Road surface condition monitoring system based on multi-source data

Abstract

The invention discloses a pavement condition monitoring system based on multi-source data, which belongs to the technical field of pavement monitoring and comprises a multi-source data acquisition layer for acquiring data information related to pavement conditions; the data transmission layer is used for primarily processing the acquired data information and uploading the data information to the data analysis layer; the data analysis layer is used for analyzing and calculating the acquired data information so as to judge whether the pavement condition is abnormal or not; and the alarm layer is used for performing response alarm on the pavement which is judged to be abnormal in pavement condition. According to the invention, a multi-source data fusion technology is adopted, the data information related to the road surface condition is obtained from different channels, the data information is processed, whether the appearance abnormity or hidden abnormity exists in the monitored road surface is judged according to the data information, the road surface condition can be accurately known without manual inspection, and the detection efficiency is improved. And high-frequency and comprehensive monitoring of a large-area road can be realized, so that the accuracy of road surface monitoring is greatly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of pavement monitoring, and particularly relates to a pavement condition monitoring system based on multi-source data. Background Art

[0002] As a key component of the transportation network, roads are an important support for the development of the national economy and the normal operation of social activities. A good pavement condition plays a decisive role in ensuring traffic safety, improving transportation efficiency, reducing transportation costs, and enhancing travel comfort. However, with the continuous growth of traffic flow, the continuous increase in vehicle load, and the long-term influence of natural environment and other factors, roads are facing severe tests. Pavement diseases such as cracks, potholes, and ruts frequently appear, which not only affect the service life of the road but also increase the risk of traffic accidents. Therefore, accurately and timely grasping the pavement condition is crucial for road maintenance and management.

[0003] Currently, most of the monitoring of pavement conditions is carried out through manual inspections or through the alarms of drivers on the road. However, due to the physical strength and time limitations of maintenance personnel, it is difficult to achieve high-frequency and comprehensive monitoring of large areas of roads, resulting in poor timeliness; in addition, when monitoring pavement conditions currently, most can only find obvious abnormal places on the road surface. For some minor diseases or diseases hidden inside the pavement structure, it is difficult to be discovered by manual inspections, and effective maintenance measures cannot be taken in time, thus accelerating road damage. Summary of the Invention

[0004] The purpose of the present invention is to provide a pavement condition monitoring system based on multi-source data to solve the problems faced in the above background art.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A pavement condition monitoring system based on multi-source data, the monitoring system includes:

[0007] A multi-source data acquisition layer, which is used to acquire data information related to pavement conditions from different channels;

[0008] A data transmission layer, which is used to upload the acquired data information to the data analysis layer after preliminary processing;

[0009] A data analysis layer, which is used to analyze and calculate the acquired data information to determine whether the pavement condition is abnormal;

[0010] An alarm layer, which is used to respond and alarm the pavement with abnormal pavement conditions.

[0011] Further, the data information includes image information of the monitored road surface, pressure information of the monitored road surface, deformation information, vehicle vibration information passing through the monitored road surface, braking conditions, traffic information at the monitored road surface, and weather information.

[0012] Further, the working method of the data analysis layer is as follows:

[0013] Divide the road surface in the monitoring area into multiple monitoring sections, use drone technology to obtain road surface photos of each monitoring section, and input the obtained road surface photos into a road surface model library trained by a convolutional neural network. The road surface model library contains a large number of road surface images under normal conditions, so as to obtain an output result. If the output result is no, it is determined that the road surface condition of this monitoring section is abnormal and marked as a road surface with abnormal appearance.

[0014] Further, the working method of the data analysis layer also includes:

[0015] When it is not determined that the road surface condition is abnormal, at this time, according to the historical data information of each monitoring section, within the monitoring period t n According to the obtained vibration condition value K VF of each monitoring section, pressure condition value K P and wear condition value K W , thus calculate the hidden danger coefficient K through the formula

[0016] ;

[0017] Compare the hidden danger coefficient K with the set hidden danger coefficient judgment threshold K TF :

[0018] When K > K TF , it is determined that the road surface condition of this monitoring section is abnormal and marked as a hidden abnormal road surface;

[0019] Among them, μ emp is the environmental impact coefficient, and τ1, τ2, and τ3 are preset proportionality coefficients.

[0020] Further, the obtaining methods of the vibration condition value K VF and the wear condition value K W are as follows:

[0021] Obtain the vibration frequency of the vehicles passing through this monitoring section every day. The vibration frequency is obtained through vibration sensors installed on the vehicles, so as to obtain the average daily vibration frequency VF. Within the monitoring period t n , draw a curve function VF(d) of the average daily vibration frequency changing with the number of days, and through the formula

[0022] Get the vibration condition value K VF , where γ d VF is the number of days during the monitoring period when the daily average vibration frequency exceeds the average daily average vibration frequency, m is the total number of days during the monitoring period, and i is the average daily vibration frequency obtained on the ith day, and i∈[1, m], VF TH is the standard vibration frequency preset by the system, d1 is the first day of the monitoring period, d2 is the last day of the monitoring period, α1 and α2 are proportional coefficients;

[0023] At the same time, the number of brakes of each vehicle passing through the monitoring section every day is obtained, so as to obtain the average daily brake number W B , obtain the traffic volume W passing through the monitoring section every day Q , through the formula Obtain the wear condition value K W , where T a is the number of traffic accidents in the monitoring area during the monitoring period, W Bi is the average number of daily braking times obtained in the i-th day, W Qi is the traffic flow of the i-th day.

[0024] Furthermore, the pressure condition value K P The acquisition method is:

[0025] n monitoring points are set in the monitoring section, each of which is equipped with a pressure sensor. Get the pressure status value P of the jth monitoring point j , and then through the formula Get the pressure state value K P ;

[0026] Among them, t1 is the monitoring period t n The start time of t2 is the monitoring period t n The end time, P j (t) is the pressure variation curve function of the jth monitoring point, P jth (t) is the standard curve function of pressure variation with time proposed for the jth monitoring point, β1 and β2 are weight coefficients, max{P, t n} is the monitoring period t n Maximum pressure condition value within.

[0027] Furthermore, the environmental impact coefficient μ emp The acquisition method is:

[0028] According to the historical weather information of the monitoring area, obtain the number of days with high temperature in the previous G days D TG 、Number of low temperature days D TD 、Acid rain days DR , and the average ultraviolet intensity U within the previous G days c and the average sunshine duration S T ;

[0029] Through the formula the environmental impact coefficient μ is obtained emp ;

[0030] where U c0 is the ultraviolet intensity reference value, and S T0 is the sunshine duration reference value.

[0031] Furthermore, the working method of the warning layer is as follows:

[0032] When it is determined that there is an abnormal situation in the road surface condition of this monitoring section and it is an abnormally surfaced road, a reminder of abnormal road surface appearance is generated, and at the same time, the defect type of the abnormal road surface is judged according to the AI algorithm;

[0033] When it is determined that there is an abnormal situation in the road surface condition of this monitoring section and it is a hidden abnormal road surface, a reminder of hidden road surface abnormality is generated, and at the same time, the problem location area is located and professional personnel are dispatched for further inspection and processing.

[0034] Advantages of the present invention:

[0035] The present invention adopts a multi-source data fusion technology to obtain data information related to the road surface condition from different channels, thereby processing these data information and judging whether there is an abnormal appearance or a hidden abnormality in the monitored road surface according to these data information. It can accurately understand the road surface condition without manual inspection, and can achieve high-frequency and comprehensive monitoring of large-area roads, thus greatly improving the accuracy of road surface monitoring.

[0036] The present invention can not only judge the obvious abnormalities that have occurred on the road surface, but also comprehensively analyze according to the vibration condition, pressure condition, wear condition of the road surface and the environmental conditions of the area where it is located, monitor the hidden, invisible or potential abnormal phenomena on the road surface, and can more accurately grasp the road surface condition, so as to timely formulate scientific and reasonable maintenance strategies to ensure the safety and service life of the road.

[0037] Of course, it is not necessary for any product implementing the present invention to simultaneously achieve all the above-mentioned advantages. Description of the Drawings

[0038] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0039] Figure 1 It is the system block diagram of the present invention. Specific implementation manners

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0041] In one embodiment, a road surface condition monitoring system based on multi-source data is disclosed, as Figure 1 shown. The monitoring system includes:

[0042] The multi-source data acquisition layer is used to obtain data information related to the road surface condition from different channels. The data information includes image information of the monitored road surface, pressure information of the monitored road surface, deformation information, vehicle vibration information passing through the monitored road surface, braking conditions, traffic information at the monitored road surface, and weather information;

[0043] The data transmission layer is used to upload the obtained data information to the data analysis layer after preliminary processing;

[0044] The data analysis layer is used to analyze and calculate the obtained data information to determine whether the road surface condition is abnormal;

[0045] The alarm layer is used to respond and alarm the road surface determined to have an abnormal road surface condition.

[0046] The present application adopts multi-source data fusion technology to obtain data information related to road conditions from different channels, including image information of the monitored road surface, pressure information of the monitored road surface, deformation information, vibration information of vehicles passing through the monitored road surface, braking conditions, traffic information at the monitored road surface, and weather information, etc., so as to process these data information, including data cleaning, compression and format conversion, normalization and other processing steps, and then judge whether there are appearance abnormalities or hidden abnormalities on the monitored road surface according to the data analysis layer. It can accurately understand the condition of the road surface without manual inspection, and can realize high-frequency and comprehensive monitoring of large-area roads, thereby greatly improving the accuracy of road surface monitoring; in addition, the present application can not only judge the obvious abnormalities that have appeared on the road surface through the data analysis layer, but also comprehensively analyze the vibration condition, pressure condition, wear condition of the road surface and the environmental conditions of the area, and monitor the hidden, invisible or potential abnormal phenomena of the road surface, so as to more accurately grasp the condition of the road surface, so as to formulate scientific and reasonable maintenance strategies in time to ensure the safety and service life of the road.

[0047] The working method of the data analysis layer is: divide the road surface in the monitoring area into multiple monitoring sections, use drone technology to obtain road surface photos of each monitoring section, and input the acquired road surface photos into the road surface model library trained by convolutional neural network. The road surface model library contains a large number of normal and abnormal road surface images, so as to obtain the output result. If the output result is no, it is judged that the road surface condition of the monitoring section is abnormal and marked as abnormal road surface.

[0048] The above technical solution provides a specific method for the data analysis layer to determine whether there are obvious abnormalities in the appearance of the road surface. First, a large number of road surface images are collected, and a road surface model library is trained through a convolutional neural network. The road surface in the monitoring area is divided into multiple monitoring sections. Unmanned aerial vehicle technology is used to obtain road surface photos of each monitoring section. The acquired road surface photos are input into the road surface model library trained by the convolutional neural network. If the output result is no, it is determined that there are abnormalities in the road condition of the monitoring section and marked as an abnormal road surface. In this way, the more obvious abnormalities on the road surface can be quickly judged, and the location of the abnormality can be understood, so as to quickly repair and ensure the quality of the road. The entire road surface can be analyzed and judged based on the acquired image information, without the need for manual inspection, and the monitoring is more comprehensive.

[0049] The working method of the data analysis layer also includes: when the road condition is not judged to be abnormal, according to the historical data information of each monitoring section, in the monitoring period t n According to the vibration condition value K of each monitoring section, VF , pressure state value K P And the wear condition value KW , so as to calculate the hidden danger coefficient K through the formula ;

[0050] Compare the hidden danger coefficient K with the set judgment threshold K of the hidden danger coefficient TF :

[0051] When K > K TF , it is determined that the road surface condition in this monitoring section is abnormal and marked as a hidden abnormal road surface;

[0052] Among them, μ emp is the environmental impact coefficient, and τ1, τ2, and τ3 are preset proportionality coefficients;

[0053] The vibration condition value K VF and the wear condition value K W The acquisition method is as follows: Obtain the vibration frequency of the vehicles passing through this monitoring section every day. The vibration frequency is obtained through the vibration sensors installed on the vehicles, so as to obtain the average daily vibration frequency VF. During the monitoring period t n , draw the curve function VF(d) of the average daily vibration frequency changing with the number of days. Through the formula

[0054] Obtain the vibration condition value K VF , where γ d is the number of days when the average daily vibration frequency in the monitoring period exceeds the average average daily vibration frequency, m is the total number of days in the monitoring period, VF i is the average daily vibration frequency obtained on the i-th day, and i ∈ [1, m], VF TH is the standard vibration frequency preset by the system, d1 is the first day in the monitoring period, d2 is the last day in the monitoring period, and α1 and α2 are proportionality coefficients;

[0055] At the same time, obtain the number of braking times of each vehicle passing through this monitoring section every day, so as to obtain the average daily braking times W B , obtain the traffic flow W of the vehicles passing through this monitoring section every day Q , and obtain the wear condition value K through the formula ; W , where T a is the number of traffic accidents occurring in this monitoring area during the monitoring period, W Bi is the average daily braking times obtained on the i-th day, and W Qi is the traffic flow on the i-th day;

[0056] Set n monitoring points in the monitoring section, and a pressure sensor is installed at each monitoring point. Through the formula Obtain the pressure condition value P of the j-th monitoring point j , and then through the formula Obtain the pressure condition value K P ; where t1 is the start time of the monitoring period t n and t2 is the end time of the monitoring period t n , P j (t) is the function of the pressure varying with time formulated for the j-th monitoring point, and P jth (t) is the standard curve function of the pressure varying with time formulated for the j-th monitoring point. β1 and β2 are weight coefficients, and max{P, t n} is the maximum pressure condition value within the monitoring period t n ;

[0057] According to the historical weather information of the monitoring area, obtain the number of days D of high temperature, the number of days D of low temperature, and the number of days D of acid rain within the previous G days TG , as well as the average ultraviolet intensity U TD and the average sunshine duration S R within the previous G days c ; T

[0058] Obtain the environmental impact coefficient μ through the formula ; emp

[0059] where U c0 is the reference value of ultraviolet intensity, and S T0 is the reference value of sunshine duration

[0060] The above solution provides a method for the data analysis layer to judge hidden anomalies on the road surface. Generally speaking, when there are hidden anomalies on the road surface, the vehicle vibration frequency, road surface pressure, and road surface wear condition will all change. For example, when a vehicle has abnormal high-frequency vibrations when driving on a certain specific section of the road, this may be due to undetected small potholes or cracks on this section. Similarly, if the pressure readings at some monitoring points on the road surface exceed the design standard for a long time, it indicates that this section of the road may need to be strengthened in maintenance, and the greater the possibility of anomalies. Similarly, high-density traffic flow and frequent braking will cause accelerated wear of local road surfaces. Therefore, when the road surface condition is not judged to be abnormal, at this time, according to the historical data information of each monitoring section, a monitoring period t n is set. Within the monitoring period t n , according to the obtained vibration condition value K VF , pressure condition value K P and wear condition value K W of each monitoring section, and then through the formula

[0061] ​​Calculate the hidden danger coefficient K, and combine the environmental impact to judge the hidden condition of the road surface. Obviously, the larger the value of the hidden danger coefficient K, the greater the possibility of hidden anomalies on the road surface. Therefore, compare the hidden danger coefficient K with the set hidden danger coefficient judgment threshold K TF for comparison. The hidden danger coefficient judgment threshold K TF and each preset proportional coefficient are determined according to empirical data. When K > K TF , it is determined that there is an abnormal condition in the road surface of this monitoring section and it is marked as a hidden abnormal road surface. In this way, through comprehensive analysis based on the vibration condition, pressure condition, wear condition of the road surface and the environmental conditions of the area where it is located, the hidden, invisible or potential abnormal phenomena of the road surface can be monitored, and the condition of the road surface can be grasped more accurately, so as to formulate a scientific and reasonable maintenance strategy in a timely manner to ensure the safety and service life of the road.

[0062] Obtain the vibration frequency of the vehicles passing through this monitoring section every day. The vibration frequency is obtained through the vibration sensors installed on the vehicles, so as to obtain the average daily vibration frequency VF. During the monitoring period t n , formulate the curve function VF(d) of the average daily vibration frequency changing with the number of days. Through the formula

[0063] obtain the vibration condition value K VF , where γ d is the number of days when the average daily vibration frequency exceeds the average average daily vibration frequency during the monitoring period, m is the total number of days during the monitoring period, VF i is the average daily vibration frequency obtained on the i-th day, and i ∈ [1, m], VF TH is the standard vibration frequency preset by the system, which is determined according to the historical data of the road surface. α1 and α2 are proportional coefficients, which are determined according to experience. It can be seen from the formula that the larger the vibration condition value, the greater the possibility of hidden anomalies existing on this road surface. Similarly, obtain the number of braking times of each vehicle passing through this monitoring section every day. Data information such as the number of braking times and traffic flow can be obtained from the vehicle networking system, so as to obtain the average daily braking number W B , obtain the traffic flow W Q passing through this monitoring section every day. Through the formula

[0064] obtain the wear condition value K W , where T a is the number of traffic accidents occurring in this monitoring area during the monitoring period, Wx i is the average daily braking number obtained on the i-th day, W Qiis the traffic volume of the ith day; from the formula, it can be seen that the more traffic times occur during the monitoring period, the higher the braking frequency, and the larger the traffic volume, the greater the wear on the road surface, indicating that the possibility of hidden abnormalities is greater. Therefore, when the wear condition value K W The larger the value is, the greater the possibility of hidden abnormalities in the road surface; similarly, n monitoring points are set in the monitoring section, and each monitoring point is equipped with a pressure sensor. Get the pressure status value P of the jth monitoring point j , and then through the formula Get the pressure state value K P ; Among them, P j (t) is the pressure variation curve function of the jth monitoring point, P jth (t) is the standard curve function of pressure variation over time proposed for the jth monitoring point, which is proposed based on the historical data of the road surface. β1 and β2 are weight coefficients, which are determined based on experience. From the formula, it can be seen that the more the pressure change exceeds the standard pressure change, the greater the possibility of hidden abnormalities in the road surface. Therefore, when the pressure condition value K P The larger the value, the greater the possibility of hidden abnormalities in the road surface. The possibility of abnormalities in the road surface is also related to bad weather. For example, high temperature, low temperature, acid rain, etc. will accelerate the damage of the road surface. High radiation or long-term light will also accelerate the aging of the road surface. Therefore, according to the historical weather information of the monitoring area, the number of days with high temperature in the previous G days is obtained. TG 、Number of low temperature days D TD 、Acid rain days D R , and the average UV intensity U in the previous G days c And the average sunshine duration S T ; Through the formula

[0065] The environmental impact coefficient μ is obtained emp , where U c0 is the reference value of ultraviolet intensity, S T0 The reference values ​​of sunshine duration can be determined based on empirical data. From the formula, it can be seen that the larger the environmental impact coefficient value, the greater the impact on the road surface, and the greater the possibility of hidden abnormalities on the road surface. The vibration condition value K is obtained by the above method. VF , wear condition value K W , pressure state value K P , Environmental impact coefficient μ emp , and conduct comprehensive analysis to judge the hidden abnormal conditions of the road surface, which can greatly improve the monitoring accuracy and grasp the road condition more accurately.

[0066] The working method of the alarm layer is as follows: When it is determined that the road surface condition in the monitored section is abnormal and it is an externally abnormal road surface, a reminder of the externally abnormal road surface is generated, and at the same time, the defect type of the abnormal road surface is judged according to the AI algorithm;

[0067] When it is determined that the road surface condition in the monitored section is abnormal and it is a hidden abnormal road surface, a reminder of the hidden abnormal road surface is generated, and at the same time, the problem location area is located and professional personnel are dispatched for further detection and processing.

[0068] The above technical solution provides the specific working mode of the alarm layer. When it is determined that the road surface condition in the monitored section is abnormal and it is an externally abnormal road surface, a reminder of the externally abnormal road surface is generated, and at the same time, the defect type of the abnormal road surface is judged according to the AI algorithm. This can remind the maintenance management personnel of the specific defect type of the abnormal road surface, facilitating better maintenance by the maintenance personnel; when it is determined that the road surface condition in the monitored section is abnormal and it is a hidden abnormal road surface, a reminder of the hidden abnormal road surface is generated, and at the same time, the problem location area is located and professional personnel are dispatched for further detection and processing.

[0069] It should be noted that for the convenience of calculation and processing, the above calculation methods are all dimensionless calculations after processing, and the specific method of dimensionless processing is solved by the existing technology and will not be elaborated here.

[0070] The above content is only an example and explanation of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by this claim book, they should all belong to the protection scope of the present invention.

Claims

1. A road surface condition monitoring system based on multi-source data, characterized in that, The monitoring system includes: A multi-source data acquisition layer, which is used to obtain data information related to road surface conditions from different channels; A data transmission layer, which is used to upload the acquired data information to the data analysis layer after preliminary processing; A data analysis layer, which is used to analyze and calculate the acquired data information to determine whether the road surface condition is abnormal; An alarm layer, which is used to respond and alarm the road surface judged to have abnormal road surface conditions.

2. The pavement condition monitoring system based on multi-source data according to claim 1, characterized in that, The data information includes image information of the monitored road surface, pressure information of the monitored road surface, deformation information, vehicle vibration information passing through the monitored road surface, braking conditions, traffic information at the monitored road surface, and weather information.

3. A pavement condition monitoring system based on multi-source data according to claim 2, characterized in that, The working method of the data analysis layer is as follows: The road surface of the monitoring area is divided into multiple monitoring sections. The unmanned aerial vehicle technology is used to obtain road surface photos of each monitoring section, and the obtained road surface photos are input into the road surface model library trained by the convolutional neural network. The road surface model library contains a large number of road surface images under normal conditions, so as to obtain the output result. If the output result is negative, it is judged that there is an abnormal situation in the road surface condition of this monitoring section and it is marked as an abnormally-appearing road surface.

4. A pavement condition monitoring system based on multi-source data according to claim 3, characterized in that, The working method of the data analysis layer further includes: When the abnormal road surface condition is not detected, according to the historical data information of each monitoring section at this time, within the monitoring period t n According to the vibration condition value K of each monitoring section obtained VF , the pressure condition value K P And the wear condition value K W , thus through the formula Calculate the hidden danger coefficient K; Compare the hidden danger coefficient K with the set judgment threshold K of the hidden danger coefficient TF as follows: When K > K TF , it is determined that there is an abnormal situation in the road surface condition of the monitoring section, and it is marked as a hidden abnormal road surface; Among them, μ emp is the environmental impact coefficient, and τ1, τ2, and τ3 are preset proportionality coefficients.

5. The pavement condition monitoring system based on multi-source data according to claim 4, characterized in that, The vibration condition value K VF and the wear condition value K W are obtained as follows: Obtain the vibration frequency of vehicles passing through the monitoring section daily. The vibration frequency is obtained through vibration sensors installed on the vehicles, so as to obtain the average daily vibration frequency VF. During the monitoring period t n , formulate the curve function VF(d) of the average daily vibration frequency varying with the number of days, through the formula Obtain the vibration condition value K VF , where γ d is the number of days when the daily average vibration frequency exceeds the average daily average vibration frequency within the monitoring period, m is the total number of days within the monitoring period, VF i is the daily average vibration frequency obtained on the i-th day, and i ∈ [1, m], VF TH is the standard vibration frequency preset by the system, d1 is the first day within the monitoring period, d2 is the last day within the monitoring period, and α1 and α2 are proportionality coefficients; Simultaneously obtain the number of brake applications of each vehicle passing through the monitoring section daily, so as to obtain the average daily number of brake applications W B , obtain the traffic flow W of vehicles passing through the monitoring section daily Q , through the formula obtain the wear condition value K W , where T a is the number of traffic accidents occurring in the monitoring area during the monitoring period, W Bi is the average daily number of brake applications obtained on the i-th day, W Qi is the traffic flow on the i-th day.

6. The pavement condition monitoring system based on multi-source data according to claim 4, characterized in that The pressure condition value K P The acquisition method is as follows: Set n monitoring points in the monitoring section, and a pressure sensor is installed at each monitoring point. Through the formula obtain the pressure condition value P of the j-th monitoring point j , and then through the formula obtain the pressure condition value K P ; Among them, t1 is the monitoring period t n The start time of t2 is the monitoring period t n The end time, P j (t) is the pressure variation curve function of the jth monitoring point, P jth (t) is the standard curve function of pressure variation with time proposed for the jth monitoring point, β1 and β2 are weight coefficients, max{P, t n } is the monitoring period t n Maximum pressure condition value within.

7. A pavement condition monitoring system based on multi-source data according to claim 4, characterized in that, The environmental impact coefficient μ emp The acquisition method is as follows: Obtain the number of days D with high temperature, the number of days D with low temperature, the number of days D with acid rain within the previous G days according to the historical weather information of the monitoring area, as well as the average ultraviolet intensity U and the average sunshine duration S within the previous G days; TG and the number of days D with low temperature TD and the number of days D with acid rain R , as well as the average ultraviolet intensity U within the previous G days c and the average sunshine duration S T ; Through the formula the environmental impact coefficient μ is obtained emp ; Among them, U c0 is the ultraviolet intensity reference value, and S T0 is the sunshine duration reference value.

8. A pavement condition monitoring system based on multi-source data according to claim 1, characterized in that, The working method of the alarm layer is as follows: When it is judged that there is an abnormal situation in the road surface condition of this monitoring section and it is an abnormally-appearing road surface, a road surface appearance abnormality reminder is generated, and at the same time, the defect type of the abnormal road surface is judged according to the AI algorithm; When it is judged that there is an abnormal situation in the road surface condition of this monitoring section and it is a hidden-abnormality road surface, a road surface hidden-abnormality reminder is generated, and at the same time, the problem location area is located and professional personnel are dispatched for further detection and processing.

Images