Ecological slope protection structure real-time monitoring system based on sensor and Internet of Things

Abstract

The invention relates to the technical field of ecological monitoring, and discloses an ecological slope protection structure real-time monitoring system based on a sensor and the Internet of Things, and the system comprises an ecological data collection module which is used for collecting key index data such as displacement, inclination, stress and water level change of a slope in real time through the sensor, and carrying out the preprocessing of the collected index data; the data processing module is used for fusing the data of a plurality of sensor nodes, transmitting the preprocessed data to a control center through a wireless communication technology, carrying out preliminary data processing and analysis, and giving an alarm in real time when the sensor data is lacked; and the slope protection structure model module divides the processed index data into a training set and a verification set, establishes an ecological slope protection structure model, and performs identification and early warning on potential dangers by analyzing change trends of multiple parameters such as soil humidity, rainfall and displacement in combination with historical data and real-time monitoring results. Safety and stability of the slope are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological monitoring, and in particular to a real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things. Background Art

[0002] The core purpose of ecological slope protection technology is to achieve stable slope protection and ecological environment improvement by combining the natural characteristics of plants and soil; with the advancement of ecological civilization construction, ecological slope protection technology has gradually developed in a green and sustainable direction, while incorporating digital and intelligent technologies, such as the Internet and big data analysis, to improve the efficiency of monitoring and management; real-time monitoring systems are an important technical means to ensure slope safety; by installing GNSS displacement monitoring stations, sensors and other equipment, all-weather monitoring of multi-dimensional parameters such as slope uniqueness, soil moisture, and rainfall can be achieved; with the development of the Internet of Things and artificial intelligence technologies, ecological slope protection monitoring systems are gradually moving towards intelligence.

[0003] Prior art one, Chinese patent, application number 202410897127.1 discloses a rock slope ecological slope protection matrix deformation monitoring device, including a slope, two groups of fixing nails are provided on the slope, the fixing nails are inserted into the slope, one side of the fixing nails is provided with a mounting piece, the mounting piece is fixedly connected to the upper end of the fixing nail, one group of fixing nails is provided with a pull rope sensor, the pull rope sensor is fixedly connected to the mounting piece, one side of the pull rope sensor is provided with an information transmission platform, the information transmission platform is fixedly connected to the slope, and the pull rope sensor is electrically connected to the information transmission platform. Although the use of the pull rope sensor can perform long-term real-time detection of the slope during slope detection, and the data can be transmitted to a computer or mobile phone through the information transmission platform for real-time viewing to monitor the deformation condition of the slope; however, the pull rope sensor may be susceptible to external interference in certain environments, affecting the accuracy of the data.

[0004] Prior art two, Chinese patent, application number 202010307979.2 discloses an urban river ecological slope protection monitoring system, in which retention aquatic breeding areas are arranged at intervals on one side of the river slope protection surface. The retention aquatic breeding area is formed by excavating the slope protection base laterally outward to form a depression area, and the surrounding side walls of the depression area are built with stones and cementitious materials to form a mortar stone depression area slope protection. A water retention shallow cut is built on the bottom of the side of the retention aquatic breeding area connected to the river to ensure that the minimum ecological water use is maintained in the retention aquatic breeding area. A horizontal net is fixed on the upper side of the shallow cut to filter floating objects in the river. The mesh of the horizontal net is based on allowing small zooplankton to pass through. The height of the horizontal net is slightly higher than the annual average water level of the river. An external water level sensor, water quality detector and oxygen detector are arranged below the water level of the retention aquatic breeding area. Although the management technology based on aquatic biological measures combines terrestrial vegetation ecology with aquatic plant and animal ecology, making the urban river ecosystem more complete and complex and improving the stability and sustainability of the ecosystem; however, the installation and maintenance costs of the equipment are high, and it requires regular calibration and replacement, which imposes a large economic burden on long-term operation.

[0005] Prior art three, Chinese patent, application number 202110143067.0 discloses an ecological slope protection that can be used for hydrological monitoring, including a slope body, which is a stepped shape composed of multiple inclined sides and bottom sides interlaced with each other, and the inclination angles of the multiple inclined sides decrease from top to bottom, and each inclined side of the slope body is made of concrete material cast in one piece, a water tank is fixedly installed in the slope body, a movable plate is installed in the water tank through a sliding mechanism, a one-way drain pipe is fixedly installed between the water tank and the slope body, and a control mechanism is installed between the one-way drain pipe and the movable plate and the water tank, a water collection trough is opened at the bottom of the slope body, and a filter net is fixedly installed in the water collection trough, and a downpipe is fixedly installed between the water collection trough and the water tank. Although it has high protection, it can divert and collect rainwater falling on the slope during rain for reuse, and can monitor and alarm the water level, water quality, and flow rate of the river, and has high safety; however, the construction cost of concrete slope protection is high and resource consumption is large.

[0006] Currently, existing technologies 1, 2, and 3 are susceptible to external interference in certain environments, affecting data accuracy. The equipment installation and maintenance costs are high, and regular calibration and replacement are required. Long-term operation creates a significant economic burden, high construction costs, and significant resource consumption. Therefore, the present invention proposes a real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things. Summary of the Invention

[0007] The main purpose of the present invention is to provide a real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things, so as to solve the problems in the existing technology that the system is easily affected by external interference in certain environments, affecting the accuracy of data, the installation and maintenance costs of the equipment are high, and regular calibration and replacement are required, resulting in a large economic burden in long-term operation, high construction costs, and large resource consumption.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A real-time monitoring system for an ecological slope protection structure based on sensors and the Internet of Things, comprising:

[0010] The ecological data acquisition module is used to collect key indicator data of slope displacement, inclination, stress and water level changes in real time through sensors, and pre-process the collected indicator data;

[0011] The data processing module is used to fuse the data from multiple sensor nodes, transmit the pre-processed data to the control center through wireless communication technology, and perform preliminary data processing and analysis;

[0012] The slope protection structure model module divides the processed index data into training sets and validation sets, establishes an ecological slope protection structure model, and identifies and warns of potential dangers by analyzing the changing trends of multiple parameters such as soil moisture, rainfall, and displacement, combined with historical data and real-time monitoring results.

[0013] As a further improvement of the present invention, the ecological data acquisition module includes:

[0014] The sensor deployment submodule is used to install sensors at slope monitoring points to monitor the slope's displacement, tilt angle, stress, and key indicator data of water level changes in real time.

[0015] The data acquisition submodule is used to obtain the displacement and rate of the slope through the displacement sensor; measure the change of the slope inclination angle using the inclinometer; obtain the stress condition inside the soil through the soil pressure sensor or strain gauge; and monitor the rainfall and groundwater level changes through the rain sensor and groundwater level gauge;

[0016] The data preprocessing submodule is used to perform corrections according to the characteristics of different sensors, perform preliminary preprocessing on the collected data, and uniformly format the data from different sensors.

[0017] As a further improvement of the present invention, the data acquisition submodule includes:

[0018] The displacement monitoring unit is used to monitor the horizontal and vertical displacement changes of the slope surface in real time using a high-precision displacement sensor, and combines it with an inclinometer to measure the slope's inclination angle changes to comprehensively monitor the slope's deformation;

[0019] The stress monitoring unit is used to bury soil pressure sensors in drilled holes inside the slope. The soil stress conditions are obtained through soil pressure sensors or strain gauges, and stress changes at different depths are monitored in real time.

[0020] The rainfall monitoring unit is used to deploy rain sensors around the target slope, monitor rainfall changes through the rain sensors, and deploy groundwater level sensors inside the slope to detect changes in groundwater levels.

[0021] As a further improvement of the present invention, the data processing module includes:

[0022] The data fusion submodule is used to aggregate the pre-processed data of each sensor node to the data fusion submodule for data fusion processing;

[0023] The wireless communication transmission submodule is used to compress the fused data of each sensor node and transmit it to the analysis and alarm submodule through wireless communication technology;

[0024] The analysis and alarm submodule is used to perform preliminary analysis on the received sensor data to detect abnormal events or patterns. If missing sensor data is found or data anomalies are detected, the alarm mechanism is triggered to notify relevant personnel to take measures.

[0025] As a further improvement of the present invention, the analysis and alarm submodule includes:

[0026] Anomaly detection unit, which is used to analyze the data using preset thresholds and statistically detect data points that fall outside the normal range to determine whether there are abnormal events or patterns;

[0027] An alarm setting unit, used to set alarm rules so that when sensor data exceeds a preset threshold or no data is received within a specific time period, the system generates an alarm signal;

[0028] The emergency response unit is used to record detailed analysis of each alarm and grade the severity of the alarm; after the alarm is lifted, the system automatically cancels the alarm and records the reason for the release.

[0029] As a further improvement of the present invention, the slope protection structure model module includes:

[0030] The data collection submodule is used to receive the processed indicator data collected by the sensor and the historical data of the target slope protection, extract key features from the indicator data and historical data, and divide the processed data into a training set and a validation set;

[0031] The model building submodule is used to train the slope protection structure model and optimize the model parameters by combining cross-validation technology; the model is trained using the training set data and the model performance is evaluated using the validation set;

[0032] The identification and early warning submodule is used to use the trained and evaluated slope protection structure model for real-time monitoring data, and conduct dynamic analysis in combination with historical data to identify potential danger areas and issue early warning information, and generate risk level maps and early warning reports.

[0033] As a further improvement of the present invention, the data collection submodule includes:

[0034] A feature extraction unit is used to calculate the high-order statistics of each index data and the target slope protection historical data, and extract features and parameters from the index data and the target slope protection historical data;

[0035] The feature fusion unit is used to cascade the index data of different sensors and the feature information in the historical data of the target slope protection, fuse them and form a comprehensive slope protection data set;

[0036] The data partitioning unit is used to perform dimensionality reduction processing on the feature vector and filter out feature subsets through feature selection; the processed slope protection comprehensive data set is divided into a training set and a validation set.

[0037] As a further improvement of the present invention, the model establishment submodule includes:

[0038] The model training unit is used to build a decision tree to train the slope protection structure model according to the objectives of the slope protection structure model; the slope protection structure model is trained using the training set data, and 10-fold cross-validation is used to optimize the model parameters and adjust the hyperparameters;

[0039] Among them, a comprehensive evaluation function C is defined, which consists of two parts: the complexity of the tree T and the prediction error E i′ ; The comprehensive evaluation function C is defined as:

[0040]

[0041] Among them, C is the comprehensive evaluation function that you want to minimize, n′ is the number of leaf nodes in the decision tree, which represents the complexity of the tree; E i′ is the prediction error on the i′th leaf node, α and β are coefficients that balance complexity and error;

[0042] Define the prediction error E i′is:

[0043]

[0044] where y j′ is the true value, is the predicted value, N i′ is the number of samples on the i'-th leaf node, I(N i′ <k) is an indicator function. When the number of samples on the leaf node is less than k, I(N i′ <k) = 1, otherwise I(N i′ <k) ≠ 1; The function prevents the leaf node from being too small by adding a penalty term; γ is the coefficient of the penalty term, and k is a threshold;

[0045] The complexity T of the tree is further defined as:

[0046]

[0047] where log(N i′ ) represents the logarithm of the number of samples on the i'-th leaf node, and there is a natural penalty for the complexity of the tree; δ is a coefficient used to balance the impact of the number of leaf nodes on the complexity; Finally, the goal is to find the optimal decision tree structure to minimize C;

[0048] A model evaluation unit for evaluating the performance of the slope protection structure model using the validation set data and using the random search method to find the best hyperparameter combination of the slope protection structure model;

[0049] A model analysis unit for retraining on the training set using the optimized slope protection structure model and performing a final performance evaluation on the test set; calculating the accuracy and recall rate metrics of the slope protection structure model based on historical data analysis of the prediction performance of the model.

[0050] As a further improvement of the present invention, the identification and warning sub-module includes:

[0051] A warning threshold setting unit for constructing derivative indicators of each monitoring index, determining the risk types of each derivative indicator, setting the warning thresholds of each index, comparing the data values of each derivative indicator with the corresponding warning thresholds in real time, and determining whether to give a warning according to the number of derivative indicators exceeding the warning thresholds;

[0052] A risk level classification unit for calculating the comprehensive hazard degree of each monitoring point in combination with the weight coefficient according to the calculation result;

[0053] A warning response unit for automatically generating a warning message by the system when the detected data exceeds the warning threshold and generating a corresponding warning report according to the risk level.

[0054] As a further improvement of the present invention, the risk level classification unit classifies landslide risk into a normal level with no emergency, a warning level with sliding volume exceeding seasonal disturbance, and an alarm level with severe activation of unstable areas.

[0055] The real-time data acquisition and preprocessing of the present invention are key to monitoring slope stability, helping to promptly identify potential problems and provide support for decision-making; data fusion and real-time alarms help to promptly identify and resolve problems in data transmission, ensuring the stability and reliability of the monitoring system; the establishment and application of slope protection structure models help to detect the risk of slope instability in advance, providing a time window for collecting corresponding prevention and control measures, thereby ensuring the safety and stability of the slope. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a functional module diagram of an embodiment of a real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0057] Figure 2 This is a schematic diagram of the functional modules of the ecological data acquisition module of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0058] Figure 3 This is a schematic diagram of the functional modules of the data acquisition submodule of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0059] Figure 4 This is a schematic diagram of the functional modules of the data processing module of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0060] Figure 5 This is a schematic diagram of the functional modules of the analysis and alarm submodule of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0061] Figure 6 This is a schematic diagram of the functional modules of the slope protection structure model module of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0062] Figure 7 This is a schematic diagram of the functional modules of the data collection submodule of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0063] Figure 8 This is a schematic diagram of the functional modules of the model establishment submodule of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0064] Figure 9This is a schematic diagram of the functional modules of the identification and warning submodule of an embodiment of the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things of the present invention;

[0065] Figure 10 This is a schematic structural diagram of an embodiment of an electronic device of the present invention;

[0066] Figure 11 This is a schematic structural diagram of an embodiment of a storage medium of the present invention. DETAILED DESCRIPTION

[0067] 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0068] The terms "first", "second" and "third" in the present invention are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of the present invention (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0069] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0070] like Figure 1As shown, this embodiment provides an embodiment of a real-time monitoring system for an ecological slope protection structure based on sensors and the Internet of Things. In this embodiment, the real-time monitoring system for an ecological slope protection structure based on sensors and the Internet of Things specifically includes:

[0071] Ecological data acquisition module 1 is used to collect key indicator data such as slope displacement, inclination, stress and water level change in real time through displacement sensors, rainfall sensors, soil moisture sensors, etc., and pre-process the collected indicator data;

[0072] Data processing module 2 is used to fuse data from multiple sensor nodes, transmit the pre-processed data to the control center through wireless communication technology, perform preliminary data processing and analysis, and issue real-time alarms when sensor data is missing;

[0073] Slope protection structure model module 3 divides the processed index data into training sets and validation sets, establishes an ecological slope protection structure model, and identifies and warns of potential dangers by analyzing the changing trends of multiple parameters such as soil moisture, rainfall, and displacement, combining historical data and real-time monitoring results.

[0074] Preferably, the ecological data acquisition module 1 of this embodiment collects key indicator data such as displacement, inclination, stress, water level change, etc. of the slope in real time through displacement sensors, rainfall sensors, soil moisture sensors, etc., and performs preprocessing; ensures the accuracy and integrity of the data, and provides a reliable basis for analysis; the data processing module 2 fuses the data of multiple sensor nodes and transmits it to the control center through wireless communication technology for preliminary data processing and analysis, and issues a real-time alarm when sensor data is missing; improves data transmission efficiency and data quality, ensures that the control center can obtain a complete data set in real time, and issues an alarm in time when data is missing; the slope protection structure model module 3 divides the processed indicator data into a training set and a validation set, establishes an ecological slope protection structure model, and identifies and warns potential dangers by analyzing the changing trends of multiple parameters such as soil moisture, rainfall, displacement, etc., combined with historical data and real-time monitoring results; through model prediction and analysis, improves the accuracy of slope stability assessment, and provides a scientific basis for the optimization and maintenance of slope protection structures.

[0075] In summary, real-time data acquisition and preprocessing in this embodiment are key to monitoring slope stability, helping to promptly identify potential problems and provide support for decision-making; data fusion and real-time alarms help to promptly identify and resolve problems in data transmission, ensuring the stability and reliability of the monitoring system; the establishment and application of slope protection structure models help to detect the risk of slope instability in advance, providing a time window for acquiring corresponding prevention and control measures, thereby ensuring the safety and stability of the slope.

[0076] Further, if Figure 2As shown, the ecological data collection module 1 specifically includes:

[0077] The sensor deployment submodule 11 is used to install sensors at the slope monitoring points to monitor the slope displacement, tilt angle, stress, water level and other key indicator data in real time;

[0078] The data acquisition submodule 12 is used to obtain the displacement and rate of the slope through the displacement sensor; measure the change of the slope inclination angle using the inclinometer; obtain the stress condition inside the soil through the soil pressure sensor or strain gauge; and monitor the rainfall and groundwater level changes through the rain sensor and groundwater level gauge;

[0079] The data pre-processing submodule 13 is used to perform corrections according to the characteristics of different sensors, perform preliminary pre-processing on the collected data, and uniformly format the data from different sensors.

[0080] Preferably, the sensors of the sensor deployment submodule 11 of this embodiment are installed at key monitoring points of the slope; ensuring that the sensors can accurately and in real time monitor various key indicator data of the slope, such as displacement changes, inclination angles, stress conditions, and water level changes; the data acquisition submodule obtains the displacement and rate of the slope through the displacement sensor to reflect the deformation of the slope; uses the inclinometer to measure the changes in the inclination angle of the slope to understand the inclination state of the slope; obtains the stress conditions inside the soil through the soil pressure sensor or strain gauge to judge the stability of the slope; monitors the rainfall and groundwater level changes through the rain sensor and the groundwater level meter, and analyzes their impact on the stability of the slope; the data preprocessing submodule 13 performs corrections according to the characteristics of each sensor to ensure the accuracy of the data; performs preliminary preprocessing on the collected data, such as denoising and filtering, to improve the data quality; and formats the data of different sensors in a unified manner to facilitate data analysis and processing.

[0081] In summary, this embodiment can timely detect abnormal changes in slopes through comprehensive and real-time monitoring, providing data support for preventing disasters such as slope landslides and collapses; it helps managers understand the stability of slopes and provides a basis for decision-making and maintenance; the collected data provides a basis for slope stability analysis and assessment; the accuracy and real-time nature of the data are crucial for timely detection of potential risks in slopes; protective gear preprocessing is an important prerequisite for data analysis, which can ensure the accuracy and reliability of the analysis; uniformly formatted data facilitates storage, management and sharing, improving the efficiency of data processing.

[0082] Furthermore, if Figure 3 As shown, the data acquisition submodule 12 in the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things in this embodiment includes:

[0083] The displacement monitoring unit 121 is used to monitor the horizontal and vertical displacement changes of the slope surface in real time using a high-precision displacement sensor, and to measure the slope's tilt angle changes in combination with an inclinometer to comprehensively monitor the deformation of the slope;

[0084] The stress monitoring unit 122 is used to bury a soil pressure sensor in a drilled hole inside the slope, obtain the stress condition inside the soil through the soil pressure sensor or strain gauge, and monitor the stress changes at different depths in real time;

[0085] The rainfall monitoring unit 123 is used to deploy rain sensors around the target slope to monitor rainfall changes through the rain sensors, and to deploy groundwater level sensors inside the slope to detect changes in groundwater levels.

[0086] Preferably, the displacement monitoring unit 121 of this embodiment uses a high-precision displacement sensor to monitor the horizontal and vertical displacement changes of the slope surface in real time, and can provide displacement data accurate to the millimeter level; combined with the inclinometer to measure the inclination angle change of the slope, the deformation of the slope in three-dimensional space can be fully understood; the stress monitoring unit 122 soil pressure sensor is buried in the drilled hole inside the slope, and can monitor the stress distribution inside the soil in real time; the stress change of the soil at different depths is obtained through the strain gauge, and the stress state inside the slope and its change trend over time can be understood; the rainfall monitoring unit 123 arranges rainfall sensors around the target slope, which can monitor the rainfall change in real time and provide meteorological data for slope stability analysis; the groundwater level sensor is arranged inside the slope, which can detect the change of the groundwater level and reflect the moisture dynamics inside the slope.

[0087] In summary, this embodiment can timely detect small deformations of the slope, which helps to predict potential landslide or collapse risks; provide key data support for the assessment of slope stability, which helps to formulate effective protective measures; evaluate the bearing capacity and stability of the soil inside the slope, and provide a basis for slope reinforcement design; timely detect stress concentration areas and prevent slope damage caused by excessive stress; rainfall is one of the important factors leading to slope instability, and real-time monitoring of rainfall can help predict changes in slope stability under rainfall conditions; changes in groundwater level directly affect the moisture content and mechanical properties of slope soil, and monitoring of groundwater level can help to timely detect potential hydrogeological problems.

[0088] Furthermore, if Figure 4 As shown, the data processing module 2 in the real-time monitoring system of the ecological slope protection structure based on sensors and the Internet of Things in this embodiment includes:

[0089] The data fusion submodule 21 is used to aggregate the pre-processed data of each sensor node to the data fusion submodule for data fusion processing;

[0090] The wireless communication transmission submodule 22 is used to compress the fused data of each sensor node and transmit it to the analysis and alarm submodule through wireless communication technology;

[0091] The analysis and alarm submodule 23 is used to perform preliminary analysis on the received sensor data to detect abnormal events or patterns. If missing sensor data is found or data anomalies are detected, an alarm mechanism is triggered to notify relevant personnel to take measures.

[0092] Among them, the expression of the data fusion submodule 21 is:

[0093]

[0094] Where, F 21 Indicates the fused data value; w i represents the weight of the i-th sensor data, which is determined according to the importance and reliability of the sensor; x i Represents the raw data value of the i-th sensor; ∈ i represents the error term of the i-th sensor data; δ i represents the uncertainty coefficient of the i-th sensor data; n represents the total number of sensors;

[0095] The expression of the wireless communication transmission submodule 22 is:

[0096]

[0097] Where: C 22 Indicates wireless communication transmission efficiency; s j Indicates the size of the jth data packet; t j represents the time taken to transmit the jth data packet; γ j represents the additional delay of the jth packet transmission; β j represents the priority coefficient of the jth data packet transmission; m represents the total number of data packets transmitted.

[0098] Preferably, the data fusion submodule 21 of this embodiment aggregates the preprocessed data from different sensor nodes; integrates the data through a data fusion algorithm or model to provide more comprehensive and accurate information; the wireless communication transmission submodule 22 compresses the fused data to reduce the amount of data required for transmission; utilizes wireless communication technology to efficiently and reliably transmit the compressed data to the analysis and alarm submodule; the analysis and alarm submodule 23 performs a preliminary analysis on the received sensor data to detect abnormal events or patterns; and triggers an alarm mechanism when a lack of sensor data or data anomalies is detected.

[0099] In summary, data fusion in this embodiment can reduce the noise and uncertainty of individual sensor data, improving data reliability and accuracy. By integrating information from multiple sensors, a more comprehensive system view can be obtained, facilitating analysis and decision-making. Data compression reduces transmission costs and time, improving system efficiency. Wireless communication frees data transmission from the constraints of physical connections, increasing system flexibility and scalability. Reliable transmission ensures data integrity and accuracy, providing a foundation for analysis.

[0100] Further, if Figure 5 As shown, the analysis and alarm submodule 23 in the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things in this embodiment includes:

[0101] Anomaly detection unit 231 is used to analyze the data using a preset threshold value and statistically detect data points that are outside the normal range to determine whether there are abnormal events or patterns;

[0102] an alarm setting unit 232 for setting alarm rules so that the system generates an alarm signal when sensor data exceeds a preset threshold or no data is received within a specific time period;

[0103] The emergency response unit 233 is used to record a detailed analysis of each alarm and classify the severity of the alarm; after the alarm is released, the system automatically cancels the alarm and records the reason for the release.

[0104] Among them, the expression of the abnormality detection unit 231 is:

[0105]

[0106] Where: A 231 Indicates the result of anomaly detection; y k represents the actual value of the kth data point; represents the mean value of the data set; θ k represents the abnormal weight of the kth data point; p represents the total number of data points;

[0107] The expression of the alarm setting unit 232 is:

[0108]

[0109] Where: T 232 Indicates the alarm threshold; z l represents the lth preset threshold; Represents the average value of the preset threshold; φ l represents the sensitivity factor of the lth preset threshold; q represents the number of preset thresholds;

[0110] Expression of emergency response unit 233:

[0111]

[0112] Where: R 233 Indicates the emergency response level; v u Indicates the severity of the u-th alarm; Indicates the average value of alarm severity; κ u It represents the urgency coefficient of the u-th alarm; r represents the number of alarms.

[0113] Preferably, the anomaly detection unit 231 of this embodiment uses a preset threshold to perform statistical analysis on the data, which can efficiently identify data points that are beyond the normal range; through statistical methods, it can more accurately judge abnormal events or patterns in the data and reduce false alarms and missed alarms; the alarm setting unit 232 allows users to set flexible alarm rules according to actual needs, such as triggering an alarm when the data exceeds a preset threshold or no data is received within a specific time period; the system can automatically generate an alarm signal and promptly notify relevant personnel for processing; the emergency response unit 233 records a detailed analysis of each alarm, including information such as the alarm time, cause, severity, etc., which provides an important basis for analysis and investigation; grading the severity of the alarm helps enterprises take corresponding emergency measures according to different levels of alarms; after the alarm is lifted, the system automatically cancels the alarm and records the reason for the release, ensuring the accuracy and completeness of the alarm information.

[0114] In summary, this embodiment improves the accuracy and efficiency of anomaly detection, and provides reliable data support for alarm and emergency response; enables the system to promptly detect potential problems or risks, and provides strong protection for the safe operation of the enterprise; enhances the flexibility and configurability of the system, and meets the needs of different users and application scenarios; by timely generating alarm signals, it improves the enterprise's response speed and processing capabilities to abnormal events, and reduces potential losses; improves the efficiency and accuracy of emergency response, and provides strong support for enterprises to deal with emergencies; by recording and analyzing alarm information, it helps enterprises discover potential problems and loopholes, and provides direction for improvement and optimization; ensures the accuracy and completeness of alarm information, and avoids misjudgments and delays caused by inaccurate or missing information.

[0115] Furthermore, if Figure 6 As shown, the slope protection structure model module 3 in the real-time monitoring system of ecological slope protection structure based on sensors and the Internet of Things in this embodiment includes:

[0116] The data collection submodule 31 is used to receive the processed index data collected by the sensor and the historical data of the target slope protection, extract key features from the index data and the historical data, and divide the processed data into a training set and a validation set;

[0117] The model building submodule 32 is used to train the slope protection structure model and optimize the model parameters by combining the cross-validation technology; the model is trained using the training set data and the model performance is evaluated using the validation set;

[0118] The identification and warning submodule 33 is used to use the trained and evaluated slope protection structure model for real-time monitoring data, and conduct dynamic analysis in combination with historical data to identify potential danger areas and issue warning information, and generate risk level maps and warning reports.

[0119] Preferably, the data collection submodule 31 of this embodiment can efficiently receive the processed indicator data collected by the sensor, reflecting the real-time status of the slope protection structure; at the same time, it receives the historical data of the target slope protection, providing rich background information for model training and analysis; extracts key features from the indicator data and historical data; divides the processed data into a training set and a validation set to provide data support for model training and evaluation; the model establishment submodule 32 can select a suitable machine learning algorithm for model training according to the characteristics of the slope protection structure; optimizes the model parameters in combination with cross-validation technology to improve the generalization ability of the model; uses the training set data to train the model, and evaluates the model performance through the validation set to ensure the accuracy and reliability of the model; the identification and warning submodule 33 uses the trained and evaluated slope protection structure model for real-time monitoring data to realize dynamic monitoring of the slope protection structure; combines historical data for dynamic analysis to more accurately identify potential danger areas; when potential dangers are identified, timely issues warning information to provide time guarantee for relevant personnel to take measures; generates risk level maps and warning reports to intuitively display the safety status and potential risks of the slope protection structure.

[0120] In summary, data collection in this embodiment is a prerequisite for model training and early warning analysis, feature extraction improves data utilization and model accuracy; data set division ensures the fairness and effectiveness of model training and evaluation; model establishment is the core of the early warning system and determines the system's early warning accuracy and reliability; cross-validation optimization improves the generalization ability of the model and reduces the risk of overfitting; model training and evaluation provide strong support for early warning analysis; real-time monitoring and dynamic analysis improve the timeliness and accuracy of the early warning system; early warning information generation and risk level maps and reports provide strong decision-making support for relevant personnel; the entire identification and early warning process helps to timely discover and deal with safety hazards of slope protection structures and protect people's lives and property.

[0121] Further, if Figure 7 As shown, the data collection submodule 31 in the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things in this embodiment includes:

[0122] The feature extraction unit 311 is used to calculate the high-order statistics of each index data and the target slope protection historical data, including mean, variance and skewness, and extract features and parameters from the index data and the target slope protection historical data;

[0123] The feature fusion unit 312 is used to cascade the index data of different sensors and the feature information in the historical data of the target slope protection, and perform feature fusion to form a comprehensive slope protection data set;

[0124] The data partitioning unit 313 is used to perform dimensionality reduction processing on the feature vector and select a feature subset through feature selection; and to divide the processed slope protection comprehensive data set into a training set and a validation set.

[0125] Preferably, the feature extraction unit 311 of this embodiment calculates high-order statistics of each indicator data and the historical data of the target slope protection, such as the mean, variance and skewness, etc.; extracts features and parameters that are indicative of the slope protection status from these data; the feature fusion unit 312 performs feature fusion by cascading the indicator data of different sensors and the feature information in the historical data of the target slope protection; forms a comprehensive data set containing multiple dimensions and sources to more comprehensively reflect the status of the slope protection; the data partitioning unit 313 performs dimensionality reduction processing on the feature vector to reduce computational complexity and avoid overfitting; screens out the feature subset that is most useful for target prediction through feature selection; and divides the processed slope protection comprehensive data set into a training set and a validation set for training and validating the model.

[0126] In summary, the high-order statistics of this embodiment provide richer information than a single numerical value, which helps to capture the distribution characteristics and changing trends of the data; the extracted features and parameters can serve as the basis for analysis to help identify potential problems or risks in slope protection; feature fusion can integrate information from different sensors to improve the integrity and accuracy of the data; the comprehensive data set provides richer input for machine learning or data analysis, which helps to improve the accuracy of prediction or diagnosis; dimensionality reduction processing can improve computational efficiency while retaining information useful for target prediction; feature selection helps to remove redundant and noisy data and improve the generalization ability of the model; the division of training sets and validation sets can ensure that the model can also perform well on unseen data, thereby verifying the reliability and practicality of the model.

[0127] Furthermore, if Figure 8 As shown, the model building submodule 32 in the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things in this embodiment includes:

[0128] The model training unit 321 is used to construct a decision tree to train the slope protection structure model according to the target of the slope protection structure model; use the training set data to train the slope protection structure model, and adapt 10-fold cross validation to optimize model parameters and adjust hyperparameters;

[0129] The model evaluation unit 322 is used to evaluate the performance of the slope protection structure model using the validation set data, and use the random search method to find the best hyperparameter combination of the slope protection structure model;

[0130] The model analysis unit 323 is used to retrain on the training set using the optimized slope protection structure model and perform the final performance evaluation on the test set; Analyze the prediction performance of the model based on historical data, and calculate the accuracy and recall rate indicators of the slope protection structure model.

[0131] Among them, when constructing a decision tree to solve the underfitting problem, it is to minimize the combination of the complexity of the decision tree and the prediction error; Define a comprehensive evaluation function C, which consists of two parts: the complexity T of the tree and the prediction error E i′ ; The comprehensive evaluation function C is defined as:

[0132]

[0133] Among them, C is the comprehensive evaluation function to be minimized, n′ is the number of leaf nodes of the decision tree, representing the complexity of the tree; E i′ is the prediction error on the i′-th leaf node, which can be calculated by the weighted error sum, and α and β are the coefficients to balance the complexity and the error;

[0134] Define the prediction error E i′ as:

[0135]

[0136] In the formula, y j′ is the true value, is the predicted value, N i′ is the number of samples on the i′-th leaf node, I(N i′ <k) is an indicator function. When the number of samples on the leaf node is less than k, I(N i′ <k) = 1, otherwise I(N i′ <k) ≠ 1; The function adds a penalty term to prevent the leaf node from being too small, thus avoiding overfitting; γ is the coefficient of the penalty term, and k is a threshold;

[0137] The complexity T of the tree can be further defined as:

[0138]

[0139] In the formula, log(N i′) represents the logarithm of the number of samples on the i′th leaf node, which has a natural penalty on the complexity of the tree, because the more samples there are, the more important the corresponding leaf node is; δ is a coefficient used to balance the impact of the number of leaf nodes on complexity; ultimately, the goal is to find the optimal decision tree structure that minimizes C; taking into account the complexity of the tree and the prediction error.

[0140] Preferably, the model training unit 321 of this embodiment selects a decision tree as a basic model for training according to the goal of the slope protection structure model; trains the decision tree model through the training set data so that it can learn the characteristics and rules in the data; adopts a 10-fold cross-validation method to divide the training set data into 10 parts, and uses 9 of them as training data and 1 as verification data in turn to evaluate and adjust the model parameters; this helps to reduce overfitting and improve the generalization ability of the model; on the basis of cross-validation, adjusts the hyperparameters of the model (such as the depth of the decision tree, the minimum number of samples for splitting nodes, etc.) to further optimize the performance of the model; the model evaluation unit 322 uses the cross-validation method to evaluate the model parameters; The performance of the preliminarily trained decision tree model is evaluated on the evidence set data to test the performance of the model on unseen data; a random search method is used to find the best hyperparameter combination in the predefined parameter space; different parameter combinations can be efficiently explored to find the hyperparameters that optimize the model performance; the model analysis unit 323 uses the optimized hyperparameter combination to retrain the decision tree model on the training set to ensure that the model can fully utilize the advantages of these parameters; a final performance evaluation is performed on the retrained model on the test set to test the performance of the model in actual applications; based on historical data, the accuracy and recall rate indicators of the model are calculated to comprehensively evaluate the predictive performance of the model.

[0141] In summary, this embodiment ensures that the model can be fully optimized during the training phase, thereby improving the model's prediction accuracy and generalization ability; through 10-fold cross-validation and hyperparameter adjustment, the model can better adapt to different data sets, laying a solid foundation for performance evaluation and practical application; through strict performance evaluation and parameter tuning, the stability and reliability of the model in practical applications are guaranteed; through the random search method, the model can find the optimal hyperparameter combination, further improving the model's prediction accuracy and generalization ability; through the final performance evaluation and indicator calculation, strong support is provided for the practical application of the model; through indicators such as accuracy and recall rate, the performance of the model in different aspects can be intuitively understood, providing a basis for model improvement and optimization; at the same time, the retrained and optimized model also ensures the stability and reliability of the model in practical applications.

[0142] Further, if Figure 9 As shown, the identification and warning submodule 33 in the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things in this embodiment includes:

[0143] The warning threshold setting unit 331 is used to construct a derivative indicator for each monitoring indicator, determine the risk type of each derivative indicator, set a warning threshold for each indicator, compare the data value of each derivative indicator with the corresponding warning threshold in real time, and determine whether to issue a warning based on the number of derivative indicators that exceed the warning threshold;

[0144] The risk level classification unit 332 is used to calculate the comprehensive danger level of each monitoring point in combination with the weight coefficient, and according to the calculation result, classify the landslide risk into a normal level with no emergency, a warning level with the amount of sliding exceeding the seasonal disturbance, and an alarm level with severe activation in unstable areas;

[0145] The early warning response unit 333 is used to determine when the detection data exceeds the early warning threshold, the system automatically generates early warning information, and generates a corresponding early warning report according to the risk level.

[0146] Preferably, the warning threshold setting unit 331 of this embodiment constructs a derivative indicator, determines the risk type, sets a warning threshold, and compares the data value with the warning threshold in real time to determine whether to issue a warning; by accurately setting the warning threshold, the unit can promptly identify derivative indicators that exceed the normal range, thereby triggering the warning mechanism; the risk level division unit 332 calculates the comprehensive degree of danger in combination with the weight coefficient, and divides the landslide risk into different levels; by comprehensively considering multiple monitoring indicators and their weights, the unit can more comprehensively assess the landslide risk and provide a scientific basis for risk response; the warning response unit 333 automatically generates warning information when the detection data exceeds the warning threshold, and generates a warning report according to the risk level; it realizes the automatic generation and reporting of warning information, and improves the efficiency and accuracy of emergency response.

[0147] In summary, this embodiment improves the sensitivity and accuracy of the early warning system, helps to timely detect potential risks; helps decision makers take corresponding measures according to the risk level and improve the prevention and control capabilities of landslide disasters; helps relevant departments quickly understand the risk situation, take timely response measures, and reduce disaster losses.

[0148] like Figure 10 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 4 includes a processor 41 and a memory 42 coupled to the processor 41.

[0149] The memory 42 stores program instructions for implementing the real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things according to any of the above embodiments.

[0150] The processor 41 is used to execute program instructions stored in the memory 42 to layout the real-time monitoring system of the ecological slope protection structure based on sensors and the Internet of Things.

[0151] The processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having signal processing capabilities. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The general-purpose processor may be a microprocessor or any conventional processor.

[0152] Furthermore, Figure 11 This is a schematic diagram of the structure of a storage medium in an embodiment of the present application. The storage medium 5 in the embodiment of the present application stores program instructions 51 that can implement all the above methods, wherein the program instructions 51 can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, server, mobile phone, and tablet.

[0153] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0154] In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units. The above is only an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0155] The above detailed description of the specific embodiments of the invention is intended to be illustrative only, and the present invention is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of the present invention. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present invention are also encompassed within the scope of the present invention.

Claims

1. A real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things, characterized in that: The real-time monitoring system for ecological slope protection structures based on sensors and the Internet of Things includes: The ecological data acquisition module is used to collect key indicator data of slope displacement, inclination, stress and water level changes in real time through sensors, and pre-process the collected indicator data; The data processing module is used to fuse the data from multiple sensor nodes, transmit the pre-processed data to the control center through wireless communication technology, and perform preliminary data processing and analysis; The slope protection structure model module divides the processed index data into training sets and validation sets, establishes an ecological slope protection structure model, and identifies and warns of potential dangers by analyzing the changing trends of multiple parameters such as soil moisture, rainfall, and displacement, combined with historical data and real-time monitoring results.

2. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 1 is characterized in that: Ecological data collection module, including: The sensor deployment submodule is used to install sensors at slope monitoring points to monitor the slope's displacement, tilt angle, stress, and key indicator data of water level changes in real time. The data acquisition submodule is used to obtain the displacement and rate of the slope through the displacement sensor; measure the change of the slope inclination angle using the inclinometer; obtain the stress condition inside the soil through the soil pressure sensor or strain gauge; and monitor the rainfall and groundwater level changes through the rain sensor and groundwater level gauge; The data preprocessing submodule is used to perform corrections according to the characteristics of different sensors, perform preliminary preprocessing on the collected data, and uniformly format the data from different sensors.

3. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 2 is characterized in that: Data acquisition submodule, including: The displacement monitoring unit is used to monitor the horizontal and vertical displacement changes of the slope surface in real time using a high-precision displacement sensor, and combines it with an inclinometer to measure the slope's inclination angle changes to comprehensively monitor the slope's deformation; The stress monitoring unit is used to bury soil pressure sensors in drilled holes inside the slope. The soil stress conditions are obtained through soil pressure sensors or strain gauges, and stress changes at different depths are monitored in real time. The rainfall monitoring unit is used to deploy rain sensors around the target slope, monitor rainfall changes through the rain sensors, and deploy groundwater level sensors inside the slope to detect changes in groundwater levels.

4. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 1 is characterized in that: Data processing module, including: The data fusion submodule is used to aggregate the pre-processed data of each sensor node to the data fusion submodule for data fusion processing; The wireless communication transmission submodule is used to compress the fused data of each sensor node and transmit it to the analysis and alarm submodule through wireless communication technology; The analysis and alarm submodule is used to perform preliminary analysis on the received sensor data to detect abnormal events or patterns. If missing sensor data is found or data anomalies are detected, the alarm mechanism is triggered to notify relevant personnel to take measures.

5. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 4 is characterized in that: Analysis and alarm submodule, including: Anomaly detection unit, which is used to analyze the data using preset thresholds and statistically detect data points that fall outside the normal range to determine whether there are abnormal events or patterns; An alarm setting unit, used to set alarm rules so that when sensor data exceeds a preset threshold or no data is received within a specific time period, the system generates an alarm signal; The emergency response unit is used to record detailed analysis of each alarm and grade the severity of the alarm; after the alarm is lifted, the system automatically cancels the alarm and records the reason for the release.

6. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 1 is characterized in that: Slope protection structure model module, including: The data collection submodule is used to receive the processed indicator data collected by the sensor and the historical data of the target slope protection, extract key features from the indicator data and historical data, and divide the processed data into a training set and a validation set; The model building submodule is used to train the slope protection structure model and optimize the model parameters by combining cross-validation technology; the model is trained using the training set data and the model performance is evaluated using the validation set; The identification and early warning submodule is used to use the trained and evaluated slope protection structure model for real-time monitoring data, and conduct dynamic analysis in combination with historical data to identify potential danger areas and issue early warning information, and generate risk level maps and early warning reports.

7. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 6 is characterized in that: Data collection submodule, including: A feature extraction unit is used to calculate the high-order statistics of each index data and the target slope protection historical data, and extract features and parameters from the index data and the target slope protection historical data; The feature fusion unit is used to cascade the index data of different sensors and the feature information in the historical data of the target slope protection, fuse them and form a comprehensive slope protection data set; The data partitioning unit is used to perform dimensionality reduction processing on the feature vector and filter out feature subsets through feature selection; the processed slope protection comprehensive data set is divided into a training set and a validation set.

8. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 6 is characterized in that: Model building submodule, including: The model training unit is used to build a decision tree to train the slope protection structure model according to the objectives of the slope protection structure model; the slope protection structure model is trained using the training set data, and 10-fold cross-validation is used to optimize the model parameters and adjust the hyperparameters; Among them, a comprehensive evaluation function C is defined, which consists of two parts: the complexity of the tree T and the prediction error E i′ ; The comprehensive evaluation function C is defined as: Among them, C is the comprehensive evaluation function that you want to minimize, n′ is the number of leaf nodes in the decision tree, which represents the complexity of the tree; E i′ is the prediction error on the i′th leaf node, α and β are coefficients that balance complexity and error; Define the prediction error E i′ for: where y j′ is the true value, is the predicted value, N i′ is the number of samples on the i'-th leaf node, I(N i′ <k) is an indicator function. When the number of samples on the leaf node is less than k, I(N i′ <k) = 1, otherwise I(N i′ <k) ≠ 1; The function prevents the leaf node from being too small by adding a penalty term; γ is the coefficient of the penalty term, and k is a threshold; The complexity T of a tree is further defined as: Where, log(N i′ ) represents the logarithm of the number of samples on the i′th leaf node, which has a natural penalty on the complexity of the tree; δ is a coefficient used to balance the impact of the number of leaf nodes on the complexity; ultimately, the goal is to find the optimal decision tree structure that minimizes C; The model evaluation unit is used to evaluate the performance of the slope protection structure model using the validation set data and to find the optimal hyperparameter combination of the slope protection structure model using a random search method; The model analysis unit is used to retrain the optimized slope protection structure model on the training set and perform final performance evaluation on the test set; the prediction performance of the model is analyzed based on historical data, and the accuracy and recall rate indicators of the slope protection structure model are calculated.

9. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 6 is characterized in that: Identification and early warning submodules include: The warning threshold setting unit is used to construct the derivative indicators of each monitoring indicator, determine the risk type of each derivative indicator, set the warning threshold of each indicator, compare the data value of each derivative indicator with the corresponding warning threshold in real time, and determine whether to issue a warning based on the number of derivative indicators that exceed the warning threshold; The risk level division unit is used to calculate the comprehensive risk level of each monitoring point in combination with the weight coefficient, based on the calculation results; The early warning response unit is used to determine when the detection data exceeds the early warning threshold. The system automatically generates early warning information and generates corresponding early warning reports based on the risk level.

10. The real-time monitoring system for ecological slope protection structure based on sensors and the Internet of Things according to claim 9 is characterized in that: The risk classification unit classifies landslide risk into a normal level with no emergency, a warning level where the amount of sliding exceeds seasonal disturbances, and an alert level with severe activation in unstable areas.

Images