vehicles in bridge collapse based on the bridge collapse time information of the multiple vehicles in continuous bridge collapse, and adjusting the credibility of the bridge collapse based on the falling height of the multiple vehicles in bridge collapse; The smaller the variance value of the falling height of the multiple vehicles in bridge collapse, the higher the credibility of the bridge collapse; The greater the variance value of the falling height of the multiple vehicles in bridge collapse, the lower the credibility of the bridge collapse; The adjustment of the credibility of the bridge collapse based on the falling height of the multiple vehicles in bridge collapse comprises: Determining the variance value of the falling height of the multiple vehicles in bridge collapse based on the falling height of the multiple vehicles in bridge collapse; Adjusting the credibility of the bridge collapse based on the variance value of the falling height of the multiple vehicles in bridge collapse; The bridge collapse time information comprises the starting bridge collapse time of the vehicle in bridge collapse and the ending bridge collapse time of the vehicle in bridge collapse; The acquisition of the bridge collapse time information of the multiple vehicles in continuous bridge collapse based on the jerk in the vertical acceleration of the multiple vehicles comprises: Acquiring the starting bridge collapse time and the ending bridge collapse time of the multiple vehicles in continuous bridge collapse based on the jerk in the vertical acceleration of the multiple vehicles; wherein, In the case that the vertical acceleration appears a mutation, when the jerk first appears a negative pulse whose absolute value exceeds a negative threshold absolute value, the time point when the jerk first appears the negative pulse is determined as a starting falling bridge time of the target vehicle falling bridge; After the starting falling bridge time, when the vertical acceleration appears a reverse mutation and the jerk first appears a positive pulse whose absolute value exceeds a positive threshold absolute value, the time point when the jerk first appears the positive pulse is determined as an ending falling bridge time of the target vehicle falling bridge.

7. A computer readable storage medium characterized in that, A bridge collapse identification program based on vehicle mobile terminal sensing data stored thereon, which, when executed by a processor, implements the bridge collapse identification method based on vehicle mobile terminal sensing data in any one of claims 1-5.

8. An electronic device, comprising: A bridge collapse identification program based on vehicle mobile terminal sensing data stored in a memory and executable on a processor, which, when executed by the processor, implements the bridge collapse identification method based on vehicle mobile terminal sensing data in any one of claims 1-5.

Images