Early warning method and system for preventing frost heaving of screw anchor foundation

Abstract

The invention discloses a screw anchor foundation frost heaving prevention early warning method and system, and belongs to the technical field of geotechnical engineering safety monitoring. According to the method, basic data are collected through temperature, frost heaving force and displacement sensors on a screw anchor structure, and analog signals are converted into digital signals through a data collection module; the data transmission module transmits the data to the data analysis and processing module, and basic quantization parameters such as the temperature change rate and the temperature gradient are calculated through a set algorithm; in combination with set historical data, analyzing by using a machine learning model to obtain a frost heaving risk level; the early warning module performs graded early warning according to the risk grades; and finally, storing the basic data, the quantitative parameters and the risk levels in a classified manner, and establishing a data index. Accurate monitoring and early warning of the frost heaving risk are achieved, the engineering safety and operation and maintenance efficiency of the spiral anchor foundation in the frozen soil area are improved, and the method is suitable for engineering scenes such as wind power and power transmission.

Description

Technical Field

[0001] This invention relates to the field of geotechnical engineering safety monitoring technology, specifically to a method and system for early warning of frost heave in spiral anchor foundations. Background Technology

[0002] In permafrost regions, helical anchor foundations are widely used in various engineering projects such as wind turbine tower foundations, transmission line tower foundations, and communication base station foundations due to their advantages of convenient construction and good load-bearing capacity. However, as a special type of soil, permafrost presents a severe challenge to the long-term stability of helical anchor foundations due to its unique physical and mechanical properties, with frost heave being a particularly prominent issue.

[0003] The frost heave phenomenon in permafrost is essentially caused by the phase change and freezing of water in the soil pores at low temperatures, resulting in volume expansion. As the ambient temperature drops, unfrozen water in the soil gradually migrates towards the freezing front and freezes, causing the soil volume to continuously increase. This volume expansion generates significant frost heave forces on the helical anchor foundation, causing it to bear enormous additional loads. Under the continuous action of frost heave forces, the helical anchor foundation may experience vertical uplift, horizontal displacement, or even serious damage such as tilting and fracture, thereby threatening the safety and normal use of the entire engineering structure. According to relevant engineering statistics, the number of cases of helical anchor foundation failure due to frost heave in permafrost regions is increasing year by year. In some projects, the proportion of foundation displacement exceeding the design allowable value within 3-5 years after commissioning is as high as 20%-30%, causing not only huge economic losses but also seriously affecting the service life and reliability of the project.

[0004] Currently, monitoring methods for frost heave in helical anchor foundations have many limitations. Traditional single-sensor monitoring methods, such as using only thermometers to monitor soil temperature, can only obtain temperature change information and cannot directly reflect the effect of frost heave force on the foundation or the actual deformation of the foundation. On the other hand, relying solely on displacement sensors to monitor foundation displacement makes it difficult to trace the root cause of the displacement and accurately judge the development trend of frost heave risk. In addition, some existing monitoring systems lack intelligent data processing and analysis capabilities, and mostly rely on manual data reading and experience-based judgment, which is not only inefficient but also prone to misjudgment and omission. Even if some systems have introduced automated data acquisition functions, due to imperfect data processing algorithms, they cannot effectively integrate and analyze multi-source data, making it difficult to comprehensively and accurately assess the frost heave risk level of helical anchor foundations and failing to meet the high-precision and real-time requirements of engineering safety monitoring in permafrost areas.

[0005] In summary, existing monitoring technologies for addressing frost heave in helical anchor foundations suffer from limitations such as single monitoring parameters, insufficient data processing and analysis capabilities, and poor early warning accuracy, making it difficult to effectively control frost heave risks.

[0006] Therefore, how to invent a spiral anchor foundation anti-frost heave early warning system that can perform multi-parameter collaborative monitoring, has intelligent data processing and accurate early warning functions, has become a key technical problem that urgently needs to be solved in the field of engineering construction in permafrost areas. Summary of the Invention

[0007] To address this, the present invention provides a method and system for early warning of frost heave in spiral anchor foundations. By conducting multi-parameter collaborative monitoring, intelligent data processing, and accurate early warning, it solves the problems of single monitoring parameters, insufficient data processing and analysis capabilities, and poor early warning accuracy in existing technologies.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a method for early warning of frost heave in helical anchor foundations, comprising: Basic data is collected by sensors set on the spiral anchor structure; the basic data is then converted from analog signals to digital signals by the data acquisition module. The digital signal is transmitted to the data analysis and processing module via the data transmission module; By setting an algorithm, the raw data of temperature, frost heave force, and displacement in the digital signal are calculated to obtain basic quantitative parameters; based on the basic quantitative parameters and combined with set historical data, the frost heave risk level is obtained through analysis using a machine learning model. Based on the level of frost heave risk, the early warning module performs tiered early warning processing. The basic data, the basic quantitative parameters, and the frost heave risk level are classified and stored in the historical data storage module, and a data indexing mechanism is established.

[0009] As a preferred solution for frost heave early warning method for helical anchor foundations, during the process of calculating the original data of temperature, frost heave force, and displacement in the digital signal through the set algorithm, the dynamic temperature change is obtained by calculating the temperature change rate formula; and the temperature stratification is judged by the temperature gradient formula. The formula for the rate of temperature change is: ; In the formula, v is the rate of temperature change; The temperature at the current moment; The temperature at the previous moment; For time difference; The temperature gradient formula is: ; In the formula, For temperature gradient; , The temperatures of sensors i and j at different depths are respectively; The distance between the two sensors; The total frost heave force is calculated using the integral formula of tangential frost heave force; the total frost heave force is then corrected in real time using the frost heave force-temperature coupling formula. The integral formula for the tangential frost heave force is: ; In the formula, ρ represents the total frost heave force; s represents the contact area. Tangential stress; The frost heave force-temperature coupling formula is as follows: ; In the formula, F is the frost heave force; k is the comprehensive correction coefficient; V is the unit weight of the soil; V is the volume of soil affected by frost heave. This refers to the frost heave rate; This is the temperature gradient sensitivity coefficient.

[0010] As a preferred solution for frost heave early warning method for spiral anchor foundations, the machine learning model includes the following components during the analysis process: a feature engineering submodule, an LSTM time series prediction model, and an XGBoost risk assessment model. The feature engineering submodule performs sliding window statistical calculations and Fourier transforms on the basic quantization parameters to generate a high-latitude feature set. Based on the high-latitude feature set, the LSTM time series prediction model is used for prediction processing to output a predicted value of temperature change trend. Based on the high-latitude feature set, the predicted value of temperature change trend, and the set environmental parameters, the XGBoost risk assessment model is used for risk assessment to output the frost heave risk level.

[0011] As a preferred embodiment of a frost heave early warning method for helical anchor foundations, during the generation of the high-latitude feature set through the feature engineering submodule, the mean and standard deviation of the temperature data are calculated using the sliding window statistics; the formula for calculating the mean is: ; In the formula, The mean temperature is denoted as n; n is the number of samples in the statistical temperature data. Let be the temperature at time i. The formula for calculating the standard deviation is: ; In the formula, Standard deviation; The seasonal periodic characteristics of temperature data are extracted using Fourier transform; the Fourier transform formula is: ; In the formula, t represents the average temperature; k represents the frequency; m represents the number of harmonic frequency terms participating in the Fourier transform; t represents the time variable. For periodicity; , All are Fourier coefficients.

[0012] As a preferred embodiment of the frost heave prevention early warning method for helical anchor foundations, the early warning module sets three risk thresholds during the graded early warning process, corresponding to low-level, medium-level, and high-level early warnings. Low-level warnings trigger on-site audible and visual alarm devices; Intermediate warning triggers on-site audible and visual alarms and a remote platform warning interface; Advanced early warning triggers on-site audible and visual alarms and remote platform early warning interface, pushes early warning SMS to mobile terminals, automatically records early warning events and activates preset emergency plans.

[0013] This invention also provides a frost heave early warning system for helical anchor foundations, based on the above-mentioned frost heave early warning method for helical anchor foundations, comprising: The data acquisition unit is used to collect basic data through sensors set on the spiral anchor structure; and the data acquisition module converts the basic data from analog signals to digital signals. The data transmission unit is used to transmit the digital signal to the data analysis and processing module through the data transmission module; The data analysis and processing unit is used to calculate the raw data of temperature, frost heave force, and displacement in the digital signal through a set algorithm to obtain basic quantitative parameters; based on the basic quantitative parameters and combined with set historical data, it analyzes the data through a machine learning model to obtain the frost heave risk level. The early warning processing unit is used to perform graded early warning processing by the early warning module according to the frost heave risk level. The data storage unit is used to classify and store the basic data, the basic quantitative parameters and the frost heave risk level into the historical data storage module, and to establish a data indexing mechanism.

[0014] As a preferred solution for a frost heave early warning system for helical anchor foundations, the data analysis and processing unit calculates the original data of temperature, frost heave force, and displacement in the digital signal using the set algorithm, obtains the dynamic temperature change by calculating the temperature change rate formula, and judges the temperature stratification by using the temperature gradient formula. The formula for the rate of temperature change is: ; In the formula, v is the rate of temperature change; The temperature at the current moment; The temperature at the previous moment; For time difference; The temperature gradient formula is: ; In the formula, For temperature gradient; , The temperatures of sensors i and j at different depths are respectively; The distance between the two sensors; The total frost heave force is calculated using the integral formula of tangential frost heave force; the total frost heave force is then corrected in real time using the frost heave force-temperature coupling formula. The integral formula for the tangential frost heave force is: ; In the formula, ρ represents the total frost heave force; s represents the contact area. It is the tangential stress; The frost heave force-temperature coupling formula is as follows: ; In the formula, F is the frost heave force; k is the comprehensive correction coefficient; V is the unit weight of the soil; V is the volume of soil affected by frost heave. This refers to the frost heave rate; This is the temperature gradient sensitivity coefficient.

[0015] As a preferred solution for a frost heave early warning system for helical anchor foundations, the data analysis and processing unit includes, during the analysis process using the machine learning model, a feature engineering submodule, an LSTM time series prediction model, and an XGBoost risk assessment model. The feature engineering submodule performs sliding window statistical calculations and Fourier transforms on the basic quantization parameters to generate a high-latitude feature set. Based on the high-latitude feature set, the LSTM time series prediction model is used for prediction processing to output a predicted value of temperature change trend. Based on the high-latitude feature set, the predicted value of temperature change trend, and the set environmental parameters, the XGBoost risk assessment model is used for risk assessment to output the frost heave risk level.

[0016] As a preferred solution for a frost heave early warning system for helical anchor foundations, the data analysis and processing unit, during the generation of the high-latitude feature set through the feature engineering submodule, calculates the mean and standard deviation of the temperature data through sliding window statistics; the formula for calculating the mean is: ; In the formula, The mean temperature is denoted as n; n is the number of samples in the statistical temperature data. Let be the temperature at time i. The formula for calculating the standard deviation is: ; In the formula, Standard deviation; The seasonal periodic characteristics of temperature data are extracted using Fourier transform; the Fourier transform formula is: ; In the formula, t represents the average temperature; k represents the frequency; m represents the number of harmonic frequency terms participating in the Fourier transform; t represents the time variable. For periodicity; , All are Fourier coefficients.

[0017] As a preferred embodiment of a frost heave prevention early warning system for helical anchor foundations, in the early warning processing unit, during the process of graded early warning processing by the early warning module, the early warning module sets three risk thresholds, corresponding to low-level, medium-level, and high-level early warnings; Low-level warnings trigger on-site audible and visual alarm devices; Intermediate warning triggers on-site audible and visual alarms and a remote platform warning interface; Advanced early warning triggers on-site audible and visual alarms and remote platform early warning interface, pushes early warning SMS to mobile terminals, automatically records early warning events and activates preset emergency plans.

[0018] This invention has the following advantages: It collects basic data through sensors on the spiral anchor structure; the data acquisition module converts the basic data from analog signals to digital signals; the data transmission module transmits the digital signals to the data analysis and processing module; the algorithm calculates the raw data of temperature, frost heave force, and displacement in the digital signals to obtain basic quantitative parameters; based on the basic quantitative parameters and historical data, a machine learning model is used to analyze and obtain the frost heave risk level; according to the frost heave risk level, the early warning module performs graded early warning processing; the basic data, the basic quantitative parameters, and the frost heave risk level are classified and stored in the historical data storage module, and a data indexing mechanism is established. This invention comprehensively improves frost heave resistance by combining multi-parameter collaborative monitoring with structural optimization. Through a three-dimensional layout of thermocouple temperature sensors, miniature pressure sensors, and wire-type displacement sensors, it acquires three core parameters—temperature field, frost heave force, and displacement—in real time, overcoming the limitations of traditional single-sensor monitoring. Combined with the cross-shaped tower foundation and the structural design of four spiral anchors, a dual system of monitoring and reinforcement is formed, reducing the risk of frost heave damage from a structural perspective compared to traditional single-anchor foundations. This invention achieves dynamic quantitative assessment of frost heave risk through intelligent data processing, effectively addressing the insufficient data fusion and analysis capabilities in existing technologies. The early warning and control layer, based on multi-source data fusion results, triggers tiered early warnings through multiple methods such as audible and visual alarms and SMS push notifications, avoiding misjudgments and omissions caused by manual interpretation. Response time is reduced to minutes, significantly improving the safety and operational efficiency of helical anchor foundation projects in permafrost regions. This invention records raw monitoring data and analysis results throughout their entire lifecycle, combining historical data to achieve dynamic threshold calibration and model optimization, providing data support for the full lifecycle management of helical anchor foundations and solving the problem of insufficient data traceability and system optimization in existing technologies. This invention systematically solves the technical challenges of frost heave monitoring and control for helical anchor foundations in permafrost regions, possessing significant engineering application value and economic benefits. Attached Figure Description

[0019] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0020] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0021] Figure 1 This is a flowchart illustrating a method for early warning of frost heave in spiral anchor foundations provided in Embodiment 1 of the present invention. Figure 2 This is a schematic diagram illustrating the specific implementation process of a frost heave prevention early warning method for a spiral anchor foundation provided in Embodiment 1 of the present invention; Figure 3 This is a schematic diagram of the overall assembly structure of the spiral anchor in the anti-frost heave early warning method for spiral anchor foundations provided in Embodiment 1 of the present invention; Figure 4 This is a schematic diagram of the spiral anchor tower foundation structure in the spiral anchor foundation anti-frost heave early warning method provided in Embodiment 1 of the present invention; Figure 5 This is a schematic diagram of the internal structure of the spiral anchor in the anti-frost heave early warning method for spiral anchor foundations provided in Embodiment 1 of the present invention; Figure 6 This is a top view of the interior of the spiral anchor in the spiral anchor foundation anti-frost heave early warning method provided in Embodiment 1 of the present invention; Figure 7 This is a schematic diagram of the machine learning model processing flow in the anti-frost heave early warning method for helical anchor foundations provided in Embodiment 1 of the present invention; Figure 8 This is a schematic diagram of the architecture of a spiral anchor foundation anti-frost heave early warning system provided in Embodiment 2 of the present invention.

[0022] In the diagram, 1 is the tower foundation; 2 is the connecting column; 3 is the helical anchor foundation; 4 is the helical anchor; 5 is the helical anchor housing; 6 is the helical blade; and 7 is the thermocouple temperature sensor. Detailed Implementation

[0023] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Example 1

[0025] See Figure 1 and Figure 2 Embodiment 1 of the present invention provides a method for early warning of frost heave in spiral anchor foundations, comprising the following steps: S1. Collect basic data using sensors set on the spiral anchor structure; convert the basic data from analog signals to digital signals using a data acquisition module; S2. The digital signal is transmitted to the data analysis and processing module via the data transmission module; S3. Calculate the raw data of temperature, frost heave force, and displacement in the digital signal by setting an algorithm to obtain basic quantitative parameters; based on the basic quantitative parameters and combined with set historical data, analyze the data through a machine learning model to obtain the frost heave risk level. S4. Based on the level of frost heave risk, the early warning module performs graded early warning processing; S5. Classify and store the basic data, the basic quantitative parameters and the frost heave risk level into the historical data storage module, and establish a data indexing mechanism.

[0026] In this embodiment, in step S1, basic data is collected by a sensor set on the spiral anchor structure; the basic data is converted from analog signals to digital signals by a data acquisition module. Specifically, the overall structure of the spiral anchor is as follows: Figure 3 As shown, it includes a tower foundation 1, which is cross-shaped and connected to a helical anchor foundation 3 via four connecting columns 2. Figure 4 As shown, four spiral anchors 4 are installed on the spiral anchor foundation 3, which can increase the frost heave resistance of the transmission tower.

[0027] Among them, such as Figure 5 and Figure 6 As shown, the spiral anchor 4 includes a spiral anchor housing 5, spiral blades 6, and a thermocouple temperature sensor 7 installed on the inner wall.

[0028] In this embodiment, during the construction of the helical anchors, the tower foundation 1 adopts a cross-shaped reinforced concrete structure, prefabricated in the factory or cast on-site to ensure that its dimensional accuracy and strength meet the design requirements. Four connecting columns 2 are pre-embedded during the foundation casting to ensure a reliable connection between the connecting columns and the foundation. The helical anchor foundation 3 is manufactured according to design requirements, with reserved connection interfaces for the connecting columns 2 to ensure precise alignment with the tower foundation 1. The four helical anchors 4 are installed to the designed depth using mechanical screwing or hydraulic pressing. During installation, the verticality and embedment depth of the helical anchors are monitored using specialized equipment to ensure that the helical anchors are evenly distributed below the helical anchor foundation 3, forming a stable frost-resistant structural system.

[0029] In this embodiment, the sensor is installed as follows: Thermocouple temperature sensor 7 installation: During the fabrication of the spiral anchor 4, pre-drill mounting holes of suitable diameter at intervals of 30-50cm. Insert the thermocouple temperature sensor into the hole, and fill the gap with a high-temperature resistant, waterproof sealing material, such as silicone rubber sealant, to ensure tight contact between the sensor and the anchor rod. Around the root, middle, and end of the spiral blades, use a small drilling machine to create small holes, install the temperature sensor probes into the holes, and secure them with adhesive. The sensor wires are arranged along the anchor rod, protected by a waterproof insulating sleeve, and connected to the data acquisition module.

[0030] Miniature pressure sensor installation: On the surface of the spiral blade 6, use precision machining equipment to create mounting grooves at the designed locations. Embed the miniature pressure sensor into the groove and secure it using a high-strength adhesive, such as epoxy resin, ensuring the sensor surface is flush with the blade surface. After installation, the pressure sensor undergoes waterproofing and corrosion protection treatment, such as spraying a polytetrafluoroethylene coating, and is calibrated using pressure testing equipment to ensure accurate measurement of frost heave force.

[0031] Installation of the wire-type displacement sensor: Install the displacement sensor mounting bracket near the top of the helical anchor 4 and the root of the blade using welding or bolting. Securely connect one end of the wire to the designated location on the helical anchor foundation (such as the center of the anchor bolt top or a pre-set connection point at the root of the blade), and connect the other end to the sensor's sensing end. Adjust the wire tension to ensure the sensor is in normal working condition. After installation, test the sensor's response sensitivity and measurement accuracy by manually simulating small displacements, making fine adjustments as necessary.

[0032] In this embodiment, temperature data, frost heave force data, and displacement data of the helical anchor and surrounding soil are collected to the data acquisition module via thermocouple temperature sensors, miniature pressure sensors, and wire-type displacement sensors. The data acquisition module converts these data from analog signals to digital signals and performs preliminary filtering to eliminate high-frequency noise.

[0033] In this embodiment, in step S2, the digital signal is transmitted to the data analysis and processing module through the data transmission module; Specifically, the data transmission module uses optical fiber as the transmission medium. The optical fiber line is laid synchronously during the construction of the helical anchor foundation. The outside is wrapped with a stainless steel protective sleeve and grounded to resist electromagnetic interference. During the transmission process, a CRC check mechanism is used to ensure data integrity. When a data packet is lost or erroneous, a retransmission mechanism is automatically triggered. After photoelectric conversion, the digital signal is transmitted to the data analysis and processing module at a rate of 100Mbps, and the transmission delay is controlled within 50ms.

[0034] In this embodiment, in step S3, the original data of temperature, frost heave force, and displacement in the digital signal are calculated by setting an algorithm to obtain basic quantitative parameters; based on the basic quantitative parameters and combined with set historical data, the frost heave risk level is obtained by analyzing the data through a machine learning model. Specifically, during the calculation of the original data of temperature, frost heave force, and displacement in the digital signal using the set algorithm, the dynamic temperature change is obtained by calculating the temperature change rate formula; and the temperature stratification is judged by the temperature gradient formula. The formula for the rate of temperature change is: ; In the formula, v is the rate of temperature change; The temperature at the current moment; The temperature at the previous moment; For time difference; The temperature gradient formula is: ; In the formula, For temperature gradient; , The temperatures of sensors i and j at different depths are respectively; The distance between the two sensors; The total frost heave force is calculated using the integral formula of tangential frost heave force; the total frost heave force is then corrected in real time using the frost heave force-temperature coupling formula. The integral formula for the tangential frost heave force is: ; In the formula, ρ is the total frost heave force; s is the area of ​​the integral. It is the tangential stress; The frost heave force-temperature coupling formula is as follows: ; In the formula, F is the frost heave force; k is the comprehensive correction coefficient; V is the unit weight of the soil; V is the volume of soil affected by frost heave. This refers to the frost heave rate; This is the temperature gradient sensitivity coefficient.

[0035] In this embodiment, as Figure 7 As shown, the machine learning model includes: a feature engineering submodule, an LSTM time series prediction model, and an XGBoost risk assessment model; The feature engineering submodule performs sliding window statistical calculations and Fourier transforms on the basic quantization parameters to generate a high-latitude feature set. Based on the high-latitude feature set, the LSTM time series prediction model is used for prediction processing to output a predicted value of temperature change trend. Based on the high-latitude feature set, the predicted value of temperature change trend, and the set environmental parameters, the XGBoost risk assessment model is used for risk assessment to output the frost heave risk level.

[0036] In the process of generating the high-latitude feature set through the feature engineering submodule, the mean and standard deviation of the temperature data are calculated using the sliding window statistics; the formula for calculating the mean is: ; In the formula, The mean temperature is denoted as n; n is the number of samples in the statistical temperature data. Let be the temperature at time i. The formula for calculating the standard deviation is: ; In the formula, Standard deviation; The seasonal periodic characteristics of temperature data are extracted using Fourier transform; the Fourier transform formula is: ; In the formula, t represents the average temperature; k represents the frequency; m represents the number of harmonic frequency terms participating in the Fourier transform; t represents the time variable. For periodicity; , All are Fourier coefficients.

[0037] In this embodiment, Python is used to perform sliding window statistics with a window length of n=24 (hours) to calculate the hourly temperature mean and standard deviation. The temperature data is then subjected to Fourier transform using the scipy.fft library to extract frequency components with periods of 24 hours and 365 days, identifying the periodic patterns of permafrost temperature.

[0038] In this embodiment, the XGBoost risk assessment model uses SHAP values ​​to explain model decisions. The importance of typical features is ranked as follows: temperature gradient 45% > frost heave rate 30% > displacement acceleration 20% > seasonal factor 5%. The visualization results are displayed through the risk assessment module.

[0039] In this embodiment, in step S4, the early warning module performs graded early warning processing according to the frost heave risk level; The early warning module has three risk thresholds, corresponding to low, medium and high level warnings; Low-level warnings trigger on-site audible and visual alarm devices; Intermediate warning triggers on-site audible and visual alarms and a remote platform warning interface;

[0040] Advanced early warning triggers on-site audible and visual alarms and remote platform early warning interface, pushes early warning SMS to mobile terminals, automatically records early warning events and activates preset emergency plans.

[0041] Specifically, a low-level warning is triggered when a single core parameter reaches the "range of concern" and other parameters are normal. For example, if only the temperature gradient reaches 2-5℃ / m, but the frost heave force does not exceed 50% of the design limit and the displacement is within the allowable range, the system will trigger the on-site audible and visual alarm device to remind on-site maintenance personnel to pay attention to the foundation status and conduct timely manual inspections.

[0042] When two or more core parameters reach the "risk range," or when a single core parameter approaches the design specification limit, a medium-level early warning is triggered. For example, if the temperature gradient reaches 5-8℃ / m and the corrected frost heave exceeds 50%-80% of the design limit, or the displacement reaches 60%-80% of the design allowable value, the system will simultaneously trigger the on-site audible and visual alarm devices and the remote platform early warning interface, enabling the remote monitoring center and on-site maintenance personnel to obtain early warning information simultaneously and initiate targeted investigation and intervention measures.

[0043] When any core parameter exceeds the design limit, or multiple parameters collectively exceed the "danger zone," an advanced early warning is triggered. For example, if the temperature gradient exceeds 8℃ / m, or the corrected frost heave force exceeds 80% of the design limit, or the displacement exceeds the design limit, the system will trigger on-site audible and visual alarms and a remote platform warning interface. It will also push a warning SMS to the mobile terminal of maintenance personnel, automatically record detailed information about the warning event, such as the trigger time, core parameter values, and foundation location, and activate a preset emergency plan to minimize the impact of frost heave on foundation safety.

[0044] In this embodiment, in step S5, the basic data, the basic quantitative parameters, and the frost heave risk level are classified and stored in the historical data storage module, and a data indexing mechanism is established.

[0045] Specifically, the historical data storage module categorizes and stores raw monitoring data, intermediate calculation results, and final risk assessment results. A data indexing mechanism is established to support rapid querying and analysis of historical data, providing data support for system optimization, frost heave risk prediction, and accident analysis. Data is backed up regularly to prevent data loss and ensure data security and integrity.

[0046] The application scenarios of this invention are as follows: Wind turbine foundation monitoring in high-latitude / high-altitude permafrost regions: Adaptable to wind farms in the permafrost regions of Northeast, Northwest and Southwest China, it monitors the temperature gradient, frost heave force and displacement of the wind turbine helical anchor foundation caused by freeze-thaw cycles, predicts frost heave trends, provides timely warnings and guides reinforcement, and avoids wind turbine tower tilting and downtime losses.

[0047] Monitoring of high-voltage transmission line tower foundations in permafrost regions: Used for the spiral anchor foundations of ultra-high voltage transmission line towers in permafrost regions, monitoring frost heave force, foundation displacement and temperature field distribution. If the limits are exceeded, multi-terminal early warning is triggered to ensure tower stability and reduce the risk of line tripping.

[0048] Monitoring of oil and gas pipeline support foundations in permafrost regions: For the spiral anchor foundations supporting oil and gas pipelines traversing permafrost regions, monitor the permafrost temperature, frost heave force, and pipeline displacement to prevent pipeline joint leakage caused by foundation deformation and provide data support for operation and maintenance.

[0049] Foundation monitoring of transportation ancillary structures in permafrost regions: adaptable to helical anchor foundations of small structures such as highway billboards and railway signal towers in permafrost regions, simplifying the configuration of temperature and displacement monitoring, achieving low-cost early warning of frost heave risk, and preventing the structures from tilting and collapsing.

[0050] Monitoring and reinforcement of geological disaster control in permafrost areas: Spiral anchor reinforcement projects used for landslide and roadbed subsidence control in permafrost areas monitor the temperature gradient, frost heave force and slope displacement around the anchor body, evaluate the reinforcement effect, provide early warning of reinforcement force attenuation, and prevent secondary disasters.

[0051] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0052] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0053] Example 2

[0054] See Figure 8 Embodiment 2 of the present invention also provides a frost heave prevention early warning system for helical anchor foundations, comprising: The data acquisition unit 001 is used to acquire basic data through sensors set on the spiral anchor structure; and to convert the basic data from analog signals to digital signals through the data acquisition module. The data transmission unit 002 is used to transmit the digital signal to the data analysis and processing module through the data transmission module; The data analysis and processing unit 003 is used to calculate the raw data of temperature, frost heave force, and displacement in the digital signal through a set algorithm to obtain basic quantitative parameters; based on the basic quantitative parameters and combined with set historical data, it analyzes the data through a machine learning model to obtain the frost heave risk level. The early warning processing unit 004 is used to perform graded early warning processing by the early warning module according to the frost heave risk level. Data storage unit 005 is used to classify and store the basic data, the basic quantitative parameters and the frost heave risk level into the historical data storage module, and to establish a data indexing mechanism.

[0055] In this embodiment, the data analysis and processing unit 003 calculates the original data of temperature, frost heave force, and displacement in the digital signal using the set algorithm, obtains the dynamic temperature change by calculating the temperature change rate formula, and judges the temperature stratification by using the temperature gradient formula. The formula for the rate of temperature change is: ; In the formula, v is the rate of temperature change; The temperature at the current moment; The temperature at the previous moment; For time difference; The temperature gradient formula is: ; In the formula, For temperature gradient; , The temperatures of sensors i and j at different depths are respectively; The distance between the two sensors; The total frost heave force is calculated using the integral formula of tangential frost heave force; the total frost heave force is then corrected in real time using the frost heave force-temperature coupling formula. The integral formula for the tangential frost heave force is: ; In the formula, ρ is the total frost heave force; s is the area of ​​the integral. Tangential stress; The frost heave force-temperature coupling formula is as follows: ; In the formula, F is the frost heave force; k is the comprehensive correction coefficient; V is the unit weight of the soil; V is the volume of soil affected by frost heave. This refers to the frost heave rate; This is the temperature gradient sensitivity coefficient.

[0056] In this embodiment, the data analysis and processing unit 003, during the analysis process using the machine learning model, includes: a feature engineering submodule, an LSTM time series prediction model, and an XGBoost risk assessment model. The feature engineering submodule performs sliding window statistical calculations and Fourier transforms on the basic quantization parameters to generate a high-latitude feature set. Based on the high-latitude feature set, the LSTM time series prediction model is used for prediction processing to output a predicted value of temperature change trend. Based on the high-latitude feature set, the predicted value of temperature change trend, and the set environmental parameters, the XGBoost risk assessment model is used for risk assessment to output the frost heave risk level.

[0057] In this embodiment, in the data analysis and processing unit 003, during the process of generating the high-latitude feature set through the feature engineering submodule, the mean and standard deviation of the temperature data are calculated using the sliding window statistics; the formula for calculating the mean is: ; In the formula, The mean temperature is denoted as n; n is the number of samples in the statistical temperature data. Let be the temperature at time i. The formula for calculating the standard deviation is: ; In the formula, Standard deviation; The seasonal periodic characteristics of temperature data are extracted using Fourier transform; the Fourier transform formula is: ; In the formula, t represents the average temperature; k represents the frequency; m represents the number of harmonic frequency terms participating in the Fourier transform; t represents the time variable. For periodicity; , All are Fourier coefficients.

[0058] In this embodiment, in the early warning processing unit 004, during the process of the early warning module performing graded early warning processing, the early warning module sets three risk thresholds, corresponding to low-level, medium-level and high-level early warnings. Low-level warnings trigger on-site audible and visual alarm devices; Intermediate warning triggers on-site audible and visual alarms and a remote platform warning interface; Advanced early warning triggers on-site audible and visual alarms and remote platform early warning interface, pushes early warning SMS to mobile terminals, automatically records early warning events and activates preset emergency plans.

[0059] The method embodiments in Example 1 are based on the same concept, and the technical effects they bring are the same as those in the method embodiments of this application. For details, please refer to the description in the method embodiments shown above in this application, which will not be repeated here.

[0060] Example 3

[0061] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium storing program code for a method for early warning of frost heave in helical anchor foundations. The program code includes instructions for executing the method for early warning of frost heave in helical anchor foundations according to Embodiment 1 or any possible implementation thereof.

[0062] Computer-readable storage media can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0063] Example 4

[0064] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor; The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor can execute the frost heave prevention early warning method for helical anchor foundations according to Embodiment 1 or any possible implementation thereof by calling the program instructions.

[0065] Specifically, a processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0066] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0067] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing systems. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Optionally, they can be implemented using program code executable by a computing system, thereby storing them in a storage system for execution by the computing system. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0068] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A method for early warning of frost heave in helical anchor foundations, characterized in that, include: Basic data is collected by sensors installed on the spiral anchor structure; The basic data is converted from analog signals to digital signals through the data acquisition module; The digital signal is transmitted to the data analysis and processing module via the data transmission module; By setting an algorithm, the raw data of temperature, frost heave force, and displacement in the digital signal are calculated to obtain basic quantitative parameters; based on the basic quantitative parameters and combined with set historical data, the frost heave risk level is obtained through analysis using a machine learning model. Based on the level of frost heave risk, the early warning module performs tiered early warning processing. The basic data, the basic quantitative parameters, and the frost heave risk level are classified and stored in the historical data storage module, and a data indexing mechanism is established.

2. The method for early warning of frost heave in spiral anchor foundations according to claim 1, characterized in that, During the calculation of the original data of temperature, frost heave force, and displacement in the digital signal using the set algorithm, the dynamic temperature change is obtained by calculating the temperature change rate formula; and the temperature stratification is judged by the temperature gradient formula. The formula for the rate of temperature change is: ； In the formula, v is the rate of temperature change; The temperature at the current moment; The temperature at the previous moment; For time difference; The temperature gradient formula is: ； In the formula, For temperature gradient; , The temperatures of sensors i and j at different depths are respectively; The distance between the two sensors; The total frost heave force is calculated using the integral formula of tangential frost heave force; the total frost heave force is then corrected in real time using the frost heave force-temperature coupling formula. The integral formula for the tangential frost heave force is: ； In the formula, ρ represents the total frost heave force; s represents the contact area. Tangential stress; The frost heave force-temperature coupling formula is as follows: ； In the formula, F is the frost heave force; k is the comprehensive correction coefficient; V is the unit weight of the soil; V is the volume of soil affected by frost heave. This refers to the frost heave rate; This is the temperature gradient sensitivity coefficient.

3. The method for early warning of frost heave in spiral anchor foundations according to claim 2, characterized in that, In the process of analysis using the machine learning model, the machine learning model includes: a feature engineering submodule, an LSTM time series prediction model, and an XGBoost risk assessment model; The feature engineering submodule performs sliding window statistical calculations and Fourier transforms on the basic quantization parameters to generate a high-latitude feature set. Based on the high-latitude feature set, the LSTM time series prediction model is used for prediction processing to output a predicted value of temperature change trend. Based on the high-latitude feature set, the predicted value of temperature change trend, and the set environmental parameters, the XGBoost risk assessment model is used for risk assessment to output the frost heave risk level.

4. The method for early warning of frost heave in spiral anchor foundations according to claim 3, characterized in that, During the generation of the high-latitude feature set through the feature engineering submodule, the mean and standard deviation of the temperature data are calculated using the sliding window statistics; the formula for calculating the mean is: ； In the formula, The mean temperature is denoted as n; n is the number of samples in the statistical temperature data. Let be the temperature at time i. The formula for calculating the standard deviation is: ； In the formula, Standard deviation; The seasonal periodic characteristics of temperature data are extracted using Fourier transform; the Fourier transform formula is: ； In the formula, t represents the average temperature; k represents the frequency; m represents the number of harmonic frequency terms participating in the Fourier transform; and t represents the time variable. For periodicity; , All are Fourier coefficients.

5. The method for early warning of frost heave in spiral anchor foundations according to claim 4, characterized in that, During the tiered warning process, the warning module sets three risk thresholds, corresponding to low, medium, and high-level warnings. Low-level early warning triggers on-site audible and visual alarm devices; Intermediate warning triggers on-site audible and visual alarms and a remote platform warning interface; Advanced early warning triggers on-site audible and visual alarms and remote platform early warning interface, pushes early warning SMS to mobile terminals, automatically records early warning events and activates preset emergency plans.

6. A frost heave early warning system for helical anchor foundations, employing the frost heave early warning method for helical anchor foundations as described in any one of claims 1-5, characterized in that, include: The data acquisition unit is used to collect basic data through sensors set on the spiral anchor structure; The basic data is converted from analog signals to digital signals through the data acquisition module; The data transmission unit is used to transmit the digital signal to the data analysis and processing module through the data transmission module; The data analysis and processing unit is used to calculate the raw data of temperature, frost heave force, and displacement in the digital signal through a set algorithm to obtain basic quantitative parameters; based on the basic quantitative parameters and combined with set historical data, it analyzes the data through a machine learning model to obtain the frost heave risk level. The early warning processing unit is used to perform graded early warning processing by the early warning module according to the frost heave risk level. The data storage unit is used to classify and store the basic data, the basic quantitative parameters and the frost heave risk level into the historical data storage module, and to establish a data indexing mechanism.

7. The anti-frost heave early warning system for spiral anchor foundations according to claim 6, characterized in that, In the data analysis and processing unit, during the calculation of the original data of temperature, frost heave force, and displacement in the digital signal using the set algorithm, the dynamic temperature change is obtained by calculating the temperature change rate formula; and the temperature stratification is judged by the temperature gradient formula. The formula for the rate of temperature change is: ； In the formula, v is the rate of temperature change; The temperature at the current moment; The temperature at the previous moment; For time difference; The temperature gradient formula is: ； In the formula, For temperature gradient; , The temperatures of sensors i and j at different depths are respectively; The distance between the two sensors; The total frost heave force is calculated using the integral formula of tangential frost heave force; the total frost heave force is then corrected in real time using the frost heave force-temperature coupling formula. The integral formula for the tangential frost heave force is: ； In the formula, s is the total frost heave force; s is the contact area; It is the tangential stress; The frost heave force-temperature coupling formula is as follows: ； In the formula, F is the frost heave force; k is the comprehensive correction coefficient; V is the unit weight of the soil; V is the volume of soil affected by frost heave. This refers to the frost heave rate; This is the temperature gradient sensitivity coefficient.

8. The anti-frost heave early warning system for spiral anchor foundations according to claim 7, characterized in that, In the data analysis and processing unit, during the analysis process using the machine learning model, the machine learning model includes: a feature engineering submodule, an LSTM time series prediction model, and an XGBoost risk assessment model. The feature engineering submodule performs sliding window statistical calculations and Fourier transforms on the basic quantization parameters to generate a high-latitude feature set. Based on the high-latitude feature set, the LSTM time series prediction model is used for prediction processing to output a predicted value of temperature change trend. Based on the high-latitude feature set, the predicted value of temperature change trend, and the set environmental parameters, the XGBoost risk assessment model is used for risk assessment to output the frost heave risk level.

9. A frost heave prevention early warning system for spiral anchor foundations according to claim 8, characterized in that, In the data analysis and processing unit, during the generation of the high-latitude feature set through the feature engineering submodule, the mean and standard deviation of the temperature data are calculated using the sliding window statistics; the formula for calculating the mean is: ； In the formula, The mean temperature is denoted as n; n is the number of samples in the statistical temperature data. Let be the temperature at time i. The formula for calculating the standard deviation is: ； In the formula, Standard deviation; The seasonal periodic characteristics of temperature data are extracted using Fourier transform; the Fourier transform formula is: ； In the formula, t represents the average temperature; k represents the frequency; m represents the number of harmonic frequency terms participating in the Fourier transform; and t represents the time variable. For periodicity; , All are Fourier coefficients.

10. A frost heave prevention early warning system for spiral anchor foundations according to claim 9, characterized in that, In the aforementioned early warning processing unit, during the process of the early warning module performing graded early warning processing, the early warning module sets three risk thresholds, corresponding to low-level, medium-level, and high-level early warnings. Low-level early warning triggers on-site audible and visual alarm devices; Intermediate warning triggers on-site audible and visual alarms and a remote platform warning interface; Advanced early warning triggers on-site audible and visual alarms and remote platform early warning interface, pushes early warning SMS to mobile terminals, automatically records early warning events and activates preset emergency plans.

Images