Power transmission tower slope soil seepage field dynamic monitoring method

Abstract

The invention provides a dynamic monitoring method for a soil mass seepage field of a power transmission tower slope. According to the method, related data of the slope are acquired through multi-source data acquisition and technologies of pressure sensing and static pressure measurement, displacement monitoring, multi-sensor fusion, Beidou / GPS positioning, resistivity method exploration, soil moisture content monitoring and the like; fusing the collected multi-source data, analyzing the dynamic change of the seepage field by using a risk assessment model and a machine learning algorithm, and predicting the evolution trend of the seepage field; a lightweight model is deployed at a monitoring terminal to realize local rapid processing of data, alarm information is immediately sent out once an abnormal state is monitored, and scientific and reasonable decision support is provided for protection and treatment of a transmission tower slope according to early warning information in combination with a pre-made decision scheme; according to the invention, the accuracy and timeliness of transmission tower slope soil seepage field monitoring can be effectively improved, and the threat of landslide and other disasters to a transmission line is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of transmission tower slope monitoring, in particular to a method for dynamically monitoring soil seepage field of a transmission tower slope. Background Art

[0002] As an important supporting structure of the transmission line, the stability of the transmission tower is directly related to the safe operation of the transmission line. The seepage of the slope soil will have a significant impact on the stability of the transmission tower. For example, seepage may cause the soil strength to decrease and the slope to become unstable, thus threatening the safety of the transmission tower.

[0003] At present, the existing monitoring methods have certain limitations, such as insufficient monitoring accuracy of deep seepage fields, and long-term stability affected by environmental corrosion. Therefore, there is an urgent need for a method that can comprehensively, accurately and real-time monitor the dynamic changes of the seepage field of the slope soil of the transmission tower, so as to improve the ability to assess the stability of the slope, timely discover potential risks and take effective measures. Summary of the invention

[0004] The present invention provides a method for dynamically monitoring the seepage field of soil at the slope of a transmission tower, aiming to solve the problems raised by the above-mentioned background technology.

[0005] The present invention is implemented as follows: a method for dynamically monitoring the seepage field of a transmission tower slope soil, comprising the following steps:

[0006] Step 1: Multi-source data collection,

[0007] Using pressure sensing and static pressure measurement, burying pressure sensors and static pressure water level gauges at appropriate locations inside the slope, obtaining real-time data on the change in water head pressure inside the slope, and calculating the soil permeability coefficient through a preset algorithm combined with a permeability test;

[0008] The displacement and deformation of the slope surface and deep soil are monitored using total stations and chain displacement meters. Combined with settlement observation data, the stability changes of the slope under the influence of seepage are analyzed.

[0009] Deploy a multi-sensor fusion monitoring system integrating inclinometers, vibration sensors, soil moisture meters, and crack monitors to continuously collect multi-dimensional data on slope inclination, micro-vibration, moisture content, and crack extension, and use a data cross-validation mechanism to reduce the data false alarm rate;

[0010] With the help of Beidou ground-based augmentation network and related positioning equipment, millimeter-level three-dimensional coordinate monitoring of slope surface displacement is achieved, and the initial coordinates are compared through real-time differential processing. Once the displacement exceeds the preset threshold, an early warning is triggered immediately;

[0011] Deploy intelligent electrode arrays and use resistivity exploration technology to detect soil resistivity differences, invert the seepage field distribution and potential sliding surface locations; at the same time, use adaptive power supply and wireless networking technology to ensure stable data acquisition in complex terrain;

[0012] Install capacitive or time domain reflectometry (TDR) soil moisture sensors to monitor the changes in soil moisture content at different depths in real time to assess the impact of rainfall infiltration on the seepage field;

[0013] Step 2: Data fusion and analysis steps.

[0014] The collected multi-source data such as resistivity, displacement, meteorology, and soil moisture content are integrated to construct a risk assessment model, and the landslide risk level is quantified by the formula RiskScore = w1·F(ρ)+w2·G(ε)+w3·H(W), where w1, w2, and w3 are the weights of each factor, and F(ρ), G(ε), and H(W) are functions related to resistivity, displacement, and meteorology, respectively;

[0015] Use machine learning algorithms such as LSTM network or unscented Kalman filter to process time series data and predict the evolution trend of the seepage field;

[0016] Step 3: Early warning and decision-making steps,

[0017] Deploy lightweight models on monitoring terminals to achieve fast local data processing. Once an abnormal state is detected, an alarm message is immediately issued to reduce dependence on the cloud.

[0018] Based on the early warning information and combined with the pre-made decision-making plan, scientific and reasonable decision-making support is provided for the protection and management of transmission tower slopes.

[0019] Preferably, in the multi-source data collection step, the deployment location and density of each sensor are optimized according to the geological conditions, topography and historical seepage conditions of the slope to ensure that comprehensive and accurate data are obtained.

[0020] Preferably, in the multi-source data acquisition step, for pressure sensing and static pressure measurement technology, the selection of pressure sensors and static pressure water level gauges is determined based on the slope soil type and the expected head pressure range to ensure measurement accuracy and range adaptation.

[0021] Preferably, in the multi-source data acquisition step, the electrode spacing and arrangement of the intelligent electrode array are adjusted according to the geological complexity of the area to be monitored and the target detection depth to improve the accuracy of resistivity exploration.

[0022] Preferably, in the data fusion and analysis step, the weights w1, w2, w3 in the risk assessment model are dynamically adjusted and determined through multiple tests and data analysis according to the importance and relevance of the actual monitoring data.

[0023] Preferably, in the data fusion and analysis step, when using a machine learning algorithm to predict the evolution trend of the seepage field, the training data is regularly updated to adapt to changes in slope soil properties and environmental conditions.

[0024] Preferably, in the early warning and decision-making steps, the issuance of alarm information is carried out according to preset multi-level early warning thresholds, and different levels of early warnings correspond to different coping measures and response processes.

[0025] Preferably, in the early warning and decision-making steps, the formulation of the decision plan comprehensively considers the importance of the transmission line, the surrounding environment, and the management cost factors to ensure the scientificity and feasibility of the decision.

[0026] Due to the adoption of the above scheme, the beneficial effects of the present invention are: accurate and comprehensive monitoring of the seepage field: adopting multi-source data acquisition technology, integrating pressure sensing, displacement monitoring, multi-sensor fusion, Beidou / GPS positioning, resistivity exploration and soil moisture monitoring and other means, to obtain slope data from different dimensions. Pressure sensing and static pressure measurement can directly obtain head pressure change data and deduce soil permeability; resistivity exploration can invert the seepage field distribution and potential sliding surface position, realize comprehensive and accurate dynamic monitoring of soil seepage field, and make up for the shortcomings of single monitoring technology.

[0027] Timely and accurate early warning of risks: By building a risk assessment model to quantify the landslide risk level, using machine learning algorithms to predict the evolution trend of the seepage field, and deploying lightweight models at the monitoring terminal to achieve local and rapid data processing. Once an abnormal state is detected, an alarm message can be issued immediately, reducing dependence on the cloud, greatly improving the timeliness and accuracy of the early warning, and enabling operation and maintenance personnel to grasp the slope risk status in a timely manner and take preventive measures in advance.

[0028] Ensure safe and stable operation of transmission lines: effectively monitor the dynamic changes of seepage fields, timely discover potential risks and issue early warnings, provide a scientific basis for the protection and management of transmission tower slopes, avoid damage to transmission towers due to slope instability, ensure the safe and stable operation of transmission lines, and reduce economic losses and social impacts caused by line failures.

[0029] Provide scientific and reasonable decision support: Based on the early warning information, combined with the pre-made decision plan, and taking into account the importance of the transmission line, the surrounding environment, the cost of governance and other factors, provide scientific and reasonable decision support for slope protection and governance. When making decisions, take into account the importance of the line, take more active and effective protection measures for key lines, ensure the scientificity and feasibility of the decision, and improve the efficiency and effectiveness of slope governance. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0032] like Figure 1 As shown: A method for dynamic monitoring of soil seepage field on the slope of a transmission tower includes the following steps:

[0033] Step 1: Multi-source data collection,

[0034] Using pressure sensing and static pressure measurement, burying pressure sensors and static pressure water level gauges at appropriate locations inside the slope, obtaining real-time data on the change in water head pressure inside the slope, and calculating the soil permeability coefficient through a preset algorithm combined with a permeability test;

[0035] The displacement and deformation of the slope surface and deep soil are monitored using total stations and chain displacement meters. Combined with settlement observation data, the stability changes of the slope under the influence of seepage are analyzed.

[0036] Deploy a multi-sensor fusion monitoring system integrating inclinometers, vibration sensors, soil moisture meters, and crack monitors to continuously collect multi-dimensional data on slope inclination, micro-vibration, moisture content, and crack extension, and use a data cross-validation mechanism to reduce the data false alarm rate;

[0037] With the help of Beidou ground-based augmentation network and related positioning equipment, millimeter-level three-dimensional coordinate monitoring of slope surface displacement is achieved, and the initial coordinates are compared through real-time differential processing. Once the displacement exceeds the preset threshold, an early warning is triggered immediately;

[0038] Deploy intelligent electrode arrays and use resistivity exploration technology to detect soil resistivity differences, invert the seepage field distribution and potential sliding surface locations; at the same time, use adaptive power supply and wireless networking technology to ensure stable data acquisition in complex terrain;

[0039] Install capacitive or time domain reflectometry (TDR) soil moisture sensors to monitor the changes in soil moisture content at different depths in real time to assess the impact of rainfall infiltration on the seepage field;

[0040] Step 2: Data fusion and analysis steps.

[0041] The collected multi-source data such as resistivity, displacement, meteorology, and soil moisture content are integrated to construct a risk assessment model, and the landslide risk level is quantified by the formula RiskScore = w1·F(ρ)+w2·G(ε)+w3·H(W), where w1, w2, and w3 are the weights of each factor, and F(ρ), G(ε), and H(W) are functions related to resistivity, displacement, and meteorology, respectively;

[0042] Use machine learning algorithms such as LSTM network or unscented Kalman filter to process time series data and predict the evolution trend of the seepage field;

[0043] Step 3: Early warning and decision-making steps,

[0044] Deploy lightweight models on monitoring terminals to achieve fast local data processing. Once an abnormal state is detected, an alarm message is immediately issued to reduce dependence on the cloud.

[0045] Based on the early warning information and combined with the pre-made decision-making plan, scientific and reasonable decision-making support is provided for the protection and management of transmission tower slopes.

[0046] Preferably, in the multi-source data collection step, the deployment location and density of each sensor are optimized according to the geological conditions, topography and historical seepage conditions of the slope to ensure that comprehensive and accurate data are obtained.

[0047] In the multi-source data collection step, for pressure sensing and static pressure measurement technology, the selection of pressure sensors and static pressure water level gauges is determined based on the slope soil type and the expected head pressure range to ensure measurement accuracy and range adaptation.

[0048] In the multi-source data acquisition step, the electrode spacing and arrangement of the intelligent electrode array are adjusted according to the geological complexity of the area to be monitored and the target detection depth to improve the accuracy of resistivity exploration.

[0049] In the data fusion and analysis step, the weights w1, w2, and w3 in the risk assessment model are dynamically adjusted and determined through multiple tests and data analysis based on the importance and relevance of the actual monitoring data.

[0050] In the data fusion and analysis step, when using the machine learning algorithm to predict the evolution trend of the seepage field, the training data is regularly updated to adapt to changes in slope soil characteristics and environmental conditions.

[0051] In the early warning and decision-making steps, the issuance of alarm information is carried out according to preset multi-level early warning thresholds, and different levels of early warnings correspond to different coping measures and response processes.

[0052] In the above-mentioned early warning and decision-making steps, the formulation of the decision-making plan comprehensively considers the importance of the transmission line, the surrounding environment, and the cost of governance to ensure the scientificity and feasibility of the decision.

[0053] In this embodiment, a variety of physical principles and technical means are used to obtain data of different dimensions. Pressure sensing and static pressure measurement use pressure sensors and static pressure water level gauges. Based on the principle of force and electrical signal conversion, the head pressure change inside the slope is converted into an electrical signal to obtain pressure data. Combined with the permeability test principle, the soil permeability coefficient is deduced through relevant formulas such as Darcy's law. Displacement monitoring equipment such as total stations use the reflection and angle measurement principles of light. Chain displacement meters measure the displacement deformation of the slope surface and deep soil based on the relationship between displacement and resistance or potential change. In the multi-sensor fusion monitoring system, the inclinometer measures the inclination based on the gravity sensing principle, the vibration sensor senses micro-vibration through electromagnetic induction or piezoelectric effect, the soil moisture meter uses capacitance change or time domain reflection principle to monitor the moisture content, and the crack monitor uses optical imaging or strain sensing principle to monitor crack expansion. The data of each sensor complements and verifies each other. Beidou / GPS positioning is based on the principles of satellite signal propagation and triangulation to achieve high-precision three-dimensional coordinate monitoring of slope surface displacement; resistivity exploration is based on the difference in resistivity between dry and wet soils. By applying current to the soil, the potential difference at different positions is measured and the seepage field distribution is inverted; soil moisture monitoring uses the changes in electrical properties caused by the interaction between capacitive or TDR sensors and soil moisture to monitor moisture content.

[0054] Data fusion is the process of integrating multi-source data according to certain rules, eliminating redundant and contradictory information, and improving data reliability and integrity. The construction of a risk assessment model is based on the degree of influence of various factors on landslide risk, and the relationship between each factor and the risk level is quantified through mathematical functions. Machine learning algorithms such as LSTM networks are based on the characteristics of time series data, learn long-term dependencies in data through memory units and gating mechanisms, and predict the evolution trend of the seepage field; Unscented Kalman Filter (UKF) is based on probability statistics and state estimation theory, and improves the accuracy of the estimation of the seepage field state by predicting and measuring the system state.

[0055] Lightweight models are deployed at monitoring terminals, and the processed data is quickly classified and identified using the models. Once the data characteristics meet the preset abnormal patterns, the alarm mechanism is triggered immediately. Decision-making plans are formulated based on early warning information, taking into account the importance of transmission lines, surrounding environment, governance costs and other factors, and using multi-objective decision analysis methods to weigh the pros and cons of various factors and formulate scientific and reasonable response strategies.

[0056] Specifically, based on the slope geological survey report, topographic mapping and historical seepage monitoring data, the Geographic Information System (GIS) analysis technology is used to determine the optimal deployment location and quantity of pressure sensors, static pressure water level gauges, total stations, chain displacement meters, multi-sensor fusion monitoring equipment, Beidou / GPS positioning equipment, smart electrode arrays and soil moisture sensors. For example, in areas with complex geological structures and high seepage risks, dense sensor deployment is required.

[0057] According to the slope soil type (such as sand, clay, etc.) and the expected head pressure range, select pressure sensors and static pressure water level gauges with appropriate range and accuracy by referring to the sensor selection manual and relevant technical standards, and bury them according to the installation specifications to ensure good contact with the soil and avoid measurement errors.

[0058] According to the geological complexity of the monitored area (such as formation uniformity, fault distribution, etc.) and the target detection depth, numerical simulation software (such as COMSOL, etc.) is used to simulate the electric field distribution under different electrode spacing and arrangement methods, optimize the layout of the intelligent electrode array, and improve the accuracy of resistivity exploration.

[0059] Build a multi-source data fusion platform, and use data interface technology to unify the collected resistivity, displacement, meteorology, soil moisture and other data into a unified format and connect them to the platform. Through multiple field tests and historical data comparison and analysis, use the analytic hierarchy process (AHP) and other methods to determine the weights w1, w2, and w3 of each factor in the risk assessment model, so that the model is more in line with the actual situation.

[0060] Regularly collect new monitoring data, use data cleaning algorithms to remove outliers and noise, add the cleaned data to the training data set, retrain and optimize the LSTM network or UKF model, and improve the accuracy of the model's prediction of the evolution trend of the seepage field.

[0061] Based on historical accident data, expert experience and slope stability analysis results, multi-level warning thresholds are set. For example, yellow warnings indicate potential risks that require attention, orange warnings indicate increased risks and need to prepare countermeasures, and red warnings indicate serious risks and need immediate action. The warning threshold parameters are input into the lightweight model of the monitoring terminal. When the monitoring data triggers a warning, the operation and maintenance personnel are notified in a timely manner through SMS, email, sound and light alarms, and other methods.

[0062] Prepare decision plans corresponding to different warning levels in advance. For example, when a red warning is received, immediately organize professional and technical personnel to conduct on-site inspections and formulate emergency reinforcement plans. For important transmission lines, give priority to ensuring their safety and increase investment in protection. Comprehensively consider the surrounding environment (such as whether it is close to residential areas, major traffic arteries, etc.) and governance costs, and choose the most economical and effective governance measures, such as using retaining walls, drainage system modifications and other methods to reinforce slopes.

[0063] The above description of the embodiments is to facilitate the understanding and use of the present invention by those skilled in the art. It is obvious that those skilled in the art can easily make various modifications to these embodiments and apply the general principles described herein to other embodiments without creative work. Therefore, the present invention is not limited to the above embodiments. Improvements and modifications made by those skilled in the art based on the principles of the present invention without departing from the scope of the present invention should be within the protection scope of the present invention. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for dynamic monitoring of soil seepage field on the slope of a transmission tower, characterized in that: The following steps are involved: Step 1: Multi-source data collection, Using pressure sensing and static pressure measurement, burying pressure sensors and static pressure water level gauges at appropriate locations inside the slope, obtaining real-time data on the change in water head pressure inside the slope, and calculating the soil permeability coefficient through a preset algorithm combined with a permeability test; The displacement and deformation of the slope surface and deep soil are monitored using total stations and chain displacement meters. Combined with settlement observation data, the stability changes of the slope under the influence of seepage are analyzed. Deploy a multi-sensor fusion monitoring system integrating inclinometers, vibration sensors, soil moisture meters, and crack monitors to continuously collect multi-dimensional data on slope inclination, micro-vibration, moisture content, and crack extension, and use a data cross-validation mechanism to reduce the data false alarm rate; With the help of Beidou ground-based augmentation network and related positioning equipment, millimeter-level three-dimensional coordinate monitoring of slope surface displacement is achieved, and the initial coordinates are compared through real-time differential processing. Once the displacement exceeds the preset threshold, an early warning is triggered immediately; Deploy intelligent electrode arrays and use resistivity exploration technology to detect soil resistivity differences, invert the seepage field distribution and potential sliding surface locations; at the same time, use adaptive power supply and wireless networking technology to ensure stable data acquisition in complex terrain; Install capacitive or time domain reflectometry (TDR) soil moisture sensors to monitor the changes in soil moisture content at different depths in real time to assess the impact of rainfall infiltration on the seepage field; Step 2: Data fusion and analysis steps. The collected multi-source data such as resistivity, displacement, meteorology, and soil moisture content are integrated to construct a risk assessment model, and the landslide risk level is quantified by the formula RiskScore = w1·F(ρ)+w2·G(ε)+w3·H(W), where w1, w2, and w3 are the weights of each factor, and F(ρ), G(ε), and H(W) are functions related to resistivity, displacement, and meteorology, respectively; Use machine learning algorithms such as LSTM network or unscented Kalman filter to process time series data and predict the evolution trend of the seepage field; Step 3: Early warning and decision-making steps, Deploy lightweight models on monitoring terminals to achieve fast local data processing. Once an abnormal state is detected, an alarm message is immediately issued to reduce dependence on the cloud. Based on the early warning information and combined with the pre-made decision-making plan, scientific and reasonable decision-making support is provided for the protection and management of transmission tower slopes.

2. The method for dynamic monitoring of soil seepage field of transmission tower slope according to claim 1, characterized in that: In the multi-source data collection step, the deployment location and density of each sensor are optimized according to the geological conditions, topography and historical seepage conditions of the slope to ensure that comprehensive and accurate data are obtained.

3. The method for dynamic monitoring of soil seepage field of transmission tower slope according to claim 2, characterized in that: In the multi-source data acquisition step, for pressure sensing and static pressure measurement technology, the selection of pressure sensors and static pressure water level gauges is determined based on the slope soil type and the expected head pressure range to ensure measurement accuracy and range adaptation.

4. The method for dynamic monitoring of soil seepage field of transmission tower slope according to claim 3 is characterized in that: In the multi-source data acquisition step, the electrode spacing and arrangement of the intelligent electrode array are adjusted according to the geological complexity of the area to be monitored and the target detection depth to improve the accuracy of resistivity exploration.

5. The method for dynamic monitoring of soil seepage field of transmission tower slope according to claim 4, characterized in that: In the data fusion and analysis step, the weights w1, w2, and w3 in the risk assessment model are dynamically adjusted and determined through multiple tests and data analysis based on the importance and relevance of the actual monitoring data.

6. The method for dynamic monitoring of soil seepage field of transmission tower slope according to claim 5, characterized in that: In the data fusion and analysis step, when using the machine learning algorithm to predict the evolution trend of the seepage field, the training data is regularly updated to adapt to the changes in slope soil characteristics and environmental conditions.

7. The method for dynamic monitoring of soil seepage field of transmission tower slope according to claim 6, characterized in that: In the early warning and decision-making steps, the issuance of alarm information is carried out according to preset multi-level early warning thresholds, and different levels of early warnings correspond to different coping measures and response processes.

8. The method for dynamic monitoring of soil seepage field of transmission tower slope according to claim 7, characterized in that: In the above-mentioned early warning and decision-making steps, the formulation of the decision plan comprehensively considers the importance of the transmission line, the surrounding environment, and the management cost factors to ensure the scientificity and feasibility of the decision.

Images