Power transmission line tower footing red soil analysis method based on big data

Abstract

The invention relates to the technical field of soil data analysis, in particular to a power transmission line tower footing red soil analysis method based on big data, and the method comprises the steps: collecting red soil data of a power transmission line tower footing area, and sequentially carrying out the cleaning, denoising, filtering and feature extraction operation on the red soil data to output red soil features, training an initial model according to the red soil features to output a deep learning model; analyzing red soil data by using the deep learning model to output an analysis result, and determining fertility application of the red soil in the tower footing area of the power transmission line according to the analysis result; based on the loss rate of the red soil data, determining whether the analysis accuracy of the red soil data meets the requirement or not; if the analysis accuracy does not meet the requirement, adjusting the acquisition frequency of the red soil data; and if the analysis reliability does not meet the requirement, adjusting the learning rate of the deep learning model. According to the method, the analysis accuracy of red soil data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of soil data analysis, and particularly to an analysis method for red soil of transmission line tower bases based on big data. Background Art

[0002] With the continuous advancement of the construction of power infrastructure, as a key carrier for power transmission, the stability and security of transmission lines are crucial for ensuring power supply. As the basic structure supporting the lines, transmission line tower bases are in a complex geological environment for a long time, and the tower bases in red soil areas face special challenges. Red soil is rich in metal compounds and has characteristics such as strong acidity, high clay content, and complex fertility conditions, which are extremely likely to corrode the tower base materials and affect the stability of the tower bases.

[0003] Traditional analysis methods for red soil of transmission line tower bases mostly rely on manual sampling and empirical judgment, which are not only inefficient but also difficult to guarantee accuracy, and cannot meet the high standards for tower base safety in modern power systems. With the rapid development of big data, sensor technology, and deep learning algorithms, although some studies have tried to apply them to the field of soil analysis, there are still many problems in the analysis of red soil of transmission line tower bases.

[0004] Chinese Patent Publication No.: CN117408430A discloses a soil improvement evaluation system for agricultural planting based on big data, including a primary soil collection module, a primary soil detection and analysis module, an improvement method determination module, a regional division and improvement module, a secondary soil collection module, a comparison and analysis module, an evaluation result generation module, a sampling effectiveness evaluation module, a big data platform, and a data import module; the primary soil collection module is used to collect samples before the land is improved; the primary soil detection and analysis module is used to detect and analyze the primary collected soil samples to determine soil indicators; the improvement method determination module is used to screen out all the schemes adopted for successful soil improvement corresponding to the determined soil indicators from the big data platform, and each scheme is marked as Ai, i = 1···n, n is a positive integer; the regional division and improvement module is used to divide the land to be improved into n regions, and each region implements one improvement scheme; the secondary soil collection module is used to determine the number of sampling points in each region, and then collect and mix the samples of the land in each region after improvement according to the number of sampling points; the secondary soil collection module is used to detect and analyze the secondary collected soil samples to determine soil indicators. It can be seen that the soil improvement evaluation system for agricultural planting based on big data has the problem that due to only determining the number of sampling points and not strictly evaluating the standardization of the sampling process and the effectiveness of the samples, it is impossible to ensure that the collected samples can truly reflect the soil improvement situation, resulting in inaccurate evaluation results. Summary of the Invention

[0005] To this end, the present invention provides an analysis method for red soil at the tower base of a transmission line based on big data, so as to overcome the problem in the prior art that due to only determining the number of sampling points and not strictly evaluating the standardization of the sampling process and the effectiveness of the samples, it is impossible to ensure that the collected samples can truly reflect the soil improvement situation, resulting in inaccurate evaluation results.

[0006] To achieve the above object, the present invention provides an analysis method for red soil at the tower base of a transmission line based on big data, including:

[0007] Collect red soil data in the tower base area of the transmission line, and sequentially perform cleaning, denoising, filtering, and feature extraction operations on the red soil data to output red soil features, and train an initial model according to the red soil features to output a deep learning model;

[0008] Use the deep learning model to analyze the red soil data to output an analysis result, and determine the fertilizer application of the red soil in the tower base area of the transmission line according to the analysis result;

[0009] Obtain the loss rate of the red soil data;

[0010] Based on the loss rate of the red soil data, determine whether the analysis accuracy of the red soil data meets the requirements;

[0011] If the analysis accuracy does not meet the requirements, adjust the sampling frequency of the red soil data, or determine whether the analysis reliability of the deep learning model meets the requirements based on the accuracy rate of the red soil data analysis;

[0012] If the analysis reliability does not meet the requirements, adjust the learning rate of the deep learning model, or adjust the cut-off frequency of the filter based on the response delay duration of the soil pH sensor;

[0013] Wherein, the red soil data includes the pH value of the red soil, the nitrogen content of the red soil, the phosphorus content of the red soil, and the water content of the red soil, and the pH value of the red soil is detected by the soil pH sensor.

[0014] Further, determining the analysis accuracy of the red soil data includes:

[0015] Compare the loss rate of the red soil data with a preset first loss rate;

[0016] If the loss rate of the red soil data is greater than the preset first loss rate, determine that the analysis accuracy of the red soil data does not meet the requirements.

[0017] Further, determining the analysis reliability of the deep learning model includes:

[0018] Compare the loss rate of the red soil data with the preset first loss rate and the preset second loss rate respectively;

[0019] If the loss rate of the red soil data is greater than the preset first loss rate and less than or equal to the preset second loss rate, preliminarily determine that the analysis reliability of the deep learning model does not meet the requirements, and determine whether the analysis reliability of the deep learning model meets the requirements according to the accuracy rate of the red soil data analysis.

[0020] Further, adjust the acquisition frequency of the red soil data, including:

[0021] Compare the loss rate of the red soil data with the preset second loss rate;

[0022] If the loss rate of the red soil data is greater than the preset second loss rate, increase the acquisition frequency of the red soil data.

[0023] Further, the increase amplitude of the acquisition frequency of the red soil data is determined by the difference between the loss rate of the red soil data and the preset second loss rate.

[0024] Further, adjust the learning rate of the deep learning model, including:

[0025] Compare the accuracy rate of the red soil data analysis with the preset first accuracy rate and the preset second accuracy rate respectively;

[0026] If the accuracy rate of the red soil data analysis is less than the preset second accuracy rate, determine that the analysis reliability of the deep learning model does not meet the requirements;

[0027] If the accuracy rate of the red soil data analysis is greater than the preset first accuracy rate and less than the preset second accuracy rate, decrease the learning rate of the deep learning model;

[0028] If the accuracy rate of the red soil data analysis is less than or equal to the preset first accuracy rate, preliminarily determine that the environmental stability of the red soil data acquisition does not meet the requirements, and determine whether the environmental stability of the red soil data acquisition meets the requirements according to the response delay duration of the soil pH sensor.

[0029] Further, the decrease amplitude of the learning rate of the deep learning model is determined by the difference between the accuracy rate of the red soil data analysis and the preset first accuracy rate.

[0030] Further, the accuracy rate of the red soil data analysis is the ratio of the number of accurate red soil data analyses to the total number of red soil data analyses.

[0031] Further, adjust the cut-off frequency of the filter, including:

[0032] Compare the response delay duration of the soil pH sensor with the preset delay duration;

[0033] If the response delay duration of the soil pH sensor is greater than the preset delay duration, it is determined that the environmental stability of red soil data collection does not meet the requirements, and the cut-off frequency of the filter is reduced.

[0034] Furthermore, the reduction amplitude of the cut-off frequency of the filter is determined by the difference between the response delay duration of the soil pH sensor and the preset delay duration.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows. The method of the present invention adjusts the acquisition frequency of red soil data according to the loss rate of red soil data. Since the sensor for collecting red soil data is subject to signal interference, resulting in partial data loss, which leads to inaccurate results when analyzing red soil data. By increasing the acquisition frequency of red soil data, more data points can be obtained within the same time, which helps to fill the data gaps caused by interference, make the data sequence more complete, make the analysis results better reflect the real situation of red soil, reduce the analysis deviation caused by data loss, adjust the learning rate of the deep learning model according to the accuracy rate of red soil data analysis. Since there are too many parameters for training the model, the model conducts detailed training on some of the noise and unrepresentative features, resulting in overfitting of the model, which leads to poor generalization ability for new data in application. By reducing the learning rate of the deep learning model, the model can adjust the parameters more carefully, reduce the overfitting to noise and unrepresentative features, and thus improve the generalization ability of the model on new data. Adjust the cut-off frequency of the filter according to the response delay duration of the soil pH sensor. Since there are many metal compounds in red soil, it may cause corrosion and aging of the sensor after long-term use, resulting in inaccurate measurement data of the sensor. By reducing the cut-off frequency of the filter, the filter can better suppress high-frequency noise and retain relatively low-frequency effective measurement signals, thereby improving the accuracy of measurement data and the analysis accuracy of red soil data.

[0036] Furthermore, the method of the present invention adjusts the acquisition frequency of red soil data by setting a preset first loss rate and a preset second loss rate. Since the sensor for collecting red soil data is subject to signal interference, resulting in partial data loss, which leads to inaccurate results when analyzing red soil data. By increasing the acquisition frequency of red soil data, more data points can be obtained within the same time, which helps to fill the data gaps caused by interference, make the data sequence more complete, make the analysis results better reflect the real situation of red soil, reduce the analysis deviation caused by data loss, and further improve the analysis accuracy of red soil data.

[0037] Furthermore, the method of the present invention adjusts the learning rate of the deep learning model by setting a preset first accuracy rate and a preset second accuracy rate. Since there are too many parameters for training the model, the model conducts detailed training on some of the noise and unrepresentative features therein, resulting in overfitting of the model, and thus poor generalization ability for new data in applications. By reducing the learning rate of the deep learning model, the model can more carefully adjust the parameters, reduce overfitting to noise and unrepresentative features, thereby improving the generalization ability of the model on new data and further enhancing the analysis accuracy of red soil data.

[0038] Furthermore, the method of the present invention adjusts the cut-off frequency of the filter by setting a preset delay duration. Since there are many metal compounds in red soil, it may cause corrosion and aging of the sensor after long-term use, resulting in inaccurate measurement data of the sensor. By reducing the cut-off frequency of the filter, the filter can better suppress high-frequency noise and retain relatively low-frequency effective measurement signals, thereby improving the accuracy of the measurement data and further enhancing the analysis accuracy of red soil data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is the overall flowchart of the analysis method of the red soil at the transmission line tower base based on big data according to the embodiment of the present invention;

[0040] Figure 2 is the logic flowchart of the process of adjusting the acquisition frequency of red soil data in the analysis method of the red soil at the transmission line tower base based on big data according to the embodiment of the present invention;

[0041] Figure 3 is the logic flowchart of the process of adjusting the learning rate of the deep learning model in the analysis method of the red soil at the transmission line tower base based on big data according to the embodiment of the present invention;

[0042] Figure 4 is the logic flowchart of the process of adjusting the cut-off frequency of the filter in the analysis method of the red soil at the transmission line tower base based on big data according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] In order to make the objectives and advantages of the present invention clearer and more understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0044] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0045] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0046] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and defined, the terms "installation", "connection", "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0047] Please refer to Figure 1 、 Figure 2 、 Figure 3 and Figure 4 as shown, which are respectively the overall flowchart of the analysis method of the red soil of the transmission line tower base based on big data in the embodiment of the present invention, the logical flowchart of the process of adjusting the acquisition frequency of the red soil data, the logical flowchart of the process of adjusting the learning rate of the deep learning model, and the logical flowchart of the process of adjusting the cut-off frequency of the filter. An analysis method of the red soil of the transmission line tower base based on big data of the present invention includes:

[0048] Step S1, collect the red soil data in the area of the transmission line tower base, and successively perform cleaning, denoising, filtering, and feature extraction operations on the red soil data to output red soil features, and train the initial model according to the red soil features to output a deep learning model;

[0049] Step S2, use the deep learning model to analyze the red soil data to output an analysis result, and determine the fertility application of the red soil in the area of the transmission line tower base according to the analysis result;

[0050] Step S3, obtain the loss rate of the red soil data;

[0051] Step S4, determine whether the analysis accuracy of the red soil data meets the requirements based on the loss rate of the red soil data;

[0052] Step S5, if the analysis accuracy does not meet the requirements, adjust the acquisition frequency of the red soil data, or determine whether the analysis reliability of the deep learning model meets the requirements based on the accuracy rate of the red soil data analysis;

[0053] Step S6, if the analysis reliability does not meet the requirements, adjust the learning rate of the deep learning model, or adjust the cut-off frequency of the filter based on the response delay duration of the soil pH sensor;

[0054] Among them, the red soil data includes the pH value of the red soil, the nitrogen content of the red soil, the phosphorus content of the red soil, and the water content of the red soil, and the pH value of the red soil is detected by the soil pH sensor.

[0055] Specifically, the red soil characteristics include the bulk density of the red soil, the water content of the red soil, and the pH value of the red soil.

[0056] Specifically, the deep learning model includes a convolutional neural network, a recurrent neural network, and a multi-layer perceptron.

[0057] Specifically, the analysis results include the fertility of the red soil, the settlement risk of the red soil, and the suitability of the red soil for vegetation growth.

[0058] Specifically, the filter includes a low-pass filter, a high-pass filter, and a band-stop filter, and its preferred embodiment is a low-pass filter.

[0059] In implementation, the method of the present invention adjusts the acquisition frequency of the red soil data according to the loss rate of the red soil data. Since the sensor for collecting the red soil data is affected by signal interference, some data is lost, resulting in inaccurate results when analyzing the red soil data. By increasing the acquisition frequency of the red soil data, more data points can be obtained in the same time, which helps to fill the data gaps caused by interference, make the data sequence more complete, make the analysis results better reflect the real situation of the red soil, reduce the analysis deviation caused by data loss, and adjust the learning rate of the deep learning model according to the accuracy rate of the red soil data analysis. Since there are too many parameters for training the model, the model has carefully trained some of the noise and unrepresentative features, resulting in overfitting of the model, and thus poor generalization ability for new data in application. By reducing the learning rate of the deep learning model, the model can more carefully adjust the parameters, reduce the overfitting of noise and unrepresentative features, and thus improve the generalization ability of the model on new data. Adjust the cut-off frequency of the filter according to the response delay duration of the soil pH sensor. Since there are many metal compounds in the red soil, the sensor may be corroded and aged after long-term use, resulting in inaccurate measurement data of the sensor. By reducing the cut-off frequency of the filter, the filter can better suppress high-frequency noise and retain relatively low-frequency effective measurement signals, thereby improving the accuracy of the measurement data and the analysis accuracy of the red soil data.

[0060] Specifically, determining the analysis accuracy of the red soil data includes:

[0061] Compare the loss rate of the red soil data with a preset first loss rate;

[0062] If the loss rate of the red soil data is greater than the preset first loss rate, it is determined that the analysis accuracy of the red soil data does not meet the requirements.

[0063] Specifically, determining the analysis reliability of the deep learning model includes:

[0064] Compare the loss rate of the red soil data with the preset first loss rate and the preset second loss rate respectively;

[0065] If the loss rate of the red soil data is greater than the preset first loss rate and less than or equal to the preset second loss rate, it is preliminarily determined that the analysis reliability of the deep learning model does not meet the requirements, and it is determined whether the analysis reliability of the deep learning model meets the requirements according to the accuracy rate of the red soil data analysis.

[0066] It can be understood that the three intervals divided by the preset first loss rate and the preset second loss rate respectively correspond to three situations:

[0067] The first interval is that the loss rate of the red soil data is less than or equal to the preset first loss rate, and the corresponding situation is: it is determined that the analysis accuracy of the red soil data meets the requirements;

[0068] The second interval is that the loss rate of the red soil data is greater than the preset first loss rate and less than or equal to the preset second loss rate, and the corresponding situation is: because there are too many parameters for training the model, the model has carefully trained some of the noise and unrepresentative features, resulting in overfitting of the model, and thus resulting in poor generalization ability for new data in the application;

[0069] The third interval is that the loss rate of the red soil data is greater than the preset second loss rate, and the corresponding situation is: because the sensor for collecting the red soil data is affected by signal interference, some data is lost, resulting in inaccurate results when analyzing the red soil data.

[0070] In implementation, the generally selected range of the preset first loss rate is [0.2%, 0.4%], and the generally selected range of the preset second loss rate is [0.5%, 0.7%].

[0071] Preferably, the preferred embodiment of the preset first loss rate is 0.3%, and the preferred embodiment of the preset second loss rate is 0.6%.

[0072] Specifically, the loss rate of the red soil data is the ratio of the amount of lost red soil data to the total amount of red soil data.

[0073] In implementation, the method of the present invention determines the analysis accuracy of red soil data by setting a preset first loss rate and a preset second loss rate, reducing the impact of the decline in the analysis stability of red soil data caused by inaccurate determination of the analysis accuracy of red soil data, and further improving the analysis accuracy of red soil data.

[0074] Specifically, adjusting the acquisition frequency of the red soil data includes:

[0075] Comparing the loss rate of the red soil data with the preset second loss rate;

[0076] If the loss rate of the red soil data is greater than the preset second loss rate, increase the acquisition frequency of the red soil data.

[0077] Specifically, the increase amplitude of the acquisition frequency of the red soil data is determined by the difference between the loss rate of the red soil data and the preset second loss rate.

[0078] Specifically, when the difference between the loss rate of the red soil data and the preset second loss rate is within 0.2%, the acquisition frequency of the red soil data is increased to 1.2 times the original; when the difference between the loss rate of the red soil data and the preset second loss rate exceeds 0.2%, on the basis of increasing to 1.2 times the original, for every 0.1% exceeded, the acquisition frequency of the red soil data is increased 1 time / minute. For example, if the difference between the loss rate of the red soil data and the preset second loss rate is 0.4% and the current acquisition frequency of the red soil data is 5 times / minute, the increased acquisition frequency of the red soil data is 5×1.2 + 1×2 = 8 times / minute.

[0079] In implementation, the method of the present invention adjusts the acquisition frequency of the red soil data by setting a preset first loss rate and a preset second loss rate. Since the sensor for acquiring the red soil data is affected by signal interference, resulting in partial data loss, and thus the analysis result of the red soil data is inaccurate. By increasing the acquisition frequency of the red soil data, more data points can be obtained in the same time, which helps to fill the data gaps caused by interference, make the data sequence more complete, make the analysis result better reflect the real situation of the red soil, reduce the analysis deviation caused by data loss, and further improve the analysis accuracy of the red soil data.

[0080] Specifically, adjusting the learning rate of the deep learning model includes:

[0081] Comparing the accuracy rate of the red soil data analysis with a preset first accuracy rate and a preset second accuracy rate respectively;

[0082] If the accuracy rate of the red soil data analysis is less than the preset second accuracy rate, it is determined that the analysis reliability of the deep learning model does not meet the requirements;

[0083] If the accuracy rate of the red soil data analysis is greater than the preset first accuracy rate and less than the preset second accuracy rate, then reduce the learning rate of the deep learning model;

[0084] If the accuracy rate of the red soil data analysis is less than or equal to the preset first accuracy rate, initially determine that the environmental stability of the red soil data collection does not meet the requirements, and determine whether the environmental stability of the red soil data collection meets the requirements according to the response delay duration of the soil pH sensor.

[0085] It can be understood that the three intervals divided by the preset first accuracy rate and the preset second accuracy rate respectively correspond to three situations:

[0086] The first interval is that the accuracy rate of the red soil data analysis is less than or equal to the preset first accuracy rate, and the corresponding situation is: due to the large amount of metal compounds in the red soil, it may cause the sensor to corrode and age after long-term use, resulting in inaccurate measurement data of the sensor;

[0087] The second interval is that the accuracy rate of the red soil data analysis is greater than the preset first accuracy rate and less than the preset second accuracy rate, and the corresponding situation is: due to too many parameters for training the model, the model has carefully trained some of the noise and unrepresentative features, resulting in overfitting of the model, and thus poor generalization ability for new data in the application;

[0088] The third interval is that the accuracy rate of the red soil data analysis is greater than or equal to the preset second accuracy rate, and the corresponding situation is: it is determined that the analysis reliability of the deep learning model meets the requirements.

[0089] In implementation, the generally selected range of the preset first accuracy rate is [93%, 95%], and the generally selected range of the preset second accuracy rate is [96%, 98%].

[0090] Preferably, the preferred embodiment of the preset first accuracy rate is 94%, and the preferred embodiment of the preset second accuracy rate is 97%.

[0091] In implementation, the method of the present invention determines the analysis reliability of the deep learning model by setting the preset first accuracy rate and the preset second accuracy rate, reduces the influence of the decrease in the analysis accuracy of the red soil data caused by inaccurate determination of the analysis reliability of the deep learning model, and further improves the analysis accuracy of the red soil data.

[0092] Specifically, the reduction amplitude of the learning rate of the deep learning model is determined by the difference between the accuracy rate of the red soil data analysis and the preset first accuracy rate.

[0093] Specifically, when the difference between the accuracy rate of red soil data analysis and the preset first accuracy rate is within 3%, the learning rate of the deep learning model is reduced to 0.9 times of the original; when the difference between the accuracy rate of red soil data analysis and the preset first accuracy rate exceeds 3%, on the basis of reducing to 0.9 times of the original, for every 1% exceeding, the learning rate of the deep learning model is reduced by 0.002. For example, if the difference between the accuracy rate of red soil data analysis and the preset first accuracy rate is 5% and the current learning rate of the deep learning model is 0.01, the reduced learning rate of the deep learning model is 0.01×0.9 - 0.002×2 = 0.005.

[0094] In implementation, the method of the present invention adjusts the learning rate of the deep learning model by setting a preset first accuracy rate and a preset second accuracy rate. Since there are too many parameters for training the model, the model conducts detailed training on some of the noise and unrepresentative features therein, resulting in overfitting of the model, and thus resulting in poor generalization ability for new data in application. By reducing the learning rate of the deep learning model, the model can more carefully adjust the parameters, reduce overfitting to noise and unrepresentative features, thereby improving the generalization ability of the model on new data and further improving the analysis accuracy of red soil data.

[0095] Specifically, the accuracy rate of the red soil data analysis is the ratio of the number of accurate red soil data analyses to the total number of red soil data analyses.

[0096] Specifically, adjusting the cut-off frequency of the filter includes:

[0097] Comparing the response delay duration of the soil pH sensor with the preset delay duration;

[0098] If the response delay duration of the soil pH sensor is greater than the preset delay duration, it is determined that the environmental stability of red soil data collection does not meet the requirements, and the cut-off frequency of the filter is reduced.

[0099] It can be understood that the two intervals divided by the preset delay duration respectively correspond to two situations:

[0100] The first interval is that the response delay duration of the soil pH sensor is less than or equal to the preset delay duration, and the corresponding situation is: it is determined that the environmental stability of red soil data collection meets the requirements;

[0101] The second interval is that the response delay duration of the soil pH sensor is greater than the preset delay duration, and the corresponding situation is: due to the large amount of metal compounds in red soil, the sensor may be corroded and aged after long-term use, resulting in inaccurate measurement data of the sensor.

[0102] In implementation, the generally selected range of the preset delay duration is [2 min, 3 min].

[0103] Preferably, the preferred embodiment of the preset delay duration is 2.5 min.

[0104] In implementation, by setting the preset delay duration, the method of the present invention determines the environmental stability of the red soil data collection, reduces the impact of the decline in the analysis accuracy of the red soil data caused by inaccurate determination of the environmental stability of the red soil data collection, and further improves the analysis accuracy of the red soil data.

[0105] Specifically, the reduction amplitude of the cut-off frequency of the filter is determined by the difference between the response delay duration of the soil pH sensor and the preset delay duration.

[0106] Specifically, when the difference between the response delay duration of the soil pH sensor and the preset delay duration is within 2 min, the cut-off frequency of the filter is reduced to 0.92 times the original; when the difference between the response delay duration of the soil pH sensor and the preset delay duration exceeds 2 min, on the basis of being reduced to 0.92 times the original, for every 1 min exceeded, the cut-off frequency of the filter is reduced by 3 Hz. For example, when the difference between the response delay duration of the soil pH sensor and the preset delay duration is 4 min and the current cut-off frequency of the filter is 50 Hz, the reduced cut-off frequency of the filter is 50×0.92 - 3×2 = 40 Hz.

[0107] In implementation, by setting the preset delay duration, the method of the present invention adjusts the cut-off frequency of the filter. Since there are many metal compounds in the red soil, it may cause corrosion and aging of the sensor after long-term use, resulting in inaccurate measurement data of the sensor. By reducing the cut-off frequency of the filter, the filter can better suppress high-frequency noise and retain relatively low-frequency effective measurement signals, thereby improving the accuracy of the measurement data and further improving the analysis accuracy of the red soil data.

[0108] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. An analysis method for red soil of transmission line tower bases based on big data, characterized in that, Including: Collecting red soil data in the tower base area of the transmission line, and successively performing cleaning, denoising, filtering, and feature extraction operations on the red soil data to output red soil features, and training an initial model according to the red soil features to output a deep learning model; Analyzing the red soil data using the deep learning model to output an analysis result, and determining the fertility application of the red soil in the tower base area of the transmission line according to the analysis result; Obtaining the loss rate of the red soil data; Determining whether the analysis accuracy of the red soil data meets the requirements based on the loss rate of the red soil data; If the analysis accuracy does not meet the requirements, adjust the collection frequency of the red soil data, or determine whether the analysis reliability of the deep learning model meets the requirements based on the accuracy rate of the red soil data analysis; If the analysis reliability does not meet the requirements, adjust the learning rate of the deep learning model, or adjust the cut-off frequency of the filter based on the response delay duration of the soil pH sensor; Wherein, the red soil data includes the pH value of the red soil, the nitrogen content of the red soil, the phosphorus content of the red soil, and the water content of the red soil, and the pH value of the red soil is detected by the soil pH sensor.

2. The analysis method of red soil at the tower base of a transmission line based on big data according to claim 1, characterized in that Determining the analysis accuracy of the red soil data includes: Comparing the loss rate of the red soil data with a preset first loss rate; If the loss rate of the red soil data is greater than the preset first loss rate, it is determined that the analysis accuracy of the red soil data does not meet the requirements.

3. The analysis method of red soil for transmission line tower bases based on big data according to claim 2, wherein Determining the analysis reliability of the deep learning model includes: Comparing the loss rate of the red soil data with the preset first loss rate and the preset second loss rate respectively; If the loss rate of the red soil data is greater than the preset first loss rate and less than or equal to the preset second loss rate, it is preliminarily determined that the analysis reliability of the deep learning model does not meet the requirements, and it is determined whether the analysis reliability of the deep learning model meets the requirements according to the accuracy rate of the red soil data analysis.

4. The analysis method of red soil at the tower base of a transmission line based on big data according to claim 3, characterized in that Adjusting the collection frequency of the red soil data includes: Comparing the loss rate of the red soil data with the preset second loss rate; If the loss rate of the red soil data is greater than the preset second loss rate, increase the collection frequency of the red soil data.

5. The analysis method of red soil at the tower base of a transmission line based on big data according to claim 4, characterized in that The increase amplitude of the collection frequency of the red soil data is determined by the difference between the loss rate of the red soil data and the preset second loss rate.

6. The analysis method of red soil at the tower base of a transmission line based on big data according to claim 5, characterized in that, Adjusting the learning rate of the deep learning model includes: Comparing the accuracy rate of the red soil data analysis with a preset first accuracy rate and a preset second accuracy rate respectively; If the accuracy rate of the red soil data analysis is less than the preset second accuracy rate, it is determined that the analysis reliability of the deep learning model does not meet the requirements; If the accuracy rate of the red soil data analysis is greater than the preset first accuracy rate and less than the preset second accuracy rate, reduce the learning rate of the deep learning model; If the accuracy rate of the red soil data analysis is less than or equal to the preset first accuracy rate, it is preliminarily determined that the environmental stability of the red soil data collection does not meet the requirements, and it is determined whether the environmental stability of the red soil data collection meets the requirements according to the response delay duration of the soil pH sensor.

7. The analysis method of red soil at the tower base of a transmission line based on big data according to claim 6, characterized in that, The reduction amplitude of the learning rate of the deep learning model is determined by the difference between the accuracy rate of the red soil data analysis and the preset first accuracy rate.

8. The analysis method of red soil for transmission line tower bases based on big data according to claim 7, characterized in that, The accuracy rate of the red soil data analysis is the ratio of the number of accurate red soil data analyses to the total number of red soil data analyses.

9. The analysis method of red soil at the tower base of a transmission line based on big data according to claim 8, characterized in that, Adjusting the cut-off frequency of the filter includes: Comparing the response delay duration of the soil pH sensor with the preset delay duration; If the response delay duration of the soil pH sensor is greater than the preset delay duration, it is determined that the environmental stability of the red soil data collection does not meet the requirements, and the cut-off frequency of the filter is reduced.

10. The analysis method of red soil at the tower base of a transmission line based on big data according to claim 9, characterized in that The reduction amplitude of the cut-off frequency of the filter is determined by the difference between the response delay duration of the soil pH sensor and the preset delay duration.

Images