Power transmission line tower inclination early warning method based on Internet of Things

Abstract

The invention discloses a power transmission line tower inclination early warning method based on the Internet of Things, and belongs to the technical field of tower inclination early warning. The problem that existing tower inclination early warning is not timely is solved, inclination data of a power transmission line tower and surrounding soil humidity are collected through the inclination monitoring equipment and the soil moisture content automatic observation instrument, and the inclination data and the surrounding soil humidity are labeled through the radio frequency card; the upper computer server side obtains an inclination threshold value and a humidity threshold value through a neural network model; the current inclination data and humidity data are compared with corresponding threshold values, the tower with the inclination and humidity exceeding the threshold values is extracted, the position of the tower is obtained by combining Beidou positioning information, the radio frequency card information of the tower is read by a reader to obtain a serial number, and inclination tri-color lamp early warning and to-be-overhauled blue lamp early warning are carried out on an upper computer client; and the possibility that the tower is inclined is pre-judged in advance in combination with the soil humidity, so that early warning delay caused by single inclination threshold comparison is prevented, and the timeliness and accuracy of tower inclination early warning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pole tower tilt warning, and in particular to a transmission line pole tower tilt warning method based on the Internet of Things. Background Art

[0002] At present, electricity consumption has increased significantly, which has put forward higher and higher requirements for the safety and reliability of power supply of the power grid. The transmission and distribution of electricity cannot be separated from the transmission lines. However, my country has a wide geographical distribution and complex and diverse geological conditions. When the transmission lines pass through unfavorable geological areas such as coal mining areas, soft soil areas, hillsides, desert areas, riverbed areas, etc., under the influence of the natural environment and external conditions, the towers are easily affected by natural factors such as wind, frost, rain and snow, as well as human factors such as underground goafs of various shapes caused by mineral mining in recent years. In mild cases, it can cause cracking, tilting, and deformation of the towers. In severe cases, it can cause the towers to topple and collapse, posing a great threat to the safe operation of the transmission network and causing losses to people’s lives and property.

[0003] Therefore, it does not meet the existing needs. For this reason, we propose a transmission line tower tilt warning method based on the Internet of Things. Summary of the invention

[0004] The object of the present invention is to provide a transmission line tower tilt warning method based on the Internet of Things. The tilt data of the transmission line tower and the surrounding soil moisture are collected by tilt monitoring equipment and an automatic soil moisture observation instrument, and a radio frequency card is used to label them; the upper computer server obtains a tilt threshold and a humidity threshold through a neural network model; then the current tilt data and humidity data are compared with the corresponding thresholds, and the towers whose tilt and humidity exceed the thresholds are extracted, and the location is obtained in combination with Beidou positioning information, and the radio frequency card information of the tower is read by a reader to obtain the number, so as to perform a tilt three-color light warning and a blue light warning for maintenance on the upper computer client; the possibility of the tower tilting is predicted in advance in combination with soil moisture, so as to prevent the warning delay caused by a single tilt threshold comparison, thereby improving the timeliness and accuracy of the tower tilt warning, and solving the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a transmission line tower tilt early warning method based on the Internet of Things, comprising the following steps: S1. Install tilt monitoring equipment and Beidou positioning equipment to collect tilt data and Beidou location information of each transmission line tower, and send tilt data information and Beidou location information to the upper computer server based on GPRS; S2. Monitor the soil moisture and weather around each transmission line tower by installing an automatic soil moisture observation instrument and a weather monitor, and send the surrounding soil moisture information and weather information to the upper computer server based on GPRS; S3. Label each transmission line tower and its associated tilt monitoring equipment and soil moisture automatic observation instrument through wireless radio frequency technology; S4, the upper computer server trains the historical tilt data of the tower through a preset neural network model and outputs a tilt threshold, and compares the current tilt data of the tower with the tilt threshold to determine the tilt state of the tower; S5. The host computer server trains the historical soil moisture information through a preset neural network model and outputs a humidity threshold, compares the current soil moisture information around the tower with the humidity threshold to determine the current soil moisture state around the tower, and marks the transmission line tower whose surrounding soil moisture exceeds the humidity threshold as a tower to be repaired in combination with the Beidou position information; S6. The tilt state of the pole tower determined by the upper computer server and the marked pole tower to be repaired are transmitted to the upper computer client via GPRS for display and early warning, thereby realizing remote monitoring and multi-machine display.

[0006] Furthermore, the tilt monitoring equipment, Beidou positioning equipment, soil moisture automatic observation instrument and meteorological monitoring instrument installed in S1 and S2 are all powered by a combination of solar energy and batteries.

[0007] Furthermore, after labeling each transmission line tower and its corresponding tilt monitoring device and soil moisture automatic observation instrument in S3, it is also necessary to match the number of each transmission line tower with the number of the corresponding tilt monitoring device and soil moisture automatic observation instrument.

[0008] Furthermore, before the host computer server presets the neural network model in S4 and S5, the following steps are also included: Receive the Beidou positioning information of the target transmission line tower and the number of each transmission line tower and the number of the tilt monitoring equipment and soil moisture automatic observation instrument to which it belongs, and transmit it to the host computer server for display via GPRS; The tilt data of each transmission line tower, surrounding soil moisture information and meteorological information are received, and multiple data are saved in time series to form a database.

[0009] Furthermore, the neural network model is preset in S4 to train the historical inclination data of the tower, specifically: Data that meets the normal range of inclination in the historical inclination data of the tower are selected as samples, and the samples are divided into a training set and a test set. A neural network model is created and the training set is imported for training, thereby outputting the training results; the test set is then imported into the trained neural network model for testing, thereby outputting the test results, namely: the inclination threshold.

[0010] Furthermore, the determination of the tilt state of the tower in S4 is specifically as follows: Based on the tilt threshold as a comparison benchmark, the currently collected tilt data of the transmission line tower is compared with the tilt threshold. If the current tilt data is greater than the tilt threshold, it indicates that the transmission line tower is in a dangerous tilt state, and the signal is immediately transmitted to the host computer client based on GPRS for a red light warning; if the current tilt data is critical to the tilt threshold, it indicates that the transmission line tower is in a waiting tilt state, and the signal is transmitted to the host computer client based on GPRS for a yellow light warning; if the current tilt data is within the tilt threshold range, it indicates that the transmission line tower is in a normal state, and the signal is transmitted to the host computer client based on GPRS for a green light notification.

[0011] Furthermore, the neural network model is preset in S5 to train the historical soil moisture information, specifically: Based on the historical meteorological information around the tower, soil moisture information of the day when the weather was sunny and the air humidity was low and the day when the weather was rainy and the air humidity was high were selected as samples, and the samples were fused and divided into a training set and a test set. A neural network model was created and the training set was imported for training, thereby outputting the training results; the test set was then imported into the trained neural network model for testing, thereby outputting the test results, namely: humidity threshold.

[0012] Furthermore, the current soil moisture state around the tower is determined in S5, specifically: Based on the weather information of the day and the humidity threshold, if the weather information of the day shows that it is sunny or rainy, the air humidity is low or high, and the surrounding soil humidity of the transmission line tower is within the humidity threshold, it indicates that the current transmission line tower is in normal state; if the weather information of the day shows that it is sunny or rainy, the air humidity is low or high, and the surrounding soil humidity of one or more transmission line towers exceeds the humidity threshold, it indicates that the transmission line tower is in an abnormal state, and the transmission line tower is marked as a tower to be repaired, and the signal is transmitted to the upper computer client based on GPRS for a blue light warning.

[0013] Furthermore, the numbering is performed by wireless radio frequency technology in S3, specifically: By installing a radio frequency card on each transmission line tower and its associated tilt monitoring equipment and soil moisture automatic observation instrument, the radio frequency card is pre-entered with the serial numbers of the tilt monitoring equipment and soil moisture automatic observation instrument.

[0014] Furthermore, after the radio frequency card is installed in S3, a reader of the same model needs to be configured to identify and read the content stored in the radio frequency card.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention collects the tilt data of the transmission line tower, the surrounding soil moisture and the Beidou position information by installing the tilt monitoring equipment, the soil moisture automatic observation instrument and the Beidou positioning equipment, and the radio frequency card marks the transmission line tower, the tilt monitoring equipment and the soil moisture automatic observation instrument; the upper computer service end respectively obtains the tilt threshold and the humidity threshold through the neural network model; then the current tilt data and the humidity data are respectively compared with the corresponding thresholds, the tower whose tilt data and soil moisture both exceed the threshold are extracted, and the position of the tower is obtained in combination with the Beidou positioning information, and the radio frequency card information of the tower is read by the reader, thereby obtaining the actual number of the tower, so as to perform the tilt three-color light warning and the blue light warning for maintenance on the upper computer client; by combining the soil moisture to predict in advance the possibility that the tower will tilt, the tilt state of the tower can be quickly warned, thereby preventing the warning delay caused by the single tilt threshold comparison, and improving the timeliness and accuracy of the tower tilt warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a flow chart of the power transmission line tower tilt warning method based on the Internet of Things. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In order to solve the technical problem that the existing towers are easily affected by natural factors such as wind, frost, rain and snow, as well as human factors such as underground goafs of various shapes caused by mineral mining in recent years, which may cause cracking, tilting, and deformation of the towers at the least, and may cause the towers to fall and collapse at the worst, posing a great threat to the safe operation of the power transmission network and causing losses to people's lives and property, please refer to Figure 1 , this embodiment provides the following technical solutions: The transmission line tower tilt early warning method based on the Internet of Things includes the following steps: S1. Install tilt monitoring equipment and Beidou positioning equipment to collect tilt data and Beidou position information of each transmission line tower, and send the tilt data information and Beidou position information to the upper computer server based on GPRS. In this embodiment, for example, a transmission line in a certain area is selected, and a tilt monitoring equipment is installed on each transmission line tower. The tilt monitoring equipment can be selected as: ZCT330Ex-SWP-N-YKC1 Internet of Things tilt sensor. The tilt sensor is used to monitor the tilt state of each transmission line tower in real time, and the monitored tilt data is transmitted to the upper computer server based on the GPRS network for processing; the Beidou positioning equipment is then used to obtain the position information of the target area, so as to determine the position of the tower with signs of tilt at a later time.

[0019] S2, monitor the soil moisture and weather around each transmission line tower by installing an automatic soil moisture observation instrument and a meteorological monitor, and send the surrounding soil moisture information and meteorological information to the upper computer server based on GPRS; wherein the tilt monitoring equipment, Beidou positioning equipment, automatic soil moisture observation instrument and meteorological monitor installed in S1 and S2 are all powered by solar energy and batteries; following the above embodiment, the daily meteorological information in the target area is obtained through the meteorological monitor, so as to understand the daily weather conditions and air humidity conditions in the target area in advance, In the rainy season or in weather with high air humidity, the soil moisture conditions in the target area can be checked in particular; the soil moisture automatic observation instrument monitors the soil moisture around the transmission line towers in real time. The model that can be used for specific implementation is: OK-TR4 soil moisture monitoring station. After monitoring and analyzing the soil moisture, it is known that if the soil moisture is too high, the soil is relatively loose, so the possibility of the tower tilting is greater; by combining soil moisture analysis, it is easy to predict in advance the towers that may tilt in the target area, thereby improving the timeliness and accuracy of the tower tilt warning.

[0020] S3. Label each transmission line tower and its tilt monitoring equipment and soil moisture automatic observation instrument by wireless radio frequency technology; specifically, install a radio frequency card on each transmission line tower and its tilt monitoring equipment and soil moisture automatic observation instrument, in which the numbers of the tilt monitoring equipment and soil moisture automatic observation instrument are pre-entered; after installing the radio frequency card, a reader of the same model is required to identify and read the contents stored in the radio frequency card; after labeling, the number of each transmission line tower needs to be compared with the number of its tower. The numbers of the tilt monitoring device and the automatic soil moisture observation instrument are matched; continuing with the above embodiment, such as: by installing the radio frequency card on each transmission line tower and its corresponding tilt monitoring device and automatic soil moisture observation instrument, and pre-entering the number in the radio frequency card; such as: the tower is numbered G1, and the tilt monitoring device and automatic soil moisture observation instrument belonging to the tower are numbered Q1 and T1 respectively, and so on, and marking is performed one by one; when marking, it should be noted that the number in the current tower number must correspond to the numbers of the two corresponding devices, so as to match their relationship.

[0021] S4, the upper computer server trains the historical tilt data of the tower through a preset neural network model and outputs a tilt threshold, and compares the current tilt data of the tower with the tilt threshold to determine the tilt state of the tower; S5. The host computer server trains the historical soil moisture information through a preset neural network model and outputs a humidity threshold, compares the current surrounding soil moisture information of the tower with the humidity threshold to determine the soil moisture status around the current tower, and marks the transmission line tower whose surrounding soil moisture exceeds the humidity threshold as a tower to be repaired in combination with the Beidou position information; wherein, before the host computer server presets the neural network model in S4 and S5, it also includes: receiving the Beidou positioning information of the target transmission line tower and the number of each transmission line tower and the number of the tilt monitoring equipment and the soil moisture automatic observation instrument to which it belongs, and transmitting it to the host computer server via GPRS for display; receiving the tilt data of each transmission line tower, the surrounding soil moisture information and the meteorological information, and saving multiple data in time series, thereby forming a database.

[0022] S6. The tilt state of the pole tower determined by the host computer server and the marked pole tower to be repaired are transmitted to the host computer client through GPRS for display and warning, thereby realizing remote monitoring and multi-machine display; it should be noted that the host computer server and the host computer client form an overall host computer monitoring center, and the host computer server obtains data through the GPRS network and processes it; the host computer client is connected to the host computer server through the GPRS network, thereby realizing remote monitoring and multi-machine display.

[0023] The neural network model preset in S4 is used to train the historical inclination data of the tower, specifically: Data that meets the normal range of inclination in the historical inclination data of the tower are selected as samples, and the samples are divided into a training set and a test set. A neural network model is created and the training set is imported for training, thereby outputting the training results; the test set is then imported into the trained neural network model for testing, thereby outputting the test results, namely: the inclination threshold.

[0024] Continuing with the above embodiment, for example, by selecting a portion of normal tower tilt data from a database, copying the portion of data into two parts, one for training and the other for testing, so as to improve the accuracy of the model output; importing the training sample into a preset neural network model for training, thereby outputting a training result A; then importing the test sample into the trained neural network model for testing, thereby outputting a test structure B. If the results of A and B are consistent, it indicates that the current model calculation result is normal; if the results of A and B are inconsistent, it indicates that the current model calculation result is abnormal, and the training sample and the test sample need to be imported into the model again for training until the output A is consistent with B. At this time, B is the tilt threshold, such as: B is between 0.2°-0.5°.

[0025] Based on the tilt threshold as a comparison benchmark, the currently collected tilt data of the transmission line tower is compared with the tilt threshold. If the current tilt data is greater than the tilt threshold, it indicates that the transmission line tower is in a dangerous tilt state, and the signal is immediately transmitted to the host computer client based on GPRS for a red light warning; if the current tilt data is critical to the tilt threshold, it indicates that the transmission line tower is in a waiting tilt state, and the signal is transmitted to the host computer client based on GPRS for a yellow light warning; if the current tilt data is within the tilt threshold range, it indicates that the transmission line tower is in a normal state, and the signal is transmitted to the host computer client based on GPRS for a green light notification.

[0026] Continuing with the above embodiment, if the tilt threshold B is 0.2°-0.5°, and the tilt angle sensor of the Internet of Things monitors that the tilt angle of the transmission line tower is between 0.2°-0.5°, it indicates that the current transmission line tower is in a normal vertical state, and the processing result is transmitted to the host computer client based on GPRS. The host computer client combines the received Beidou positioning information to give a green light notification to all the towers in the target area; if the tilt data of any transmission line tower is 0.5°, it indicates that the transmission line tower is in a state of waiting to be tilted, and the processing result is transmitted to the host computer client based on GPRS. The host computer client obtains the location of the pole tower through Beidou positioning information, and uses the reader to read the radio frequency card information of the pole tower. For example, if the pole tower number is G1, the host computer client will issue a yellow light warning for the G1 tower on the display terminal; if the tilt data of any transmission line tower is 0.7°, it indicates that the transmission line tower is in a dangerous state of tilt. The number of the pole tower is determined according to the above-mentioned position determination method, and a red light warning is issued for the pole tower on the host computer client; this makes it easy for staff to determine the tilt status of the tower in the target area based on the display status of the three-color light, thereby providing an early warning function for the tilt of the tower.

[0027] The neural network model preset in S5 is used to train the historical soil moisture information, specifically: Based on the historical meteorological information around the tower, soil moisture information of the day when the weather was sunny and the air humidity was low and the day when the weather was rainy and the air humidity was high were selected as samples, and the samples were fused and divided into a training set and a test set. A neural network model was created and the training set was imported for training, thereby outputting the training results; the test set was then imported into the trained neural network model for testing, thereby outputting the test results, namely: humidity threshold.

[0028] Continuing with the above embodiment, for example, by selecting a part of soil moisture samples in a sunny state and a part of soil moisture samples in a rainy state from the database, it should be noted that when the two states are selected, the inclination of the tower to which they belong is in a normal state; by mixing and copying the two samples, the two samples are divided into training samples and test samples; the training samples are imported into a preset neural network model for training, thereby outputting a training result C; the test samples are then imported into the trained neural network model for testing, thereby outputting a test structure D, if the results of C and D are consistent, it indicates that the current model calculation result is normal; if the results of C and D are inconsistent, it indicates that the current model calculation result is abnormal, and the training samples and the test samples need to be imported into the model again for training until the output C is consistent with D, at which time D is the inclination threshold, such as: D is between 30% and 50%.

[0029] Based on the weather information of the day and the humidity threshold, if the weather information of the day shows that it is sunny or rainy, the air humidity is low or high, and the surrounding soil humidity of the transmission line tower is within the humidity threshold, it indicates that the current transmission line tower is in normal state; if the weather information of the day shows that it is sunny or rainy, the air humidity is low or high, and the surrounding soil humidity of one or more transmission line towers exceeds the humidity threshold, it indicates that the transmission line tower is in an abnormal state, and the transmission line tower is marked as a tower to be repaired, and the signal is transmitted to the upper computer client based on GPRS for a blue light warning.

[0030] Continuing with the above embodiment, if the tilt threshold D is 30%-50%, and the tilt of the transmission line tower is monitored to be between 30%-50%, it indicates that the soil moisture and soil quality in the target area are in normal state; if the soil moisture data around any of the transmission line towers is 60%, it indicates that the soil moisture around the transmission line tower is too high and the soil quality is relatively loose, which can easily cause the tower to tilt, and transmit the signal to the host computer client based on GPRS. The host computer client obtains the position of the tower through Beidou positioning information, and uses the reader to read the radio frequency card information of the tower. For example, if the tower number is G4, the host computer client will issue a blue light warning for the G4 tower on the display terminal, thereby prompting the staff to check and repair the G4 tower in advance to avoid the G4 tower from tilting quickly in the later stage and being difficult to remedy in time, thereby effectively improving the timeliness of the tower tilt warning.

[0031] The working principle of the above content is: by collecting the tilt data of the transmission line tower, the surrounding soil moisture and Beidou position information, the transmission line tower, the tilt monitoring equipment and the automatic soil moisture observation instrument are labeled using the radio frequency card; the upper computer server obtains the tilt threshold and the humidity threshold respectively through the neural network model; then the current tilt data and humidity data are compared with the corresponding thresholds respectively, and the towers whose tilt data and soil moisture exceed the threshold are extracted, and the position of the tower is obtained in combination with the Beidou positioning information, and the radio frequency card information of the tower is read by the reader, thereby obtaining the actual number of the tower, so as to perform the tilt three-color light warning and the blue light warning for maintenance on the upper computer client; by combining the soil moisture to predict in advance the possibility of the tower tilting, it can quickly warn the tilt state of the tower, thereby preventing the warning delay caused by the single tilt threshold comparison, and improving the timeliness and accuracy of the tower tilt warning.

[0032] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0033] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A transmission line tower tilt warning method based on the Internet of Things, characterized in that: The following steps are involved: S1. Install tilt monitoring equipment and Beidou positioning equipment to collect tilt data and Beidou location information of each transmission line tower, and send tilt data information and Beidou location information to the upper computer server based on GPRS; S2. Monitor the soil moisture and weather around each transmission line tower by installing an automatic soil moisture observation instrument and a weather monitor, and send the surrounding soil moisture information and weather information to the upper computer server based on GPRS; S3. Label each transmission line tower and its associated tilt monitoring equipment and soil moisture automatic observation instrument through wireless radio frequency technology; S4, the upper computer server trains the historical tilt data of the tower through a preset neural network model and outputs a tilt threshold, and compares the current tilt data of the tower with the tilt threshold to determine the tilt state of the tower; S5. The host computer server trains the historical soil moisture information through a preset neural network model and outputs a humidity threshold, compares the current soil moisture information around the tower with the humidity threshold to determine the current soil moisture state around the tower, and marks the transmission line tower whose surrounding soil moisture exceeds the humidity threshold as a tower to be repaired in combination with the Beidou position information; S6. The tilt state of the pole tower determined by the upper computer server and the marked pole tower to be repaired are transmitted to the upper computer client via GPRS for display and early warning, thereby realizing remote monitoring and multi-machine display.

2. The method for early warning of transmission line tower tilt based on the Internet of Things according to claim 1, characterized in that: The tilt monitoring equipment, Beidou positioning equipment, soil moisture automatic observation instrument and meteorological monitoring instrument installed in S1 and S2 are all powered by solar energy and batteries.

3. The transmission line tower tilt early warning method based on the Internet of Things according to claim 1 is characterized in that: After labeling each transmission line tower and its corresponding tilt monitoring device and soil moisture automatic observation instrument in S3, the number of each transmission line tower is matched with the number of the corresponding tilt monitoring device and soil moisture automatic observation instrument.

4. The method for early warning of transmission line tower tilt based on the Internet of Things according to claim 1, characterized in that: Before the host computer server presets the neural network model in S4 and S5, it also includes: Receive the Beidou positioning information of the target transmission line tower and the number of each transmission line tower and the number of the tilt monitoring equipment and soil moisture automatic observation instrument to which it belongs, and transmit it to the host computer server for display via GPRS; The tilt data of each transmission line tower, surrounding soil moisture information and meteorological information are received, and multiple data are saved in time series to form a database.

5. The transmission line tower tilt early warning method based on the Internet of Things according to claim 1 is characterized in that: The neural network model is preset in S4 to train the historical inclination data of the tower, specifically: Data that meet the normal range of inclination in the historical inclination data of the tower are selected as samples, and the samples are divided into a training set and a test set. A neural network model is created and the training set is imported for training, thereby outputting the training results; the test set is then imported into the trained neural network model for testing, thereby outputting the test results.

6. The method for early warning of transmission line tower tilt based on the Internet of Things according to claim 1, characterized in that: The determination of the tilt state of the tower in S4 is specifically as follows: Based on the tilt threshold as a comparison benchmark, the currently collected tilt data of the transmission line tower is compared with the tilt threshold. If the current tilt data is greater than the tilt threshold, it indicates that the transmission line tower is in a dangerous tilt state, and the signal is immediately transmitted to the host computer client based on GPRS for a red light warning; if the current tilt data is critical to the tilt threshold, it indicates that the transmission line tower is in a waiting tilt state, and the signal is transmitted to the host computer client based on GPRS for a yellow light warning; If the current tilt data is within the tilt threshold range, it indicates that the transmission line tower is in a normal state, and the signal is transmitted to the host computer client based on GPRS for green light notification.

7. The transmission line tower tilt early warning method based on the Internet of Things according to claim 1 is characterized in that: The neural network model is preset in S5 to train the historical soil moisture information, specifically: Based on the historical meteorological information around the tower, soil moisture information of the day when the weather was sunny and the air humidity was low and the day when the weather was rainy and the air humidity was high were selected as samples, and the samples were fused and divided into training set and test set. A neural network model was created and the training set was imported for training, thereby outputting the training results; the test set was then imported into the trained neural network model for testing, thereby outputting the test results.

8. The method for early warning of transmission line tower tilt based on the Internet of Things according to claim 1, characterized in that: The determination of the soil moisture state around the current tower in S5 is specifically as follows: Based on the weather information of the day and the humidity threshold, if the weather information of the day shows that it is sunny or rainy, the air humidity is low or high, and the surrounding soil humidity of the transmission line tower is within the humidity threshold, it indicates that the current transmission line tower is in normal state; if the weather information of the day shows that it is sunny or rainy, the air humidity is low or high, and the surrounding soil humidity of one or more transmission line towers exceeds the humidity threshold, it indicates that the transmission line tower is in an abnormal state, and the transmission line tower is marked as a tower to be repaired, and the signal is transmitted to the upper computer client based on GPRS for a blue light warning.

9. The method for early warning of transmission line tower tilt based on the Internet of Things according to claim 1, characterized in that: The numbering in S3 is performed by wireless radio frequency technology, specifically: By installing a radio frequency card on each transmission line tower and its associated tilt monitoring equipment and soil moisture automatic observation instrument, the radio frequency card is pre-entered with the serial numbers of the tilt monitoring equipment and soil moisture automatic observation instrument.

10. The method for early warning of transmission line tower tilt based on the Internet of Things according to claim 9, characterized in that: After the radio frequency card is installed in S3, a reader of the same model is configured to identify and read the content stored in the radio frequency card.

Images