Intelligent stay wire system and method for improving disaster resistance toughness and load analysis of electric pole

Abstract

The invention relates to an intelligent stay wire system and method for improving disaster resistance toughness and load analysis of an electric pole. The intelligent stay wire system comprises a tension sensing module arranged on an electric pole stay wire, an inclination sensing module arranged on an electric pole, a weather sensing module, an electric pole stay wire disc soil pressure sensing module, a power supply module, a data acquisition and transmission module and a processor. The tension sensing module is used for acquiring tension data of an electric pole stay wire, the inclination sensing module is used for acquiring electric pole inclination data, the meteorological sensing module is used for acquiring real-time meteorological data, and the electric pole stay wire disc soil pressure sensing module is used for acquiring stay wire disc soil pressure data; a state prediction model and a fault identification model are arranged in the processor, and the state prediction model is used for predicting the working state and disaster resistance toughness of the electric pole; the fault recognition model is used for recognizing whether the electric pole breaks down or not and outputting the recognized fault type.

Description

Technical Field

[0001] The present invention relates to an intelligent wire pulling system and method for improving the disaster resistance toughness and load analysis of electric poles, belonging to the technical field of distribution line operation status perception. Background Art

[0002] Electric poles are the main support for overhead power distribution lines in my country. There are a large number of them. Once the electric poles are tilted or collapsed, it will seriously affect people's electricity consumption in production and life. With the frequent occurrence of extreme weather conditions such as freezing rain, snow, and typhoons, which have repeatedly broken extreme values, a large number of pole collapses, broken poles, and tilting accidents have occurred in each disaster. In addition, the load calculation of distribution lines is simple and conservative during design, and the structural toughness is poor. Therefore, the operation of electric poles in the context of multiple disasters is greatly challenged. It is urgent to improve the disaster resistance of electric poles and identify the effective design load of electric poles based on reliability.

[0003] The purpose of the pole guy wire is to balance the forces from all sides of the pole and resist wind pressure to prevent the pole from falling. Generally, the guy wires are driven diagonally from the lower part of the pole cross arm to the ground to connect to the guy wire reel buried underground. Most poles with guy wires are terminal poles, corner poles or tension poles, which are subjected to large horizontal forces. Once the guy wires are loosened, broken, pulled out, etc. due to factors such as strong winds and impact forces, serious power grid accidents such as broken wires, fallen poles and tilted poles are very likely to occur under the action of unbalanced tension of the horizontal conductor. Moreover, most guy wire poles are on the roadside and in farmland, and are easily damaged by external forces such as vehicles, agricultural machinery, and trees, and lose their function of stabilizing the poles. Therefore, they become a weak link in improving the resilience of distribution lines. The operating status of the guy wire system of the guy wire pole directly determines the safe and stable operation of the distribution line. However, at present, problems can only be discovered through manual inspections and public alarms after accidents. There is no relevant online monitoring method to monitor the operation of the poles. The load design of the poles under multiple disasters and the optimal configuration of guy wires based on improving the resilience of the poles are still blank. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes an intelligent wire pulling system and method for improving the disaster resistance and load analysis of electric poles.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention proposes an intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles, comprising:

[0007] A tension sensing module arranged on the pole cable, a tilt sensing module, a weather sensing module, an earth pressure sensing module of the pole cable tray, a power supply module, a data acquisition and transmission module, and a processor arranged on the pole;

[0008] The tension sensing module is used to obtain the tension data of the pole wire, the tilt sensing module is used to obtain the pole tilt data, the meteorological sensing module is used to obtain real-time meteorological data, and the pole wire drum soil pressure sensing module is used to obtain the wire drum soil pressure data;

[0009] The processor is provided with a state prediction model and a fault identification model, wherein:

[0010] The state prediction model predicts the working state and disaster resilience of the pole based on the tension data of the pole guy wire, the pole inclination data, the real-time meteorological data, and the earth pressure data of the guy wire reel;

[0011] The fault identification model identifies whether a fault occurs on the pole based on the time series data of the tension data of the pole guy wire and outputs the identified fault type.

[0012] As a preferred embodiment, the tension sensing module includes a vibrating-wire strain gauge, and both ends of the vibrating-wire strain gauge are fixedly connected to the pole tension wire through parallel groove clamps.

[0013] As a preferred embodiment, the tension sensing module further includes a protective shell, which is hollow and sleeved on the pole tension wire, and the vibrating-wire strain gauge is arranged in the hollow inner cavity of the protective shell.

[0014] As a preferred embodiment, the tilt sensing module is arranged on the clamp of the pole guy wire, and is used to obtain the pole tilt angle data in the horizontal and vertical directions within the plane where the pole guy wire is located.

[0015] As a preferred implementation, the meteorological sensing module is arranged on the cross arm of the pole, and the meteorological sensing module includes a wind speed sensor, a wind direction sensor, and a temperature and humidity sensor.

[0016] As a preferred implementation, the training process of the state prediction model is specifically as follows:

[0017] Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, and obtain historical data of each sample tower, including tension data of the pole guy wires corresponding to the sample towers at different historical periods, pole tilt data, real-time meteorological data, earth pressure data of the guy wire reel, and tower status labels and disaster resilience labels, where the tower status labels and disaster resilience labels are obtained through manual labeling;

[0018] Normalizing the tension data of the pole guy wire, the pole tilt data, the real-time meteorological data, and the earth pressure data of the guy wire reel in the historical data, and putting each normalized historical data into the first training sample set as a training sample;

[0019] The first neural network is constructed, and the normalized pole guy wire tension data, pole inclination data, real-time meteorological data, and cable drum earth pressure data of each training sample in the first training sample set are constructed as input vectors. The first neural network is iteratively trained with the pole tower state label and disaster resistance resilience label as the true label to obtain a trained state prediction model.

[0020] As a preferred implementation, the training process of the fault identification model is specifically as follows:

[0021] Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, obtain the historical daily tension change curve and fault state label of each sample tower as an initial sample set, wherein the fault state label includes a no-fault label and a plurality of fault type labels corresponding to different fault types;

[0022] Based on the quantitative relationship between the no-fault type labels and the fault type labels of different fault types, the initial sample set is subjected to sample multiplication processing, so that the ratio of the no-fault label to the fault type label meets the predetermined threshold range, and the quantitative ratio between the fault type labels of different fault types meets the predetermined threshold range, thereby obtaining a second training sample set;

[0023] A second neural network is constructed, the tension change curve of each training sample in the second training sample set is used as input, and the second neural network is iteratively trained with the rod fault state label as the true label to obtain a trained fault recognition model.

[0024] On the other hand, the present invention also proposes a method for improving the disaster resistance resilience and load analysis of electric poles, comprising the following steps:

[0025] Obtain the inclination data, real-time meteorological data and earth pressure data of the target pole, and obtain the tension data of the pole wire of the target pole.

[0026] Construct a state prediction model and a fault identification model, where:

[0027] The state prediction model predicts the working state and disaster resilience of the pole based on the tension data of the pole guy wire, the pole inclination data, the real-time meteorological data, and the earth pressure data of the guy wire reel;

[0028] The fault identification model identifies whether a pole has a fault based on the time series data of the tension data of the pole guy wire and outputs the identified fault type;

[0029] The disaster resistance and load capacity of electric poles are improved based on the output results of the state prediction model and fault identification model.

[0030] On the other hand, the present invention further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for improving the disaster resistance and load analysis of electric poles as described in any embodiment of the present invention is implemented.

[0031] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for improving the disaster resistance resilience and load analysis of electric poles as described in any embodiment of the present invention.

[0032] The present invention has the following beneficial effects:

[0033] 1. The present invention monitors the operating status of the guyed poles online by setting up a tension sensing module, an inclination sensing module, a meteorological sensing module, and a pole guyed reel earth pressure sensing module, and can monitor the guyed poles at key pole positions all the time. At the same time, the meteorological monitoring data and the guyed tension data, pole inclination data, and guyed reel earth pressure data of multiple dimensions are integrated to perform deep machine learning to construct a pole operating status perception model and a fault identification model. The digital model can more accurately predict the operating status of guyed poles under multiple disasters, and determine the causes of various faults, providing data support for the disaster resilience assessment of guyed poles under multiple disasters.

[0034] 2. The present invention takes into account that it is difficult to detect through surface observation when a small change in tension occurs in the wire pulling system due to various reasons. By obtaining the wire pulling changes through a high-precision vibrating wire strain gauge and a wire pulling reel soil pressure box, it is possible to provide early warning of dangerous conditions of poles and wires, thereby ensuring safe and stable operation of distribution lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a schematic diagram of system installation in Embodiment 1 of the present invention;

[0036] Figure 2 This is a structural schematic diagram of a tension sensing module according to Embodiment 1 of the present invention;

[0037] Figure 3 Schematic diagram of the parallel groove clamp structure in an embodiment of the present invention;

[0038] Figure 4 This is a schematic diagram of the structure of a protective shell in an embodiment of the present invention;

[0039] Figure 5 It is a schematic diagram of the change of the tension of the guy wire and the corresponding fault cause when the pole is tilted toward the guy wire side in an embodiment of the present invention;

[0040] Figure 6 It is a schematic diagram of the change of the tension of the guy wire and the corresponding fault cause when the electric pole is tilted to the opposite side of the guy wire in an embodiment of the present invention;

[0041] Figure 7 This is a schematic diagram of the method flow of Embodiment 2 of the present invention.

[0042] The accompanying drawings in the figure are marked as follows:

[0043] 1. Electric pole; 2. Guy wire; 3. Guy wire drum; 4. Chuck; 5. Chassis; 6. Tension sensing module; 7. Tilt sensing module; 8. Weather sensing module; 9. Earth pressure sensing module for guy wire drum of electric pole; 10. Control box; 11. Vibrating wire strain gauge; 12. Parallel groove wire clamp; 13 Extension rod; 21. Protective shell; 22. Bolt; 23. Sealing pad. DETAILED DESCRIPTION

[0044] 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.

[0045] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0046] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0047] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0048] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0049] Embodiment 1:

[0050] See also Figure 1 This embodiment provides an intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles, which specifically includes:

[0051] A tension sensing module 6 is arranged on the pole guy wire 2, a tilt sensing module 7, a meteorological sensing module 8, a pole guy wire tray earth pressure sensing module 9, a power supply module, a data acquisition and transmission module and a processor are arranged on the pole 1; the power supply module, the data acquisition and transmission module and the processor are arranged together in a control box 10 on the pole cross arm, wherein the power supply module adopts solar energy to provide electrical energy to the electrical devices in the system, and the data acquisition and transmission module is responsible for data collection and edge computing.

[0052] Among them, the tension sensing module 6 is used to obtain the tension data of the pole wire 2, the tilt sensing module 7 is used to obtain the tilt data of the pole 1, the meteorological sensing module 8 is used to obtain real-time meteorological data, and the pole wire drum soil pressure sensing module 9 is used to obtain the wire drum soil pressure data;

[0053] The processor is provided with a state prediction model and a fault identification model, wherein:

[0054] The state prediction model predicts the working state and disaster resistance resilience of the pole 1 based on the tension data of the pole guy wire 2, the pole inclination data, the real-time meteorological data, and the earth pressure data of the guy wire reel;

[0055] The fault identification model identifies whether a fault occurs in the pole 1 based on the time series data of the tension data of the pole guy wire 2 and outputs the identified fault type.

[0056] See Figure 2 As a preferred implementation of this embodiment, the tension sensing module 6 is installed on the pull rod of the pull wire, and its core component is a vibrating wire strain gauge 11. The vibrating wire strain gauge 11 has the advantages of strong weather resistance, strong anti-interference ability, data memory, and a wide operating temperature range, and is suitable for long-term strain monitoring; the vibrating wire strain gauge is Figure 2 The parallel groove clamp 12 is fixed with the extension rod 13 of the pull rod. The structure of the groove clamp 12 is as follows: Figure 3 described.

[0057] See Figure 4 As a preferred implementation of this embodiment, in order to ensure that the vibrating-wire strain gauge works stably for a long time and is not disturbed by the environment and external forces, the tension sensing module 6 also includes a protective shell 21. The protective shell 21 is made of steel and is hollow, and is sleeved on the pole wire 2. The vibrating-wire strain gauge 11 is arranged in the hollow inner cavity of the protective shell 21. The end of the protective shell 21 is fixed by bolts 22, and a sealing rubber pad 23 is also provided at the port of the protective shell 21.

[0058] As a preferred implementation of this embodiment, the tilt sensing module 7 is arranged on the clamp of the pole guy wire 2, and is used to obtain the pole tilt angle data in the horizontal and vertical directions within the plane where the pole guy wire 2 is located.

[0059] As a preferred implementation of this embodiment, the meteorological sensing module 8 is arranged on the cross arm of the pole. The meteorological sensing module 8 includes a wind speed sensor, a wind direction sensor and a temperature and humidity sensor, and the wind speed, wind direction and temperature and humidity data are sensed by each sensor.

[0060] As a preferred implementation of this embodiment, the pole cable drum soil pressure sensing module 9 senses soil pressure change data on the upper surface of the drum.

[0061] As a preferred implementation of this embodiment, the training process of the state prediction model is specifically as follows:

[0062] Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, and obtain historical data of each sample tower, the historical data including the tension data of the pole guy wire 2 corresponding to the sample tower in different historical periods, pole inclination data, real-time meteorological data, cable drum soil pressure data, tower status label and disaster resistance resilience label, wherein the tower status label and disaster resistance resilience label are obtained through manual labeling; specifically, through comprehensive real-time perception of wind speed and direction, temperature and humidity, pole inclination angle, guy wire tension, and cable drum soil pressure, these parameters can accurately evaluate the operating status of the pole; and through theoretical calculation, the ultimate disaster resistance resilience of the guy wire and the pole can be obtained, and 60% to 80% of the ultimate disaster resistance resilience is set as a caution state, 80% to 90% as a warning state, and ≥90% as a dangerous state.

[0063] Normalizing the tension data of the pole guy wire 2, the pole tilt data, the real-time meteorological data, and the earth pressure data of the guy wire reel in the historical data, and putting each normalized historical data into the first training sample set as a training sample;

[0064] The first neural network is constructed, and the normalized tension data of the pole guy wire 2, the pole inclination data, the real-time meteorological data, and the earth pressure data of the guy wire reel of each training sample in the first training sample set are constructed as input vectors. The first neural network is iteratively trained with the pole tower state label and the disaster resistance resilience label as the true label to obtain a trained state prediction model.

[0065] The first neural network mentioned above can adopt LSTM neural network. LSTM (Long Short-Term Memory Neural Network) can learn long-term dependency information through its unique gating mechanism, effectively avoiding the gradient vanishing problem in traditional recurrent neural networks.

[0066] After identifying the operating status of the pole, the edge computing function can be used to obtain various operating statuses and automatically change the data collection and transmission frequency. The attention status collection and transmission interval is 60 seconds, the warning status is 30 seconds, and the danger status is 10 seconds. The state below 60% is a safe state, with a collection interval of 60 seconds and a transmission interval of 30 minutes, while the state below 40% is a dormant state, with a collection interval of 60 seconds and a transmission interval of 12 hours. The edge computing function can dynamically adjust the data collection and transmission frequency, reduce system energy consumption, reasonably use power supply, and reduce the interference of invalid redundant data on the terminal.

[0067] like Figure 5 and Figure 6 As shown, specifically, the thin wires of electric poles have low resilience to disasters and are easily overlooked when exposed to the natural environment. Once they are hit by external forces such as vehicles and agricultural machinery, or are washed away by floods or illegally taken soil, resulting in the pull plate being pulled out or not buried deep enough, or the wires being pressed by trees, or wires being broken, or wires being loose, or connecting hardware being loose and failing, the tension of the wires will change accordingly, and the tensile strain of the wire rods will reflect the change in tension of the wire system. As a preferred implementation of this embodiment, in order to identify the above-mentioned fault types, a fault recognition model is designed, and the training process of the fault recognition model is specifically as follows:

[0068] Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, obtain the historical daily tension change curve and fault state label of each sample tower as an initial sample set, wherein the fault state label includes a no-fault label and a plurality of fault type labels corresponding to different fault types;

[0069] Based on the quantitative relationship between the no-fault type labels and the fault type labels of different fault types, the initial sample set is subjected to sample multiplication processing, so that the ratio of the no-fault label to the fault type label meets the predetermined threshold range, and the quantitative ratio between the fault type labels of different fault types meets the predetermined threshold range, thereby obtaining a second training sample set;

[0070] A second neural network is constructed, the tension change curve of each training sample in the second training sample set is used as input, and the second neural network is iteratively trained with the rod fault state label as the true label to obtain a trained fault recognition model.

[0071] The second neural network adopts a convolutional neural network (CNN), which can automatically extract image features by simulating the working principle of the human visual system, greatly improving the accuracy of image classification and recognition. In this embodiment, a multi-layer convolutional neural network model is designed, which includes multiple convolutional layers, pooling layers, and fully connected layers to achieve efficient processing of daily tensile change curve image data. By training on a large-scale daily tensile change curve image data set, the model can learn the deep features in the daily tensile change curve to make accurate predictions based on the image features.

[0072] Based on the above implementation, this embodiment obtains data such as the force, inclination angle, and earth pressure of the cable tray of the poles and cables when various load combinations act under a multi-hazard background, and trains through machine learning to obtain a digital model of the response of the cable poles corresponding to the load. The load values ​​can be obtained by monitoring the various responses of the cable poles under multi-hazard conditions, providing a basis for the standard of design loads under multi-hazard conditions.

[0073] Embodiment 2:

[0074] See Figure 7 This embodiment provides a method for improving the disaster resistance resilience and load analysis of electric poles, which specifically includes the following steps:

[0075] S100, obtaining the inclination data, real-time meteorological data and earth pressure data of the cable tray of the target pole, and obtaining the tension data of the cable tray of the target pole,

[0076] S200, constructing a state prediction model and a fault identification model, wherein:

[0077] The state prediction model predicts the working state and disaster resilience of the pole based on the tension data of the pole guy wire, the pole inclination data, the real-time meteorological data, and the earth pressure data of the guy wire reel;

[0078] The fault identification model identifies whether a pole has a fault based on the time series data of the tension data of the pole guy wire and outputs the identified fault type;

[0079] S300: Improve the disaster resistance and load capacity of the pole based on the output results of the state prediction model and the fault identification model.

[0080] As a preferred implementation of this embodiment, the training process of the state prediction model is specifically as follows:

[0081] Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, and obtain historical data of each sample tower, the historical data including the tension data of the pole guy wires, pole inclination data, real-time meteorological data, earth pressure data of the guy wire reel, and tower status labels and disaster resilience labels corresponding to the sample towers in different historical periods, wherein the tower status labels and disaster resilience labels are obtained through manual labeling; specifically, through comprehensive and real-time perception of wind speed and direction, temperature and humidity, pole inclination angle, guy wire tension, and earth pressure of the guy wire reel, these parameters can accurately evaluate the operating status of the pole; and through theoretical calculation, the ultimate disaster resilience of the guy wires and poles can be obtained, and 60% to 80% of the ultimate disaster resilience is set as a caution state, 80% to 90% as a warning state, and ≥90% as a dangerous state.

[0082] Normalizing the tension data of the pole guy wire, the pole tilt data, the real-time meteorological data, and the earth pressure data of the guy wire reel in the historical data, and putting each normalized historical data into the first training sample set as a training sample;

[0083] The first neural network is constructed, and the normalized pole guy wire tension data, pole inclination data, real-time meteorological data, and cable drum earth pressure data of each training sample in the first training sample set are constructed as input vectors. The first neural network is iteratively trained with the pole tower state label and disaster resistance resilience label as the true label to obtain a trained state prediction model.

[0084] The first neural network mentioned above can adopt LSTM neural network. LSTM (Long Short-Term Memory Neural Network) can learn long-term dependency information through its unique gating mechanism, effectively avoiding the gradient vanishing problem in traditional recurrent neural networks.

[0085] As a preferred implementation of this embodiment, a fault identification model is designed, and the training process of the fault identification model is specifically as follows:

[0086] Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, obtain the historical daily tension change curve and fault state label of each sample tower as an initial sample set, wherein the fault state label includes a no-fault label and a plurality of fault type labels corresponding to different fault types;

[0087] Based on the quantitative relationship between the no-fault type labels and the fault type labels of different fault types, the initial sample set is subjected to sample multiplication processing, so that the ratio of the no-fault label to the fault type label meets the predetermined threshold range, and the quantitative ratio between the fault type labels of different fault types meets the predetermined threshold range, thereby obtaining a second training sample set;

[0088] A second neural network is constructed, the tension change curve of each training sample in the second training sample set is used as input, and the second neural network is iteratively trained with the rod fault state label as the true label to obtain a trained fault recognition model.

[0089] The second neural network adopts a convolutional neural network (CNN), which can automatically extract image features by simulating the working principle of the human visual system, greatly improving the accuracy of image classification and recognition. In this embodiment, a multi-layer convolutional neural network model is designed, which includes multiple convolutional layers, pooling layers, and fully connected layers to achieve efficient processing of daily tensile change curve image data. By training on a large-scale daily tensile change curve image data set, the model can learn the deep features in the daily tensile change curve to make accurate predictions based on the image features.

[0090] Embodiment three:

[0091] This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for improving the disaster resistance resilience and load analysis of electric poles as described in any embodiment of the present invention is implemented.

[0092] Embodiment 4:

[0093] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for improving the disaster resistance resilience and load analysis of electric poles as described in any embodiment of the present invention is implemented.

[0094] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0095] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0098] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles, characterized in that: include: A tension sensing module arranged on the pole cable, a tilt sensing module, a weather sensing module, an earth pressure sensing module of the pole cable tray, a power supply module, a data acquisition and transmission module, and a processor arranged on the pole; The tension sensing module is used to obtain the tension data of the pole wire, the tilt sensing module is used to obtain the pole tilt data, the meteorological sensing module is used to obtain real-time meteorological data, and the pole wire drum soil pressure sensing module is used to obtain the wire drum soil pressure data; The processor is provided with a state prediction model and a fault identification model, wherein: The state prediction model predicts the working state and disaster resilience of the pole based on the tension data of the pole guy wire, the pole inclination data, the real-time meteorological data, and the earth pressure data of the guy wire reel; The fault identification model identifies whether a fault occurs on the pole based on the time series data of the tension data of the pole guy wire and outputs the identified fault type.

2. According to claim 1, the intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles is characterized by: The tension sensing module comprises a vibrating-wire strain gauge, and two ends of the vibrating-wire strain gauge are fixedly connected to the pole tension wire through parallel groove clamps.

3. The intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles according to claim 2 is characterized by: The tension sensing module also includes a protective shell, which is hollow and sleeved on the pole tension wire, and the vibrating-wire strain gauge is arranged in the hollow inner cavity of the protective shell.

4. The intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles according to claim 1 is characterized in that: The tilt sensing module is arranged on the clamp of the pole guy wire and is used to obtain the tilt angle data of the pole in the horizontal and vertical directions within the plane where the pole guy wire is located.

5. The intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles according to claim 1 is characterized in that: The meteorological sensing module is arranged on the cross arm of the pole, and the meteorological sensing module includes a wind speed sensor, a wind direction sensor and a temperature and humidity sensor.

6. The intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles according to claim 1 is characterized in that: The training process of the state prediction model is specifically as follows: Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, and obtain historical data of each sample tower, including tension data of the pole guy wires corresponding to the sample towers at different historical periods, pole tilt data, real-time meteorological data, earth pressure data of the guy wire reel, and tower status labels and disaster resilience labels, where the tower status labels and disaster resilience labels are obtained through manual labeling; Normalizing the tension data of the pole guy wire, the pole tilt data, the real-time meteorological data, and the earth pressure data of the guy wire reel in the historical data, and putting each normalized historical data into the first training sample set as a training sample; The first neural network is constructed, and the normalized pole guy wire tension data, pole inclination data, real-time meteorological data, and cable drum earth pressure data of each training sample in the first training sample set are constructed as input vectors. The first neural network is iteratively trained with the pole tower state label and disaster resistance resilience label as the true label to obtain a trained state prediction model.

7. The intelligent cable pulling system for improving the disaster resistance and load analysis of electric poles according to claim 1, characterized in that: The training process of the fault identification model is specifically as follows: Determine the latitude of the current tower, determine the target latitude range according to the latitude of the current tower, obtain a given number of other towers within the target latitude as sample towers, obtain the historical daily tension change curve and fault state label of each sample tower as an initial sample set, wherein the fault state label includes a no-fault label and a plurality of fault type labels corresponding to different fault types; Based on the quantitative relationship between the no-fault type labels and the fault type labels of different fault types, the initial sample set is subjected to sample multiplication processing, so that the ratio of the no-fault label to the fault type label meets the predetermined threshold range, and the quantitative ratio between the fault type labels of different fault types meets the predetermined threshold range, thereby obtaining a second training sample set; A second neural network is constructed, the tension change curve of each training sample in the second training sample set is used as input, and the second neural network is iteratively trained with the rod fault state label as the true label to obtain a trained fault recognition model.

8. A method for improving the disaster resistance toughness and load analysis of electric poles, characterized in that: The following steps are involved: Obtain the inclination data, real-time meteorological data and earth pressure data of the target pole, and obtain the tension data of the pole wire of the target pole. Construct a state prediction model and a fault identification model, where: The state prediction model predicts the working state and disaster resilience of the pole based on the tension data of the pole guy wire, the pole inclination data, the real-time meteorological data, and the earth pressure data of the guy wire reel; The fault identification model identifies whether a pole has a fault based on the time series data of the tension data of the pole guy wire and outputs the identified fault type; The disaster resistance and load capacity of electric poles are improved based on the output results of the state prediction model and fault identification model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for improving the disaster resistance resilience and load analysis of electric poles as described in claim 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a method for improving disaster resistance resilience and load analysis of electric poles as described in claim 8 is implemented.

Images