Ground surface crack monitoring device

Abstract

The invention discloses a surface crack monitoring device, which relates to the field of geological engineering monitoring, and comprises the following steps: 1, installing a temperature and humidity sensor, a rain gauge and an optical fiber strain sensor at a surface crack monitoring point, and regularly monitoring and transmitting data to a cloud end by using a wireless sensor network, and real-time monitoring and recording of the ground surface crack monitoring point environment and crack deformation are realized. The temperature and humidity sensor, the rain gauge and the optical fiber strain sensor are installed at the monitoring points, timely recording of crack deformation and environmental conditions is ensured, the influence of the crack deformation and environmental conditions on earth surface cracks is comprehensively analyzed, smoothing processing is conducted on collected data through moving average filtering, and by calculating the Pearson's correlation coefficient, the earth surface crack detection accuracy is improved. The influence degree of temperature, humidity and rainfall changes on crack deformation is evaluated, a ridge regression model is applied to predict the crack deformation width, a visual interface is created, the change state and meteorological data of a monitoring point are displayed, and the change condition of the crack position is visually presented in combination with GPS positioning.

Description

Technical Field

[0001] The invention relates to the field of geological engineering monitoring, and in particular to a surface crack monitoring device. Background Art

[0002] As global urbanization accelerates, infrastructure construction is advancing by leaps and bounds, increasing the demand for land and natural resources. While this rapid development has promoted economic growth, it has also brought potential risks such as surface deformation and cracks. With the increasing number of buildings, roads, bridges and high-rise buildings, it is particularly important to ensure the safety and durability of these infrastructures.

[0003] The impact of natural factors on surface cracks cannot be ignored. Climate change has led to the frequent occurrence of extreme weather events, and the rapid changes in soil moisture have seriously threatened the stability of the surface, which in turn has caused the formation of cracks. Timely monitoring of potential cracks can minimize the risks caused by structural damage and help to formulate effective response measures and maintenance plans.

[0004] The existing technology has the following deficiencies: Traditional monitoring methods mainly rely on manual inspections, and the real-time implementation is extremely limited. The data update frequency of this monitoring mode is low, and it is difficult to capture the ever-changing crack status, resulting in a lack of timeliness of the data. In data processing, there is often a lack of systematicity, and it is easily affected by environmental interference, resulting in noise and duplicate data, making the final analysis results inaccurate. In the absence of effective filtering and cleaning mechanisms, the reliability of the data is questioned, further reducing the effectiveness of monitoring. There are deficiencies in feature extraction, and the complex relationship between environmental factors such as temperature and humidity changes and rainfall and crack deformation has not been deeply explored. The lack of modular design leads to insufficient flexibility and scalability, reducing the long-term value of monitoring. The existing prediction models are usually relatively simple and fail to fully consider complex environmental factors, resulting in insufficient prediction accuracy of crack deformation. In a rapidly changing environment, this limitation may lead to misjudgment of crack development, and the lack of intuitiveness in data display makes it difficult for users to quickly understand and respond.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a surface crack monitoring device to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a surface crack monitoring device, specifically comprising the following steps:

[0008] Step 1: Install temperature and humidity sensors, rain gauges and optical fiber strain sensors at the surface crack monitoring points, and use wireless sensor networks to regularly monitor and transmit data to the cloud to achieve real-time monitoring and recording of the environment and crack deformation at the surface crack monitoring points;

[0009] Step 2: Smooth and fill the cleaning temperature and humidity change data, rainfall change data and crack deformation data through moving average filtering, identify and delete duplicate records, use weighted average to achieve normalization, and extract temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics through first-order difference;

[0010] Step 3: Calculate the Pearson correlation coefficient and evaluate the influence of temperature and humidity change characteristics and rainfall change characteristics on crack deformation characteristics according to contribution degree and weight;

[0011] Step 4: Connect the temperature and humidity change data, rainfall change data and crack deformation data according to the sensor monitoring timestamp, construct a design matrix, and use the closed-form solution formula of ridge regression to calculate the regression coefficient vector to predict the crack deformation width;

[0012] Step 5: Create a visualization interface to display the current status of the surface crack monitoring points and the current meteorological changes in temperature and humidity, and compare the changes in the crack locations with GPS positioning.

[0013] Preferably, temperature and humidity sensors, rain gauges and optical fiber strain sensors are installed at the surface crack monitoring points, integrated into a modular framework, and timers are set according to the microcontrollers inside the temperature and humidity sensors, rain gauges and optical fiber strain sensors to monitor once per hour. The wireless communication modules inside the temperature and humidity sensors, rain gauges and optical fiber strain sensors are mapped as wireless nodes to the key nodes of the surface crack monitoring points to form a wireless sensor network to transmit the monitoring data to the cloud for storage.

[0014] Preferably, moving average filtering is used to smooth the temperature and humidity change data, rainfall change data and crack deformation data to reduce the impact of random noise, and filling and cleaning are performed according to the central values ​​of the temperature and humidity change data, rainfall change data and crack deformation data respectively. According to the records of the timestamp and sensor ID field, completely identical records are identified and deleted, and only partially repeated records are identified and merged through a time window. The temperature and humidity change data, rainfall change data and crack deformation data are normalized by weighted average based on the proportion of the temperature and humidity change data, rainfall change data and crack deformation data, and the temperature and humidity change data, rainfall change data and crack deformation data are converted into structured data, and the temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics are extracted by first-order differences.

[0015] Preferably, the influence of the crack deformation characteristics is determined by selecting the correlation between the temperature and humidity change characteristics and the rainfall change characteristics through the Pearson correlation coefficient, and the specific formula is:

[0016]

[0017] Where r represents the Pearson coefficient, W Z X,Y Indicates the contribution of temperature and humidity change characteristics and rainfall change characteristics to crack deformation characteristics, W Z X , W Z Y They represent the weight coefficients of temperature and humidity change characteristics and rainfall change characteristics for crack deformation characteristics, X represents temperature and humidity change characteristics, Y represents rainfall change characteristics, and Z represents crack deformation characteristics. Represents the mean of the temperature and humidity change characteristics, The mean value representing the rainfall variation characteristics.

[0018] Preferably, the temperature and humidity change data, the rainfall change data and the crack deformation data are connected according to the sensor monitoring timestamp, the temperature and humidity change characteristics and the rainfall change characteristics are combined into a design matrix, the regression coefficient is initialized to a zero vector, the optimal regularization parameter value is selected through cross-validation, and the closed-form solution formula of ridge regression is used to calculate the regression coefficient vector of the crack deformation characteristics. The specific formula is:

[0019]

[0020] Among them, β represents the regression coefficient vector of crack deformation characteristics, A represents the design matrix, α represents the regularization parameter in ridge regression, and B represents the crack deformation characteristics. The crack deformation width is predicted by the regression coefficient vector of crack deformation characteristics and the temperature and humidity change characteristics and rainfall change characteristics.

[0021] Preferably, a visualization interface is created to display the current change status of the surface crack monitoring points and the current meteorological changes in temperature and humidity. A line graph is used to display the trend of surface cracks changing with the corresponding sensor monitoring timestamp and the predicted crack deformation width. A heat map is used to display the overall situation of multiple surface cracks, and the severity of the surface cracks is reflected by the depth of color. The GPS is connected to compare the surface crack position positioning of the previous corresponding sensor monitoring timestamp and the surface crack position positioning of the current corresponding sensor monitoring timestamp to intuitively display the changes in the surface cracks.

[0022] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0023] 1. By integrating temperature and humidity sensors, rain gauges, and optical fiber strain sensors into a modular framework, environmental changes and the status of surface cracks can be monitored in real time. Each sensor is equipped with a microcontroller and a timer, which enables data collection once an hour to ensure the timeliness and continuity of the data; the wireless communication module inside the sensor is used as a wireless node to transmit the monitoring data to the cloud for storage through the wireless sensor network. It not only improves the efficiency of data transmission, but also enhances flexibility, and more monitoring points can be expanded at any time as needed; by storing data in the cloud, monitoring information can be accessed anytime and anywhere, thus realizing remote monitoring and management.

[0024] 2. Use moving average filtering to smooth the temperature and humidity change data, rainfall change data and crack deformation data to reduce the impact of random noise and ensure the stability of the data. Fill and clean the data according to the central value of the temperature and humidity change data, rainfall change data and crack deformation data to ensure the integrity of the data. Through the records of timestamp and sensor ID fields, the system can identify exactly the same records and delete them. At the same time, for only partially repeated records, the system will merge them through the time window to ensure the accuracy and consistency of the data. The weighted average method is used to normalize the temperature and humidity change data, rainfall change data and crack deformation data according to the proportion, so that different types of data can be compared and analyzed under the same standard. The temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics are extracted by first-order difference, and the relationship between these characteristics can be deeply analyzed. The Pearson correlation coefficient is used to analyze the influence of temperature and humidity change characteristics and rainfall change characteristics on crack deformation characteristics, thereby providing a scientific basis for the prediction of crack deformation. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0026] Figure 1 The present invention is a method flow chart of a surface crack monitoring device. DETAILED DESCRIPTION

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0028] The present invention provides Figure 1 A surface crack monitoring device shown in the figure specifically comprises the following steps:

[0029] Step 1: Install temperature and humidity sensors, rain gauges and optical fiber strain sensors at the surface crack monitoring points, and use wireless sensor networks to regularly monitor and transmit data to the cloud to achieve real-time monitoring and recording of the environment and crack deformation at the surface crack monitoring points;

[0030] Temperature and humidity sensors, rain gauges and optical fiber strain sensors are installed at the surface crack monitoring points, integrated into a modular framework, and timers are set according to the microcontrollers inside the temperature and humidity sensors, rain gauges and optical fiber strain sensors to monitor once an hour. The wireless communication modules inside the temperature and humidity sensors, rain gauges and optical fiber strain sensors are mapped as wireless nodes to the key nodes of the surface crack monitoring points to form a wireless sensor network to transmit the monitoring data to the cloud for storage.

[0031] The temperature and humidity sensor is used to monitor the temperature and humidity change data of the surface crack monitoring point in real time. The rain gauge is used to monitor the rainfall change data of the surface crack monitoring point in real time. The optical fiber strain sensor is used to monitor the crack deformation data of the surface crack monitoring point in real time, and record the sensor ID field and the corresponding sensor monitoring timestamp.

[0032] By installing temperature and humidity sensors, rain gauges and fiber optic strain sensors at surface crack monitoring points, real-time temperature and humidity change data, rainfall change data and crack deformation data are obtained to ensure the timeliness and accuracy of monitoring information. The data is transmitted to the cloud via wireless networks to improve security and accessibility. By comprehensively monitoring different environmental factors, their impact on surface cracks is comprehensively analyzed. Timer settings are used to achieve automated monitoring, reducing the need for manual intervention and improving monitoring efficiency. The sensor ID and monitoring timestamp are recorded to ensure data traceability and accuracy.

[0033] Step 2: Smooth and fill the cleaning temperature and humidity change data, rainfall change data and crack deformation data through moving average filtering, identify and delete duplicate records, use weighted average to achieve normalization, and extract temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics through first-order difference;

[0034] The temperature and humidity change data, rainfall change data and crack deformation data are smoothed by moving average filtering to reduce the impact of random noise. The temperature and humidity change data, rainfall change data and crack deformation data are filled and cleaned according to the central values. According to the records of timestamp and sensor ID field, the completely identical records are identified and deleted. The partially repeated records are identified and merged through time windows. The temperature and humidity change data, rainfall change data and crack deformation data are normalized by weighted average according to their proportions. The temperature and humidity change data, rainfall change data and crack deformation data are converted into structured data. The temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics are extracted by first-order difference.

[0035] The moving average filter is used to smooth the temperature and humidity change data, rainfall change data and crack deformation data, which effectively reduces the impact of random noise and improves the stability and reliability of the temperature and humidity change data, rainfall change data and crack deformation data. The redundancy of the temperature and humidity change data, rainfall change data and crack deformation data is reduced by identifying and deleting duplicate records and merging some duplicate records. The weighted average is used to normalize the temperature and humidity change data, rainfall change data and crack deformation data, so that different features can be compared on the same scale. The temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics are extracted by first-order difference, which can better capture the dynamic changes of the temperature and humidity change data, rainfall change data and crack deformation data, and help analyze the impact of temperature and humidity changes and rainfall changes on crack deformation.

[0036] Step 3: Calculate the Pearson correlation coefficient and evaluate the influence of temperature and humidity change characteristics and rainfall change characteristics on crack deformation characteristics according to contribution degree and weight;

[0037] The influence of crack deformation characteristics is determined by selecting the correlation between temperature and humidity change characteristics and rainfall change characteristics through the Pearson correlation coefficient. The specific formula is:

[0038]

[0039] Where r represents the Pearson coefficient, W Z X,Y Indicates the contribution of temperature and humidity change characteristics and rainfall change characteristics to crack deformation characteristics, W Z X , W Z Y They represent the weight coefficients of temperature and humidity change characteristics and rainfall change characteristics for crack deformation characteristics, X represents temperature and humidity change characteristics, Y represents rainfall change characteristics, and Z represents crack deformation characteristics. Represents the mean of the temperature and humidity change characteristics, Represents the mean of rainfall variation characteristics. The Pearson correlation coefficient ranges from [-1,1]. The closer its absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is.

[0040] By calculating the Pearson correlation coefficient of the temperature and humidity change characteristics and the rainfall change characteristics on the crack deformation characteristics, the influence of different characteristics on the crack deformation can be quantified. The humidity change and rainfall change are linked to the crack deformation by using the Pearson correlation coefficient formula. By evaluating their contribution degree and weight, data-driven decision making is provided. By identifying highly correlated features, redundant variables are reduced.

[0041] Step 4: Connect the temperature and humidity change data, rainfall change data and crack deformation data according to the sensor monitoring timestamp, construct a design matrix, and use the closed-form solution formula of ridge regression to calculate the regression coefficient vector to predict the crack deformation width;

[0042] According to the sensor monitoring timestamp, the temperature and humidity change data, rainfall change data and crack deformation data are connected, and the temperature and humidity change characteristics and rainfall change characteristics are combined into a design matrix. The regression coefficient is initialized to a zero vector, and the optimal regularization parameter value is selected through cross-validation. The closed-form solution formula of ridge regression is used to calculate the regression coefficient vector of the crack deformation characteristics. The specific formula is:

[0043]

[0044] Among them, β represents the regression coefficient vector of crack deformation characteristics, A represents the design matrix, α represents the regularization parameter in ridge regression, and B represents the crack deformation characteristics. The crack deformation width is predicted by the regression coefficient vector of crack deformation characteristics and the temperature and humidity change characteristics and rainfall change characteristics.

[0045] By connecting the temperature and humidity change data, rainfall change data and crack deformation data according to the sensor monitoring timestamp, a design matrix is ​​constructed to achieve effective integration of multidimensional data, which helps to capture the various factors that affect crack deformation. The optimal regularization parameter value is selected through cross-validation. The regularization mechanism in ridge regression is used to reduce the overfitting risk of the model. The closed-form solution formula of ridge regression is used to calculate the regression coefficient vector, which can quickly and effectively obtain the parameters of the prediction model. The crack deformation width is accurately predicted by combining the regression coefficient vector with the characteristic data.

[0046] Step 5: Create a visualization interface to display the current change status of the surface crack monitoring points and the current meteorological changes of temperature and humidity, and compare the changes in the crack positions in combination with GPS positioning;

[0047] Create a visualization interface to display the current change status of the surface crack monitoring points and the current meteorological changes in temperature and humidity. Use a line graph to show the trend of surface cracks changing with the corresponding sensor monitoring timestamp and predict the crack deformation width. Use a heat map to show the overall situation of multiple surface cracks and reflect the severity of the surface cracks through the depth of color. Connect GPS to compare the surface crack position positioning of the previous corresponding sensor monitoring timestamp and the surface crack position positioning of the current corresponding sensor monitoring timestamp to intuitively display the changes in surface cracks.

[0048] The visualization interface displays the changing trend of cracks over time through a line graph, which can intuitively reflect the real-time changes in the crack deformation width and the current meteorological changes in temperature and humidity. Combined with the crack monitoring data, it can understand the impact of environmental factors on crack changes in real time, enhance the timeliness of monitoring, integrate meteorological data, crack monitoring data and GPS positioning information in one interface, improve the comprehensiveness and systematicness of data analysis, and help to fully understand the background of crack changes.

[0049] Example 1

[0050] The present invention selects the measuring range of the temperature sensor to be -40°C to 80°C, the measuring range of the temperature sensor to be 0% to 100%, the measuring range of the rain gauge to be 0-100mm, the accuracy to be ±0.2mm, and the modular frame to be designed to be 30cm long, 20cm wide and 10cm high.

[0051] The present invention sets the window size in the moving average filter to 3 hours. Assuming that the temperature and humidity change data is [25.1, 25.3, 25.2], the temperature and humidity change data obtained after moving average is 25.2°C. For the filling step, assuming that the temperature and humidity change data is [25.2, null, 25.4], the filled data is [25.2, 25.3, 25.4]. The features are extracted by first-order difference. Assuming that the temperature and humidity change features are [0.1, -0.1, 0.2], and the crack deformation features are [0.1, 0.2, 0.1], the feature matrix is:

[0052]

[0053] Assuming that the calculated Pearson coefficient is 0.85, indicating that there is a strong positive correlation between the two, the ridge regression model is used to perform regression analysis on the crack deformation characteristics, assuming that the design matrix is:

[0054]

[0055] The regularization parameter is selected as 0.01 through cross-validation, and the regression coefficient vector calculated by the closed-form solution formula of ridge regression is:

[0056]

[0057] Through the above regression coefficient vector, the crack deformation width can be predicted, assuming that the predicted result is 0.3mm.

[0058] Example 2

[0059] The present invention integrates temperature and humidity sensors, rain gauges and optical fiber strain sensors into a modular framework, which can monitor environmental changes and the status of surface cracks in real time. Each sensor is equipped with a microcontroller and a timer, which enables it to collect data once an hour, ensuring the timeliness and continuity of the data; the wireless communication module inside the sensor is used as a wireless node to transmit the monitoring data to the cloud for storage through the wireless sensor network. Not only does it improve the efficiency of data transmission, but it also enhances flexibility, and more monitoring points can be expanded at any time as needed; by storing data in the cloud, monitoring information can be accessed anytime and anywhere, thereby realizing remote monitoring and management.

[0060] The present invention utilizes moving average filtering to smooth the temperature and humidity change data, rainfall change data and crack deformation data to reduce the impact of random noise and ensure the stability of the data. Filling and cleaning are performed according to the central value of the temperature and humidity change data, rainfall change data and crack deformation data to ensure the integrity of the data. Through the recording of timestamp and sensor ID field, the system can identify and delete completely identical records. At the same time, for only partially repeated records, the system will merge them through a time window to ensure the accuracy and consistency of the data. The weighted average method is adopted to perform normalization processing according to the proportion of the temperature and humidity change data, rainfall change data and crack deformation data, so that different types of data can be compared and analyzed under the same standard. The temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics are extracted by first-order difference, and the relationship between these characteristics can be deeply analyzed. The Pearson correlation coefficient is used to analyze the influence of the temperature and humidity change characteristics and the rainfall change characteristics on the crack deformation characteristics, thereby providing a scientific basis for the prediction of crack deformation.

[0061] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A surface crack monitoring device, characterized in that: The specific steps include: Step 1: Install temperature and humidity sensors, rain gauges and optical fiber strain sensors at the surface crack monitoring points, and use wireless sensor networks to regularly monitor and transmit data to the cloud to achieve real-time monitoring and recording of the environment and crack deformation at the surface crack monitoring points; Step 2: Smooth and fill the cleaning temperature and humidity change data, rainfall change data and crack deformation data through moving average filtering, identify and delete duplicate records, use weighted average to achieve normalization, and extract temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics through first-order difference; Step 3: Calculate the Pearson correlation coefficient and evaluate the influence of temperature and humidity change characteristics and rainfall change characteristics on crack deformation characteristics according to contribution degree and weight; Step 4: Connect the temperature and humidity change data, rainfall change data and crack deformation data according to the sensor monitoring timestamp, construct a design matrix, and use the closed-form solution formula of ridge regression to calculate the regression coefficient vector to predict the crack deformation width; Step 5: Create a visualization interface to display the current status of the surface crack monitoring points and the current meteorological changes in temperature and humidity, and compare the changes in the crack locations with GPS positioning.

2. A surface crack monitoring device according to claim 1, characterized in that: In the step 1, a temperature and humidity sensor, a rain gauge and an optical fiber strain sensor are installed at the surface crack monitoring point, the temperature and humidity sensor, the rain gauge and the optical fiber strain sensor are integrated into a modular framework, a timer is set according to the microcontroller inside the temperature and humidity sensor, the rain gauge and the optical fiber strain sensor to monitor once per hour, the wireless communication modules inside the temperature and humidity sensor, the rain gauge and the optical fiber strain sensor are mapped as wireless nodes to the key nodes of the surface crack monitoring point, and a wireless sensor network is formed to transmit the monitoring data to the cloud for storage.

3. A surface crack monitoring device according to claim 1, characterized in that: In the step 2, the temperature and humidity change data, rainfall change data and crack deformation data are smoothed by moving average filtering to reduce the impact of random noise, and the temperature and humidity change data, rainfall change data and crack deformation data are filled and cleaned according to the central values, and the identical records are identified and deleted according to the records of the timestamp and sensor ID field, and the partially repeated records are identified and merged through the time window, and the temperature and humidity change data, rainfall change data and crack deformation data are normalized by weighted average according to the proportion of the temperature and humidity change data, rainfall change data and crack deformation data, and the temperature and humidity change data, rainfall change data and crack deformation data are converted into structured data, and the temperature and humidity change characteristics, rainfall change characteristics and crack deformation characteristics are extracted by first-order differences.

4. A surface crack monitoring device according to claim 1, characterized in that: In the step three, the influence of the crack deformation characteristics is determined by selecting the correlation between the temperature and humidity change characteristics and the rainfall change characteristics through the Pearson correlation coefficient.

5. A surface crack monitoring device according to claim 4, characterized in that: The specific formula of the Pearson correlation coefficient is: Where r represents the Pearson coefficient, W Z X,Y Indicates the contribution of temperature and humidity change characteristics and rainfall change characteristics to crack deformation characteristics, W Z X , W Z Y They represent the weight coefficients of temperature and humidity change characteristics and rainfall change characteristics for crack deformation characteristics, X represents temperature and humidity change characteristics, Y represents rainfall change characteristics, and Z represents crack deformation characteristics. Represents the mean of temperature and humidity change characteristics, The mean value representing the rainfall variation characteristics.

6. A surface crack monitoring device according to claim 1, characterized in that: In the step four, the temperature and humidity change data, rainfall change data and crack deformation data are connected according to the sensor monitoring timestamp, the temperature and humidity change characteristics and rainfall change characteristics are combined into a design matrix, the regression coefficient is initialized to a zero vector, the optimal regularization parameter value is selected through cross-validation, and the closed-form solution formula of ridge regression is used to calculate the regression coefficient vector of the crack deformation characteristic, and the crack deformation width is predicted by the regression coefficient vector of the crack deformation characteristic and the temperature and humidity change characteristics and rainfall change characteristics.

7. A surface crack monitoring device according to claim 6, characterized in that: The specific formula for calculating the regression coefficient vector of the crack deformation characteristics is: β=[(A T A+αW Z X W Z Y ) -1 A T B] Among them, β represents the regression coefficient vector of the crack deformation characteristics, A represents the design matrix, α represents the regularization parameter in ridge regression, and B represents the crack deformation characteristics.

8. A surface crack monitoring device according to claim 1, characterized in that: In the step five, a visualization interface is created to display the current change status of the surface crack monitoring point and the current meteorological changes in temperature and humidity, and the severity of the surface cracks is reflected by the depth of color. The GPS is connected to compare the surface crack position positioning of the previous corresponding sensor monitoring timestamp and the surface crack position positioning of the current corresponding sensor monitoring timestamp to intuitively display the changes in the surface cracks.

Images