Power transmission line slope stability early warning method and system for short-time heavy rainfall

Abstract

The invention relates to a power transmission line slope stability early warning method and system for short-time heavy rainfall, and the method comprises the following steps: collecting first pore water pressure and first temperature change data through arranging pore water pressure sensors and temperature sensors in different depth directions of a slope; obtaining a first infiltration depth and a first infiltration speed according to the first pore water pressure and the first temperature change data in different depth directions; establishing a correlation prediction model of the infiltration depth, the infiltration speed and the slope stability coefficient, and predicting a first slope stability coefficient; constructing a pre-training model through a clustering algorithm, and storing model parameters in a non-short-time heavy rainfall period; when a short-time heavy rainfall event is detected, second pore water pressure and second temperature change data are collected, a second slope stability coefficient is obtained through the correlation prediction model, and the current slope stability early warning level is obtained through the existing clusters of the pre-training model.

Description

Technical Field

[0001] The invention relates to a transmission line slope stability early warning method and system for short-term heavy rainfall, belonging to the technical field of transmission line slope stability early warning. Background Art

[0002] In the field of power transmission line engineering, slope stability is the fundamental cornerstone to ensure the safe and stable operation of power transmission lines. Traditional slope stability monitoring technologies have been widely used, including ground displacement monitoring and groundwater level monitoring. Ground displacement monitoring mainly uses specific measuring instruments and equipment to accurately measure the position changes of various points on the slope surface at different times, and then infer the stability of the slope based on the change trend of displacement data; while groundwater level monitoring focuses on real-time monitoring of water level changes inside the slope soil or rock mass, because the rise and fall of groundwater levels often have a critical impact on the mechanical properties of the slope soil, which is indirectly related to the overall stability of the slope.

[0003] Although these traditional monitoring technologies have played a certain role for a long time in the past and can reflect the stability of the slope more intuitively to a certain extent, it cannot be ignored that they generally have many defects.

[0004] First, the real-time performance of traditional monitoring technology is poor. Most traditional monitoring technologies rely on manual data collection and analysis on a regular basis, which makes it difficult to achieve real-time and uninterrupted monitoring of slope conditions. For example, during the interval between two monitoring data collections, the slope may have undergone some subtle but potentially serious changes, but these changes cannot be captured in time, resulting in a lag in monitoring data, making it difficult to provide the most timely and effective information support for subsequent decision-making and early warning.

[0005] Secondly, the accuracy of early warnings of these traditional methods is not satisfactory. Due to the limitations of monitoring methods and the interference of complex external environmental factors, the slope stability early warning based on the data obtained by traditional monitoring technology often has a high false alarm rate and missed alarm rate. For example, when facing some complex geological conditions or changeable climate environments, relying solely on ground displacement monitoring data or groundwater level monitoring data may not be able to fully and accurately reflect the true stability status of the slope, resulting in deviations between the early warning information and the actual slope conditions, making it difficult to accurately implement relevant maintenance and prevention measures.

[0006] Especially under extreme climatic conditions, such as short-term heavy rainfall, which is very likely to have a huge impact on slope stability, slope stability will face unprecedented severe challenges. Short-term heavy rainfall will rapidly increase the water content of the slope soil in a short period of time, increase the weight of the soil, and reduce the shear strength index of the soil, thereby greatly weakening the stability of the slope. In this case, the risk of slope instability and damage increases sharply, which is very likely to cause transmission line failures, such as tower tilting, wire breakage and other serious problems, and may even cause more serious safety accidents, posing a serious threat to the safety of life and property of surrounding personnel and the stable and reliable operation of the power system.

[0007] At present, the use of machine learning algorithms to predict the slope stability warning level has the following difficulties: when using supervised machine learning algorithms, such as support vector machines (SVM), decision trees (DT) or neural networks (NN) to build models, it is first necessary to collect a large amount of slope monitoring data, such as collecting and collating location data where slope instability events have occurred in history and slope data that has been in a stable state, or building an experimental system. However, both collecting historical data and building systems are difficult and time-consuming. When using unsupervised machine learning algorithms, such as K-Means, when faced with a large amount of real-time monitoring data, such as short-term heavy rainfall, it is impossible to quickly complete clustering and warning level judgment, resulting in delayed warnings. Summary of the invention

[0008] In order to solve the above problems existing in the prior art, the present invention proposes a transmission line slope stability early warning method and system for short-term heavy rainfall.

[0009] The technical solution of the present invention is as follows:

[0010] On the one hand, the present invention provides a transmission line slope stability early warning method for short-term heavy rainfall, comprising the following steps:

[0011] By synchronously arranging pore water pressure sensors and temperature sensors at different depths of the potential sliding surface of the slope of the transmission line, first pore water pressure and first temperature change data are collected;

[0012] The first infiltration depth and the first infiltration speed of rainwater into the slope are obtained through the first pore water pressure and the first temperature change data in different depth directions;

[0013] Establish a correlation prediction model between infiltration depth, infiltration velocity and slope stability coefficient, and predict the first slope stability coefficient through the first infiltration depth and the first infiltration velocity;

[0014] According to the first pore water pressure, the first temperature change data and the first slope stability coefficient during the non-short-term heavy rainfall period, a pre-training model is constructed by using the K-Means clustering algorithm, and the model parameters during the non-short-term heavy rainfall period are saved;

[0015] When a short-term heavy rainfall event is detected, the real-time monitoring mode is started, and the second pore water pressure and the second temperature change data are collected in real time through the pore water pressure sensor and the temperature sensor; the second slope stability coefficient is obtained through the associated prediction model; the second pore water pressure, the second temperature change data and the second slope stability coefficient are allocated to the existing clusters of the pre-trained model to obtain the current slope stability warning level, and a warning is issued according to the current slope stability warning level.

[0016] As a preferred implementation, when a short-term heavy rainfall event occurs, the distance between the acquired second pore water pressure, second temperature change data and second slope stability coefficient and the cluster center of the pre-trained model is greater than a preset threshold, the cluster center is adjusted, and the slope stability warning level is updated.

[0017] As a preferred implementation, when a short-term heavy rainfall event occurs, if the acquired change trends of the second pore water pressure, second temperature change data and second slope stability coefficient are different from the change trends of historical data, the cluster center is adjusted and the slope stability warning level is updated.

[0018] As a preferred implementation, the steps of establishing a correlation prediction model between the infiltration depth and infiltration velocity and the slope stability coefficient are specifically as follows:

[0019] Collect model parameters, including slope dimensions, shear strength index, bulk density, and porosity parameterization index of the soil layer, calculate the slope stability coefficient corresponding to the rainwater infiltration depth and infiltration velocity under different model parameter conditions, and construct a data set;

[0020] The data set is input into the neural network model, and a nonlinear correlation prediction model between different infiltration depths and infiltration speeds and the slope stability coefficient is established to output the slope stability coefficient.

[0021] On the other hand, the present invention also proposes a transmission line slope stability early warning system for short-term heavy rainfall, comprising:

[0022] Pore ​​water pressure sensors and temperature sensors are synchronously arranged at different depths of the potential sliding surface of the slope of the transmission line, and the pore water pressure sensors and temperature sensors are used to collect first pore water pressure and first temperature change data respectively;

[0023] A data conversion module, used to obtain a first infiltration depth and a first infiltration speed of rainwater into the slope through first pore water pressure and first temperature change data in different depth directions;

[0024] A correlation prediction model building module is used to build a correlation prediction model between the infiltration depth, the infiltration velocity and the slope stability coefficient, and predict the first slope stability coefficient through the first infiltration depth and the first infiltration velocity;

[0025] A clustering module, used to construct a pre-trained model by using a K-Means clustering algorithm according to the first pore water pressure, the first temperature change data and the first slope stability coefficient during the non-short-term heavy rainfall period, and save the model parameters during the non-short-term heavy rainfall period;

[0026] The early warning module is used to start the real-time monitoring mode when a short-term heavy rainfall event is detected, collect the second pore water pressure and the second temperature change data in real time through the pore water pressure sensor and the temperature sensor; obtain the second slope stability coefficient through the associated prediction model; allocate the second pore water pressure, the second temperature change data and the second slope stability coefficient to the existing clusters of the pre-trained model, obtain the current slope stability early warning level, and issue an early warning according to the current slope stability early warning level.

[0027] As a preferred implementation, when a short-term heavy rainfall event occurs, the distance between the acquired second pore water pressure, second temperature change data and second slope stability coefficient and the cluster center of the pre-trained model is greater than a preset threshold, the cluster center is adjusted, and the slope stability warning level is updated.

[0028] As a preferred implementation, when a short-term heavy rainfall event occurs, if the acquired change trends of the second pore water pressure, second temperature change data and second slope stability coefficient are different from the change trends of historical data, the cluster center is adjusted and the slope stability warning level is updated.

[0029] As a preferred implementation, the steps of establishing a correlation prediction model between the infiltration depth and infiltration velocity and the slope stability coefficient are specifically as follows:

[0030] Collect model parameters, including slope dimensions, shear strength index, bulk density, and porosity parameterization index of the soil layer, calculate the slope stability coefficient corresponding to the rainwater infiltration depth and infiltration velocity under different model parameter conditions, and construct a data set;

[0031] The data set is input into the neural network model, and a nonlinear correlation prediction model between different infiltration depths and infiltration speeds and the slope stability coefficient is established to output the slope stability coefficient.

[0032] On the other hand, the present invention further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for early warning of slope stability of a transmission line for short-term heavy rainfall as described in any embodiment of the present invention is implemented.

[0033] On the other hand, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the transmission line slope stability early warning method for short-term heavy rainfall as described in any embodiment of the present invention.

[0034] The beneficial effects of the present invention are as follows:

[0035] The present invention provides a transmission line slope stability early warning method and system for short-term heavy rainfall. By constructing a pre-trained model for a period without short-term heavy rainfall, the model parameters are saved. When short-term heavy rainfall comes, in the face of a large amount of new input data, the pre-trained pre-trained model is used to directly assign new data points to existing clusters, and the slope stability early warning level is quickly obtained. Since the pre-trained model has been trained on a large amount of data in the non-rainfall period, the high-cost calculation process of training the model from scratch during short-term heavy rainfall is avoided.

[0036] Additional aspects and advantages of the present invention will be set forth in the following description, and some of them will be apparent from the description, or may be understood by practicing the present invention. In addition, the various aspects and advantages of the present invention may be realized and obtained by the method steps and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of a method according to Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0040] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0041] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0042] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0043] Embodiment 1:

[0044] See also Figure 1 This embodiment provides a transmission line slope stability early warning method for short-term heavy rainfall, comprising the following steps:

[0045] S100, collecting first pore water pressure and first temperature change data by synchronously arranging pore water pressure sensors and temperature sensors at different depths of the potential sliding surface of the slope of the transmission line;

[0046] S200, obtaining a first infiltration depth and a first infiltration speed of rainwater into the slope through first pore water pressure and first temperature change data in different depth directions;

[0047] When rainwater infiltrates the slope, the pore water pressure will change with the infiltration of rainwater. The pore water pressure sensor close to the infiltration area will first detect the increase in pressure. As the rainwater continues to infiltrate, sensors at different depths respond in turn. The infiltration depth of rainwater can be preliminarily determined based on the position of the sensor that first detects the change in pore water pressure. Temperature changes can also assist in determining the infiltration depth. The temperature of the soil will change during the infiltration of rainwater, because the temperature of rainwater is usually different from the initial temperature of the soil. If the temperature sensor at a certain depth detects a significant change in temperature, and it is synchronized with the change in pore water pressure, it can also be used as a basis for determining that the rainwater has reached that depth.

[0048] The infiltration rate is determined by analyzing the time difference of the pore water pressure sensor response at different depths. Assuming that the sensor at depth h1 detects the beginning of the pore water pressure change at time t1, and the sensor at depth h2 detects the change at time t2, the average infiltration rate of rainwater between these two depths can be estimated based on the principle of Darcy's law.

[0049] S300: Establish a correlation prediction model between the infiltration depth, the infiltration velocity and the slope stability coefficient, and predict the first slope stability coefficient according to the first infiltration depth and the first infiltration velocity.

[0050] In one embodiment, step S300 specifically includes:

[0051] S301, collecting model parameters, including the size of the slope, the shear strength index, bulk density, and porosity parameterization index of the soil layer, calculating the slope stability coefficient corresponding to the rainwater infiltration depth and infiltration speed under different parameter conditions, and constructing a data set;

[0052] Method for obtaining model parameters: for the target slope, measure its dimensional information, including geometric dimensional data such as slope height, slope angle, and slope length; obtain the shear strength index of the soil layer, including the internal friction angle and cohesion. In this embodiment, accurate values ​​are obtained by testing the soil samples of the target soil layer through indoor geotechnical test direct shear test and triaxial test; the bulk density data of the target soil layer can be recorded by on-site in-situ testing. In this embodiment, the ring knife method is used in combination with indoor tests to determine the bulk density values ​​corresponding to different soil layers; the porosity data can also be measured by geotechnical test means.

[0053] The collected parameter data are organized in a unified format, where each row represents the slope state of an observation, and each column corresponds to parameters such as slope size, shear strength index, bulk density, porosity, rainwater infiltration depth, and infiltration velocity, to obtain the original data set.

[0054] The finite element method is used to calculate the slope stability coefficient. First, use finite element analysis software (such as ABAQUS, etc.) to build a model, input the geometric dimensions of the target slope, divide the units, set the soil material properties, including shear strength index, bulk density, and porosity, and then simulate the rainwater infiltration process by inputting the rainwater infiltration depth and infiltration velocity. Finally, run the calculation and obtain the corresponding slope stability coefficient under different parameter conditions through the strength reduction method. The results are recorded and sorted out in correspondence with the parameters of the original data set.

[0055] S302, inputting the data set into the neural network model, establishing a nonlinear correlation prediction model between different infiltration depths and infiltration speeds and the slope stability coefficient, and outputting the slope stability coefficient;

[0056] First, perform data cleaning to check whether there are abnormal values ​​in the data set calculated by S301, such as unreasonable negative numbers or maximum and minimum values ​​of the slope stability coefficient. For such abnormal values, it is possible to determine whether it is caused by measurement errors or other reasons by analyzing the corresponding other parameters and referring to previous experience, physical laws, etc. If it is determined to be erroneous data, it is corrected or eliminated; check whether there are missing values. If there are some missing parameters, fill them according to the correlation of the data. For example, if the infiltration velocity is missing in a set of data, but the rainfall intensity at that moment and other related information are known and have a certain correlation with the infiltration velocity, the missing infiltration velocity value can be estimated by empirical formulas and other methods.

[0057] Then the data is normalized. Since the dimensions and numerical ranges of various parameters such as slope size, shear strength index, bulk density, porosity, infiltration depth, infiltration velocity and stability coefficient vary greatly, in order to facilitate the training of the neural network, the minimum-maximum normalization method is used to map the parameter data to the [0,1] interval. Data standardization can also be performed through other methods.

[0058] In this embodiment, the number of input layer nodes is 2, and the output layer selects the sigmoid activation function to map the output to the interval [0,1]. The optimization algorithm of this embodiment selects stochastic gradient descent (SGD), and other algorithms such as Adagrad, Adadelta, and Adam can also be selected.

[0059] S400, constructing a pre-training model through a K-Means clustering algorithm according to the first pore water pressure, the first temperature change data and the first slope stability coefficient during the non-short-term heavy rainfall period, and saving the model parameters during the non-short-term heavy rainfall period.

[0060] First, the K-Means clustering algorithm is used to pre-train the clustering model for non-short-term heavy rainfall periods. When the pre-trained model reaches convergence, the model parameters are saved, including the cluster center, the number of clusters, and other information related to the model, so that it can be quickly loaded and used when short-term heavy rainfall comes. The warning levels calibrated by the pre-trained model are as follows:

[0061] Blue warning level (Level IV - basically stable state)

[0062] Pore ​​water pressure characteristics: The pore water pressure changes very little and remains in a relatively stable range for a long time. The fluctuation range is usually within ±5% of the reasonable mean (this ratio can be adjusted appropriately according to the historical stability data of the specific slope and the actual project situation). For example, if the pore water pressure of the slope is stable between 10kPa and 12kPa for a long time during the normal stability period, then in the cluster data belonging to the blue warning level, its value basically fluctuates in this range, and there is no sudden increase or decrease in the short term.

[0063] Temperature change value characteristics: The temperature remains basically stable, without obvious abnormal fluctuations. Generally speaking, the daily temperature change range is consistent with the normal day and night temperature difference in the local area, and there will be no phenomenon of sharp temperature rise or drop in a certain period of time and deviating from the normal seasonal temperature change law. For example, in a normal spring, the daily temperature fluctuates between 10℃-20℃, and the temperature trend between days is stable. There is no abnormal situation such as sudden temperature rise to 30℃ or temperature drop to 5℃ on a certain day.

[0064] Characteristics of slope stability coefficient: The slope stability coefficient always remains at a high level, and the value is usually greater than 1.3, which means that the overall structure of the slope is stable and can withstand external interference factors within the normal range, such as rainfall, small vibrations, etc., and the possibility of instability is extremely low.

[0065] Yellow warning level (Level III - stability has decreased)

[0066] Pore ​​water pressure characteristics: Pore water pressure begins to fluctuate to a certain extent, and the fluctuation range is larger than that of the blue warning level, roughly around ±10%-±15% of the reasonable mean. For example, the pore water pressure that was previously stable at 10kPa-12kPa now occasionally exceeds this range and reaches 8kPa or 14kPa, and the frequency of this fluctuation has increased compared to the stable period, and may fluctuate slightly every few days.

[0067] Temperature change characteristics: The temperature has exceeded the normal fluctuation range, but it is not serious. For example, in a season with a stable temperature difference between day and night, the temperature difference between day and night on some days has increased by about 3℃-5℃ than usual, or the temperature in a local area has a short-term abnormal rise or fall, but this abnormal situation lasts for a short time, usually a few hours to a day, and then returns to a relatively normal fluctuation range.

[0068] Slope stability coefficient characteristics: The slope stability coefficient has declined to a certain extent, and the value has begun to approach but is still higher than the critical safety value, between 1.1 and 1.3. This shows that although the slope is still in a relatively stable state as a whole, the influence of unstable factors is gradually accumulating, and its ability to resist external interference has weakened compared to the blue warning level, and it needs to be monitored and paid attention to.

[0069] Orange warning level (Level II - poor stability)

[0070] Pore ​​water pressure characteristics: The fluctuation of pore water pressure becomes more frequent and the amplitude further increases, and the fluctuation range can reach ±20%-±30% of the reasonable mean. For example, the pore water pressure, which was originally stable in the range of 10kPa-12kPa, now often appears below 8kPa or above 15kPa, and the interval of such large fluctuations is shortened, and there may be several large changes every day, indicating that the potential impact of changes in pore water pressure on slope stability is increasing.

[0071] Temperature change value characteristics: The temperature changes significantly and for a long time. For example, the temperature in a local area is 5℃-10℃ higher or lower than the normal temperature range for several consecutive days, or the temperature difference at different locations of the entire slope becomes abnormally large. This temperature anomaly interacts with factors such as the change in the internal stress of the slope, which may accelerate the development of the slope towards an unstable state.

[0072] Slope stability coefficient characteristics: The slope stability coefficient continues to decrease, and the value is close to the critical value, between 0.9 and 1.1. At this time, the slope is likely to be locally unstable, such as small-scale collapse or block falling on some slopes. It is necessary to take corresponding protection and reinforcement measures and pay close attention to its changing trend.

[0073] Red alert level (Level I - extremely dangerous state)

[0074] Pore ​​water pressure characteristics: The pore water pressure fluctuates violently, and the fluctuation range is far beyond the normal range, which may reach ±50% of the reasonable average or even higher, and the fluctuation is completely irregular. The value may show a huge jump in a short period of time, which indicates that the water pressure condition inside the slope has seriously destroyed the original stress balance and posed a great threat to the stability of the slope soil.

[0075] Characteristics of temperature change values: Severe abnormal temperature changes may occur, and the temperature in some local areas may rise or fall sharply, with a deviation of more than 10°C compared with the normal temperature. This abnormal temperature phenomenon persists for many days without improvement, or the temperature field of the entire slope becomes chaotic and disordered, which is intertwined with factors such as the deformation of the slope rock and soil, changes in pore water pressure, etc., accelerating the instability of the slope.

[0076] Characteristics of slope stability coefficient: The slope stability coefficient is lower than the critical safety value, less than 0.9, which means that the slope is about to or has already experienced large-scale overall instability, and large-scale sliding and collapse of the soil have occurred, posing a serious threat to the surrounding buildings, transportation facilities and human life safety. The emergency plan must be immediately activated, the surrounding personnel must be evacuated and emergency rescue measures must be taken.

[0077] S500. When a short-term heavy rainfall event is detected, the real-time monitoring mode is started, and the second pore water pressure and the second temperature change data are collected in real time through the pore water pressure sensor and the temperature sensor; the second slope stability coefficient is obtained through the associated prediction model; the second pore water pressure, the second temperature change data and the second slope stability coefficient are allocated to the existing clusters of the pre-trained model to obtain the current slope stability warning level, and a warning is issued according to the current slope stability warning level.

[0078] When a short-term heavy rainfall event is detected, the real-time monitoring mode is immediately started to collect the pore water pressure and temperature change values ​​of the potential sliding surface at a high frequency (such as once every few minutes). These newly collected data are pre-processed in real time, including outlier removal (because rainfall may cause short-term abnormal fluctuations in some sensor data, these outliers need to be identified and processed in time) and normalization processing in the same way as non-rainfall periods to ensure that the new data is consistent with the data format and scale of the pre-trained model. The pre-trained clustering model for non-short-term heavy rainfall periods is quickly loaded, and the newly collected short-term heavy rainfall period data points are directly assigned to the existing clusters to quickly obtain preliminary clustering assignment results. Since the pre-trained model has learned the stable state mode of the slope during non-heavy rainfall periods, this rapid classification based on the pre-trained model can preliminarily classify the new data in a short time, avoiding the large amount of computing time and resources required to train the model from scratch in an emergency.

[0079] In some embodiments, based on the pre-trained clustering model for non-short-term heavy rainfall periods, the pre-trained model is fine-tuned according to the distribution characteristics of the new data and the actual situation. For example, if it is found that there are more data points in the new data that are far away from the original cluster center, or the data points in some clusters show a change trend that is significantly different from the historical data (such as a sharp increase in pore water pressure, abnormal temperature fluctuations, and a rapid decrease in slope stability coefficient), it is necessary to appropriately adjust the cluster center, use the incremental learning method, gradually incorporate the new data into the model update process, and optimize the model parameters slightly to adapt to the impact of short-term heavy rainfall on the slope state. According to the fine-tuned clustering results, the slope warning level of each cluster is updated in real time. For example, if the data in a cluster shows obvious unstable characteristics during heavy rainfall, and is similar to the data characteristics of the slope when dangerous conditions occur in history, the warning level corresponding to the cluster is raised to a higher level (such as from yellow to orange or red); while for those clusters whose data changes during heavy rainfall are relatively small and are still close to the cluster characteristics of the stable state during non-heavy rainfall periods, a lower warning level (such as blue or yellow) is maintained.

[0080] Once the slope stability warning level reaches or exceeds the preset danger threshold, for example, when the warning level reaches orange or red, the corresponding alarm system will be triggered immediately to send detailed warning information to relevant personnel, including the specific location of the slope, the current warning level, the possible degree of danger, and recommended response measures, so that effective protection and control actions can be taken in time to ensure the safety of life and property around the slope.

[0081] Embodiment 2:

[0082] This embodiment provides a transmission line slope stability early warning system for short-term heavy rainfall, including:

[0083] The pore water pressure sensor and the temperature sensor are synchronously arranged at different depths of the potential sliding surface of the slope of the transmission line, and the pore water pressure sensor and the temperature sensor are used to collect the first pore water pressure and the first temperature change data respectively; this module is used to implement the function of step S100 in the first embodiment, and will not be repeated here;

[0084] A data conversion module, used to obtain a first infiltration depth and a first infiltration speed of rainwater into the slope through first pore water pressure and first temperature change data in different depth directions; this module is used to implement the function of step S200 in the first embodiment, which will not be described in detail here;

[0085] A correlation prediction model establishment module is used to establish a correlation prediction model between the infiltration depth and the infiltration speed and the slope stability coefficient, and predict the first slope stability coefficient according to the first infiltration depth and the first infiltration speed; this module is used to implement the function of step S300 in the first embodiment, and will not be repeated here;

[0086] A clustering module is used to construct a pre-trained model by a K-Means clustering algorithm according to the first pore water pressure, the first temperature change data and the first slope stability coefficient during the non-short-term heavy rainfall period, and save the model parameters during the non-short-term heavy rainfall period; this module is used to implement the function of step S400 in the first embodiment, which will not be described in detail here;

[0087] The early warning module is used to start the real-time monitoring mode when a short-term heavy rainfall event is detected, and collect the second pore water pressure and the second temperature change data in real time through the pore water pressure sensor and the temperature sensor; obtain the second slope stability coefficient through the associated prediction model; allocate the second pore water pressure, the second temperature change data and the second slope stability coefficient to the existing clusters of the pre-trained model, obtain the current slope stability early warning level, and issue an early warning according to the current slope stability early warning level; this module is used to implement the function of step S500 in Example 1, which will not be repeated here.

[0088] As a preferred implementation mode of this embodiment, when a short-term heavy rainfall event occurs, the distance between the acquired second pore water pressure, second temperature change data and second slope stability coefficient and the cluster center of the pre-trained model is greater than a preset threshold, the cluster center is adjusted, and the slope stability warning level is updated.

[0089] As a preferred implementation mode of this embodiment, when a short-term heavy rainfall event occurs, if the change trends of the acquired second pore water pressure, second temperature change data and second slope stability coefficient are different from the change trends of historical data, the cluster center is adjusted and the slope stability warning level is updated.

[0090] As a preferred implementation of this embodiment, the steps of establishing a correlation prediction model between the infiltration depth and infiltration velocity and the slope stability coefficient are specifically as follows:

[0091] Collect model parameters, including slope dimensions, shear strength index, bulk density, and porosity parameterization index of the soil layer, calculate the slope stability coefficient corresponding to the rainwater infiltration depth and infiltration velocity under different model parameter conditions, and construct a data set;

[0092] The data set is input into the neural network model, and a nonlinear correlation prediction model between different infiltration depths and infiltration speeds and the slope stability coefficient is established to output the slope stability coefficient.

[0093] Embodiment three:

[0094] This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the transmission line slope stability early warning method for short-term heavy rainfall as described in any embodiment of the present invention is implemented.

[0095] Embodiment 4:

[0096] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for early warning of slope stability of a power transmission line for short-term heavy rainfall as described in any embodiment of the present invention is implemented.

[0097] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0098] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0100] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk and other media that can store program codes.

[0101] The above descriptions are merely embodiments of the present invention and are not intended to 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.

Claims

1. A transmission line slope stability early warning method for short-term heavy rainfall, characterized in that: The following steps are involved: By synchronously arranging pore water pressure sensors and temperature sensors at different depths of the potential sliding surface of the slope of the transmission line, first pore water pressure and first temperature change data are collected; The first infiltration depth and the first infiltration speed of rainwater into the slope are obtained through the first pore water pressure and the first temperature change data in different depth directions; Establish a correlation prediction model between infiltration depth, infiltration velocity and slope stability coefficient, and predict the first slope stability coefficient through the first infiltration depth and the first infiltration velocity; According to the first pore water pressure, the first temperature change data and the first slope stability coefficient during the non-short-term heavy rainfall period, a pre-training model is constructed by using the K-Means clustering algorithm, and the model parameters during the non-short-term heavy rainfall period are saved; When a short-term heavy rainfall event is detected, the real-time monitoring mode is started, and the second pore water pressure and the second temperature change data are collected in real time through the pore water pressure sensor and the temperature sensor; the second slope stability coefficient is obtained through the associated prediction model; the second pore water pressure, the second temperature change data and the second slope stability coefficient are allocated to the existing clusters of the pre-trained model to obtain the current slope stability warning level, and a warning is issued according to the current slope stability warning level.

2. A transmission line slope stability early warning method for short-term heavy rainfall according to claim 1, characterized in that: When a short-term heavy rainfall event occurs, the distance between the acquired second pore water pressure, second temperature change data and second slope stability coefficient and the cluster center of the pre-trained model is greater than a preset threshold, the cluster center is adjusted, and the slope stability warning level is updated.

3. The method for early warning of slope stability of power transmission lines for short-term heavy rainfall according to claim 1, characterized in that: When a short-term heavy rainfall event occurs, if the variation trends of the second pore water pressure, the second temperature change data and the second slope stability coefficient obtained are different from the variation trends of the historical data, the cluster center is adjusted and the slope stability warning level is updated.

4. The method for early warning of slope stability of power transmission lines for short-term heavy rainfall according to claim 1, characterized in that: The steps of establishing the correlation prediction model between the infiltration depth and the infiltration velocity and the slope stability coefficient are specifically as follows: Collect model parameters, including slope dimensions, shear strength index, bulk density, and porosity parameterization index of the soil layer, calculate the slope stability coefficient corresponding to the rainwater infiltration depth and infiltration velocity under different model parameter conditions, and construct a data set; The data set is input into the neural network model, and a nonlinear correlation prediction model between different infiltration depths and infiltration speeds and the slope stability coefficient is established to output the slope stability coefficient.

5. A transmission line slope stability early warning system for short-term heavy rainfall, characterized in that: include: Pore ​​water pressure sensors and temperature sensors are synchronously arranged at different depths of the potential sliding surface of the slope of the transmission line, and the pore water pressure sensors and temperature sensors are used to collect first pore water pressure and first temperature change data respectively; A data conversion module, used to obtain a first infiltration depth and a first infiltration speed of rainwater into the slope through first pore water pressure and first temperature change data in different depth directions; A correlation prediction model building module is used to build a correlation prediction model between the infiltration depth, the infiltration velocity and the slope stability coefficient, and predict the first slope stability coefficient through the first infiltration depth and the first infiltration velocity; A clustering module, used to construct a pre-trained model by using a K-Means clustering algorithm according to the first pore water pressure, the first temperature change data and the first slope stability coefficient during the non-short-term heavy rainfall period, and save the model parameters during the non-short-term heavy rainfall period; The early warning module is used to start the real-time monitoring mode when a short-term heavy rainfall event is detected, collect the second pore water pressure and the second temperature change data in real time through the pore water pressure sensor and the temperature sensor; obtain the second slope stability coefficient through the associated prediction model; allocate the second pore water pressure, the second temperature change data and the second slope stability coefficient to the existing clusters of the pre-trained model, obtain the current slope stability early warning level, and issue an early warning according to the current slope stability early warning level.

6. The power transmission line slope stability early warning system for short-term heavy rainfall according to claim 5 is characterized by: When a short-term heavy rainfall event occurs, the distance between the acquired second pore water pressure, second temperature change data and second slope stability coefficient and the cluster center of the pre-trained model is greater than a preset threshold, the cluster center is adjusted, and the slope stability warning level is updated.

7. The power transmission line slope stability early warning system for short-term heavy rainfall according to claim 5, characterized in that: When a short-term heavy rainfall event occurs, if the variation trends of the second pore water pressure, the second temperature variation data and the second slope stability coefficient obtained are different from the variation trends of the historical data, the cluster center is adjusted and the slope stability warning level is updated.

8. The power transmission line slope stability early warning system for short-term heavy rainfall according to claim 5, characterized in that: The steps of establishing the correlation prediction model between the infiltration depth and the infiltration velocity and the slope stability coefficient are specifically as follows: Collect model parameters, including slope dimensions, shear strength index, bulk density, and porosity parameterization index of the soil layer, calculate the slope stability coefficient corresponding to the rainwater infiltration depth and infiltration velocity under different model parameter conditions, and construct a data set; The data set is input into the neural network model, and a nonlinear correlation prediction model between different infiltration depths and infiltration speeds and the slope stability coefficient is established to output the slope stability coefficient.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images