Road settlement monitoring analysis and early warning system based on artificial intelligence

Abstract

The invention relates to the technical field of road settlement monitoring and early warning, in particular to a road settlement monitoring analysis and early warning system based on artificial intelligence. Comprising a monitoring area division module, an influence factor monitoring analysis module, a road state monitoring analysis module, a soil layer state monitoring analysis module, a settlement area identification module, a settlement degree analysis module, an early warning execution module and a display terminal. Through cooperative work of a plurality of modules such as monitoring area division, influence factor analysis, road state and soil layer state monitoring and the like, a potential settlement risk area can be found and identified in time, and corresponding early warning and execution instructions are automatically triggered according to different settlement degrees, so that the settlement risk is effectively improved. Therefore, the traffic of vehicles is limited, the ground load is reduced, and time is won for first-aid repair and reinforcement work, so that the safety of roads and infrastructures is effectively protected, and the smoothness and safety of urban traffic are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of road subsidence monitoring and early warning, and in particular to a road subsidence monitoring, analysis and early warning system based on artificial intelligence. Background Art

[0002] With the acceleration of urbanization and the surge in traffic volume, roads, as the lifeline of cities, are crucial to traffic flow and public safety. However, road subsidence, as a common road disease, is often affected by a variety of complex factors, which leads to changes in the road structure and the soil layer below, thus causing road subsidence, which seriously threatens the performance of the road and driving safety.

[0003] Traditional road settlement monitoring methods mainly rely on manual inspections, GPS measurements, and remote sensing technology. Although these methods can reflect the situation of road settlement to a certain extent, they have many limitations. They cannot detect and deal with small settlement changes in time, nor can they penetrate into the road structure layer, making it difficult to accurately reflect the actual changes in the soil layer.

[0004] More importantly, traditional monitoring methods can usually only provide static or intermittent monitoring data, and cannot achieve real-time and continuous monitoring of road subsidence, thus limiting the timely warning of road subsidence by relevant departments. In the early stage of subsidence, if it is not discovered in time and intervention measures are not taken, the subsidence phenomenon will often deteriorate rapidly, causing serious damage to the road structure and even traffic accidents, causing huge economic losses and adverse effects on society.

[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0006] The purpose of the present invention is to solve the problem that the traditional road subsidence monitoring method is relatively limited, cannot timely detect and deal with small settlement changes, and cannot realize real-time and continuous monitoring of road subsidence, and proposes a road subsidence monitoring, analysis and early warning system based on artificial intelligence.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] Road subsidence monitoring, analysis and early warning system based on artificial intelligence, including:

[0009] The monitoring area division module is used to analyze the historical traffic parameters of the target monitoring road to obtain the division distance, and divide the target monitoring road into several equidistant areas according to the division distance, thereby obtaining each monitoring area;

[0010] The influencing factor monitoring and analysis module is used to analyze the influencing factors of each monitoring area and obtain the influencing coefficient;

[0011] The road state monitoring and analysis module is used to monitor the road state information of each monitoring area, obtain the use influence index and the road surface state evaluation index, and based on the influence coefficient, obtain the road state evaluation coefficient of each monitoring area;

[0012] The soil layer status monitoring and analysis module is used to monitor the soil layer status information of each monitoring area, obtain the water content change assessment index, the pressure change assessment index and the falling object change assessment index, and based on the influence coefficient, obtain the soil layer status assessment coefficient of each monitoring area;

[0013] The settlement area identification module is used to receive the road state assessment coefficient and soil layer state assessment coefficient of each monitoring area, thereby making a judgment and analysis on each monitoring area to obtain an abnormal area;

[0014] The settlement degree analysis module is used to monitor the settlement status information of the abnormal area, obtain the settlement amount, settlement velocity and settlement distribution area, thereby analyzing the settlement degree of the abnormal area and obtaining the settlement warning level type signal;

[0015] The warning execution module is used to receive the settlement warning level type signal, thereby triggering the corresponding restriction instruction.

[0016] Furthermore, the process of solving the partition distance is:

[0017] Obtain the historical traffic parameters of the target monitored road, extract the traffic flow value, heavy vehicle proportion value and congestion value in the historical traffic parameters, perform normalization processing, and obtain the traffic load value;

[0018] The traffic load value of the target monitored road is matched and analyzed with the traffic load status table stored in the system to obtain the traffic load level, and then matched with the division distance corresponding to the traffic load level to obtain the division distance.

[0019] Furthermore, the process of solving the influence coefficient is:

[0020] By obtaining the groundwater level, rainfall and load-bearing value of each monitoring area during the current monitoring period, the three values ​​are extracted and normalized to obtain the influence coefficient Δ q , q represents the number of each monitoring area, and q=1, 2, 3…m, m represents the total number of the monitoring area numbers.

[0021] Furthermore, the solution process for the use impact index and road surface condition evaluation index is as follows:

[0022] Obtain the historical use records of the roads in each monitoring area during the current monitoring period, and obtain the continuous use time of each historical use, calculate the average value thereof, obtain the average continuous use time of the roads in each monitoring area, and at the same time obtain the years of use of the roads in each monitoring area;

[0023] The average continuous use time and years of use of roads in each monitoring area are normalized and their values ​​are taken to obtain the use impact index θ1 q ;

[0024] By collecting the road surface images of each monitoring area in the current monitoring time period, the road surface images of each monitoring area in the current monitoring time period are obtained, and the number of bumps, the total area of ​​bumps, the number of cracks and the total length of cracks on the road surface of each monitoring area are obtained;

[0025] The use impact index of each monitoring area is matched with the use impact index threshold value corresponding to the set use impact level to obtain the use impact level of each monitoring area, and it is matched with the reference road surface parameter set corresponding to the set use impact level to obtain the reference road surface parameter set of each monitoring area, and the reference bump number, reference bump total area, reference crack number and reference crack total length of the road surface of each monitoring area are extracted therefrom;

[0026] The number of bumps, total bump area, number of cracks and total length of cracks, reference bump number, reference bump total area, reference crack number and reference crack total length of the road surface in each monitoring area are extracted for analysis and processing, thereby obtaining the road surface condition evaluation index θ2 q .

[0027] Furthermore, the solution process for the road condition evaluation coefficient of each monitoring area is:

[0028] Extract influence coefficient Δ q 、Use influence index θ1 q and road surface condition evaluation index θ2 q The value of is normalized according to the formula: Calculate the road status evaluation coefficient DLP of each monitoring area q , where η1 and η2 represent the correction coefficients of the influence index and the road surface condition evaluation index, respectively.

[0029] Furthermore, the solution process for the water content change assessment index, the pressure change assessment index and the falling object change assessment index is as follows:

[0030] The water content of the soil layer in each monitoring area during the current monitoring period is obtained by obtaining the water content of the soil layer in each monitoring area during the current monitoring period. iq The water content corresponding to the first monitoring time point is extracted from it as the initial water content Asz0 of the soil layer in each monitoring area during the current monitoring period. q ;

[0031] According to the formula: Calculate the water content change assessment index δ1 q , where i represents the number of each monitoring time point in the current monitoring time period, and i = 1, 2, 3...n, n represents the total number of monitoring time point numbers in the current monitoring time period, Asz i-1 q represents the water content at the i-1th time point in the current monitoring period, and x1 and x2 represent the preset weight factors respectively;

[0032] The same analysis method as above can be used to obtain the pressure change evaluation index δ2 q and the falling object change assessment index δ3 q .

[0033] Furthermore, the solution process for the soil state assessment coefficient of each monitoring area is as follows:

[0034] Extract influence coefficient Δ q , water content change assessment index δ1 q , Pressure change evaluation index δ2 q and the falling object change assessment index δ3 q The value of is normalized according to the formula: Calculate the soil state assessment coefficient TCP of each monitoring area q , where μ1, μ2, and μ3 represent the correction coefficients of the water content change assessment index, the pressure change assessment index, and the falling object amount change assessment index, respectively.

[0035] Furthermore, the process of determining and analyzing each monitoring area is as follows:

[0036] Extract the road status evaluation coefficient DLP of each monitoring area q and soil state assessment coefficient TCP q The value of is normalized according to the formula: Calculate the settlement state assessment coefficient CJQ of each monitoring area, where e represents a natural constant, and λ1 and λ2 represent the weight coefficients of the road state assessment coefficient and the soil layer state assessment coefficient, respectively;

[0037] Set the settlement state assessment threshold of each monitoring area, compare and analyze the settlement state assessment coefficient of each monitoring area with the settlement state assessment threshold, and if the settlement state assessment coefficient of a monitoring area is greater than or equal to the settlement state assessment threshold, the monitoring area is judged to be in an abnormal settlement state;

[0038] The monitoring area judged to be in an abnormal subsidence state is marked as an abnormal area.

[0039] Furthermore, the solution process for the settlement amount, settlement velocity and settlement distribution area is:

[0040] Settle settlement detection points in abnormal areas, thereby obtaining settlement detection points in abnormal areas, and obtain the elevation values ​​of settlement detection points corresponding to each monitoring time point within a period of time, marked as GC jh , where j represents the number of each monitoring time point within a period of time, and j = 1, 2, 3...n1, n1 represents the total number of numbers of each monitoring time point within a period of time, h represents the number of each settlement detection point, and h = 1, 2, 3...d, d represents the total number of numbers of each settlement detection point, and then obtain the basic elevation value of the abnormal area, marked as GC * , according to the formula: Calculate the settlement amount Ujl corresponding to each monitoring time point within a period of time j ;

[0041] Extract the settlement amount Ujl corresponding to each monitoring time point within a period of time j The value of is based on the formula: Calculate the sedimentation velocity Usdj corresponding to each monitoring time point within a period of time, where t (j,j-1) Indicates the monitoring duration between the jth monitoring time point and the j-1th monitoring time point within a period of time;

[0042] Extract the elevation value of each settlement detection point corresponding to each monitoring time point within a period of time, compare and analyze the elevation value of each settlement detection point corresponding to each monitoring time point within a period of time with the base elevation value. If the elevation value of a settlement detection point corresponding to each monitoring time point within a period of time is less than the base elevation value, then mark the settlement detection point corresponding to each monitoring time point within a period of time as an abnormal settlement detection point, integrate the abnormal settlement detection points, and obtain the settlement distribution area Ufm corresponding to each monitoring time point within a period of time. j .

[0043] Furthermore, the process of analyzing the subsidence degree of the abnormal area is as follows:

[0044] Extract the settlement amount Ujl corresponding to each monitoring time point within a period of time j , sedimentation velocity Usd j and sedimentation distribution area Ufm j The value of is normalized according to the formula: The settlement degree value Ψ of the abnormal area is calculated, where ζ represents a natural constant greater than zero, and γ1, γ2 and γ3 represent the weight coefficients of settlement amount, settlement velocity and settlement distribution area respectively;

[0045] Compare and analyze the settlement degree value of the abnormal area with the set reference comparison interval. If the settlement degree value of the abnormal area is less than the minimum value of the reference comparison interval, a third-level settlement warning signal is generated. If the settlement degree value of the abnormal area is within the reference comparison interval, a second-level settlement warning signal is generated. If the settlement degree value of the abnormal area is greater than the maximum value of the reference comparison interval, a first-level settlement warning signal is generated.

[0046] The generated third-level settlement warning signal, second-level settlement warning signal and first-level settlement warning signal constitute the settlement warning level type signal.

[0047] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects:

[0048] 1. The present invention collects and analyzes the historical traffic parameters of the target monitoring road to obtain the division distance, and divides the target monitoring road into regions, so that the division basis is not only derived from actual data, but also takes into account the traffic conditions in multiple dimensions, ensuring the scientific nature of the division. Based on the scientific regional division, monitoring equipment and resources can be deployed more effectively, thereby realizing the rapid positioning of monitoring and taking measures to solve the problem, thereby improving the accuracy and timeliness of monitoring;

[0049] 2. The present invention automatically identifies and quantifies various factors that affect road settlement and calculates the influence coefficient. This intelligent analysis method not only reduces the workload of manual analysis, but also improves the accuracy and efficiency of analysis;

[0050] 3. The present invention constructs a multi-index evaluation system that integrates multiple evaluation indexes, aiming to comprehensively and meticulously reflect the actual status of the road and the soil layer below it. Through this carefully designed evaluation framework, it can deeply understand the health status of the road and the changes in the soil layer status, thereby realizing a more accurate identification of the road settlement risk. It not only enriches the data dimension, but also significantly enhances the depth and breadth of the analysis, providing solid and accurate data support for subsequent settlement warnings, and ensuring the timeliness and effectiveness of early warning measures;

[0051] 4. The present invention, through comprehensive evaluation results of road status and soil layer status, intelligently identifies abnormal areas and determines their degree of settlement, thereby triggering corresponding early warning and restriction instructions. This intelligent early warning and decision support function not only improves the timeliness and accuracy of early warning, but also provides powerful decision support for relevant departments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 It is the overall module block diagram of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] like Figure 1 As shown, the road settlement monitoring, analysis and early warning system based on artificial intelligence includes: a monitoring area division module, an influencing factor monitoring and analysis module, a road state monitoring and analysis module, a soil layer state monitoring and analysis module, a settlement area identification module, a settlement degree analysis module, an early warning execution module and a display terminal;

[0056] The monitoring area division module is used to obtain the historical traffic parameters of the target monitoring road. The historical traffic parameters include the traffic flow value Qc, the heavy vehicle proportion value Qz and the congestion value Qy. The traffic flow value, the heavy vehicle proportion value and the congestion value are extracted and normalized. According to the formula: QW = Qc × a1 + Qz × a2 + Qy × a3, the traffic load value QW is calculated, where a1, a2 and a3 represent the set weight factors respectively.

[0057] The specific process of obtaining historical traffic parameters is as follows: through detailed data collection of the traffic conditions of the target monitoring road in the past unit time period (in years), including a comprehensive record of the daily traffic volume, the proportion of heavy vehicles and the number of congestion, and then calculating the average value of the daily traffic volume, the proportion of heavy vehicles and the number of congestion in the past unit time period of the target monitoring road, thereby obtaining the average traffic volume, the average proportion of heavy vehicles and the average number of congestion in the past unit time period of the target monitoring road, and taking the average traffic volume, the average proportion of heavy vehicles and the average number of congestion in the past unit time period of the target monitoring road as the historical traffic parameters of the target monitoring road;

[0058] The traffic load value QW of the target monitoring road is matched and analyzed with the traffic load state table stored in the system, thereby obtaining the traffic load level, and each traffic load value QW of the target monitoring road corresponds to a traffic load level, and is then matched with the division distance corresponding to the traffic load level, thereby obtaining the division distance;

[0059] The target monitoring road is divided into several equally spaced areas according to the division distance, thus obtaining each monitoring area, and each monitoring area is assigned a unique number q, where the value of q starts from 1 and increases to m, and m represents the total number of all monitoring area numbers;

[0060] The influencing factor monitoring and analysis module is used to monitor the influencing factor information of each monitoring area, thereby analyzing the influencing factors of each monitoring area. The specific analysis is as follows:

[0061] By obtaining the groundwater level value Rw of each monitoring area during the current monitoring period iq , rainfall value Ry iq And load-bearing value Rz iq , extract the three values ​​for normalization, according to the formula: Calculate the influence coefficient Δ q , where i represents the number of each monitoring time point in the current monitoring time period, and i = 1, 2, 3...n, n represents the total number of monitoring time point numbers in the current monitoring time period, Rw q * , Ry q * and Rz q * represent the reference groundwater level, reference rainfall and reference load-bearing value respectively, b1, b2 and b3 represent the weight coefficients of groundwater level, rainfall and load-bearing value respectively, and b1>b2>b3;

[0062] It should be noted that the groundwater level value refers to the height of the groundwater level in the monitoring area, the rainfall value refers to the total amount of rainwater received in the monitoring area, and the load-bearing value refers to the actual load borne by the road or foundation in the monitoring area;

[0063] The road status monitoring and analysis module is used to monitor the road status information of each monitoring area, thereby analyzing the road status of each monitoring area. The specific analysis is as follows:

[0064] Obtain the historical usage records of the roads in each monitoring area during the current monitoring period, and obtain the continuous usage time of each historical usage, calculate the average value, and obtain the average continuous usage time Tsc of the roads in each monitoring area q At the same time, the service life Tnx of the roads in each monitoring area is obtainedq ;

[0065] The average continuous use time Tsc of the roads in each monitoring area q 、Years of use Tnx q Normalize and take its value according to the formula: θ1 q =ln(Tsc q ×β1+Tnx q ×β2), calculate the usage impact index θ1 q , where β1 and β2 represent the preset exponential factors respectively;

[0066] The road surface images of each monitoring area in the current monitoring time period are collected by high-definition cameras, and the road surface images of each monitoring area in the current monitoring time period are obtained, and the number of concave and convex surfaces of each monitoring area is obtained from them. q 、Total concave and convex area Ymj q , number of cracks Yfs q and the total crack length Yfc q ;

[0067] The usage impact index of each monitoring area is matched with the usage impact index threshold corresponding to the set usage impact level to obtain the usage impact level of each monitoring area, and it is matched with the reference road surface parameter set corresponding to the set usage impact level to obtain the reference road surface parameter set of each monitoring area, and the reference concave-convex number Yat of the road surface of each monitoring area is extracted from it. q * , reference concave and convex total area Ymj q * , reference crack number Yfs q * and the total length of the reference crack Yfc q * ;

[0068] According to the formula: Calculate the road surface condition evaluation index θ2 q , where e represents a natural constant, and β1, β2, β3 and β4 represent preset exponential factors respectively;

[0069] Extract influence coefficient Δ q 、Use influence index θ1 q and road surface condition evaluation index θ2 q The value of is normalized according to the formula: Calculate the road status evaluation coefficient DLP of each monitoring area q , where η1 and η2 represent the correction coefficients of the use influence index and the road surface condition evaluation index respectively;

[0070] The generated road condition assessment coefficients of each monitoring area are sent to the settlement area identification module;

[0071] The soil layer status monitoring and analysis module is used to monitor the soil layer status information of each monitoring area, thereby analyzing the soil layer status of each monitoring area. The specific analysis is as follows:

[0072] The water content of the soil layer in each monitoring area during the current monitoring period is obtained by obtaining the water content of the soil layer in each monitoring area during the current monitoring period. i q The water content corresponding to the first monitoring time point is extracted from it as the initial water content Asz0 of the soil layer in each monitoring area during the current monitoring period. q ;

[0073] By obtaining the pressure of the soil layer in each monitoring area during the current monitoring period, the pressure Ayg of the soil layer in each monitoring area during the current monitoring period is obtained. i q The pressure corresponding to the first monitoring time point is extracted as the initial pressure Ayg0 of the soil layer in each monitoring area during the current monitoring period. q , where the pressure refers to the lateral pressure exerted by the fill behind the supporting structure on the structure;

[0074] By obtaining the amount of fallen objects in the soil layer of each monitoring area during the current monitoring period, the amount of fallen objects Alw in the soil layer of each monitoring area during the current monitoring period is obtained. i q The amount of falling objects corresponding to the first monitoring time point is extracted as the initial amount of falling objects Alw0 in each monitoring area during the current monitoring period. q ; The amount of falling debris refers to the total amount of solid materials such as gravel, sand, etc. that are scattered and accumulated from the surface of the soil layer;

[0075] According to the formula: Calculate the water content change assessment index δ1 q , among which Asz i-1 q represents the water content at the i-1th time point in the current monitoring period, and x1 and x2 represent the preset weight factors respectively;

[0076] According to the formula: Calculate the pressure change assessment index δ2 q , among which Ayg i-1 q represents the pressure at the i-1th time point in the current monitoring period, and x3 and x4 represent the preset weight factors respectively;

[0077] According to the formula: Calculate the falling object change assessment index δ3 q , among which Alw i-1 q represents the amount of falling objects at the i-1th time point in the current monitoring period, and x5 and x6 represent the preset weight factors respectively;

[0078] Extract influence coefficient Δ q , water content change assessment index δ1 q , Pressure change evaluation index δ2 q and the falling object change assessment index δ3 q The value of is normalized according to the formula: Calculate the soil state assessment coefficient TCP of each monitoring area q , where μ1, μ2, and μ3 represent the correction coefficients of the water content change assessment index, the pressure change assessment index, and the falling object change assessment index, respectively;

[0079] The generated soil layer state assessment coefficients of each monitoring area are sent to the settlement area identification module;

[0080] The settlement area identification module is used to receive the road state assessment coefficient and soil state assessment coefficient of each monitoring area, and then make judgments and analyses on each monitoring area. The specific analysis is as follows:

[0081] Extract the road status evaluation coefficient DLP of each monitoring area q and soil state assessment coefficient TCP q The value of is normalized according to the formula: Calculate the settlement state assessment coefficient CJQ of each monitoring area, where λ1 and λ2 represent the weight coefficients of the road state assessment coefficient and the soil state assessment coefficient respectively;

[0082] Set the settlement state assessment threshold of each monitoring area as CYY, compare and analyze the settlement state assessment coefficient CJQ of each monitoring area with the settlement state assessment threshold CYY, if the settlement state assessment coefficient CJQ of a monitoring area is greater than or equal to the settlement state assessment threshold CYY, then the monitoring area is judged to be in an abnormal settlement state, if the settlement state assessment coefficient CJQ of a monitoring area is less than the settlement state assessment threshold CYY, then the monitoring area is judged to be in a normal settlement state;

[0083] The monitoring area determined to be in an abnormal subsidence state is marked as an abnormal area;

[0084] The settlement degree analysis module is used to monitor the settlement status information of the abnormal area, thereby analyzing the settlement degree of the abnormal area. The specific analysis is as follows:

[0085] Settle settlement detection points in abnormal areas, thereby obtaining settlement detection points in abnormal areas, and obtain the elevation values ​​of settlement detection points corresponding to each monitoring time point within a period of time, marked as GC jh , where j represents the number of each monitoring time point within a period of time, and j = 1, 2, 3...n1, n1 represents the total number of numbers of each monitoring time point within a period of time, h represents the number of each settlement detection point, and h = 1, 2, 3...d, d represents the total number of numbers of each settlement detection point, and then obtain the basic elevation value of the abnormal area, marked as GC * , according to the formula: Calculate the settlement amount Ujl corresponding to each monitoring time point within a period of time j ;

[0086] Extract the settlement amount Ujl corresponding to each monitoring time point within a period of time j The value of is based on the formula: Calculate the sedimentation velocity Usd corresponding to each monitoring time point within a period of time j , where t (j,j-1) Indicates the monitoring duration between the jth monitoring time point and the j-1th monitoring time point within a period of time;

[0087] Extract the elevation value of each settlement detection point corresponding to each monitoring time point within a period of time, compare and analyze the elevation value of each settlement detection point corresponding to each monitoring time point within a period of time with the base elevation value. If the elevation value of a settlement detection point corresponding to each monitoring time point within a period of time is less than the base elevation value, then mark the settlement detection point corresponding to each monitoring time point within a period of time as an abnormal settlement detection point, integrate the abnormal settlement detection points, and obtain the settlement distribution area Ufm corresponding to each monitoring time point within a period of time. j ;

[0088] Extract the settlement amount Ujl corresponding to each monitoring time point within a period of time j , sedimentation velocity Usd j and sedimentation distribution area Ufm j The value of is normalized according to the formula: Calculate the settlement degree value Ψ of the abnormal area, where ζ represents a natural constant greater than zero, γ1, γ2 and γ3 represent the weight coefficients of settlement amount, settlement velocity and settlement distribution area respectively, and γ1>γ2>γ3;

[0089] Compare and analyze the settlement degree value of the abnormal area with the set reference comparison interval. If the settlement degree value of the abnormal area is less than the minimum value of the reference comparison interval, a third-level settlement warning signal is generated. If the settlement degree value of the abnormal area is within the reference comparison interval, a second-level settlement warning signal is generated. If the settlement degree value of the abnormal area is greater than the maximum value of the reference comparison interval, a first-level settlement warning signal is generated.

[0090] Sending the generated settlement warning level type signal to the warning execution module, wherein the settlement warning level type signal includes a third-level settlement warning signal, a second-level settlement warning signal and a first-level settlement warning signal;

[0091] The early warning execution module is used to receive the settlement early warning level type signal, and then perform early warning execution processing. The specific operation process is as follows:

[0092] If a level 3 settlement warning signal is detected, a vehicle limit instruction will be triggered. Based on the triggered vehicle limit instruction, the total number of vehicles entering the abnormal area will be limited to reduce the further pressure on the ground caused by the increase in the number of vehicles, thereby slowing down the settlement speed, protecting the safety of roads and infrastructure, and displaying a notification on the display terminal;

[0093] If a secondary settlement warning signal is captured, a heavy vehicle restriction instruction will be triggered. According to the triggered heavy vehicle restriction instruction, heavy vehicles are restricted from entering the abnormal area, which can effectively reduce the ground load and buy time for further emergency repairs and reinforcement work, and a notification will be displayed on the display terminal;

[0094] If a first-level settlement warning signal is captured, a traffic restriction instruction will be triggered. According to the triggered traffic restriction instruction, a comprehensive road blockade will be implemented in the abnormal area, and a display notification will be made on the display terminal;

[0095] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The road settlement monitoring, analysis and early warning system based on artificial intelligence is characterized by: include: The monitoring area division module is used to analyze the historical traffic parameters of the target monitoring road to obtain the division distance, and divide the target monitoring road into several equidistant areas according to the division distance, thereby obtaining each monitoring area; The influencing factor monitoring and analysis module is used to analyze the influencing factors of each monitoring area and obtain the influencing coefficient; The road state monitoring and analysis module is used to monitor the road state information of each monitoring area, obtain the use influence index and the road surface state evaluation index, and based on the influence coefficient, obtain the road state evaluation coefficient of each monitoring area; The soil layer status monitoring and analysis module is used to monitor the soil layer status information of each monitoring area, obtain the water content change assessment index, the pressure change assessment index and the falling object change assessment index, and based on the influence coefficient, obtain the soil layer status assessment coefficient of each monitoring area; The settlement area identification module is used to receive the road state assessment coefficient and the soil state assessment coefficient of each monitoring area, thereby making a judgment and analysis on each monitoring area to obtain an abnormal area; The settlement degree analysis module is used to monitor the settlement status information of the abnormal area, obtain the settlement amount, settlement velocity and settlement distribution area, thereby analyzing the settlement degree of the abnormal area and obtaining the settlement warning level type signal; The warning execution module is used to receive the settlement warning level type signal, thereby triggering the corresponding restriction instruction.

2. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The process of solving the partition distance is: Obtain the historical traffic parameters of the target monitored road, extract the traffic flow value, heavy vehicle proportion value and congestion value in the historical traffic parameters, perform normalization processing, and obtain the traffic load value; The traffic load value of the target monitored road is matched and analyzed with the traffic load status table stored in the system to obtain the traffic load level, and then matched with the division distance corresponding to the traffic load level to obtain the division distance.

3. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The process of solving the influence coefficient is: By obtaining the groundwater level, rainfall and load-bearing value of each monitoring area during the current monitoring period, the three values ​​are extracted and normalized to obtain the influence coefficient Δ q , q represents the number of each monitoring area, and q=1, 2, 3…m, m represents the total number of the monitoring area numbers.

4. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The solution process for the use impact index and road surface condition evaluation index is as follows: Obtain the historical use records of the roads in each monitoring area during the current monitoring period, and obtain the continuous use time of each historical use, calculate the average value thereof, obtain the average continuous use time of the roads in each monitoring area, and at the same time obtain the years of use of the roads in each monitoring area; The average continuous use time and years of use of roads in each monitoring area are normalized and their values ​​are taken to obtain the use impact index θ1 q ; By collecting the road surface images of each monitoring area in the current monitoring time period, the road surface images of each monitoring area in the current monitoring time period are obtained, and the number of bumps, the total area of ​​bumps, the number of cracks and the total length of cracks on the road surface of each monitoring area are obtained; The use impact index of each monitoring area is matched with the use impact index threshold value corresponding to the set use impact level to obtain the use impact level of each monitoring area, and it is matched with the reference road surface parameter set corresponding to the set use impact level to obtain the reference road surface parameter set of each monitoring area, and the reference bump number, reference bump total area, reference crack number and reference crack total length of the road surface of each monitoring area are extracted therefrom; The number of bumps, total bump area, number of cracks and total length of cracks, reference bump number, reference bump total area, reference crack number and reference crack total length of the road surface in each monitoring area are extracted for analysis and processing, thereby obtaining the road surface condition evaluation index θ2 q .

5. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The solution process for the road condition evaluation coefficient of each monitoring area is: Extract influence coefficient Δ q 、Use influence index θ1 q and road surface condition evaluation index θ2 q The value of is normalized according to the formula: Calculate the road status evaluation coefficient DLP of each monitoring area q , where η1 and η2 represent the correction coefficients of the influence index and the road surface condition evaluation index, respectively.

6. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The solution process for the water content change assessment index, pressure change assessment index and falling object change assessment index is as follows: The water content of the soil layer in each monitoring area during the current monitoring period is obtained by obtaining the water content of the soil layer in each monitoring area during the current monitoring period. i q The water content corresponding to the first monitoring time point is extracted from it as the initial water content Asz0 of the soil layer in each monitoring area during the current monitoring period. q ; According to the formula: Calculate the water content change assessment index δ1 q , where i represents the number of each monitoring time point in the current monitoring time period, and i = 1, 2, 3...n, n represents the total number of monitoring time point numbers in the current monitoring time period, Asz i-1 q represents the water content at the i-1th time point in the current monitoring period, and x1 and x2 represent the preset weight factors respectively; The same analysis method as above can be used to obtain the pressure change evaluation index δ2 q and the falling object change assessment index δ3 q .

7. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The solution process for the soil state assessment coefficient of each monitoring area is as follows: Extract influence coefficient Δ q , water content change assessment index δ1 q , Pressure change evaluation index δ2 q and the falling object change assessment index δ3 q The value of is normalized according to the formula: Calculate the soil state assessment coefficient TCP of each monitoring area q , where μ1, μ2, and μ3 represent the correction coefficients of the water content change assessment index, the pressure change assessment index, and the falling object amount change assessment index, respectively.

8. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The process of judging and analyzing each monitoring area is as follows: Extract the road status evaluation coefficient DLP of each monitoring area q and soil state assessment coefficient TCP q The value of is normalized according to the formula: Calculate the settlement state assessment coefficient CJQ of each monitoring area, where e represents a natural constant, and λ1 and λ2 represent the weight coefficients of the road state assessment coefficient and the soil layer state assessment coefficient, respectively; Set the settlement state assessment threshold of each monitoring area, compare and analyze the settlement state assessment coefficient of each monitoring area with the settlement state assessment threshold, and if the settlement state assessment coefficient of a monitoring area is greater than or equal to the settlement state assessment threshold, the monitoring area is judged to be in an abnormal settlement state; The monitoring area judged to be in an abnormal subsidence state is marked as an abnormal area.

9. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The solution process for settlement amount, settlement velocity and settlement distribution area is: Set up settlement detection points in the abnormal area, thereby obtaining the settlement detection points in the abnormal area, and obtaining the elevation values ​​of each settlement detection point corresponding to each monitoring time point within a period of time, marked as GC jh , where j represents the number of each monitoring time point within a period of time, and j = 1, 2, 3...n1, n1 represents the total number of numbers of each monitoring time point within a period of time, h represents the number of each settlement detection point, and h = 1, 2, 3...d, d represents the total number of numbers of each settlement detection point, and then obtain the basic elevation value of the abnormal area, marked as GC * , according to the formula: Calculate the settlement amount Ujl corresponding to each monitoring time point within a period of time j ; Extract the settlement amount Ujl corresponding to each monitoring time point within a period of time j The value of is based on the formula: Calculate the sedimentation velocity Usd corresponding to each monitoring time point within a period of time j , where t (j,j-1) Indicates the monitoring duration between the jth monitoring time point and the j-1th monitoring time point within a period of time; Extract the elevation value of each settlement detection point corresponding to each monitoring time point within a period of time, compare and analyze the elevation value of each settlement detection point corresponding to each monitoring time point within a period of time with the base elevation value. If the elevation value of a settlement detection point corresponding to each monitoring time point within a period of time is less than the base elevation value, then mark the settlement detection point corresponding to each monitoring time point within a period of time as an abnormal settlement detection point, integrate the abnormal settlement detection points, and obtain the settlement distribution area Ufm corresponding to each monitoring time point within a period of time. j .

10. The road subsidence monitoring, analysis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The process of analyzing the degree of subsidence in abnormal areas is as follows: Extract the settlement amount Ujl corresponding to each monitoring time point within a period of time j , sedimentation velocity Usd j and sedimentation distribution area Ufm j The value of is normalized according to the formula: The settlement degree value Ψ of the abnormal area is calculated, where ζ represents a natural constant greater than zero, and γ1, γ2 and γ3 represent the weight coefficients of settlement amount, settlement velocity and settlement distribution area respectively; Compare and analyze the settlement degree value of the abnormal area with the set reference comparison interval. If the settlement degree value of the abnormal area is less than the minimum value of the reference comparison interval, a third-level settlement warning signal is generated. If the settlement degree value of the abnormal area is within the reference comparison interval, a second-level settlement warning signal is generated. If the settlement degree value of the abnormal area is greater than the maximum value of the reference comparison interval, a first-level settlement warning signal is generated. The generated third-level settlement warning signal, second-level settlement warning signal and first-level settlement warning signal constitute the settlement warning level type signal.

Images