Slope stability early warning method and system for power transmission line in short-time heavy rain

Abstract

The present application relates to a kind of power transmission line slope stability early warning method and system for short time heavy rain, wherein the method comprises the following steps: by arranging the pore water pressure sensor and temperature sensor in different depth direction of slope, first pore water pressure and first temperature change data are collected;By the first pore water pressure and first temperature change data in different depth direction, first infiltration depth and first infiltration speed are obtained;Establish the correlation prediction model of infiltration depth and infiltration speed and slope stability coefficient, predict first slope stability coefficient;By clustering algorithm, pre-training model is constructed, and the model parameters of non-short time heavy rain period are saved;When detecting short time heavy rain event occurs, second pore water pressure and second temperature change data are collected, second slope stability coefficient is obtained by correlation prediction model, and current slope stability early warning grade is obtained by the clustering of pre-training model already had.

Description

TECHNICAL FIELD

[0001] The present application relates to a power transmission line slope stability early warning method and system for short-time heavy rain, belonging to the technical field of power transmission line slope stability early warning. BACKGROUND

[0002] In the field of power transmission line engineering, the stability of the slope is the fundamental cornerstone to ensure the safe and stable operation of the power transmission line. For a long time, traditional slope stability monitoring technology has been widely used, including ground displacement monitoring and underground water level monitoring and other methods. 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 infers the stability of the slope according to the variation trend of the displacement data; while underground water level monitoring focuses on real-time monitoring of the water level changes in the soil or rock mass inside the slope, because the rise and fall of the underground water level often has a very critical impact on the mechanical properties of the slope soil, thereby indirectly relating to the overall stability of the slope.

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

[0004] Firstly, the real-time performance of traditional monitoring technology is poor. Traditional monitoring technology mostly relies on manual periodic data collection and analysis, which is difficult to achieve real-time and uninterrupted monitoring of the slope conditions. For example, during the interval between two monitoring data collection, the slope may have undergone some subtle changes that could lead to serious consequences, but these changes cannot be captured in time, resulting in monitoring data lag and making it difficult to provide the most timely and effective information support for subsequent decision-making and early warning.

[0005] Secondly, the early warning accuracy of these traditional methods is not satisfactory. Due to the limitations of monitoring methods and the interference of complex environmental factors, the slope stability early warning based on the data obtained by traditional monitoring technology often has high false positive rate and false negative rate. For example, in the face of some complex geological conditions or variable climate environment, relying solely on ground displacement monitoring data or underground water level monitoring data may not be able to fully and accurately reflect the true stability of the slope, resulting in a deviation between the early warning information and the actual slope conditions, making it difficult to accurately implement related maintenance and prevention measures.

[0006] Especially in extreme weather conditions, such as short-time heavy rainfall, which has a great impact on the stability of the slope, the slope stability will face unprecedented severe challenges. Short-time heavy rainfall can rapidly increase the water content of the slope soil in a short time, increase the unit weight of the soil, and at the same time, 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 failure rises sharply, which is likely to cause serious problems such as tower tilt, conductor fracture and other serious problems of the power transmission line, and even more serious safety accidents, which poses a serious threat to the stable and reliable operation of the power system.

[0007] At present, the following difficulties exist in predicting the slope stability warning level by using machine learning algorithms: using supervised machine learning algorithms such as support vector machine (SVM), decision tree (DT) or neural network (NN) to build a model, first, a large amount of slope monitoring data needs to be collected, such as collecting and sorting the data of the places where the slope instability events have occurred in history and the slope data that has been in a stable state together or building an experimental system, but both collecting historical data and building a system have certain difficulties and are time-consuming and laborious; and using unsupervised machine learning algorithms such as K-Means, when facing a large amount of real-time monitoring data, such as short-time heavy rainfall, it is impossible to quickly complete clustering and warning level judgment, resulting in delayed warning. SUMMARY

[0008] In order to solve the problems existing in the prior art, the present application provides a power transmission line slope stability warning method and system for short-time heavy rainfall.

[0009] The technical scheme of the present application is as follows:

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

[0011] Collecting first pore water pressure and first temperature change data by synchronously arranging pore water pressure sensors and temperature sensors in different depth directions of the potential sliding surface of the power transmission line slope;

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

[0013] Establishing a correlation prediction model of the infiltration depth and the infiltration speed and the slope stability coefficient, and predicting the first slope stability coefficient through the first infiltration depth and the first infiltration speed;

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

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

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

[0017] As a preferred embodiment, when a short-time heavy rainfall event occurs, the change trend of the obtained second pore water pressure, second temperature change data and second slope stability coefficient is different from the change trend of historical data, the cluster center is adjusted, and the slope stability early warning level is updated.

[0018] As a preferred embodiment, the step of establishing the correlation prediction model of the infiltration depth and the infiltration speed and the slope stability coefficient is specifically:

[0019] The model parameters are collected, including the size of the slope, the shear strength index of the soil layer, the unit weight, and the porosity parameterization index, the slope stability coefficient corresponding to the rainwater infiltration depth and infiltration speed under different model parameter conditions is calculated, and a data set is constructed;

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

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

[0022] The pore water pressure sensor and the temperature sensor are synchronously arranged in different depth directions of the potential sliding surface of the power transmission line slope, and are respectively used for collecting first pore water pressure and first temperature change data;

[0023] The data conversion module is used for obtaining the first infiltration depth and the first infiltration speed of the rainwater into the slope through the first pore water pressure and the first temperature change data in different depth directions.

[0024] The correlation prediction model establishing module is configured to establish a correlation prediction model of the infiltration depth and the infiltration speed and the slope stability coefficient, and to predict a first slope stability coefficient through the first infiltration depth and the first infiltration speed;

[0025] The clustering module is configured to construct 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 in the non-short-time heavy rainfall period, and to save model parameters of the non-short-time heavy rainfall period;

[0026] The early warning module is configured to start a real-time monitoring mode when detecting that the short-time heavy rainfall event occurs, to collect second pore water pressure and second temperature change data in real time through the pore water pressure sensor and the temperature sensor, to obtain a second slope stability coefficient through the correlation prediction model, to distribute the second pore water pressure, the second temperature change data and the second slope stability coefficient to the existing cluster of the pre-training model, to obtain a current slope stability early warning level, and to perform early warning according to the current slope stability early warning level.

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

[0028] As a preferred embodiment, when the short-time heavy rainfall event occurs, the change trend of the obtained second pore water pressure, the second temperature change data and the second slope stability coefficient is different from the change trend of the historical data, the cluster center is adjusted, and the slope stability early warning level is updated.

[0029] As a preferred embodiment, the step of establishing the correlation prediction model of the infiltration depth and the infiltration speed and the slope stability coefficient specifically includes the following steps:

[0030] The model parameters are collected, including the size of the slope, the shear strength index of the soil layer, the unit weight, and the porosity parameterization index, the slope stability coefficients corresponding to the rainwater infiltration depth and the infiltration speed under different model parameter conditions are calculated, and a data set is constructed;

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

[0032] In another aspect, the application further provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the method for early warning of the slope stability of a power transmission line in a short-time heavy rainfall according to any one of the embodiments of the application when executing the program.

[0033] In still another aspect, the present application also provides a computer readable storage medium, having stored thereon a computer program, which when executed by a processor implements the power transmission line slope stability early warning method for short-time heavy rainfall as described in any of the embodiments of the present application.

[0034] The present application has the following beneficial effects:

[0035] The present application provides a power transmission line slope stability early warning method and system for short-time heavy rainfall, by constructing a pre-training model in a non-short-time heavy rainfall period, saving the parameters of the model, when short-time heavy rainfall comes, facing a large amount of new input data, using the pre-trained pre-training model, directly assigning the new data points to the existing clusters, quickly obtaining the slope stability early warning level. Since the pre-training 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 the short-time heavy rainfall period is avoided.

[0036] Additional aspects and advantages of the present application will be set forth in the description below, and in part will become apparent from the description, or can be learned by practice of the present application. Moreover, those skilled in the art will realize that the various aspects and advantages of the present application can be achieved with the processes and combinations specifically pointed out herein below. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 Flow chart of the method of embodiment one of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0039] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

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

[0041] The terms "comprise" and "contain" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

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

[0043] Embodiment one:

[0044] Referring to Figure 1 The embodiment provides a power transmission line slope stability early warning method for short-time heavy rainfall, comprising the following steps:

[0045] S100, collecting first pore water pressure and first temperature change data through pore water pressure sensors and temperature sensors arranged in different depth directions of a potential sliding surface of a power transmission line slope in synchronization;

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

[0047] When rainwater infiltrates into 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. With the continuous infiltration of rainwater, the sensors at different depths will respond in turn. According to the position of the sensor that first detects the change in pore water pressure, the infiltration depth of rainwater can be preliminarily judged. Temperature change can also assist in judging the infiltration depth. Rainwater infiltration will change the temperature of the soil body because the temperature of rainwater is usually different from the initial temperature of the soil body. If the temperature sensor at a certain depth detects that the temperature changes significantly and synchronously with the change in pore water pressure, it can also be used as a basis for judging that rainwater has reached that depth.

[0048] The infiltration speed is determined by analyzing the time difference of the response of the pore water pressure sensors at different depths. It is assumed that the sensor at depth h1 detects the change in pore water pressure at time t1, and the sensor at depth h2 detects the change at time t2. According to the principle of Darcy's law, the average infiltration speed of rainwater between the two depths can be estimated.

[0049] S300, establishing a correlation prediction model of the infiltration depth and the infiltration speed and the slope stability coefficient, and predicting a first slope stability coefficient through the first infiltration depth and the first infiltration speed.

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

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

[0052] The method for obtaining the model parameters is as follows: for the target slope, the size information is measured, including the geometric size data such as the slope height, the slope angle, and the slope length; the shear strength index of the soil layer is obtained, including the internal friction angle and the cohesion, in this embodiment, the accurate values are obtained by testing the soil sample of the target soil layer through the indoor soil test direct shear test, and the triaxial test and the like can also be used; the bulk density data of the target soil layer is recorded, which can be tested in situ, and in this embodiment, the ring cutter method is used in combination with the indoor test to determine the bulk density values corresponding to different soil layers; the porosity data can also be measured through the soil test means.

[0053] The collected parameter data is arranged in a unified format, and each row represents the slope state of one observation, and each column corresponds to the slope size, the shear strength index, the bulk density, the porosity, the rainwater infiltration depth, the infiltration velocity and the like, to obtain the original data set.

[0054] The finite element method is used to calculate the slope stability coefficient, the finite element analysis software (such as ABAQUS) is used for modeling, the geometric size of the target slope is input, the element is divided, the soil layer material properties are set, including the shear strength index, the bulk density, and the porosity, the rainwater infiltration depth and the infiltration velocity are input to simulate the rainwater infiltration process, and finally the calculation is run to obtain the corresponding slope stability coefficient under different parameter conditions by the strength reduction method, and the results are recorded and arranged corresponding to the parameters of the original data set.

[0055] S302, input the data set into the neural network model, establish a nonlinear correlation prediction model of different infiltration depth and infiltration velocity and slope stability coefficient, and output the slope stability coefficient;

[0056] First, data cleaning is performed to check whether there are abnormal values in the data set calculated in S301, such as unreasonable negative numbers or maximum and minimum values of the slope stability coefficient, for such abnormal values, whether the measurement error or other reasons is determined by analyzing the corresponding other parameter conditions and referring to the past experience, physical law and the like, if it is determined that the data is wrong, it is modified or excluded; if there are missing values, the missing values are filled according to the correlation of the data. For example, if the infiltration velocity is missing in a certain group of data, but the rainfall intensity and other related information at that time are known and have a certain correlation with the infiltration velocity, the missing infiltration velocity value can be estimated by an empirical formula or the like.

[0057] Then the data standardization processing is carried out. Since the dimensions and numerical ranges of the parameters such as the size of the slope, the shear strength index, the unit weight, the porosity, the infiltration depth, the infiltration speed and the stability coefficient are quite different, in order to facilitate the training of the neural network, the minimum-maximum normalization method is used to map the parameter data to the interval [0, 1], and the data standardization can also be carried out by other methods.

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

[0059] S400, according to the first pore water pressure, the first temperature change data and the first slope stability coefficient in the non-short-time heavy rainfall period, a pre-training model is constructed by the K-Means clustering algorithm, and the model parameters in the non-short-time heavy rainfall period are saved.

[0060] Firstly, the K-Means clustering algorithm is used to pre-train the clustering model in the non-short-time heavy rainfall period. When the pre-training model reaches the convergence state, the parameters of the model are saved, including the cluster center, the cluster number and other information related to the model, so as to be quickly loaded and used when the short-time heavy rainfall comes. The pre-warning levels calibrated by the pre-training model are as follows:

[0061] Blue pre-warning level (level IV-basic stable state)

[0062] Pore water pressure characteristics: the amplitude of the change of the pore water pressure is very small, and the pore water pressure is in a relatively stable numerical interval for a long time, and the fluctuation range is usually within ±5% of the reasonable mean value (this proportion can be adjusted according to the historical stability data of the specific slope and the actual engineering situation). For example, if the pore water pressure of the slope is long-term stable at 10kPa-12kPa in the normal stable period, in the clustering data belonging to the blue pre-warning level, the value basically maintains fluctuation in this interval, and there is no sudden increase or decrease in a short period of time.

[0063] Temperature change value characteristics: the temperature is basically stable, and there is no obvious abnormal fluctuation. Generally speaking, the daily temperature change amplitude is consistent with the normal diurnal temperature difference in the local area, and there is no phenomenon that the temperature suddenly rises or falls in a certain period of time and deviates from the conventional seasonal temperature change rule. For example, in the normal spring, the daily temperature fluctuation is between 10℃-20℃, and the temperature trend is stable between days, and there is no abnormal situation that the temperature suddenly rises to 30℃ or falls to 5℃ on a certain day.

[0064] Slope stability coefficient characteristics: The slope stability coefficient remains at a high level, with a value usually greater than 1.3, indicating that the overall structure of the slope is stable and can resist external interference factors within a normal range, such as rainfall and small vibrations, with a very low possibility of instability.

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

[0066] Pore water pressure characteristics: Pore water pressure starts to fluctuate to some extent, with a fluctuation range that has increased compared to the blue warning level, roughly ±10%-±15% around the reasonable mean value. For example, the pore water pressure that was previously stable at 10kPa-12kPa now occasionally exceeds this interval, reaching 8kPa or 14kPa, and the frequency of such fluctuations has increased compared to the stable period, possibly occurring once every few days with small amplitude fluctuations.

[0067] Temperature change value characteristics: The temperature has appeared some fluctuations beyond the normal range, but not serious. For example, in seasons where the diurnal temperature difference is stable, the diurnal temperature difference of individual days has increased by 3-5°C compared to usual, or the temperature in local areas has experienced short-term abnormal heating or cooling. However, 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 decreased to some extent, with a value close to but still above the critical safety value, between 1.1-1.3. This indicates that although the slope is still relatively stable overall, the influence of unstable factors is gradually accumulating, and its ability to resist external interference has weakened compared to the blue warning level, requiring increased monitoring and attention.

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

[0070] Pore water pressure characteristics: Pore water pressure fluctuations become more frequent and further increase in amplitude, with a fluctuation range of ±20%-±30% of the reasonable mean value. For example, pore water pressure that was previously stable in the interval of 10kPa-12kPa now often appears below 8kPa or above 15kPa, and the interval time of such large fluctuations is shortened, possibly occurring several times a day, indicating that the potential impact of pore water pressure changes on slope stability is increasing.

[0071] Temperature change value feature: the temperature appears relatively obvious and long duration of abnormal change. For example, the local area temperature appears higher or lower than the normal temperature interval 5-10℃ for several days, or the temperature difference of different positions of the whole slope becomes abnormally large. This temperature anomaly phenomenon interacts with factors such as internal stress change of the slope, and may accelerate the development of the slope to an unstable state.

[0072] Slope stability coefficient feature: the slope stability coefficient continues to decline, and the value is in the range close to the critical value, between 0.9 and 1.1. At this time, the slope has a high possibility of local instability, such as small-scale collapse or blockage of part of the slope surface, and corresponding protection and reinforcement measures need to be taken, and the trend needs to be closely monitored.

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

[0074] Pore water pressure feature: the pore water pressure appears severe fluctuation, the fluctuation range far exceeds the normal interval, and may reach ±50% of the reasonable mean value or even higher, and the fluctuation has no rules, and the value may jump greatly in a short time, which indicates that the internal water pressure of the slope has seriously destroyed the original stress balance, and poses a great threat to the stability of the slope soil.

[0075] Temperature change value feature: the temperature appears serious abnormal change, and the local area temperature may rise or fall sharply, with a deviation of more than 10℃ compared with the normal temperature, and this abnormal temperature phenomenon lasts for several days without improvement, or the whole slope temperature field presents a chaotic and disordered state, which is interwoven with factors such as deformation of the slope rock-soil body and change of pore water pressure, and accelerates the instability process of the slope.

[0076] Slope stability coefficient feature: the slope stability coefficient is lower than the critical safety value, less than 0.9, which means that the slope is in a state of imminent or already large-scale overall instability, and the soil body appears large-area sliding, collapse and other phenomena, which poses a serious threat to the surrounding buildings, traffic facilities and personnel life safety, and emergency plans must be started immediately, surrounding personnel must be evacuated and emergency rescue measures must be taken.

[0077] S500, when a short-time heavy rainfall event is detected, a real-time monitoring mode is started, and second pore water pressure and second temperature change data are collected in real time through the pore water pressure sensor and the temperature sensor; a second slope stability coefficient is obtained through the correlation prediction model; the second pore water pressure, the second temperature change data and the second slope stability coefficient are distributed to the existing cluster of the pre-trained model, to obtain a current slope stability warning level, and a warning is given 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 activated to collect the pore water pressure and temperature change values of the potential sliding surface at a higher frequency (e.g., every few minutes). Real-time preprocessing is performed on these newly collected data, including outlier removal (due to rainfall, some sensor data may exhibit temporary abnormal fluctuations, which need to be identified and processed in a timely manner) and normalization with the same process as during non-rainfall periods, ensuring that the new data is consistent with the data format and scale of the pre-trained model. The pre-trained non-short-term heavy rainfall period clustering model is quickly loaded, and the newly collected short-term heavy rainfall period data points are directly assigned to existing clusters to quickly obtain the preliminary clustering assignment results. Since the pre-trained model has learned the stable state patterns 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 computation time and resources required to train the model from scratch in an emergency.

[0079] In some embodiments, based on the pre-trained non-short-term heavy rainfall period clustering model, the pre-trained model is fine-tuned according to the distribution characteristics and actual situation of the new data. For example, if it is found that many data points in the new data are far away from the original cluster centers, or the data points in some clusters exhibit a trend significantly different from the historical data (such as a sharp rise in pore water pressure, abnormal fluctuations in temperature, and a rapid decrease in slope stability coefficient), the cluster centers need to be adjusted appropriately. Incremental learning is used to gradually incorporate new data into the model update process, and the model parameters are optimized slightly to adapt to the impact of short-term heavy rainfall on the slope state. According to the fine-tuned clustering results, the real-time slope warning level of each cluster is updated. For example, if the data in a cluster during heavy rainfall shows obvious instability characteristics and is similar to the data characteristics when the slope was in danger in the past, the warning level corresponding to the cluster is raised to a higher level (such as from yellow to orange or red); for clusters whose data changes relatively small during heavy rainfall and still close to the stable state clustering characteristics during non-heavy rainfall, the warning level is maintained at a lower level (such as blue or yellow).

[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 is immediately triggered, and detailed warning information is sent to relevant personnel, including the specific location of the slope, the current warning level, the possible danger level, and the recommended response measures, etc., so that timely and effective protection and management actions can be taken to ensure the safety of life and property around the slope.

[0081] Embodiment Two:

[0082] The present embodiment proposes a power transmission line slope stability warning system for short-term heavy rainfall, comprising:

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

[0084] The data conversion module is used to obtain the first infiltration depth and the first infiltration speed of the rainwater into the slope through the first pore water pressure and the first temperature change data in the direction of different depths; this module is used to realize the function of step S200 in embodiment one, and will not be repeated here;

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

[0086] The clustering module is used to construct 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 in the non-short-time heavy rainfall period, and save the model parameters in the non-short-time heavy rainfall period; this module is used to realize the function of step S400 in embodiment one, and will not be repeated here;

[0087] The warning module is used to start a real-time monitoring mode when detecting the occurrence of a short-time heavy rainfall event, and collect second pore water pressure and second temperature change data in real time through the pore water pressure sensor and the temperature sensor; obtain a second slope stability coefficient through the correlation prediction model; distribute the second pore water pressure, the second temperature change data and the second slope stability coefficient to the existing cluster of the pre-training model to obtain a current slope stability warning level, and perform warning according to the current slope stability warning level; this module is used to realize the function of step S500 in embodiment one, and will not be repeated here.

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

[0089] As a preferred embodiment of the present embodiment, when the short-time heavy rainfall event occurs, the change trend of the obtained second pore water pressure, the second temperature change data and the second slope stability coefficient is different from the change trend of the historical data, the cluster center is adjusted, and the slope stability warning level is updated.

[0090] As a preferred embodiment of the present embodiment, the step of establishing the correlation prediction model of the infiltration depth and the infiltration speed and the slope stability coefficient is specifically:

[0091] Collecting model parameters, including the size of the slope, the shear strength index of the soil layer, the unit weight, and the porosity parameterization index, calculating the slope stability coefficient corresponding to the rainwater infiltration depth and the infiltration speed under different model parameter conditions, and constructing a data set;

[0092] Inputting the data set into a neural network model, establishing a nonlinear correlation prediction model of different infiltration depths and infiltration speeds and the slope stability coefficient, and outputting the slope stability coefficient.

[0093] Embodiment three:

[0094] The present embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to realize the power transmission line slope stability early warning method for short-time heavy rainfall as described in any embodiment of the present application.

[0095] Embodiment four:

[0096] The present embodiment provides a computer-readable storage medium having a computer program stored thereon, and the program is executed by a processor to realize the power transmission line slope stability early warning method for short-time heavy rainfall as described in any embodiment of the present application.

[0097] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, and c can be single or multiple.

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

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0100] In several embodiments provided in the present application, any function, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory; hereinafter referred to as: ROM), a random access memory (Random Access Memory; hereinafter referred to as: RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0101] The above is only an embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent flow transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for early warning of the stability of transmission line slopes in response to short-term heavy rainfall, characterized in that, Includes the following steps: By synchronously deploying pore water pressure sensors and temperature sensors at different depths on the potential sliding surface of the transmission line slope, data on the changes in the first pore water pressure and the first temperature are collected. By using the data on the first pore water pressure and the first temperature change at different depths, the first infiltration depth and the first infiltration rate of rainwater into the slope are obtained. Establish a correlation prediction model between infiltration depth and infiltration velocity and slope stability coefficient, and predict the first slope stability coefficient using the first infiltration depth and the first infiltration velocity; Based on the first pore water pressure, first temperature change data and first slope stability coefficient during non-short-term heavy rainfall periods, a pre-trained model is constructed using the K-Means clustering algorithm, and the model parameters during non-short-term heavy rainfall periods are saved. When a short-term heavy rainfall event is detected, a real-time monitoring mode is activated. The pore water pressure sensor and temperature sensor collect data on the changes in the second pore water pressure and the second temperature in real time. The second slope stability coefficient is obtained through the correlation prediction model. The data on the changes in the second pore water pressure and the second temperature, as well as the second slope stability coefficient, are assigned to the existing clusters of the pre-trained model to obtain the current slope stability warning level. A warning is then issued based on the current slope stability warning level.

2. The method for early warning of transmission line slope stability in response to short-term heavy rainfall as described in claim 1, characterized in that: When a short-term heavy rainfall event occurs, if 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 transmission line slope stability in response to short-term heavy rainfall as described in claim 1, characterized in that: When a short-term heavy rainfall event occurs, if the changing trends of the second pore water pressure, second temperature, and second slope stability coefficient differ from the changing trends of historical data, the cluster center is adjusted and the slope stability warning level is updated.

4. The method for early warning of transmission line slope stability in response to short-term heavy rainfall as described in claim 1, characterized in that, The specific steps for establishing the correlation prediction model between infiltration depth and infiltration velocity and slope stability coefficient are as follows: Collect model parameters, including slope dimensions, soil shear strength index, unit weight, and porosity parameterization index, calculate slope stability coefficients corresponding to rainwater infiltration depth and infiltration velocity under different model parameter conditions, and construct a dataset; The dataset is input into a neural network model to establish a nonlinear correlation prediction model between different infiltration depths and infiltration velocities and the slope stability coefficient, and the slope stability coefficient is output.

5. A power transmission line slope stability early warning system for short-duration heavy rainfall, characterized in that, include: Pore ​​water pressure sensors and temperature sensors are synchronously deployed at different depths along the potential sliding surface of the transmission line slope. The pore water pressure sensors and temperature sensors are used to collect data on the first pore water pressure and the first temperature change, respectively. The data conversion module is used to obtain the first infiltration depth and the first infiltration rate of rainwater into the slope by using the first pore water pressure and first temperature change data at different depth directions. The correlation prediction model building module is used to build a correlation prediction model between infiltration depth and infiltration velocity and slope stability coefficient, and predict the first slope stability coefficient through the first infiltration depth and the first infiltration velocity. The clustering module is used to build a pre-trained model based on the first pore water pressure, first temperature change data and first slope stability coefficient during non-short-term heavy rainfall periods, and to save the model parameters during non-short-term heavy rainfall periods. The early warning module is used to activate a real-time monitoring mode when a short-term heavy rainfall event is detected. It collects the second pore water pressure and second temperature change data in real time through the pore water pressure sensor and temperature sensor; obtains the second slope stability coefficient through the correlation prediction model; assigns the second pore water pressure, second temperature change data and second slope stability coefficient to the existing clusters of the pre-trained model to obtain the current slope stability early warning level, and issues an early warning based on the current slope stability early warning level.

6. The early warning system for the stability of transmission line slopes in response to short-term heavy rainfall as described in claim 5, characterized in that: When a short-term heavy rainfall event occurs, if 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 early warning system for the stability of transmission line slopes in response to short-term heavy rainfall as described in claim 5, characterized in that: When a short-term heavy rainfall event occurs, if the changing trends of the second pore water pressure, second temperature, and second slope stability coefficient differ from the changing trends of historical data, the cluster center is adjusted and the slope stability warning level is updated.

8. A power transmission line slope stability early warning system for short-term heavy rainfall as described in claim 5, characterized in that, The specific steps for establishing the correlation prediction model between infiltration depth and infiltration velocity and slope stability coefficient are as follows: Collect model parameters, including slope dimensions, soil shear strength index, unit weight, and porosity parameterization index, calculate slope stability coefficients corresponding to rainwater infiltration depth and infiltration velocity under different model parameter conditions, and construct a dataset; The dataset is input into a neural network model to establish a nonlinear correlation prediction model between different infiltration depths and infiltration velocities and the slope stability coefficient, and the slope stability coefficient is output.

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, it implements the method as described in any one of claims 1 to 4.

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

Images