Highway slope intelligent real-time monitoring and early warning system and use method

Abstract

The invention relates to the field of highway slope monitoring and early warning, and discloses an intelligent real-time highway slope monitoring and early warning system and a use method, and the system comprises a data collection subsystem which is used for collecting various data of a highway slope and obtaining parameters required by a calculation model; the data transmission subsystem is used for transmitting the collected data and parameters to each subsystem in real time; the data processing subsystem analyzes the collected data to construct a slope deformation prediction model; and the monitoring and early warning platform is used for carrying out early warning rating and risk judgment on an analysis result of the data processing subsystem, carrying out early warning and feeding back to related personnel to take measures. In the invention, the state data of the road slope is monitored in real time through a plurality of sensors of the data acquisition subsystem and is fed back to the constructed slope deformation prediction model in real time, so that monitored parameters can be processed and analyzed in a centralized manner, and monitoring personnel can intuitively judge the condition of the site slope according to an analysis and judgment result.

Description

Technical Field

[0001] The present invention relates to the field of highway slope monitoring and early warning, and in particular to an intelligent real-time monitoring and early warning system for highway slopes and a method for using the system. Background Art

[0002] As a key component of the modern transportation network, the safety and stability of highways are directly related to travel safety and smooth transportation. As one of the important structures of highways, the stability of slopes has a vital impact on the safe operation of highways.

[0003] Domestic research in the field of highway slope monitoring and early warning has also made great progress. In recent years, with the rapid development of my country's highway construction, the attention paid to slope safety issues has continued to increase, and the investment in related research has continued to increase. Domestic scholars have introduced and absorbed advanced foreign technologies and carried out a lot of research work based on the characteristics and actual needs of my country's highway slopes. In terms of monitoring technology, in addition to traditional measurement methods, my country's independently developed Beidou satellite navigation system (BDS) has been widely used in slope monitoring, realizing high-precision displacement monitoring.

[0004] However, the current intelligent real-time monitoring and early warning system for highway slopes still has some shortcomings. First, the various monitoring parameters of some systems are decentralized, and monitoring personnel cannot promptly determine whether there is a problem with the slope on site from the scattered data. Second, there is a lack of a computational model that can automatically calculate and process sensor data. Therefore, further improving and optimizing the intelligent real-time monitoring and early warning system for highway slopes remains the focus and difficulty of current research. Summary of the Invention

[0005] In order to make up for the above shortcomings, the present invention provides an intelligent real-time monitoring and early warning system and method for highway slopes, which solves the problem of decentralized monitoring parameter data in the system and provides a calculation model that can automatically calculate and process sensor data.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent real-time monitoring and early warning system for highway slopes, characterized by comprising a data acquisition subsystem, a data transmission subsystem, a data processing subsystem, and a monitoring and early warning platform. The data acquisition subsystem is used to collect various data on highway slopes and obtain parameters required for calculation models. The collected data parameters include displacement changes on the slope surface and inside, stress changes within the slope rock and soil, groundwater level, and slope inclination angle changes.

[0007] The data transmission subsystem is used to transmit the collected data and parameters to each subsystem in real time, using 5G wireless communication technology, which has a wide coverage range and can realize remote real-time data transmission;

[0008] The data processing subsystem constructs a slope deformation prediction model by analyzing the collected data, and feeds back the calculation results of the prediction model to the monitoring and early warning platform through the data transmission subsystem;

[0009] The monitoring and early warning platform is used to perform early warning rating and risk identification on the analysis results of the data processing subsystem and issue early warnings, and at the same time provide feedback to relevant personnel to take measures.

[0010] Preferably, it also includes an auxiliary subsystem, which includes a solar power supply system: providing stable power support for sensors, data transmission equipment and data processing equipment; a lightning protection system: effectively guiding lightning current into the ground, protecting monitoring equipment from lightning damage, and ensuring the normal operation of the system in thunderstorm weather.

[0011] Preferably, the data acquisition subsystem includes a data collector for collecting sensor data, a displacement sensor using a GNSS displacement monitoring station for measuring displacement changes on the surface and inside of the slope; a stress sensor using a vibrating wire stress gauge for monitoring stress changes inside the slope rock and soil; a groundwater level sensor using a drop-in water level gauge for monitoring the height of the groundwater level; and a tilt sensor for monitoring changes in the tilt angle of the slope.

[0012] Preferably, the data processing subsystem establishes a slope deformation prediction model based on multi-source monitoring data such as displacement, stress, water level, and tilt, and substitutes the real-time monitoring data into the model for analysis.

[0013] Preferably, the monitoring and early warning platform automatically performs risk identification based on set early warning thresholds and data analysis results.

[0014] A method for using an intelligent real-time monitoring and early warning system for highway slopes comprises the following steps:

[0015] Step S1: On-site investigation: Conduct a detailed investigation of the highway slope to determine the location and number of monitoring points, taking into account factors such as the slope's topography, geological conditions, and potential risk areas;

[0016] Step S2: Equipment inspection: Before installation, carefully check whether all equipment of the monitoring and early warning system is in good condition, including sensors, data collectors, transmission modules, power supply equipment, monitoring center software, etc., to ensure that the equipment is not damaged and all parts are complete, and check whether the model and quantity of the equipment are consistent with the list;

[0017] Step S3: Sensor installation: Install sensors at the top, shoulder, and bottom of the slope by drilling, embedding, or surface pasting.

[0018] Step S4: Data collector installation: The data collector is installed near the sensor to facilitate the collection of sensor data. It is usually installed in a dedicated equipment box and is waterproof and moisture-proof.

[0019] Step S5: Power supply system installation: Provide stable power supply for sensors and data collector equipment, use solar power supply, install solar panels and batteries;

[0020] Step S6: Software installation and configuration: The relevant sensors and supporting data collectors all have supporting data monitoring APPs. Follow the software installation wizard to operate and configure according to actual needs;

[0021] Step S7: Data monitoring and analysis: After the system is running, the staff can view the sensor data of each monitoring point on the slope in real time through the APP, including displacement, stress, groundwater level, tilt angle and other information, and substitute these data into the slope prediction model;

[0022] Step S8: Early warning and processing: When the monitoring data calculated by the slope prediction model exceeds the set alarm threshold, the system will automatically issue an early warning signal, including sound alarm, SMS alarm, email alarm, etc., to promptly notify relevant personnel. After receiving the early warning signal, the staff will immediately verify and analyze the alarm information to determine the safety status of the slope. After confirming that there are safety hazards on the slope, they will take corresponding disposal measures in a timely manner.

[0023] The present invention has the following beneficial effects:

[0024] 1. In the present invention, the status data of the highway slope is first monitored in real time by multiple sensors of the data acquisition subsystem and fed back to the slope deformation prediction model in real time. The monitored parameters can be centrally processed and analyzed, and the monitoring personnel can intuitively judge the situation of the on-site slope based on the results of the analysis. Unlike traditional manual monitoring that requires regular inspections, the intelligent real-time monitoring and early warning system can realize all-weather and uninterrupted monitoring of the slope status, thereby capturing the slightest changes in the slope in time, providing a strong guarantee for the timely discovery of safety hazards.

[0025] 2. The present invention provides a slope deformation prediction model that can automatically calculate and process sensor data. The constructed slope deformation prediction model is used to analyze and evaluate the stability of the slope. The data processing results are compared with the set warning threshold to judge the warning level, and a warning is issued in time when an abnormal situation occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1This is a schematic diagram of the overall framework of an intelligent real-time monitoring and early warning system for highway slopes proposed by the present invention;

[0027] Figure 2 This is a workflow diagram of an intelligent real-time monitoring and early warning system for highway slopes proposed by the present invention;

[0028] Figure 3 This is a schematic diagram of a slope deformation prediction model for an intelligent real-time monitoring and early warning system for highway slopes proposed by the present invention;

[0029] Figure 4 This is a schematic diagram of the use of an intelligent real-time monitoring and early warning system for highway slopes proposed by the present invention.

[0030] Legend:

[0031] 1. Vibrating wire strain gauge; 2. GNSS displacement monitoring station; 3. Submersible water level gauge; 4. Tilt sensor; 5. Alarm. DETAILED DESCRIPTION

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0033] Example 1: Reference Figure 1 and Figure 2An intelligent real-time monitoring and early warning system for highway slopes is characterized by comprising a data acquisition subsystem, a data transmission subsystem, a data processing subsystem, and a monitoring and early warning platform. The data acquisition subsystem is used to collect various data on highway slopes and obtain parameters required for the calculation model, wherein the collected parameters include displacement changes on the slope surface and inside, stress changes within the slope rock and soil, groundwater level, and slope inclination angle changes. The data transmission subsystem is used to transmit the collected data and parameters to each subsystem in real time, using 5G wireless communication technology with a wide coverage range, enabling remote real-time data transmission. The data processing subsystem analyzes the collected data to construct a slope deformation prediction model, and feeds back the calculation results of the prediction model to the monitoring and early warning platform through the data transmission subsystem. The monitoring and early warning platform is used to perform early warning rating and risk identification on the analysis results of the data processing subsystem, and issue early warnings, while also feeding back to relevant personnel to take measures. The system also includes auxiliary subsystems, including a solar power supply system that provides stable power support for sensors, data transmission equipment, and data processing equipment. A lightning protection system is used to effectively guide lightning current into the ground, protect monitoring equipment from lightning damage, and ensure the normal operation of the system in thunderstorms.

[0034] The data acquisition subsystem uses multiple sensors to monitor the status data of highway slopes in real time and feeds the data back to the slope deformation prediction model through 5G communication technology. The slope deformation prediction model centrally analyzes and processes the monitored parameters, and sends the results of the analysis and calculation to the monitoring and early warning platform. Monitoring personnel can intuitively judge the condition of the on-site slope based on the results of the analysis.

[0035] Example 2: Reference Figure 2 The data acquisition subsystem includes a data collector for collecting sensor data. A displacement sensor uses a GNSS displacement monitoring station 2, installed at the top of the slope, to measure displacement changes on the slope surface and inside. The GNSS displacement monitoring station 2 can receive multi-system, multi-frequency satellite signals, achieving millimeter-level positioning accuracy. It can grasp the instantaneous deformation of the slope in real time and effectively monitor the horizontal and vertical displacement trends of the slope. A stress sensor uses a vibrating wire stress gauge 1, installed at the top and bottom of the slope, to monitor stress changes within the slope rock and soil. Analysis of stress data can help understand the internal stress state of the slope and predict potential damage areas and forms. A groundwater level sensor uses a submersible water level gauge 3, installed at the bottom of the slope, to monitor the height of the groundwater level. It can accurately measure the rise and fall of the groundwater level and help analyze the impact of groundwater on slope stability. A tilt sensor 4 is installed at the slope shoulder to monitor changes in the slope's tilt angle. When the slope experiences uneven settlement or sliding, the tilt angle will change. The sensor can capture these changes in a timely manner, providing key information for slope stability assessment.

[0036] Example 3: Reference Figure 3 The data processing subsystem establishes a slope deformation prediction model based on multi-source monitoring data such as displacement, stress, water level, and tilt, and substitutes the real-time monitoring parameter data into the model for analysis. The following is the distribution modeling framework:

[0037] 1. Data feature engineering

[0038] Displacement sequence: extract cumulative displacement, rate, acceleration, and mutation point

[0039] Stress field: principal stress direction, stress concentration factor, stress relaxation rate

[0040] Hydrological parameters: water level gradient, seepage pressure coefficient

[0041] Tilt indicators: tilt angle change rate, curvature radius

[0042] 2. Multi-physics coupling model

[0043] State space model based on physical equations

[0044] def slope_dynamics(x,t,params):

[0045] #x=[displacement, stress, water level, tilt]

[0046] #params contains material parameters, boundary conditions, etc.

[0047] dxdt=[params['k1']*x[2]+params['k2']*x[3]-params['c1']*x[0],#displacement change rate

[0048] params['k3']*x[0]+params['k4']*x[3]-params['c2']*x[1],#stress change rate

[0049] params['k5']*x[0]-params['c3']*x[2],#water level change rate

[0050] params['k6']*x[1]+params['k7']*x[2]-params['c4']*x[3]#tilt change rate]

[0051] return dxdt

[0052] 3. Machine Learning Prediction Model

[0053] Long Short-Term Memory Network (LSTM) for time series forecasting:

[0054] Python

[0055] from tensorflow.keras.models import Sequential

[0056] model=Sequential()

[0057] model.add(LSTM(64,input_shape=(n_timesteps,n_features),return_sequences=True))

[0058] model.add(LSTM(32))

[0059] model.add(Dense(4))#Predict four state variables

[0060] model.compile(loss='mse',optimizer='adam')

[0061] 4. Damage pattern recognition

[0062] Random Forest Classification Model:

[0063] python from sklearn.ensemble import RandomForestClassifier clf=RandomForestClassifier(n_estimators=100,max_depth=5) # Features include: displacement rate > 5mm / d, stress drop > 20%, water level gradient > 0.3m / d, etc. clf.fit(X_train,y_train) #y is the failure mode label

[0064] 5. Real-time warning threshold system

[0065] Establish a three-level early warning mechanism:

[0066] python def alert_level(features):

[0067] score=0

[0068] if features['displacement_rate']>5:score+=1

[0069] if features['stress_drop']>0.2:score+=1

[0070] if features['water_gradient']>0.3:score+=1return['green','yellow','orange','red'][score]

[0071] The following code is generated based on the model framework:

[0072] import numpy as np

[0073] from scipy.integrate import odeint

[0074] from tensorflow.keras.models import Sequential

[0075] from tensorflow.keras.layers import LSTM,Dense

[0076] from sklearn.ensemble import RandomForestClassifier

[0077] #Data feature engineering part

[0078] #Extract displacement sequence features def extract_displacement_features(displacement_sequence):

[0079] cumulative_displacement=np.sum(displacement_sequence)

[0080] velocity=np.diff(displacement_sequence)

[0081] acceleration=np.diff(velocity)

[0082] #Simple example: Assume that the mutation point is the point where the displacement change exceeds a certain threshold

[0083] mutation_points=np.where(np.abs(velocity)>10)[0]

[0084] return cumulative_displacement,velocity,acceleration,mutation_points

[0085] #Extract stress field characteristics

[0086] def extract_stress_features(stress_field):

[0087] #Here is a simple example where the principal stress direction is the maximum direction of the stress field

[0088] principal_stress_direction=np.argmax(stress_field)

[0089] stress_concentration_factor=np.max(stress_field) / np.mean(stres_field)

[0090] stress_relaxation_rate=np.diff(stress_field)

[0091] return principal_stress_direction,stress_concentration_factor,stress_rela xation_rate

[0092] #Extract hydrological parameter features

[0093] def extract_hydrological_features(water_levels):

[0094] water_level_gradient=np.diff(water_levels)

[0095] #Simple example: the osmotic pressure coefficient is a fixed value

[0096] osmotic_pressure_coefficient=0.5

[0097] return water_level_gradient,osmotic_pressure_coefficient

[0098] #Extract tilt indicator features

[0099] def extract_tilt_features(tilt_angles):

[0100] tilt_angle_rate=np.diff(tilt_angles)

[0101] #Simple example: the curvature radius is a fixed value

[0102] curvature_radius=100

[0103] return tilt_angle_rate,curvature_radius

[0104] #Multi-physics coupling model part

[0105] def slope_dynamics(x,t,params):

[0106] #x=[displacement, stress, water level, tilt]

[0107] #params contains material parameters, boundary conditions, etc.

[0108] dxdt=[params['k1']*x[2]+params['k2']*x[3]-params['c1']*x[0],#displacement change rate

[0109] params['k3']*x[0]+params['k4']*x[3]-params['c2']*x[1],#stress change rate

[0110] params['k5']*x[0]-params['c3']*x[2],#water level change rate

[0111] params['k6']*x[1]+params['k7']*x[2]-params['c4']*x[3]#tilt change rate]

[0112] return dxdt

[0113] #Machine learning prediction model part

[0114] #Assume n_timesteps and n_features have been defined

[0115] n_timesteps=10

[0116] n_features=4

[0117] model=Sequential()

[0118] model.add(LSTM(64,input_shape=(n_timesteps,n_features),return_sequences=True))

[0119] model.add(LSTM(32))

[0120] model.add(Dense(4))#Predict four state variables

[0121] model.compile(loss='mse',optimizer='adam')

[0122] #Destruction pattern recognition part

[0123] #Assume X_train and y_train have been defined

[0124] X_train=np.random.rand(100,4)

[0125] y_train=np.random.randint(0,2,100)

[0126] clf=RandomForestClassifier(n_estimators=100,max_depth=5)

[0127] # Features include: displacement rate > 5mm / d, stress drop > 20%, water level gradient > 0.3m / d, etc.

[0128] clf.fit(X_train,y_train)#y is the failure mode label

[0129] #Real-time warning threshold system

[0130] def alert_level(features):

[0131] score=0

[0132] if features['displacement_rate']>5:

[0133] score+=1

[0134] if features['stress_drop']>0.2:

[0135] score+=1

[0136] if features['water_gradient']>0.3:

[0137] score+=1

[0138] return['green','yellow','orange','red'][score]

[0139] #Sample data

[0140] displacement_sequence=np.random.rand(100)

[0141] stress_field=np.random.rand(100)

[0142] water_levels=np.random.rand(100)

[0143] tilt_angles=np.random.rand(100)

[0144] #Extract features

[0145] cumulative_displacement,velocity,acceleration,mutation_points=extract_displacement_features(displacement_sequence)

[0146] principal_stress_direction,stress_concentration_factor,stress_relaxation_rate=extract_stress_features(stress_field)

[0147] water_level_gradient,osmotic_pressure_coefficient=extract_hydrological_features(water_levels)

[0148] tilt_angle_rate,curvature_radius=extract_tilt_features(tilt_an gles)

[0149] #Solving the multi-physics coupling model

[0150] params={'k1':0.1,'k2':0.2,'k3':0.3,'k4':0.4,'k5':0.5,'k6':0.6,'k7':0.7,

[0151] 'c1':0.1,'c2':0.2,'c3':0.3,'c4':0.4}

[0152] t = np.linspace(0,10,100)

[0153] x0=[0,0,0,0]

[0154] solution=odeint(slope_dynamics,x0,t,args=(params,))

[0155] #Real-time warning example

[0156] features={'displacement_rate':np.mean(velocity),'stress_drop':0.1,'water_gradient':np.mean(water_level_gradient)}

[0157] alert=alert_level(features)

[0158] print(f"Warning level:{alert}")

[0159] This code example covers the complete slope stability analysis process, from data feature engineering to multi-physics coupling model solution, to machine learning prediction and failure pattern recognition, and finally real-time early warning.

[0160] The monitoring and early warning platform automatically conducts risk assessment based on the set early warning thresholds and data analysis results, and sets three-level early warning thresholds. The early warning thresholds are divided into different levels: yellow warning threshold, orange warning threshold and red warning threshold, which correspond to different degrees of security risks. When the monitoring data exceeds the early warning threshold, the system immediately issues an early warning message. The early warning information includes the early warning level, warning time, abnormal monitoring parameters, etc., so that relevant personnel can respond quickly.

[0161] Example 4: Reference Figure 4 A method for using an intelligent real-time monitoring and early warning system for highway slopes includes the following steps:

[0162] Step S1: On-site survey: Conduct a detailed survey of the highway slope to determine the location and number of monitoring points, taking into account factors such as the slope's topography, geological conditions, and potential risk areas, while ensuring that the installation location will not affect the normal operation and traffic safety of the highway;

[0163] Step S2: Equipment inspection: Before installation, carefully check whether all equipment of the monitoring and early warning system is in good condition, including sensors, data collectors, transmission modules, power supply equipment, monitoring center software, etc., to ensure that the equipment is not damaged and all parts are complete, and check whether the model and quantity of the equipment are consistent with the list;

[0164] Step S3: Sensor installation: Install a GNSS displacement monitoring station 2 and a vibrating wire strain gauge 1 at the top of the slope, a tilt sensor 4 at the shoulder, and a vibrating wire strain gauge 1 and a submersible water level gauge 3 at the bottom of the slope. Use drilling and surface bonding to ensure the sensors are tightly connected to the slope soil or structure, enabling accurate measurement of slope displacement changes.

[0165] Step S4: Data collector installation: The data collector is installed near the sensor to facilitate data collection from the sensor. It is usually installed in a dedicated equipment box that is waterproof and moisture-proof, and ensures that the equipment box is well ventilated to ensure the normal operation of the data collector.

[0166] Step S5: Power supply system installation: Provide stable power supply for sensors and data collector equipment. Use solar power supply. Solar panels and batteries need to be properly installed to ensure that the power demand of the equipment can be met under different weather conditions.

[0167] Step S6: Software installation and configuration: The relevant sensors and supporting data collectors all have supporting data monitoring apps. Follow the software installation wizard and configure them according to actual needs, such as setting monitoring parameters, alarm thresholds, user permissions, etc.

[0168] Step S7: Data monitoring and analysis: After the system is running, staff can view the sensor data of each monitoring point on the slope in real time through the APP, including displacement, stress, groundwater level, tilt angle and other information, and substitute these data into the slope prediction model;

[0169] Step S8: Early warning and processing: When the monitoring data calculated by the slope prediction model exceeds the set alarm threshold, the system will automatically issue an early warning signal, including sound alarm, SMS alarm, email alarm, etc., and perform rapid positioning. The alarm 5 will sound an alarm to notify relevant personnel in time. After receiving the early warning signal, the staff will immediately verify and analyze the alarm information to determine the safety status of the slope. After confirming that there are safety hazards on the slope, they will take corresponding disposal measures in a timely manner, such as organizing personnel to conduct on-site inspections of the slope, taking temporary reinforcement measures, closing traffic, etc.

[0170] Working principle: In this system, various status data of the slope are first obtained in real time and accurately through sensors such as the GNSS displacement monitoring station 2, vibrating wire stress gauge 1, immersion water level gauge 3 and tilt sensor 4, and relevant parameters of the slope are continuously collected. The data collector collects the data and parameters of the sensors and quickly transmits these data to the slope prediction model through 5G communication technology. In the data collection link, various sensors automatically collect parameters such as slope displacement, stress, groundwater level, rainfall, etc. without human intervention, avoiding errors and uncertainties caused by manual operation. The slope deformation prediction model analyzes and processes the collected parameter data, and the results of the analysis and processing are transmitted to the monitoring and early warning platform.

[0171] The monitoring and early warning platform sets three levels of early warning thresholds, which are divided into different levels: yellow warning threshold, orange warning threshold and red warning threshold, which correspond to different degrees of security risks. According to the preset warning threshold and data analysis results, the monitoring and early warning platform automatically judges risks. When the monitoring data exceeds the warning threshold, the system immediately issues an early warning message and sounds an alarm through the alarm 5. The early warning information includes the warning level, warning time, abnormal conditions of monitoring parameters, etc., and is quickly located. Relevant personnel can respond quickly according to the early warning information. This early warning mechanism greatly improves the timeliness and accuracy of the early warning, and reduces false alarms and missed reports caused by human factors.

[0172] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent real-time monitoring and early warning system for highway slopes, characterized by: The system includes a data acquisition subsystem, a data transmission subsystem, a data processing subsystem, and a monitoring and early warning platform. The data acquisition subsystem is used to collect various data on the highway slope and obtain the parameters required for the calculation model. The collected data parameters include displacement changes on the slope surface and inside, stress changes within the slope rock and soil, groundwater level, and slope inclination angle changes. The data transmission subsystem is used to transmit the collected data and parameters to each subsystem in real time, using 5G wireless communication technology, which has a wide coverage range and can realize remote real-time data transmission; The data processing subsystem constructs a slope deformation prediction model by analyzing the collected data, and feeds back the calculation results of the prediction model to the monitoring and early warning platform through the data transmission subsystem; The monitoring and early warning platform is used to perform early warning rating and risk identification on the analysis results of the data processing subsystem and issue early warnings, and at the same time provide feedback to relevant personnel to take measures.

2. The intelligent real-time monitoring and early warning system for highway slopes according to claim 1 is characterized by: It also includes auxiliary subsystems, including a solar power supply system: providing stable power support for sensors, data transmission equipment, data processing equipment, etc.; a lightning protection system: effectively guiding lightning current into the ground, protecting monitoring equipment from damage by lightning strikes, and ensuring the normal operation of the system in thunderstorm weather.

3. The intelligent real-time monitoring and early warning system for highway slopes according to claim 1 is characterized by: The data acquisition subsystem includes a data collector for collecting sensor data, a displacement sensor using a GNSS displacement monitoring station (2) for measuring displacement changes on the surface and inside of the slope; a stress sensor using a vibrating wire stress gauge (1) for monitoring stress changes inside the slope rock and soil; a groundwater level sensor using a drop-in water level gauge (3) for monitoring the height of the groundwater level; and a tilt sensor (4) for monitoring changes in the tilt angle of the slope.

4. The intelligent real-time monitoring and early warning system for highway slopes according to claim 1 is characterized by: The data processing subsystem establishes a slope deformation prediction model based on multi-source monitoring data such as displacement, stress, water level, and tilt, and substitutes the parameter data monitored in real time into the model for analysis.

5. The intelligent real-time monitoring and early warning system for highway slopes according to claim 1 is characterized by: The monitoring and early warning platform automatically performs risk identification based on the set early warning threshold and data analysis results.

6. A method for using an intelligent real-time monitoring and early warning system for highway slopes, comprising the intelligent real-time monitoring and early warning system for highway slopes according to any one of claims 1 to 5, characterized in that: The following steps are involved: Step S1: On-site investigation: Conduct a detailed investigation of the highway slope to determine the location and number of monitoring points, taking into account factors such as the slope's topography, geological conditions, and potential risk areas; Step S2: Equipment inspection: Before installation, carefully check whether all equipment of the monitoring and early warning system is in good condition, including sensors, data collectors, transmission modules, power supply equipment, monitoring center software, etc., to ensure that the equipment is not damaged and all parts are complete, and check whether the model and quantity of the equipment are consistent with the list; Step S3: Sensor installation: Install sensors at the top, shoulder, and bottom of the slope by drilling, embedding, or surface pasting. Step S4: Data collector installation: The data collector is installed near the sensor to facilitate the collection of sensor data. It is usually installed in a dedicated equipment box and is waterproof and moisture-proof. Step S5: Power supply system installation: Provide stable power supply for sensors and data collector equipment, use solar power supply, install solar panels and batteries; Step S6: Software installation and configuration: The relevant sensors and supporting data collectors all have supporting data monitoring APPs. Follow the software installation wizard to operate and configure according to actual needs; Step S7: Data monitoring and analysis: After the system is running, the staff can view the sensor data of each monitoring point on the slope in real time through the APP, including displacement, stress, groundwater level, tilt angle and other information, and substitute these data into the slope prediction model; Step S8: Early warning and processing: When the monitoring data calculated by the slope prediction model exceeds the set alarm threshold, the system will automatically issue an early warning signal, including sound alarm, SMS alarm, email alarm, etc., to promptly notify relevant personnel. After receiving the early warning signal, the staff will immediately verify and analyze the alarm information to determine the safety status of the slope. After confirming that there are safety hazards on the slope, they will take corresponding disposal measures in a timely manner.

Images