Soil saline-alkali degree detection method and system applied to grounding grid anticorrosion operation

Abstract

The invention relates to the technical field of soil detection, in particular to a soil salinity and alkalinity degree detection method and a soil salinity and alkalinity degree detection system applied to anti-corrosion operation of a grounding grid. Acquiring at least two groups of soil physicochemical data information and at least two groups of environment state data information of the area where the grounding grid is located; performing multi-channel data feature processing on the at least two groups of soil physical and chemical data information to obtain a first soil corrosion influence feature set; performing fluctuation analysis on the at least two groups of environment state data information to obtain a correction factor set; performing feature correction on the first soil corrosion influence feature set based on the correction factor set to obtain a second soil corrosion influence feature set; inputting the second soil corrosion influence feature set into a preset soil corrosion prediction model to obtain a soil corrosion degree index; various factors are comprehensively considered, and the accuracy of corrosion prediction and the effectiveness of anti-corrosion measures are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of soil detection, and particularly to a method and system for detecting the salinity degree of soil applied to the anti-corrosion operation of a grounding grid. Background Art

[0002] In the power system, the grounding grid is a key component to ensure the safe operation of equipment and the safety of personnel; however, in a saline-alkali soil environment, the grounding grid material is prone to corrosion. The corrosion of the grounding grid by saline-alkali soil mainly stems from its special composition and properties. Factors such as high salt content, pH change, and conductivity in the soil will accelerate the corrosion process of metals; it will not only reduce the conductivity of the grounding grid, but may also cause equipment failures and safety accidents. Therefore, for the grounding grid in a saline-alkali soil environment, effective anti-corrosion measures need to be taken.

[0003] In order to effectively reduce the corrosion rate of the grounding grid material by saline-alkali soil, it is necessary to conduct a detailed analysis and detection of the saline-alkali soil; the existing methods for detecting the salinity degree of soil mainly rely on simple conductivity measurement and pH value determination, lacking a comprehensive analysis of soil components and their dynamic changes; at the same time, the influence of environmental state data on the corrosion characteristics of soil is also ignored, resulting in the implementation of anti-corrosion measures being inaccurate and inefficient. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method and system for detecting the salinity degree of soil applied to the anti-corrosion operation of a grounding grid, which comprehensively considers various factors and improves the accuracy of corrosion prediction and the effectiveness of anti-corrosion measures.

[0005] In the first aspect, the present invention provides a method for detecting the salinity degree of soil applied to the anti-corrosion operation of a grounding grid, and the method includes: Obtaining at least two groups of soil physical and chemical data information and at least two groups of environmental state data information in the area where the grounding grid is located according to a preset data acquisition frequency and a preset data acquisition period; Performing multi-channel data feature processing on at least two groups of the soil physical and chemical data information to obtain a first set of soil corrosion influence characteristics; Performing fluctuation analysis on at least two groups of the environmental state data information to obtain a set of correction factors; Performing feature correction on the first set of soil corrosion influence characteristics based on the set of correction factors to obtain a second set of soil corrosion influence characteristics; Inputting the second set of soil corrosion influence characteristics into a preset soil corrosion prediction model to obtain a soil corrosion degree index; Based on the difference between the soil corrosion degree index and a preset soil corrosion degree threshold, performing mapping in a pre-established anti-corrosion measure database to obtain an optimal anti-corrosion measure strategy.

[0006] Further, the soil physical and chemical data information includes soil salt concentration, pH value, and conductivity.

[0007] Further, the soil corrosion influence feature set includes soil salt distribution characteristics, soil pH value change characteristics, and soil conductivity change characteristics.

[0008] Further, the environmental state data information includes at least temperature, humidity, rainfall, and wind speed.

[0009] Further, the method for obtaining the soil salt distribution characteristics includes: Identifying and removing abnormal soil salt concentration data; Calculating the spatial gradient of the soil salt concentration; Decomposing the soil salt concentration data into a trend term, a seasonal term, and a residual term, analyzing the long-term trend and periodic fluctuations, and obtaining the soil salt distribution characteristics.

[0010] Further, the correction factor set includes a soil salt distribution characteristics correction factor, a soil pH value change characteristics correction factor, and a soil conductivity change characteristics correction factor.

[0011] Further, the soil corrosion prediction model adopts any one of linear regression, multiple linear regression, random forest, support vector machine, and neural network.

[0012] On the other hand, the present application also provides a soil salinity detection system applied to the anti-corrosion operation of a grounding grid. The system includes: A data acquisition module, configured to obtain at least two groups of soil physical and chemical data information and at least two groups of environmental state data information in the area where the grounding grid is located according to a preset data acquisition frequency and a preset data acquisition period; A multi-channel data feature processing module, configured to perform multi-channel data feature processing on at least two groups of the soil physical and chemical data information to obtain a first soil corrosion influence feature set; An environmental state fluctuation analysis module, configured to perform fluctuation analysis on at least two groups of the environmental state data information to obtain a correction factor set; A feature correction module, configured to perform feature correction on the first soil corrosion influence feature set based on the correction factor set to obtain a second soil corrosion influence feature set; A soil corrosion prediction module, configured to input the second soil corrosion influence feature set into a preset soil corrosion prediction model to obtain a soil corrosion degree index; An anti-corrosion measure decision-making module, configured to map based on the difference between the soil corrosion degree index and a preset soil corrosion degree threshold in a pre-established anti-corrosion measure database to match an optimal anti-corrosion measure strategy.

[0013] In a third aspect, the present application provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor. The transceiver, the memory, and the processor are connected through the bus. When the computer program is executed by the processor, the steps in any one of the above methods are implemented.

[0014] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in any one of the above methods are implemented.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: By presetting the data collection frequency and time period, soil physical and chemical and environmental state data are comprehensively collected to ensure the timeliness and accuracy of the data; The multi-channel data feature processing technology is adopted to deeply analyze key corrosion influence characteristics such as soil salinity, pH value, and conductivity, improving the accuracy of corrosion prediction; Through the fluctuation analysis of environmental state data information, a correction factor set is introduced to effectively consider the dynamic influence of environmental factors on soil corrosion characteristics, further enhancing the applicability of the prediction model; By combining the comparison of the soil corrosion degree index with a preset threshold, the optimal strategy is intelligently mapped in the anti-corrosion measure database to achieve the precision and efficiency of anti-corrosion measures; In summary, this method comprehensively considers various factors, improves the accuracy of corrosion prediction and the effectiveness of anti-corrosion measures, and provides a strong guarantee for the safe operation of the grounding grid in the saline-alkali soil environment. Description of the Drawings

[0016] Figure 1 is a flowchart of a method for detecting the degree of soil salinity and alkalinity applied to grounding grid anti-corrosion operations; Figure 2 is a structural diagram of a system for detecting the degree of soil salinity and alkalinity applied to grounding grid anti-corrosion operations. Detailed Embodiments

[0017] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, a device, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: completely hardware, completely software (including firmware, resident software, microcode, etc.), and a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage media contains computer program code.

[0018] The above computer-readable storage medium may adopt any combination of one or more computer-readable storage media. The computer-readable storage medium includes: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, a flash memory, an optical fiber, a compact disc read-only memory, an optical storage device, a magnetic storage device, or any combination thereof. In the present application, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.

[0019] In the technical solution of the present application, the acquisition, storage, use, processing, etc. of data all comply with the relevant provisions of national laws.

[0020] The present application describes the provided method, apparatus, and electronic device through flowcharts and / or block diagrams.

[0021] It should be understood that each block of the flowchart and / or block diagram, as well as the combinations of blocks in the flowchart and / or block diagram, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, thereby producing a machine. These computer-readable program instructions are executed by a computer or other programmable data processing devices, resulting in an apparatus that implements the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0022] These computer-readable program instructions can also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product that includes the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0023] The computer-readable program instructions can also be loaded onto a computer, other programmable data processing devices, or other devices, so that a series of operation steps are executed on the computer, other programmable data processing devices, or other devices, resulting in a computer-implemented process. Thus, the instructions executed on the computer or other programmable data processing devices can provide a process that implements the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0024] The present application will be described below with reference to the accompanying drawings in the present application.

[0025] Embodiment 1: As Figure 1 shown, the method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of the grounding grid of the present invention specifically includes the following steps: Step S1: Obtain at least two sets of soil physical and chemical data information and at least two sets of environmental status data information in the area where the grounding grid is located according to the preset data collection frequency and preset data collection period; the environmental status data information corresponds one-to-one with the soil physical and chemical data information; In step S1, it is necessary to clarify the preset data collection frequency and preset data collection period; the preset data collection frequency refers to how often data is collected, which usually depends on the rate of change of soil and environmental conditions and the accuracy requirements for monitoring the corrosion rate of the grounding grid; the preset data collection period refers to the time range for data collection, such as a certain time period during the day or a specific season throughout the year; specifically: Setting of the collection frequency: The setting of the preset data collection frequency needs to consider multiple factors comprehensively; for example, if the saline-alkali soil environment is relatively stable, the collection frequency can be relatively low, such as once a day; however, if there are many environmental change factors in this area, such as being close to some water sources that may bring salt changes due to seasonal water flow, or the climate in this area is changeable (such as extremely large day-night temperature differences that may cause rapid changes in soil moisture and salt status), then the collection frequency may need to be increased to once an hour or even shorter intervals. Setting of the collection period: The setting of the preset data collection period should consider different working periods in the area where the grounding grid is located; for example, in some industrial areas, factors such as heat generated during the operation of equipment during the day may affect the soil state, while the influence of these factors decreases at night; therefore, the collection period should cover different periods, including different time periods such as morning, noon, evening, and night, to ensure that the collected data can comprehensively reflect the soil state of this area.

[0026] Among them, the soil physical and chemical data information includes key parameters such as soil salinity, acidity and alkalinity (pH value), and conductivity, which are used to directly evaluate the corrosion characteristics of the soil; the environmental status data information includes environmental factors such as temperature, humidity, rainfall, and wind speed, which are used to analyze the influence of environmental conditions on the soil corrosion characteristics; Specifically, the method for collecting soil physical and chemical data information is as follows: Step S111: Select multiple representative sampling points in the area where the grounding grid is located; the sampling points should cover different depths (such as 0 - 30 cm, 30 - 60 cm, etc.) to comprehensively reflect the vertical distribution of the soil; Step S112: Use standard soil sampling tools (such as soil drills) to collect soil samples from the selected sampling points; at least two sets of samples should be collected from each sampling point to ensure the reliability and repeatability of the data; Step S113: Use a portable conductivity meter to measure the conductivity of the soil solution and evaluate the total concentration of soluble salts in the soil; Step S114: Measure the pH value of the soil solution using a portable pH meter to understand its potential corrosive effect on metal materials; Step S115: Determine the concentration of main ions in the soil through chemical analysis methods (such as ion chromatography) to evaluate the soil salt distribution.

[0027] Specifically, the method for collecting environmental status data information is as follows: Step S121: Select environmental status parameters related to soil corrosion characteristics, such as temperature, humidity, rainfall, wind speed, etc.; Step S122: Install corresponding sensors near each sampling point for real-time monitoring of the above environmental status parameters; ensure the accuracy and stability of the sensors, and calibrate them regularly to ensure data accuracy; Step S123: The sensors will automatically record the environmental status data and correspond them one by one with the corresponding soil physical and chemical data; for example, each time a soil sample is collected, the environmental status data at that moment is synchronously recorded.

[0028] Store the collected soil physical and chemical data and environmental status data in a unified database to ensure the integrity and traceability of the data. Cloud storage or local server storage methods can be adopted, depending on the system design and security requirements.

[0029] At the same time, assign a unique identifier to each group of data and ensure the one-to-one correspondence between the soil physical and chemical data and the environmental status data, so that relevant data can be accurately matched in the subsequent processing and analysis process; for example, at 10 am, the soil salt content, pH value, conductivity, etc. data collected at a specific location A in the earthing grid installation area should correspond to the environmental status data such as temperature, humidity, rainfall, etc. collected at the same location A at the same moment.

[0030] In this step, by presetting the data collection frequency and time period, data sampling can be scientifically and reasonably planned, which not only ensures the timeliness of the data but also avoids unnecessary sampling waste; secondly, in the selection of sampling points, different depths and regions are covered to comprehensively reflect the vertical and horizontal distribution of the soil and improve the representativeness of the data; at the same time, standard sampling tools and chemical analysis methods are used to ensure the accuracy and reliability of the soil physical and chemical data information; in addition, real-time monitoring of the environmental status data and one-to-one correspondence with the soil physical and chemical data not only consider the physical and chemical properties of the soil itself but also comprehensively consider the influence of environmental conditions on the soil corrosion characteristics, making the analysis more comprehensive and in-depth; finally, the unified storage of data and the assignment of unique identifiers ensure the integrity and traceability of the data, providing convenience for subsequent data processing and analysis.

[0031] Step S2: Perform multi-channel data feature processing on at least two sets of the soil physical and chemical data information to obtain a first soil corrosion influence feature set; the soil corrosion influence feature set includes soil salt distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics; In step S2, perform multi-channel data feature processing on at least two sets of soil physical and chemical data information obtained from step S1, with the aim of extracting key features that can reflect soil corrosion influence, including soil salt distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics.

[0032] Channel a: Soil salt distribution characteristics are used to quantify the spatial distribution and dynamic changes of soil salts, reflecting the direct influence of salts on metal corrosion. The specific acquisition methods include: Identify and eliminate abnormal salt concentration data through box plots or the 3σ criterion; use Kriging interpolation or inverse distance weighting method to convert the salt concentration data of discrete sampling points into a continuous spatial distribution map; Calculate the spatial gradient of salt concentration (such as the change rate per meter of concentration) to reflect the salt diffusion direction; analyze the spatial autocorrelation of salts through semi-variogram and extract parameters such as range, sill value, and nugget value; Decompose the salt concentration data into trend term, seasonal term, and residual term (such as STL decomposition) to analyze long-term trends and periodic fluctuations; based on time series data, calculate the change rate of salt concentration per unit time (such as Δsalt / Δt).

[0033] Channel b: Soil pH change characteristics are used to quantify the dynamic fluctuations of pH value and its non-linear influence on corrosion rate. The specific acquisition methods include: Correct the temperature drift error of the pH sensor according to the temperature compensation formula (such as the Nernst equation); use the Savitzky-Golay filter or moving average method to eliminate high-frequency noise; Calculate the long-term change trend of pH value (such as the change amount of pH value per year) through linear regression or Mann-Kendall trend test; use the Pettitt test or Bayesian change point analysis to identify the mutation time point of pH value; Calculate the standard deviation and range of pH value to reflect the short-term fluctuation intensity; detect the periodic changes of pH value (such as daily changes, seasonal changes) through fast Fourier transform or wavelet transform.

[0034] Channel c: Soil conductivity change characteristics are used to quantify the dynamic relationship between conductivity and soluble salts, reflecting a comprehensive index of soil corrosiveness. The specific acquisition methods include: According to the conductivity temperature coefficient formula (such as EC25 = ECt / [1 + α(T - 25)]), the conductivity data are uniformly corrected to the standard value at 25°C; a quantitative relationship model between conductivity and salt concentration is established through linear regression or machine learning (such as random forest); The Hodrick-Prescott filter is used to separate the long-term trend and short-term fluctuations of conductivity; the significance of conductivity changes is verified by the Sen slope estimation method; The coefficient of variation (CV) of conductivity is calculated through a sliding window to reflect the dynamic frequency of salt dissolution; the Pearson correlation coefficient between conductivity and salt concentration is calculated to verify their correlation.

[0035] The soil salt distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics extracted from each channel are integrated to form the first soil corrosion influence feature set, and the format example is as follows: { "Salt distribution characteristics": { "Spatial gradient": 0.5 (mg / cm³ / m), "Range": 10 (m), "Salt accumulation rate": 0.2 (mg / cm³ / day) }, "pH value change characteristics": { "Trend slope": -0.03 (pH / year), "Standard deviation": 0.5, "Main period": 24 (hours) }, "Conductivity change characteristics": { "Sen slope": 0.1 (mS / cm / year), "Coefficient of variation": 15%, "Salt correlation": 0.85 } } Step S2 precisely quantifies the key influencing factors of soil corrosion through multi-channel data feature processing; it covers three major features, namely soil salt distribution, pH change, and conductivity change, to form a complete set of soil corrosion influencing features; various data processing and analysis methods are used, such as Kriging interpolation method, Savitzky-Golay filter, linear regression, etc., to ensure the accuracy and reliability of feature extraction; it not only considers the static distribution of soil properties but also pays attention to its dynamic changes, such as time series analysis and periodic fluctuation detection, to be closer to the actual corrosion process; by integrating the features of each channel, a unified feature set is formed for subsequent data analysis and model construction; the extracted features have clear physical meanings and engineering application values and can be directly used to guide the monitoring and prevention of soil corrosion.

[0036] Step S3: Conduct fluctuation analysis on at least two groups of the environmental state data information to obtain a set of correction factors; the set of correction factors includes a correction factor for soil salt distribution characteristics, a correction factor for soil pH change characteristics, and a correction factor for soil conductivity change characteristics. The set of correction factors is used to subsequently correct the set of soil corrosion influencing features to improve the accuracy and reliability of corrosion prediction; before conducting the fluctuation analysis, it is necessary to ensure that the obtained environmental state data information is accurate and complete and corresponds one-to-one with the soil physical and chemical data information collected in Step S1, covering the environmental state related parameters of the area where the grounding grid is located at different times; conduct preliminary screening and cleaning on the collected environmental state data to remove obvious abnormal or incorrect data points to ensure data quality; for example, for temperature data, if there are extremely abnormal values beyond a reasonable range (such as local historical extremes), they can be judged as abnormal data and excluded.

[0037] Specifically, the analysis and calculation of each feature correction factor are as follows: Correction factor for soil salt distribution characteristics: Conduct time series analysis on the factors related to soil salt distribution in the environmental state data (such as precipitation, evaporation, etc., which may affect salt migration); calculate its autocorrelation function and partial autocorrelation function to determine the periodic fluctuation characteristics of the data; for example, if it is found that there is an obvious seasonal cycle in precipitation data and the soil salt distribution may be affected during the rainy season, then according to the fluctuation of precipitation intensity and duration during the rainy season, determine a corresponding correction factor to reflect the degree of influence of precipitation change on soil salt distribution. The greater the precipitation fluctuation, the larger the value of the correction factor; consider the influence of differences in environmental states in different regions on soil salt distribution; analyze the environmental state changes caused by factors such as terrain and landform, such as the humidity difference between coastal areas and inland areas may affect salt diffusion; determine a spatial correction factor for soil salt distribution characteristics according to the degree of difference in environmental states in different regions; for example, in coastal areas with higher humidity and relatively faster salt diffusion, the value of the correction factor is different from that in inland areas.

[0038] Correction factor for soil pH change characteristics: Conduct spectral analysis on factors related to soil pH in environmental state data (such as carbon dioxide concentration in the atmosphere, soil microbial activities, etc.); Convert time-domain data into frequency-domain data and analyze the energy distribution of different frequency components; For example, the daily and annual variations of carbon dioxide concentration in the atmosphere may have a periodic impact on soil pH. Determine its main fluctuation frequencies through spectral analysis; Based on the fluctuation amplitudes corresponding to these frequency components, determine the correction factor for soil pH change characteristics; The larger the fluctuation amplitude, the larger the value of the correction factor to reflect its greater impact on soil pH change; Consider the impact of chemical reactions occurring in the soil on pH; Analyze the impact of environmental state changes on soil pH change according to the relationship between chemical reaction rate and environmental factors such as temperature and humidity; For example, in a high-temperature and high-humidity environment, certain chemical reactions in the soil may accelerate, resulting in faster pH change; Determine the corresponding correction factor according to the change of chemical reaction rate under different environmental conditions.

[0039] Correction factor for soil conductivity change characteristics: Use wavelet analysis method to analyze factors related to soil conductivity in environmental state data (such as soil moisture content, ion concentration, etc.); Wavelet analysis can reveal the characteristics of data at different scales and positions. By decomposing data into wavelet coefficients at different scales, analyze the detailed characteristics of soil conductivity change; For example, during the drought period, the soil moisture content is low, the ion concentration is relatively high, and the conductivity change is large; Determine a corresponding correction factor according to the conductivity fluctuation characteristics during the drought period obtained by wavelet analysis; Consider the comprehensive impact of multiple environmental factors on soil conductivity; Select environmental state variables closely related to soil conductivity, such as temperature, humidity, soil texture, etc., and establish a multiple regression model; By analyzing the coefficients and significance levels of each variable in the model, determine the influence degree of each environmental factor on soil conductivity change, and accordingly determine the correction factor for soil conductivity change characteristics; For example, an increase in temperature may cause an increase in ion movement in the soil and an increase in conductivity. Determine the correction factor according to the influence degree of temperature change on conductivity.

[0040] In this step, through the analysis of environmental state data fluctuations, the key factors affecting soil corrosion and their dynamic changes can be accurately captured, providing a scientific basis for the determination of the correction factor set; Calculate the correction factors for different characteristics (salt distribution, pH change, conductivity change) respectively, fully considering the diversity and complexity of soil corrosion, and improving the accuracy and reliability of corrosion prediction; Moreover, by combining advanced methods such as time series analysis, spectral analysis, and wavelet analysis, not only the periodic fluctuations and detailed characteristics of environmental factors are revealed, but also the impacts of factors such as regional differences and chemical reactions on soil corrosion are considered, making the correction factors more comprehensive and detailed.

[0041] Step S4: Perform feature correction on the first soil corrosion influence feature set based on the correction factor set to obtain a second soil corrosion influence feature set; Before performing feature correction, it is necessary to ensure that the data of the correction factor set and the soil corrosion influence feature set are complete and accurately corresponding; the correction factor set includes a correction factor for soil salt distribution characteristics, a correction factor for soil pH change characteristics, and a correction factor for soil conductivity change characteristics, while the soil corrosion influence feature set includes soil salt distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics; Correction for soil salt distribution characteristics: Apply the correction factor for soil salt distribution characteristics to the soil salt distribution characteristics in the soil corrosion influence feature set; for example, if the correction factor is 1.2, it means that according to the fluctuation analysis of environmental state data, it is considered that the soil salt distribution in this area is greatly affected by environmental factors, and the actual impact on soil corrosion is 20% higher than the initially detected situation; through multiplication operations and other methods, multiply the correction factor by the original soil salt distribution characteristic value to obtain the corrected soil salt distribution characteristic value; for example, if the original soil salt distribution characteristic value is 10 mg / cm³, it becomes 12 mg / cm³ after correction to more accurately reflect the actual impact on soil corrosion; Correction for soil pH change characteristics: Incorporate the correction factor for soil pH change characteristics into the soil pH change characteristics in the soil corrosion influence feature set; for example, the correction factor is 0.8, which means that the change in the environmental state has reduced the impact of soil pH change on soil corrosion in this area by 20% compared to before; use corresponding mathematical operations, such as multiplication, to multiply the correction factor by the original soil pH change characteristic value; assume that the original soil pH change characteristic value is a change of 0.5 units per year in pH value, and it becomes a change of 0.4 units per year after correction; Correction for soil conductivity change characteristics: Apply the correction factor for soil conductivity change characteristics to the soil conductivity change characteristics in the soil corrosion influence feature set; for example, the correction factor is 1.5, indicating that environmental factors have increased the impact of soil conductivity change on soil corrosion in this area by 50% compared to the initial detection result; through multiplication and other operations, multiply the correction factor by the original soil conductivity change characteristic value; for example, if the original soil conductivity change characteristic value is an increase in conductivity of 1 mS / cm per year, it becomes an increase of 1.5 mS / cm per year after correction.

[0042] After separately correcting the soil salt distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics, recombine the corrected characteristic values to form a second soil corrosion influence feature set, which more accurately reflects the actual influence characteristics of soil corrosion considering the impact of environmental state data fluctuations.

[0043] Step S4 significantly improves the accuracy and reliability of soil corrosion impact characteristics by correcting the first soil corrosion impact characteristic set and using the correction factor set obtained in Step S3. Specifically, by applying the correction factors for soil salt distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics, it can more accurately reflect the impact of environmental conditions on soil corrosion characteristics. It not only considers the impact of single environmental factors but also reveals the interaction between multiple factors, providing a data basis for further corrosion prediction and anti-corrosion measure formulation. The generated second soil corrosion impact characteristic set provides a scientific basis for subsequent steps.

[0044] Step S5: Input the second soil corrosion impact characteristic set into a preset soil corrosion prediction model to obtain the soil corrosion degree index. Among them, the soil corrosion prediction model is a mathematical model constructed based on historical data and existing research, used to evaluate the corrosion degree of soil on metal materials. The input variables of the soil corrosion prediction model include the corrected soil salt distribution characteristics, soil pH change characteristics, soil conductivity change characteristics, etc. The output variable, namely the soil corrosion degree index, is used to measure the corrosion risk of the soil to the grounding grid material. The soil corrosion prediction model adopts any one of linear regression, multiple linear regression, random forest, support vector machine, and neural network. Taking the neural network model as an example, the specific application is as follows: The input layer of the soil corrosion prediction model includes 3 neurons, corresponding to the input characteristics such as soil salt distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics. The hidden layer has h neurons, and the output layer has 1 neuron, which represents the soil corrosion degree. Among them, the input calculation formula of the hidden layer is: ; where represents the characteristic value corresponding to the i-th neuron, that is, the characteristic value of soil salt distribution characteristics, soil pH change characteristics, or soil conductivity change characteristics; represents the input of the j-th neuron in the hidden layer; is the connection weight from the input layer to the hidden layer, indicating the connection strength from the i-th neuron in the input layer to the j-th neuron in the hidden layer. By adjusting these weights, the neural network can learn the influence degree of different input characteristics on the hidden layer neurons. For example, in soil corrosion prediction, it reflects the action weights of soil salt distribution characteristics, soil pH change characteristics, etc. on the hidden layer neurons; is the bias of the j-th neuron in the hidden layer; the bias term is used to adjust the activation threshold of the neuron, so that the neuron can have a certain output even when there is no input or the input is zero; similar to the intercept term in linear regression, it provides a basic offset for the output of the neuron; p represents the number of neurons in the input layer; in the scenario of soil corrosion prediction, it corresponds to the total number of input features, that is, the total number of input features such as soil salinity distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics.

[0045] The output calculation formula of the hidden layer is: Among them, is the output of the j-th neuron in the hidden layer, obtained by applying the activation function to The role of the activation function is to introduce non-linear factors, enabling the neural network to learn complex non-linear relationships; common activation functions include the Sigmoid function, ReLU function, etc.

[0046] The input calculation formula of the output layer is: Among them, h represents the number of neurons in the hidden layer; the hidden layer is located between the input layer and the output layer, and is used for non-linear transformation and feature extraction of the input data; the value of h can be adjusted according to the complexity of the specific problem and the characteristics of the data. A larger h can learn more complex patterns, but it may also lead to overfitting; is the input of the output layer neuron; it is obtained by multiplying the output of the hidden layer by the corresponding connection weight and summing, and then adding the bias term, is the connection weight from the hidden layer to the output layer, which determines the contribution degree of the j-th neuron in the hidden layer to the output layer neuron; in the soil corrosion prediction model, it reflects the influence weight of the features extracted by the hidden layer on the final soil corrosion degree prediction result; is the bias of the output layer neuron; similar to the bias of the hidden layer, it is used to adjust the activation threshold of the output layer neuron, providing a basic offset for the final prediction result.

[0047] The output of the output layer is: Among them, y represents the output of the output layer neuron, that is, the prediction result of the neural network for the soil corrosion degree.

[0048] In this step, by taking multiple key features such as the corrected soil salinity distribution characteristics, soil pH change characteristics, and soil conductivity change characteristics as inputs, various factors affecting soil corrosion can be comprehensively and integrally considered; the limitations of single-factor analysis can be avoided, and the actual corrosion condition of the soil can be more accurately reflected; there are complex interaction effects among the features. For example, the changes in soil salinity distribution and pH may affect each other and then jointly act on the soil conductivity and corrosion degree. These potential interaction relationships can be captured, thus more realistically simulating the soil corrosion process; taking the neural network model as an example, through the settings of hidden layers and activation functions, it can automatically learn the complex non-linear relationship between the input features and the output. The soil corrosion process is often non-linear and is affected by multiple factors comprehensively. The neural network can better capture this complex pattern and improve the prediction accuracy; the output variable, i.e., the soil corrosion degree index, provides a clear quantitative indicator for measuring the corrosion risk of the soil to the earthing grid material; this enables engineers and researchers to intuitively understand the corrosion degree of the soil and provides a scientific basis for formulating reasonable anti-corrosion measures.

[0049] Step S6: Based on the difference between the soil corrosion degree index and the preset soil corrosion degree threshold, map it in the pre-established anti-corrosion measure database to obtain the optimal anti-corrosion measure strategy.

[0050] In step S6, based on the soil corrosion degree index obtained in step S5, combined with the preset soil corrosion degree threshold, by mapping to the pre-established anti-corrosion measure database, the optimal anti-corrosion measure strategy is selected; ensuring that for soil environments with different corrosion degrees, the most appropriate and effective anti-corrosion measures can be taken to ensure the safety and reliability of the earthing grid; the specific implementation is as follows: Step S61: Determine the soil corrosion degree threshold: Before performing step S6, it is necessary to preset the soil corrosion degree threshold; the determination of the soil corrosion degree threshold is based on a comprehensive consideration of multiple factors such as the corrosion resistance research of the earthing grid material in the saline-alkali soil environment, actual engineering experience, and relevant industry standards, etc.; for example, according to a large amount of experimental data and actual operation conditions, it is determined that when the soil corrosion degree index is less than a certain value, the corrosion risk of the soil to the grounding grid is considered to be at a relatively low level; when the index exceeds this value, the corrosion risk gradually increases, and corresponding anti-corrosion measures need to be taken; Step S62: Construct an anti-corrosion measure database. Pre-build a database containing various anti-corrosion measures and their applicable scopes. Each record in this database includes a specific range of soil corrosion degree and the corresponding optimal anti-corrosion measure strategy. For example, for the area with a corrosion degree index between 0 - 0.3, the possible anti-corrosion measure is to perform surface coating maintenance regularly. For the area with a corrosion degree index between 0.3 - 0.6, sacrificial anode protection method may be required, etc. Step S63: Compare the soil corrosion degree index obtained in Step S5 with the preset soil corrosion degree threshold, and calculate the difference between the two. The difference reflects the deviation degree between the actual corrosion degree of the current soil and the set safe or acceptable corrosion degree. For example, if the soil corrosion degree index is 0.4 and the threshold is 0.3, then the difference is 0.1, indicating that the corrosion degree of the current soil is slightly higher than the set safe range. Step S64: According to the calculated difference, search in the anti-corrosion measure database for the soil corrosion degree range that matches it. Since the ranges in the database are preset in advance, by comparing the difference with the boundaries of each range, the specific interval to which the current soil corrosion degree belongs can be determined. For example, the soil corrosion degree index corresponding to the difference falls within the interval of 0.3 - 0.6. Step S65: Once the interval to which the soil corrosion degree belongs is determined, retrieve the optimal anti-corrosion measure strategy corresponding to this interval in the anti-corrosion measure database. The optimal anti-corrosion measure strategy is determined by comprehensively considering various factors, including anti-corrosion effect, cost, construction difficulty, impact on the environment, etc. For example, for the corrosion degree interval of 0.3 - 0.6 mentioned above, the optimal anti-corrosion measure strategy can be to adopt a method combining coating protection and regular monitoring, which can not only effectively prevent corrosion but also control costs and construction difficulty. Step S66: Output the retrieved optimal anti-corrosion measure strategy to provide clear guidance for actual anti-corrosion operations. At the same time, considering the complexity and variability of the actual situation, the strategy can also be appropriately adjusted and optimized according to specific engineering requirements and environmental conditions. For example, in some special environments, local improvement of the selected anti-corrosion measure or combination with other auxiliary measures may be required to achieve better anti-corrosion effects.

[0051] More specifically, the anti-corrosion measures in the anti-corrosion measure database include, but are not limited to: 1. Measures at the material level are as follows: Stainless steel materials: Some stainless steels (such as 316L stainless steel) have good corrosion resistance. They contain alloying elements such as chromium, nickel, and molybdenum, which can form a stable passivation film on the surface to prevent the further progress of the corrosion reaction. For example, in some power grounding grids with high corrosion resistance requirements, using 316L stainless steel to make grounding conductors can effectively resist the corrosion of saline-alkali soil; Copper and copper alloy materials: Copper has excellent electrical conductivity and corrosion resistance. Copper alloys (such as copper-nickel alloys) further improve the corrosion resistance while maintaining good electrical conductivity. In saline-alkali soil, a dense oxide film can form on the surface of copper and copper alloy grounding grids, playing a protective role; Epoxy coating: Epoxy coating has good adhesion, chemical corrosion resistance, and insulation properties. Coating the epoxy coating on the surface of the grounding grid can isolate the direct contact between the soil and the metal, preventing the corrosion medium from eroding the metal. For example, evenly coating a layer of epoxy coating on the surface of the grounding grid conductor can effectively reduce the corrosion of the grounding grid by saline-alkali soil; Zinc coating: Zinc can form a dense zinc oxide film in the air, playing a protective role for the base metal. When galvanizing the grounding grid surface, when the galvanized layer is damaged, zinc will preferentially corrode as a sacrificial anode, thus protecting the main metal of the grounding grid. This sacrificial anode protection method is widely used in the anti-corrosion of some grounding grids.

[0052] 2. The measures at the design and construction levels are as follows: Increase the area of the grounding grid: By increasing the area of the grounding grid, the grounding resistance can be reduced, and the concentrated flow of current in the grounding grid can be reduced, thereby reducing the possibility of local corrosion. For example, when designing the grounding grid, a grid-like structure is adopted, and the side length and quantity of the grid are appropriately increased to increase the contact area between the grounding grid and the soil; Reasonably arrange the grounding electrodes: The arrangement method of the grounding electrodes will also affect the corrosion situation of the grounding grid. For example, burying the grounding electrodes deep underground to keep them away from the high-salt and high-pH areas on the surface of saline-alkali soil can reduce the corrosion risk. At the same time, the combination of vertical grounding electrodes and horizontal grounding electrodes can improve the stability and corrosion resistance of the grounding grid.

[0053] 3. The measures at the electrochemistry protection level are as follows: Sacrificial anode cathodic protection method: Using a metal (such as magnesium, zinc, aluminum, etc.) that is more active than the metal to be protected (grounding grid) as the sacrificial anode. In the electrolyte solution (saline-alkali soil), the sacrificial anode will preferentially undergo an oxidation reaction and dissolve, thereby providing electrons for the grounding grid, making the potential on the surface of the grounding grid shift negatively and entering the immunity zone to achieve the purpose of protecting the grounding grid; reasonably select and arrange the sacrificial anodes according to the scale and shape of the grounding grid; generally speaking, for a grounding grid with a large area, multiple sacrificial anodes can be arranged dispersedly to ensure that each part can be effectively protected; for example, magnesium alloy sacrificial anodes are buried evenly around or at key parts of the grounding grid, and the sacrificial anodes are connected to the grounding grid through wires; at the same time, the number and specifications of the required sacrificial anodes need to be calculated according to factors such as soil resistivity and the material of the grounding grid to ensure the protection effect; Impressed current cathodic protection method: By applying an external DC power supply, connecting the negative electrode to the grounding grid, making the grounding grid become the cathode, thereby forcing the metal ions on the surface of the grounding grid to move towards the anode and inhibiting the corrosion of the grounding grid; it is necessary to set up an auxiliary anode (such as graphite anode, high-silicon cast iron anode, etc.), connect the positive pole of the DC power supply to the auxiliary anode, and the negative pole to the grounding grid; by adjusting the output voltage and current of the power supply, control the potential of the grounding grid to keep it within a suitable protection potential range; in practical applications, it is necessary to reasonably design the arrangement method of the auxiliary anode and the power supply parameters according to factors such as soil resistivity, the size and shape of the grounding grid to achieve the best cathodic protection effect.

[0054] In this embodiment, a complete closed-loop system is formed from data acquisition, feature processing, correction to prediction and strategy formulation; avoiding the problem that each link in the traditional method is relatively isolated and lacks overall coordination; for example, the introduction of environmental state data does not exist independently, but is interrelated and interacts with soil physical and chemical data, jointly providing support for accurately evaluating the degree of soil corrosion and making the entire analysis process more systematic and comprehensive; by fusing and processing soil physical and chemical data and environmental state data, giving full play to the advantages of both; soil physical and chemical data reflects the corrosion characteristics of the soil itself, while environmental state data reflects the influence of the external environment on soil corrosion; after the two are combined, deeper information can be mined to achieve a more accurate grasp of the soil corrosion situation, which is an effect that cannot be achieved by a single data analysis method; The introduction of the correction factor set is an optimization of the traditional soil corrosion analysis method. It can correct the characteristics of soil corrosion impact in real time according to the fluctuations of environmental state data, fully considering the influence of the dynamic changes of environmental factors on soil corrosion, making the final soil corrosion degree index more accurate and reliable, capable of truly reflecting the actual corrosion status of soil in different environments, and effectively avoiding evaluation deviations caused by ignoring environmental factors. This method can adapt to the changes in different saline-alkali soil environments and working conditions. Due to considering the dynamic changes of environmental state data and making real-time adjustments through the correction factor set, it can accurately evaluate the soil corrosion degree and give corresponding anti-corrosion measure strategies regardless of different geographical locations, climate conditions, or soil composition changes, with strong environmental adaptability and generality.

[0055] Embodiment 2: As Figure 2 shown, the soil salinity detection system of the present invention applied to the anti-corrosion operation of the grounding grid specifically includes the following modules; A data acquisition module, configured to obtain at least two groups of soil physical and chemical data information and at least two groups of environmental state data information of the area where the grounding grid is located according to a preset data acquisition frequency and a preset data acquisition period; A multi-channel data feature processing module, configured to perform multi-channel data feature processing on at least two groups of the soil physical and chemical data information to obtain a first soil corrosion impact feature set; An environmental state fluctuation analysis module, configured to perform fluctuation analysis on at least two groups of the environmental state data information to obtain a correction factor set; A feature correction module, configured to perform feature correction on the first soil corrosion impact feature set based on the correction factor set to obtain a second soil corrosion impact feature set; A soil corrosion prediction module, configured to input the second soil corrosion impact feature set into a preset soil corrosion prediction model to obtain a soil corrosion degree index; An anti-corrosion measure decision-making module, configured to map in a pre-established anti-corrosion measure database based on the difference between the soil corrosion degree index and a preset soil corrosion degree threshold, and match the optimal anti-corrosion measure strategy.

[0056] In this embodiment, the data acquisition module acquires soil physical and chemical data information and environmental status data information. The multi-channel data feature processing module extracts the first soil corrosion influence feature set. The environmental status fluctuation analysis module generates a correction factor set. The feature correction module corrects the first soil corrosion influence feature set to generate the second soil corrosion influence feature set. The soil corrosion prediction module calculates the soil corrosion degree index. The anti-corrosion measure decision module matches the optimal anti-corrosion measure strategy according to the soil corrosion degree index and the preset threshold. Through multi-dimensional data acquisition and feature processing, this system comprehensively analyzes the soil corrosion characteristics. Through environmental status fluctuation analysis and feature correction, the accuracy of soil corrosion degree prediction is improved. Based on the soil corrosion prediction model and the anti-corrosion measure database, intelligent decision-making of anti-corrosion measures is realized. Through modular design and automated processes, the implementation efficiency of anti-corrosion measures is improved.

[0057] All the various change modes and specific embodiments of the method for detecting the soil salinity degree applied to the anti-corrosion operation of the grounding grid in the foregoing Embodiment 1 are equally applicable to the system for detecting the soil salinity degree applied to the anti-corrosion operation of the grounding grid in this embodiment. Through the foregoing detailed description of the method for detecting the soil salinity degree applied to the anti-corrosion operation of the grounding grid, those skilled in the art can clearly know the implementation method of the system for detecting the soil salinity degree applied to the anti-corrosion operation of the grounding grid in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0058] In addition, this application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected through the bus. When the computer program is executed by the processor, it realizes each process of the method embodiment for controlling the output data and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0059] The foregoing is only the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid, characterized in that, The method includes: Obtaining at least two sets of soil physical and chemical data information and at least two sets of environmental status data information in the area where the grounding grid is located according to a preset data collection frequency and a preset data collection period; Performing multi-channel data feature processing on at least two sets of the soil physical and chemical data information to obtain a first soil corrosion influence feature set; Performing fluctuation analysis on at least two sets of the environmental status data information to obtain a correction factor set; Performing feature correction on the first soil corrosion influence feature set based on the correction factor set to obtain a second soil corrosion influence feature set; Inputting the second soil corrosion influence feature set into a preset soil corrosion prediction model to obtain a soil corrosion degree index; Based on the difference between the soil corrosion degree index and a preset soil corrosion degree threshold, performing mapping in a pre-established anti-corrosion measure database to obtain an optimal anti-corrosion measure strategy.

2. The method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid according to claim 1, characterized in that, The soil physical and chemical data information includes soil salt concentration, pH value, and conductivity.

3. The method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid according to claim 2, characterized in that, The soil corrosion influence feature set includes soil salt distribution characteristics, soil pH value change characteristics, and soil conductivity change characteristics.

4. The method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid according to claim 3, characterized in that, The environmental status data information includes at least temperature, humidity, rainfall, and wind speed.

5. The method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid according to claim 3, characterized in that, The method for obtaining the soil salt distribution characteristics includes: Identifying and removing abnormal soil salt concentration data; Calculating the spatial gradient of the soil salt concentration; Decomposing the soil salt concentration data into a trend term, a seasonal term, and a residual term, and analyzing the long-term trend and periodic fluctuations to obtain the soil salt distribution characteristics.

6. The method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid according to claim 3, characterized in that, The correction factor set includes a soil salt distribution characteristic correction factor, a soil pH value change characteristic correction factor, and a soil conductivity change characteristic correction factor.

7. The method for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid according to claim 6, characterized in that, The soil corrosion prediction model adopts any one of linear regression, multiple linear regression, random forest, support vector machine, and neural network.

8. A system for detecting the degree of soil salinity and alkalinity applied to the anti-corrosion operation of a grounding grid, characterized in that, The system includes: A data collection module, configured to obtain at least two sets of soil physical and chemical data information and at least two sets of environmental status data information in the area where the grounding grid is located according to a preset data collection frequency and a preset data collection period; A multi-channel data feature processing module, configured to perform multi-channel data feature processing on at least two sets of the soil physical and chemical data information to obtain a first soil corrosion influence feature set; An environmental status fluctuation analysis module, configured to perform fluctuation analysis on at least two sets of the environmental status data information to obtain a correction factor set; A feature correction module, configured to perform feature correction on the first soil corrosion influence feature set based on the correction factor set to obtain a second soil corrosion influence feature set; A soil corrosion prediction module, configured to input the second soil corrosion influence feature set into a preset soil corrosion prediction model to obtain a soil corrosion degree index; An anti-corrosion measure decision-making module, configured to perform mapping in a pre-established anti-corrosion measure database based on the difference between the soil corrosion degree index and a preset soil corrosion degree threshold, and match an optimal anti-corrosion measure strategy.

9. An electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor, the transceiver, the memory, and the processor are connected through the bus, characterized in that, When the computer program is executed by the processor, it implements the steps in the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the method according to any one of claims 1-7.

Images