Road slope superficial displacement monitoring method, system, device, equipment and medium

Abstract

The invention provides a road slope superficial displacement monitoring method, system, device, equipment and medium, and relates to the technical field of road construction. Road slope characteristic data and environment characteristic data are obtained; on the basis of the road slope feature data and the environment feature data, predicting early warning feature data of the road slope by adopting a prediction model; based on the early warning feature data and a slope geological condition early warning threshold value, determining a prediction early warning level; on the basis of the determined mapping relation between the early warning level and the response measure, determining the response measure corresponding to the predicted early warning level so as to effectively identify the subtle change of the displacement trend and reduce the false alarm rate and the missing report rate; and an efficient technical means is provided for preventing side slope disasters and guaranteeing road traffic safety.

Description

Technical Field

[0001] This invention relates to the field of road construction technology, and more specifically, to a method, system, device, equipment, and medium for monitoring shallow displacement of road slopes. Background Technology

[0002] Existing automated road slope shallow displacement monitoring systems have the following shortcomings: they mostly use a single type of sensor, such as Global Navigation Satellite System (GNSS) or crack gauges, monitoring only a single parameter and failing to comprehensively reflect the stress state and deformation mechanism of the slope; data processing relies heavily on fixed threshold alarms, lacking in-depth analysis of historical data and trend prediction capabilities, which can easily lead to false alarms or missed alarms; and they lack emergency response capabilities, failing to take timely and effective measures such as traffic control or personnel evacuation when slope instability risks occur, making it difficult to meet the actual needs of road safety management. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method, system, device, equipment and medium for monitoring shallow displacement of road slopes, so as to effectively identify subtle changes in displacement trends, reduce false alarm and false alarm rates, and provide an efficient technical means for preventing slope disasters and ensuring road traffic safety.

[0004] Firstly, this application provides a method for monitoring shallow displacement of road slopes, including: Acquire roadside slope characteristic data and environmental characteristic data; Based on road slope feature data and environmental feature data, a prediction model is used to predict the early warning feature data of road slopes. The prediction model is a recurrent neural network model that receives road slope feature data and environmental feature data through the input layer, predicts the early warning feature data of road slopes based on the road slope feature data and environmental feature data through the hidden layer, and outputs the early warning feature data of road slopes through the output layer. Based on early warning feature data and early warning thresholds for slope geological conditions, the predicted early warning level is determined; Based on the established mapping relationship between warning levels and response measures, the response measures corresponding to the predicted warning levels are determined.

[0005] Optionally, the road slope feature data includes crack width, three-dimensional displacement, and tilt angle; Environmental characteristic data include rainfall and soil moisture content.

[0006] Optionally, the early warning threshold for slope geological conditions includes a displacement rate threshold and a cumulative displacement threshold; The displacement rate is determined based on the historical average displacement rate and the historical displacement rate standard deviation; The cumulative displacement threshold is determined based on the displacement rate and monitoring time.

[0007] Optionally, based on early warning feature data and early warning thresholds for slope geological conditions, the predicted early warning level is determined as follows: If the warning feature data is determined to be greater than the first displacement rate threshold and greater than the first cumulative displacement threshold, then the predicted warning level is the yellow warning level. If the warning feature data is determined to be greater than the second displacement rate threshold and greater than the second cumulative displacement threshold, then the predicted warning level is orange warning level. If the warning feature data is determined to be greater than the third displacement rate threshold and greater than the third cumulative displacement threshold, then the predicted warning level is the red warning level; wherein, the first displacement rate threshold, the second displacement rate threshold, the third displacement rate threshold, the first cumulative displacement threshold, the second cumulative displacement threshold, and the third cumulative displacement threshold all increase sequentially.

[0008] Optionally, after acquiring road slope feature data and environmental feature data, the process may also include: The road slope feature data and environmental feature data are filtered, denoised, and outlier removed.

[0009] Optionally, the road slope shallow displacement monitoring method provided in this application further includes: Obtain a training dataset; the training dataset includes multiple training sample data; each training sample data includes road slope sample data, environmental sample data, and early warning standard data; Based on the training dataset, iterative training operations are performed on the initial prediction model until the termination condition of the iterative training is met. Then, based on the weights and thresholds of the initial prediction model updated during the last iteration, a prediction model is obtained. The iterative training operations include: Select target training sample data from the training dataset; The road slope sample data and environmental sample data in the target training sample data are input into the initial prediction model. The initial prediction model receives the road slope sample data and environmental sample data through the input layer, and predicts the early warning feature data of the road slope based on the road slope sample data and environmental sample data through the hidden layer. Finally, the early warning feature data of the road slope is output through the output layer. Based on the prediction error between the early warning feature data and the early warning standard data in the target training sample data, the weights and thresholds of the initial prediction model are updated.

[0010] Secondly, this application provides a shallow displacement monitoring system for road slopes, comprising: The data acquisition module is used to acquire roadside slope feature data and environmental feature data; The data processing module is used to predict the early warning feature data of road slopes based on road slope feature data and environmental feature data using a prediction model. The prediction model is a recurrent neural network model that receives road slope feature data and environmental feature data through the input layer, predicts the early warning feature data of road slopes based on the road slope feature data and environmental feature data through the hidden layer, and outputs the early warning feature data of road slopes through the output layer. The monitoring and early warning module is used to determine the predicted early warning level based on early warning feature data and early warning thresholds for slope geological conditions; The response measures module is used to determine the response measures corresponding to the predicted warning level based on the established mapping relationship between the warning level and the response measures.

[0011] Thirdly, this application provides a road slope shallow displacement monitoring device, including the aforementioned road slope shallow displacement monitoring system and multiple sensors; wherein the multiple sensors include: Displacement sensors are used to acquire the crack width and three-dimensional displacement of roadside slopes; Tilt angle detection sensor, used to obtain the tilt angle of roadside slope; Environmental monitoring sensors are used to obtain rainfall and soil moisture content on roadside slopes.

[0012] Fourthly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for monitoring shallow displacement of road slopes.

[0013] Fifthly, this application provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement a method for monitoring shallow displacement of road slopes.

[0014] This invention provides a method, system, device, equipment, and medium for monitoring shallow displacement of road slopes. It acquires road slope characteristic data and environmental characteristic data; based on these data, a prediction model is used to predict early warning characteristic data of the road slope; the prediction model is a recurrent neural network model that receives road slope characteristic data and environmental characteristic data through an input layer, predicts early warning characteristic data of the road slope based on these data through a hidden layer, and outputs the early warning characteristic data of the road slope through an output layer; based on the early warning characteristic data and the early warning threshold of the slope geological conditions, the predicted early warning level is determined; based on the determined mapping relationship between the early warning level and response measures, the corresponding response measures are determined to effectively identify subtle changes in displacement trends, reduce false alarms and missed alarms, and provide an efficient technical means for preventing slope disasters and ensuring road traffic safety.

[0015] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart of a method for monitoring shallow displacement of road slopes provided by an embodiment of the present invention is shown; Figure 2 A flowchart illustrating a training method for a prediction model provided in an embodiment of the present invention is shown. Figure 3 This diagram illustrates the structure of a road slope shallow displacement monitoring system provided in an embodiment of the present invention. Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] This application provides a method for monitoring shallow displacement of road slopes, see below. Figure 1 As shown in the embodiments of this application, the method for monitoring shallow displacement of road slopes includes: Step 110: Obtain road slope feature data and environmental feature data.

[0020] In this embodiment of the application, the road slope feature data includes crack width data, three-dimensional displacement data, and tilt angle data; the environmental feature data includes rainfall data and soil moisture content data.

[0021] In this application embodiment, the methods for obtaining road slope feature data and environmental feature data include, but are not limited to, the following: Crack width data can be obtained using a crack gauge; Three-dimensional displacement data can be obtained through a Global Navigation Satellite System Receiver (GNSS). Tilt angle data can be obtained through a tilt angle detection sensor; Rainfall and soil moisture content data can be obtained through environmental monitoring sensors.

[0022] In practical implementation, for example, a steep slope of a mountain highway from K12+300 to K12+500 is selected as the road slope to be monitored. The slope is about 35 meters high with a slope ratio of 1:0.75. The lithology is mainly strongly weathered sandstone with well-developed joints and fissures, and it is located in an area with concentrated rainfall during the rainy season. Multiple (e.g., 10) high-precision crack gauges (model XX-CFJ-01, accuracy ±0.01mm) are evenly spaced (e.g., 20 meters) along the length of the road slope surface, and multiple (e.g., 3) GNSS receivers (model XX-GNSS-A, positioning accuracy ±2.5mm+1ppm for horizontal plane and ±5mm+1ppm for vertical plane). Multiple micro-electro-mechanical systems (MEMS) are buried near the potential sliding surface of the road slope. The system (MEMS) includes a tilt sensor (model XX-QJ-02, resolution 0.001°); multiple (e.g., 2) tipping bucket rain gauges (model XX-YLJ-03, resolution 0.2mm) and multiple (e.g., 3) soil moisture sensors (model XX-SH-04, measurement range 0-100%, accuracy ±3%) are deployed around the roadside slope; and an industrial-grade data acquisition unit (model XX-DAS-100) supporting multi-protocol access is used. The crack gauge, GNSS receiver, tilt sensor, rain gauge and / or soil moisture sensor are connected to the data acquisition unit, and the acquisition frequency of the data acquisition unit can be set to 1 time / minute.

[0023] In this embodiment of the application, after obtaining the road slope feature data and environmental feature data, the method further includes: filtering, denoising and outlier removal processing of the road slope feature data and environmental feature data.

[0024] The specific process for processing road slope feature data and environmental feature data is as follows: The 4-20mA or 0-5V analog signals acquired by the crack gauge, tilt sensor, and soil moisture sensor are preprocessed using an 8th-order Butterworth low-pass filter. The cutoff frequency is set according to the signal characteristics (e.g., a 10Hz cutoff frequency for the crack gauge signal to filter out high-frequency interference such as environmental vibration). An integrated RC filter network is used to suppress power supply ripple (≤50mV) and electromagnetic interference (EMI). The suppression specifications are: signal-to-noise ratio (SNR) improvement ≥15dB after filtering, and signal distortion <0.5%. Preprocessing of TTL level or RS485 data signals acquired by GNSS receivers and rain gauges can be achieved by using Schmitt triggers to shape digital signals and eliminate pulse jitter (jitter time ≤100ns); and by setting up signal isolation circuits (such as optocoupler isolation) to prevent ground loop interference. The feature data acquired by soil moisture sensors and rain gauges can also be processed using sliding window mean filtering in the time domain. In this process, the window length is set to 5 time steps (i.e., 5 minutes of data) based on the sampling frequency to process the feature data and eliminate random white noise. For example, to reduce the fluctuation range of soil moisture data from ±5% to ±1.5%, the following formula is used for processing the feature data:

[0025] In the formula, This represents the data value after window smoothing at the nth time step, where n is the current time step number. The original feature data collected at the i-th time step; The feature data acquired by the soil crack gauge, GNSS receiver, and tilt sensor can also be processed by Kalman filtering optimization in the time domain. In this optimization, the state equation, observation equation, process noise covariance, and observation noise covariance are used to process the feature data to reduce data errors. For example, the root mean square error (RMSE) of the GNSS three-dimensional displacement data is reduced from 8 mm to 3 mm. Specifically, based on the slope displacement characteristics, the process noise covariance is set to diag([0.01, 0.01, 0.001]); the observation noise covariance of the crack gauge is set to... The observation noise covariance of GNSS is set as The mathematical expression for the state equation is:

[0026] In the formula, Let k be the state vector at time k. Here is the state transition matrix. For noise gain, This is the process noise vector at time k; The mathematical expression for the observation equation is:

[0027] In the formula, Let k be the observation vector at time k. For the observation matrix, Let be the observation noise vector at time k; Outlier removal and temporal correlation verification are performed on road slope feature data and environmental feature data. Outlier removal can be performed using a gross error detection method based on statistical thresholds. The discrimination condition for this method is: if feature data x satisfies... In the formula, The mean, If the standard deviation is used, the feature data is identified as an outlier. If an outlier occurs three consecutive times, the sensor corresponding to the outlier will trigger a fault alarm. If a single outlier occurs, linear interpolation between the preceding and following time points will be used to replace the single outlier; for example, if the crack width is abnormal, then... It can replace single-point outliers and perform physical constraint verification, such as marking rain gauge single-sample values ​​> 5 mm / min (extreme rainfall value) as outliers; it can perform temporal correlation verification on feature data with time continuity, such as three-dimensional displacement data and tilt angle data, by calculating the rate of change between adjacent time points. To determine whether the characteristic data are outliers, for example, if the crack width change rate is >0.5 mm / min or the GNSS displacement change rate is >2 mm / min, it is determined to be an abrupt anomaly.

[0028] After preprocessing the feature data using the methods described above, the accuracy is significantly improved compared to the original data, as shown in Table 1: Table 1 Comparison of Feature Data Before and After Preprocessing

[0029] Step 120: Based on road slope feature data and environmental feature data, a prediction model is used to predict the early warning feature data of the road slope. The prediction model is a recurrent neural network model that receives road slope feature data and environmental feature data through the input layer, predicts the early warning feature data of the road slope based on the road slope feature data and environmental feature data through the hidden layer, and outputs the early warning feature data of the road slope through the output layer.

[0030] In this embodiment, road slope feature data and environmental feature data are used as input data for the prediction model; early warning feature data is used as output data for the prediction model; the prediction model is a Long Short-Term Memory (LSTM) recurrent neural network model, which includes an input layer, a hidden layer, and an output layer connected in sequence. The input layer processes different types of feature data in parallel through multiple parameter branches, the hidden layer extracts the temporal dependencies of the feature data through LSTM units, and the output layer outputs early warning feature data. The input layer includes at least four parallel parameter processing branches (such as displacement branch, crack branch, tilt branch, and environmental branch), each specifically processing the characteristics of different feature data. The displacement branch is used to process three-dimensional displacement data (…). For example, a sliding window of 270 time steps is used to acquire the three-dimensional displacement data to be processed in order to capture subtle displacement changes. Differential operations are performed on the three-dimensional displacement data within the window, i.e., calculating the displacement difference between adjacent time steps, and displacement rate features are extracted to reflect the changing trend of structural displacement. The original displacement and rate features are also standardized. Crack branches are used to process crack width data. For example, a sliding window of 1440 time steps is used to acquire the crack width data to be processed to avoid interference from short-term noise. The crack width data within the window is smoothed (e.g., by moving average) to remove instantaneous measurement noise. The system performs several optimizations, including: 1) processing the slope angle data, 2) processing the slope angle data, 3) processing the slope angle data, 4) processing the slope angle data, 5) processing the slope angle data, 6) processing the slope angle data, 7) processing the slope angle data, 8) processing the slope angle data, 9) processing the slope angle data, 10) processing the slope angle data, 11) processing the slope angle data, 12) processing the slope angle data, 13) processing the slope angle data, 14) processing the slope angle data, 14) processing the slope angle data, 15) processing the slope angle data, 16) processing the slope angle data, 17) processing the slope angle data, 18 ... The hidden layer consists of four parallel LSTM sub-layers and one feature fusion layer. Each LSTM sub-layer corresponds to the displacement branch, crack branch, tilt branch, and environment branch of the input layer, respectively. The displacement branch LSTM sub-layer contains 64 neurons, the crack branch LSTM sub-layer contains 32 neurons, the tilt branch LSTM sub-layer contains 32 neurons, and the environment branch LSTM sub-layer contains 16 neurons. Each LSTM sub-layer autonomously learns the temporal dependencies of the corresponding data through gating mechanisms (forget gate, input gate, and output gate). The output data of each branch is processed by attention weights in the attention mechanism to highlight the information of key time steps. The feature fusion layer adopts a fully connected approach, concatenating and compressing the output features of the four LSTM sub-layers (the hidden state of the last time step) to obtain a 64-dimensional fused feature vector, realizing information complementarity from multiple sources. The output layer includes multiple output heads, each of which is a fully connected layer. It uses a linear activation function to output early warning feature data, which includes displacement feature prediction data, crack feature prediction data, tilt angle feature prediction data, environmental feature prediction data, and / or risk assessment prediction data.

[0031] Step 130: Determine the predicted warning level based on the warning feature data and the warning threshold for slope geological conditions.

[0032] In this embodiment of the application, the slope geological condition early warning threshold includes a displacement rate threshold and a cumulative displacement threshold; the displacement rate is determined based on the historical average displacement rate and the historical displacement rate standard deviation; and the cumulative displacement threshold is determined based on the displacement rate and the monitoring time.

[0033] In practical implementation, determining the early warning threshold for slope geological conditions includes, but is not limited to, the following methods: The displacement rate is determined based on the historical average displacement rate and the historical displacement rate standard deviation. The mathematical expression for the displacement rate is as follows:

[0034] In the formula, For displacement rate, This represents the average historical displacement rate. The standard deviation of the historical displacement rate, and This is an adjustment factor, and it is greater than 0; Based on displacement rate and monitoring time, a cumulative displacement threshold is determined, wherein the mathematical expression for the cumulative displacement threshold is:

[0035] In the formula, Let t be the threshold for the cumulative displacement over time t, where t is the monitoring time.

[0036] In this embodiment of the application, the predicted warning level is determined based on the warning feature data and the warning threshold for slope geological conditions, including: if the predicted warning feature data is greater than a first displacement rate threshold and greater than a first cumulative displacement threshold, the predicted warning level is a yellow warning level; if the predicted warning feature data is greater than a second displacement rate threshold and greater than a second cumulative displacement threshold, the predicted warning level is an orange warning level; if the predicted warning feature data is greater than a third displacement rate threshold and greater than a third cumulative displacement threshold, the predicted warning level is a red warning level; wherein the first displacement rate threshold, the second displacement rate threshold, and the third displacement rate threshold, as well as the first cumulative displacement threshold, the second cumulative displacement threshold, and the third cumulative displacement threshold, all increase sequentially, as shown in Table 2: Table 2 shows the early warning thresholds set based on slope geological conditions.

[0037] Step 140: Based on the established mapping relationship between warning levels and response measures, determine the response measures corresponding to the predicted warning levels.

[0038] In this embodiment of the application, the mapping relationship between the warning level and the response measures is specifically as follows: If the warning level is yellow, the response measures are as follows: traffic warning signs flash at low frequency (e.g., once every 2 seconds), variable message signs display the message "Slope Danger, Drive with Caution" in yellow font, and / or the emergency broadcast system broadcasts a warning message once every 30 seconds; and the warning information is pushed to the mobile phones of road management personnel, prompting them to strengthen on-site patrols and temporarily suspend traffic control. If the warning level is orange, multiple traffic warning signs will switch to high-frequency flashing (once every 0.5 seconds), variable message signs will display "Slope danger, slow down, pay attention" in orange font, and / or emergency broadcasts will be looped once every 10 seconds with the volume increased by 20%; and the traffic police department will be notified to prepare traffic control plans and dispatch emergency patrol personnel with equipment to the scene to provide real-time feedback on the slope status. If the warning level is red, traffic warning signs will remain constantly lit and flashing, variable message signs will display "Emergency danger on slope, no passage allowed, please detour immediately" in red text, and emergency broadcasts will continuously broadcast emergency evacuation instructions (such as "Slope ahead is unstable, vehicles and personnel should evacuate to a safe area immediately"); traffic control and personnel evacuation procedures will be initiated, automatically sending a road closure request to the traffic police command center, linking the road monitoring system to lock the dangerous road section, and simultaneously notifying fire, medical and other emergency rescue forces to stand by, ensuring that the entire process is triggered within 10 seconds.

[0039] The road slope shallow displacement monitoring method provided in this application acquires monitoring data through multiple sensors and constructs a multi-dimensional monitoring system. It employs the LSTM algorithm for deep fusion analysis of the multi-dimensional monitoring data, thereby accurately capturing the dynamic correlation between slope displacement and environmental factors, effectively identifying subtle changes in displacement trends, improving the early warning accuracy by more than 30%, and significantly reducing false alarms and missed alarms. By setting dynamic early warning thresholds, multi-level early warnings can be triggered within 10 seconds, automatically linking traffic warning signs, variable message signs, emergency broadcasts, and other hardware equipment to immediately initiate traffic control and personnel evacuation procedures, thereby improving emergency response efficiency by more than 80%. This provides an efficient technical means for preventing slope disasters and ensuring road traffic safety.

[0040] This application provides a method for training a prediction model, see embodiments below. Figure 2 As shown, the training method for the prediction model provided in this application includes: Step 210: Obtain the training data set; wherein, the training data set includes multiple training sample data; each training sample data includes road slope sample data, environmental sample data, and early warning standard data; Step 220: Select target training sample data from the training dataset; Step 230: Input the road slope sample data and environmental sample data from the target training sample data into the initial prediction model, so that the initial prediction model receives the road slope sample data and environmental sample data through the input layer, and predicts the early warning feature data of the road slope based on the road slope sample data and environmental sample data through the hidden layer, and then outputs the early warning feature data of the road slope through the output layer. Step 240: Based on the prediction error between the early warning feature data and the early warning standard data in the target training sample data, update the weights and thresholds of the initial prediction model; Step 250: Determine whether the iterative training termination condition is met; if yes, proceed to step 260; if no, return to step 220; wherein, the iterative training termination condition is that the number of iterations is not less than the number threshold, or the prediction error is not higher than the error threshold. Step 260: Based on the weights and thresholds of the initial prediction model updated during the last iteration of training, obtain the prediction model.

[0041] In practical implementation, the prediction model obtained through the above training method also includes: The process involves acquiring a test dataset and a validation dataset. The test dataset includes multiple test sample data points, and the validation dataset includes multiple validation sample data points. Each test sample data point includes road slope test data, environmental test data, and early warning standard data. Each validation sample data point includes road slope validation data, environmental validation data, and early warning standard data. Target test sample data is selected from the test dataset. The road slope test data and environmental test data from the target test sample data are input into the prediction model to obtain test early warning feature data. The prediction model is tested based on the error between the test early warning feature data and the early warning standard data in the target test sample data. Similarly, target validation sample data is selected from the validation dataset. The road slope validation data and environmental validation data from the target validation sample data are input into the prediction model to obtain validation early warning feature data. The prediction model is validated based on the error between the validation early warning feature data and the early warning standard data in the target validation sample data.

[0042] The training method of the prediction model provided in this application embodiment, through the threshold dynamic adjustment mechanism of the machine learning algorithm, can adapt to different geological conditions and working conditions, and greatly improve the universality and reliability of the monitoring method.

[0043] This application provides a shallow displacement monitoring system for road slopes. See [link to relevant documentation] Figure 3 As shown in the embodiment of this application, the road slope shallow displacement monitoring system includes: Data acquisition module 210 is used to acquire road slope feature data and environmental feature data; The data processing module 220 is used to predict the early warning feature data of road slopes based on road slope feature data and environmental feature data using a prediction model. The prediction model is a recurrent neural network model that receives road slope feature data and environmental feature data through the input layer, predicts the early warning feature data of road slopes based on the road slope feature data and environmental feature data through the hidden layer, and outputs the early warning feature data of road slopes through the output layer. The monitoring and early warning module 230 is used to determine the predicted early warning level based on early warning feature data and early warning thresholds for slope geological conditions; The response measures module 240 is used to determine the response measures corresponding to the predicted warning level based on the established mapping relationship between the warning level and the response measures.

[0044] In one optional embodiment, the road slope shallow displacement monitoring system provided in this application further includes: a communication transmission module 250, an edge computing unit 280, a data visualization module 270, and a system maintenance module; The transmission module is used to transmit the road slope feature data and environmental feature data acquired by the data collector in real time to the cloud server. The communication module includes a LoRa / NB-IoT communication unit, a 4G / 5G communication unit and a data aggregation node unit. The LoRa / NB-IoT communication unit is used to transmit the feature data to the data aggregation node unit over short distances, and the 4G / 5G communication unit serves as a backup for remotely transmitting the feature data to the cloud server.

[0045] Edge computing units are used to process acquired road slope feature data and environmental feature data; The data visualization module is used to display the prediction results obtained from the prediction model in the form of charts, curves, 3D models, etc.

[0046] The system maintenance module is used to perform remote diagnostics and periodic inspections of various modules of the system, as well as to optimize the prediction model.

[0047] This application provides a road slope shallow displacement monitoring device, which includes: the aforementioned road slope shallow displacement monitoring system and multiple sensors; wherein, the multiple sensors include: a displacement sensor for acquiring the crack width and three-dimensional displacement of the road slope; an inclination angle detection sensor for acquiring the inclination angle of the road slope; and an environmental detection sensor for acquiring the rainfall and soil moisture content of the road slope.

[0048] In practical implementation, crack width data can be obtained through crack gauges; three-dimensional displacement data can be obtained through Global Navigation Satellite System Receiver (GNSS); tilt angle data can be obtained through tilt detection sensors; and rainfall data and soil moisture content data can be obtained through environmental monitoring sensors.

[0049] It should be noted that the principle of the road slope shallow displacement monitoring system and device provided in this application embodiment to solve the technical problem is similar to that of the road slope shallow displacement monitoring method provided in this application embodiment. Therefore, the implementation of the road slope shallow displacement monitoring system and device provided in this application embodiment can refer to the implementation of the road slope shallow displacement monitoring method provided in this application embodiment, and the repeated parts will not be described again.

[0050] After introducing the road slope shallow displacement monitoring method, system and device provided in the embodiments of this application, the electronic equipment provided in the embodiments of this application will be briefly introduced next.

[0051] See Figure 4As shown, the electronic device provided in this application embodiment includes at least a processor 501, a memory 502, and a computer program stored in the memory 502 and capable of running on the processor 501. When the processor 501 executes the computer program, it implements the road slope shallow displacement monitoring method provided in this application embodiment.

[0052] The electronic device 500 provided in this application embodiment may further include a bus 503 connecting different components (including processor 501 and memory 502). The bus 503 represents one or more types of bus structures, including memory bus, peripheral bus, local area bus, etc.

[0053] Memory 502 may include a readable storage medium in the form of volatile memory, such as random access memory (RAM) 5021 and / or cache memory 5022, and may further include read-only memory (ROM) 5023. Memory 502 may also include a program tool 5025 having a set (at least one) of program modules 5024, including but not limited to an operating subsystem, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0054] Processor 501 can be a single processing element or a collective term for multiple processing elements. For example, processor 501 can be a central processing unit (CPU) or one or more integrated circuits configured to implement the road slope shallow displacement monitoring method provided in the embodiments of this application. Specifically, processor 501 can be a general-purpose processor, including but not limited to CPUs, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0055] Electronic device 500 can communicate with one or more external devices 504 (e.g., displacement sensors, tilt sensors, and environmental sensors), and also with one or more devices that enable user interaction with electronic device 500 (e.g., mobile phones, computers), and / or with devices that enable electronic device 500 to communicate with one or more other electronic devices 500 (e.g., routers, modems). This communication can be performed via input / output (I / O) interface 505. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 506. Figure 4 As shown, network adapter 506 communicates with other modules of electronic device 500 via bus 503. It should be understood that, although... Figure 4 As not shown, other hardware and / or software modules may be used in conjunction with the electronic device 500, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, Redundant Arrays of Independent Disks (RAID) subsystems, tape drives, and data backup storage subsystems.

[0056] It should be noted that, Figure 4 The electronic device 500 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0057] The computer-readable storage medium provided in the embodiments of this application is described below. The computer-readable storage medium provided in the embodiments of this application stores computer instructions, which, when executed by a processor, implement the road slope shallow displacement monitoring method provided in the embodiments of this application. Specifically, the computer instructions can be built into or installed in the processor, so that the processor can implement the road slope shallow displacement monitoring method provided in the embodiments of this application by executing the built-in or installed computer instructions.

[0058] In addition, the road slope shallow displacement monitoring method provided in this application embodiment can also be implemented as a computer program product. The computer program product includes program code, which implements the road slope shallow displacement monitoring method provided in this application embodiment when running on a processor.

[0059] The computer program product provided in this application embodiment may employ one or more computer-readable storage media, which may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination thereof. Specifically, more specific examples (a non-exhaustive list) of computer-readable storage media include electrical connections with one or more wires, portable disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM), optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0060] The computer program product provided in this application embodiment can be a CD-ROM and include program code, and can also run on electronic devices such as computers. However, the computer program product provided in this application embodiment is not limited thereto. In this application embodiment, the computer-readable storage medium can be any tangible medium that contains or stores program code, which can be used by or in conjunction with an instruction execution system, device, or apparatus.

[0061] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0062] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0063] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0064] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A method for monitoring shallow displacement of road slopes, characterized in that, include: Acquire roadside slope characteristic data and environmental characteristic data; Based on the road slope feature data and the environmental feature data, a prediction model is used to predict the early warning feature data of the road slope; wherein the prediction model is a recurrent neural network model that receives the road slope feature data and the environmental feature data through an input layer, predicts the early warning feature data of the road slope based on the road slope feature data and the environmental feature data through a hidden layer, and outputs the early warning feature data of the road slope through an output layer. Based on the aforementioned early warning feature data and the early warning threshold for slope geological conditions, the predicted early warning level is determined; Based on the established mapping relationship between early warning levels and response measures, the response measures corresponding to the predicted early warning levels are determined.

2. The method for monitoring shallow displacement of road slopes according to claim 1, characterized in that, The road slope feature data includes crack width, three-dimensional displacement, and tilt angle; The environmental characteristic data includes rainfall and soil moisture content.

3. The method for monitoring shallow displacement of road slopes according to claim 1, characterized in that, The slope geological condition early warning threshold includes the displacement rate threshold and the cumulative displacement threshold; The displacement rate is determined based on the historical average displacement rate and the historical displacement rate standard deviation; The cumulative displacement threshold is determined based on the displacement rate and monitoring time.

4. The method for monitoring shallow displacement of road slopes according to claim 1, characterized in that, Based on the aforementioned early warning feature data and the early warning threshold for slope geological conditions, the predicted early warning level is determined as follows: If the warning feature data is determined to be greater than the first displacement rate threshold and greater than the first cumulative displacement threshold, then the predicted warning level is the yellow warning level. If the warning feature data is determined to be greater than the second displacement rate threshold and greater than the second cumulative displacement threshold, then the predicted warning level is orange warning level. If the warning feature data is determined to be greater than the third displacement rate threshold and greater than the third cumulative displacement threshold, then the predicted warning level is the red warning level; wherein, the first displacement rate threshold, the second displacement rate threshold, the third displacement rate threshold, the first cumulative displacement threshold, the second cumulative displacement threshold, and the third cumulative displacement threshold all increase sequentially.

5. The method for monitoring shallow displacement of road slopes according to claim 1, characterized in that, After obtaining road slope feature data and environmental feature data, the following is also included: The road slope feature data and the environmental feature data are filtered, denoised, and outlier removed.

6. The method for monitoring shallow displacement of road slopes according to any one of claims 1 to 5, characterized in that, Also includes: Obtain a training dataset; wherein the training dataset includes multiple training sample data; each training sample data includes road slope sample data, environmental sample data, and early warning standard data; Based on the training dataset, an iterative training operation is performed on the initial prediction model until the iterative training termination condition is met. Then, based on the weights and thresholds of the initial prediction model updated during the last execution of the iterative training operation, the prediction model is obtained; wherein the iterative training operation includes: Select target training sample data from the training dataset; The road slope sample data and environmental sample data in the target training sample data are input into the initial prediction model, so that the initial prediction model receives the road slope sample data and the environmental sample data through the input layer, predicts the early warning feature data of the road slope based on the road slope sample data and the environmental sample data through the hidden layer, and outputs the early warning feature data of the road slope through the output layer. Based on the prediction error between the warning feature data and the warning standard data in the target training sample data, the weights and thresholds of the initial prediction model are updated.

7. A shallow displacement monitoring system for road slopes, characterized in that, include: The data acquisition module is used to acquire roadside slope feature data and environmental feature data; The data processing module is used to predict the early warning feature data of the road slope based on the road slope feature data and the environmental feature data using a prediction model; wherein the prediction model is a recurrent neural network model that receives the road slope feature data and the environmental feature data through an input layer, predicts the early warning feature data of the road slope based on the road slope feature data and the environmental feature data through a hidden layer, and outputs the early warning feature data of the road slope through an output layer. The monitoring and early warning module is used to determine the predicted early warning level based on the early warning feature data and the early warning threshold for slope geological conditions; The response measures module is used to determine the response measures corresponding to the predicted warning level based on the established mapping relationship between the warning level and the response measures.

8. A shallow displacement monitoring device for road slopes, characterized in that, Includes the road slope shallow displacement monitoring system as described in claim 7 and multiple sensors; wherein the multiple sensors include: Displacement sensors are used to acquire the crack width and three-dimensional displacement of the roadside slope; Inclination sensor, used to obtain the inclination angle of the roadside slope; Environmental monitoring sensors are used to obtain rainfall and soil moisture content of the roadside slope.

9. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the road slope shallow displacement monitoring method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the road slope shallow displacement monitoring method as described in any one of claims 1 to 6.

Images