Power transmission line icing on-line monitoring method and system based on multi-sensor fusion

Abstract

The invention provides a power transmission line icing on-line monitoring method and system based on multi-sensor fusion, and belongs to the technical field of monitoring. Dual-polarization mechanical transverse waves are formed through an oscillation generator and an oscillation receiver which are arranged at the two ends of a to-be-detected power transmission line, and through combination with a tension sensor, a neural network is trained; and the purpose of predicting the maximum icing thickness is achieved.

Description

Technical Field

[0001] The present application relates to the field of power equipment monitoring, and in particular to a method and system for online monitoring of icing on transmission lines based on multi-sensor fusion. Background Art

[0002] Icing of transmission lines is a major disaster that threatens the safety of the power grid, especially in high-altitude areas with heavy ice. Traditional methods frequently cause false alarms due to environmental interference, forcing operation and maintenance personnel to take the risk of on-site inspections, which is very risky.

[0003] Conventional methods using tension monitoring can only obtain the average ice load, while the maximum local ice load is the key to wire breakage. Therefore, how to measure the maximum local ice load is an urgent problem to be solved. Summary of the Invention

[0004] The embodiments of the present application provide a method and system for online monitoring of ice coating on power transmission lines based on multi-sensor fusion to improve the above-mentioned problems.

[0005] To achieve the above objectives, this application adopts the following technical solutions: In the first aspect, the present application proposes an online monitoring method for transmission line icing based on multi-sensor fusion, which is applicable to a transmission line icing monitoring device. The transmission line icing monitoring device includes an oscillation generator, an oscillation receiver, a tension sensor, and a control terminal. The method is applicable to the control terminal and includes: controlling an oscillation generator disposed at one end of the line to be inspected to generate a first mechanical shear wave and a second mechanical shear wave transmitted in a direction of the line to be inspected, wherein perpendicular directions between the crests of the first mechanical shear wave and the second mechanical shear wave and the central axis of the line to be inspected are first and second directions, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity, and the oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities; An oscillation receiver disposed at the other end away from the oscillation generator receives the first mechanical shear wave and the second mechanical shear wave, and obtains an actual first oscillation intensity and an actual second oscillation intensity corresponding to the first mechanical shear wave and the second mechanical shear wave, respectively; The basic tension of the line to be detected is obtained based on the tension sensor, and the corresponding maximum ice thickness of the line to be detected is obtained based on the basic tension, the actual first oscillation intensity and the actual second oscillation intensity.

[0006] In conjunction with the first aspect, in some embodiments, obtaining a basic tension of the line to be inspected based on a tension sensor, and obtaining a corresponding maximum ice thickness of the line to be inspected based on the basic tension, an actual first oscillation intensity, and an actual second oscillation intensity includes: Based on historical data, multiple sets of corresponding basic tension, actual first oscillation intensity, and actual second oscillation intensity are obtained when different maximum ice thicknesses are present on the line to be tested; Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated, and the trained target neural network model is output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension.

[0007] In conjunction with the first aspect, in some embodiments, obtaining a basic tension of the line to be inspected based on a tension sensor, and obtaining a corresponding maximum ice thickness of the line to be inspected based on the basic tension, an actual first oscillation intensity, and an actual second oscillation intensity includes: Based on historical data, the corresponding basic tension, actual first oscillation intensity, and actual second oscillation intensity are obtained when the maximum ice thickness on the line to be tested is 0; Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated, and the trained target neural network model is output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension, and also includes: When the maximum ice thickness on the line to be tested is 0, the corresponding basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed.

[0008] In conjunction with the first aspect, in some embodiments, multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are introduced into a neural network training model and iterative calculation is performed, and a trained target neural network model is output. The target neural network model is used to output a predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension, including: The actual first oscillation intensity, the actual second oscillation intensity, and the basic tension are taken as three different dimensions, and the dimension vectors are retained for connection. The three dimensions are connected to form a characteristic vector corresponding to the maximum ice thickness; Multiple sets of basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed. When the preset conditions are met during the iterative calculation process, the calculation is stopped and the trained target neural network model is output.

[0009] In conjunction with the first aspect, in some embodiments, multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are introduced into a neural network training model and iterative calculation is performed. When a preset condition is met during the iterative calculation, the calculation is stopped and the trained target neural network model is output, including: Multiple sets of basic tension, actual first shock intensity and actual second shock intensity are divided into two sets: training set and validation set; The neural network model is trained based on the data in the training set, and is verified based on the data in the verification set. When the verification result meets the preset conditions, the target neural network model is output.

[0010] In combination with the first aspect, in some embodiments, multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are divided into two sets: a training set and a validation set, wherein the data in the training set and the validation set are different.

[0011] In conjunction with the first aspect, in some embodiments, a neural network model is trained based on data in a training set, and the neural network model is verified based on data in a validation set. When the verification result meets a preset condition, a target neural network model is output, including: Perform iterative calculations based on the data in the training set, and generate a conditional neural network model during each iterative calculation process; Import the data in the validation set into the conditional neural network model and obtain multiple error values; Get multiple error values ​​corresponding to the validation set and get the average error value of the multiple error values; When the average error value is less than the preset value, the calculation is stopped and the conditional neural network model is used as the target neural network model and output.

[0012] In a second aspect, an embodiment of the present application provides a power transmission line icing monitoring device, characterized in that the power transmission line icing monitoring device includes: A tension sensor is provided at one end of the power transmission line to be tested and is used to monitor the tension of the power transmission line to be tested; an oscillation generator and an oscillation receiver, wherein the oscillation generator is disposed at one end of the power transmission line to be detected, and the oscillation receiver is disposed at an end of the power transmission line to be detected away from the oscillation generator. The oscillation generator is configured to generate a first mechanical shear wave and a second mechanical shear wave that are transmitted along the direction of the power transmission line to be detected, wherein the directions of perpendicular lines between the crests of the first mechanical shear wave and the second mechanical shear wave and the central axis of the power transmission line to be detected are first and second directions, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity. The oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities, and the oscillation receiver receives the first mechanical shear wave and the second mechanical shear wave; and The control terminal is communicatively connected with the tension sensor, the oscillation receiver and the oscillation generator, and is used to execute the method of the first aspect.

[0013] In a third aspect, an embodiment of the present application proposes an online monitoring system for ice coating on power transmission lines based on multi-sensor fusion, including an oscillation generator, an oscillation receiver, a tension sensor, and a control terminal. The system is configured as follows: controlling an oscillation generator disposed at one end of the line to be inspected to generate a first mechanical shear wave and a second mechanical shear wave transmitted in a direction of the line to be inspected, wherein perpendicular directions between the crests of the first mechanical shear wave and the second mechanical shear wave and the central axis of the line to be inspected are first and second directions, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity, and the oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities; An oscillation receiver disposed at the other end away from the oscillation generator receives the first mechanical shear wave and the second mechanical shear wave, and obtains an actual first oscillation intensity and an actual second oscillation intensity corresponding to the first mechanical shear wave and the second mechanical shear wave, respectively; The basic tension of the line to be detected is obtained based on the tension sensor, and the corresponding maximum ice thickness of the line to be detected is obtained based on the basic tension, the actual first oscillation intensity and the actual second oscillation intensity.

[0014] In conjunction with the third aspect, in some embodiments, the system is configured to: Obtaining a basic tension of the line to be detected based on the tension sensor, and obtaining a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity, including: Based on historical data, multiple sets of corresponding basic tension, actual first oscillation intensity, and actual second oscillation intensity are obtained when different maximum ice thicknesses are present on the line to be tested; Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated, and the trained target neural network model is output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension.

[0015] In conjunction with the third aspect, in some embodiments, the system is configured to: Obtaining a basic tension of the line to be detected based on the tension sensor, and obtaining a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity, including: Based on historical data, the corresponding basic tension, actual first oscillation intensity, and actual second oscillation intensity are obtained when the maximum ice thickness on the line to be tested is 0; Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated, and the trained target neural network model is output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension, and also includes: When the maximum ice thickness on the line to be tested is 0, the corresponding basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed.

[0016] In conjunction with the third aspect, in some embodiments, the system is configured to: Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated. The trained target neural network model is then output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension, including: The actual first oscillation intensity, the actual second oscillation intensity, and the basic tension are taken as three different dimensions, and the dimension vectors are retained for connection. The three dimensions are connected to form a characteristic vector corresponding to the maximum ice thickness; Multiple sets of basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed. When the preset conditions are met during the iterative calculation process, the calculation is stopped and the trained target neural network model is output.

[0017] In conjunction with the third aspect, in some embodiments, the system is configured to: Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated. When the preset conditions are met during the iterative calculation process, the calculation is stopped and the trained target neural network model is output, including: Multiple sets of basic tension, actual first shock intensity and actual second shock intensity are divided into two sets: training set and validation set; The neural network model is trained based on the data in the training set, and is verified based on the data in the verification set. When the verification result meets the preset conditions, the target neural network model is output.

[0018] In conjunction with the third aspect, in some embodiments, the system is configured to: Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are divided into two sets: a training set and a validation set, wherein the data in the training set and the validation set are different.

[0019] In conjunction with the third aspect, in some embodiments, the system is configured to: The neural network model is trained based on the data in the training set, and is verified based on the data in the validation set. When the verification result meets the preset conditions, the target neural network model is output, including: Perform iterative calculations based on the data in the training set, and generate a conditional neural network model during each iterative calculation process; Import the data in the validation set into the conditional neural network model and obtain multiple error values; Get multiple error values ​​corresponding to the validation set and get the average error value of the multiple error values; When the average error value is less than the preset value, the calculation is stopped and the conditional neural network model is used as the target neural network model and output.

[0020] A fourth aspect of an embodiment of the present invention provides an electronic device, including: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method proposed in the first aspect of the embodiment of the present invention.

[0021] In summary, the above method and system have the following technical effects: An embodiment of the present application proposes an online monitoring system for transmission line icing based on multi-sensor fusion. Dual-polarization mechanical shear waves are formed by an oscillation generator and an oscillation receiver arranged at both ends of the transmission line to be detected. The system is combined with a tension sensor to train a neural network to achieve the purpose of predicting the maximum ice thickness. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The present invention provides a flowchart of a method for online monitoring of icing on power transmission lines based on multi-sensor fusion according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] The present application provides a power transmission line icing monitoring device, which is characterized in that the power transmission line icing monitoring device includes: A tension sensor is installed at one end of the transmission line to be inspected and is used to monitor the tension in the line. As can be understood, by monitoring changes in the tension on the transmission line, the tension sensor can indirectly reflect the ice coverage on the line. As the ice on the transmission line gradually thickens, its weight increases, causing the tension sensor reading to change. The tension sensor's detection data, to a certain extent, reflects the total amount of ice coverage.

[0025] An oscillation generator and an oscillation receiver, wherein the oscillation generator is arranged at one end of the transmission line to be detected, and the oscillation receiver is arranged at the end of the transmission line to be detected away from the oscillation generator. The oscillation generator is used to generate a first mechanical shear wave and a second mechanical shear wave transmitted along the direction of the line to be detected.

[0026] As you can understand, mechanical shear waves are not longitudinal waves that propagate along the direction of the transmission line being tested. Therefore, the transmission attenuation of mechanical shear waves is strongly dependent on the elasticity and dimensions of the transmission medium. Consequently, when ice covers a transmission line, the transmission of mechanical shear waves is affected by the ice. However, the relationship between mechanical shear waves and ice cannot be characterized using a simple mathematical relationship.

[0027] In this embodiment, the directions of perpendicular lines between the crests of the first and second mechanical shear waves and the central axis of the circuit to be detected are the first and second directions, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity. The oscillation intensities of the first and second mechanical shear waves are both initial oscillation intensities, and the oscillation receiver receives the first and second mechanical shear waves.

[0028] It is understandable that the crest direction of the first mechanical shear wave is opposite to gravity. That is, during the transmission of the first mechanical shear wave, the particles at the crest and trough move in a direction perpendicular to the ground. In contrast, the particles at the crest and trough of the second mechanical shear wave move in a plane relatively parallel to the ground. Due to the influence of gravity, the particle motion during the transmission of the first mechanical shear wave has a vertical component. Therefore, the static tension change caused by gravity has a more direct impact. The transmission of the second mechanical shear wave mainly reflects the mass increase and uniform damping caused by ice accumulation. The attenuation of the first and second mechanical shear waves can be used to infer the thickness and even the degree of eccentricity of the ice layer to a certain extent.

[0029] Exemplarily, the oscillation generator uses a piezoelectric ceramic transducer, wherein the first mechanical acoustic wave excitation electrode is arranged in a vertical direction, and the second mechanical acoustic wave excitation electrode is arranged in a horizontal direction.

[0030] The control terminal is communicatively connected with the tension sensor, the oscillation receiver and the oscillation generator.

[0031] The control terminal can be a personal computer, a server, etc., which is not limited in this application. This application also proposes an online monitoring method for ice coating on power transmission lines based on multi-sensor fusion, in which the control terminal serves as the execution terminal, including the following steps: S101: Controlling an oscillation generator disposed at one end of the line to be detected to generate a first mechanical shear wave and a second mechanical shear wave transmitted along the direction of the line to be detected, wherein the directions of perpendicular lines between the peaks of the first mechanical shear wave and the second mechanical shear wave and the central axis of the line to be detected are a first direction and a second direction, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity, and the oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities.

[0032] S102: Receive the first mechanical shear wave and the second mechanical shear wave via an oscillation receiver located at the other end away from the oscillation generator, and obtain actual first oscillation intensities and actual second oscillation intensities corresponding to the first mechanical shear wave and the second mechanical shear wave, respectively.

[0033] For example, in this embodiment, the actual first oscillation intensity is the RMS value of the first mechanical shear wave signal within a preset time window, and the actual second oscillation intensity is the RMS value of the second mechanical shear wave signal within the same time window. The length of the time window is dynamically adjusted based on the wave frequency.

[0034] S103: Obtaining a basic tension of the line to be detected based on the tension sensor, and obtaining a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity.

[0035] For example, in this embodiment, first, a basic tension T can be obtained based on a tension sensor, and ice thickness calculation can be performed. The maximum ice thickness is obtained through a two-dimensional nonlinear mapping of the attenuation ratio and the tension increment ΔT.

[0036] In this embodiment, multiple sets of basic tension, actual first oscillation intensity and actual second oscillation intensity corresponding to different maximum ice cover thicknesses on the line to be tested can be obtained based on historical data. Then, the multiple sets of basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed, and the trained target neural network model is output. The target neural network model is used to output the predicted maximum ice cover thickness based on the input actual first oscillation intensity and actual second oscillation intensity and basic tension.

[0037] Specifically, the actual first oscillation intensity, the actual second oscillation intensity and the basic tension are taken as three different dimensions, and the dimension vectors are retained for connection. The three dimensions are connected to form a characteristic vector corresponding to the maximum ice cover thickness. Multiple sets of basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed. When the preset conditions are met during the iterative calculation process, the calculation is stopped and the trained target neural network model is output.

[0038] For example, multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity can be divided into two sets: a training set and a validation set, where the data in the training set and the validation set are different. The neural network model is trained based on the data in the training set, and the neural network model is validated based on the data in the validation set. When the validation results meet preset conditions, the target neural network model is output.

[0039] It should be noted that in this embodiment, baseline comparison parameters are required to achieve more accurate model training. In this embodiment, the baseline comparison parameters can be parameters when the maximum ice thickness on the line to be tested is 0. Therefore, in this embodiment, based on historical data, the corresponding base tension, actual first oscillation intensity, and actual second oscillation intensity when the maximum ice thickness on the line to be tested is 0 are obtained. During the iterative calculation process, the corresponding base tension, actual first oscillation intensity, and actual second oscillation intensity when the maximum ice thickness on the line to be tested is 0 are imported into the neural network training model and iterative calculations are performed.

[0040] To illustrate more specifically, the three parameters of the actually measured first oscillation intensity, second oscillation intensity, and base tension can be regarded as three independent dimensions. By retaining the vector information of these dimensions and connecting them, a feature vector can be constructed, which represents the characteristics of the maximum ice thickness. Next, multiple sets of data on base tension, actual first oscillation intensity, and actual second oscillation intensity can be input into a neural network training model and repeatedly iterated. During the iterative calculation process, once a pre-set stopping condition is met, such as an error threshold or an upper limit on the number of iterations, the calculation can be stopped and a trained target neural network model can be output.

[0041] In this embodiment, as an implementation method, iterative calculations can be performed based on the data in the training set, and a conditional neural network model can be generated during each iterative calculation; the data in the validation set is imported into the conditional neural network model, and multiple error values ​​are obtained; multiple error values ​​corresponding to the validation set are obtained, and the average error value of the multiple error values ​​is obtained; when the average error value is less than a preset value, the calculation is stopped, and the conditional neural network model is used as the target neural network model and output.

[0042] An embodiment of the present application proposes an online monitoring method for transmission line icing based on multi-sensor fusion. Dual-polarization mechanical shear waves are formed by oscillation generators and oscillation receivers arranged at both ends of the transmission line to be detected. The neural network is trained by combining the oscillation generators and the tension sensors to achieve the purpose of predicting the maximum ice thickness.

[0043] Based on the same inventive concept, the present application also proposes an online monitoring system for transmission line icing based on multi-sensor fusion, including an oscillation generator, an oscillation receiver, a tension sensor, and a control terminal. The system is configured as follows: controlling an oscillation generator disposed at one end of the line to be inspected to generate a first mechanical shear wave and a second mechanical shear wave transmitted in a direction of the line to be inspected, wherein perpendicular directions between the crests of the first mechanical shear wave and the second mechanical shear wave and the central axis of the line to be inspected are first and second directions, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity, and the oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities; An oscillation receiver disposed at the other end away from the oscillation generator receives the first mechanical shear wave and the second mechanical shear wave, and obtains an actual first oscillation intensity and an actual second oscillation intensity corresponding to the first mechanical shear wave and the second mechanical shear wave, respectively; The basic tension of the line to be detected is obtained based on the tension sensor, and the corresponding maximum ice thickness of the line to be detected is obtained based on the basic tension, the actual first oscillation intensity and the actual second oscillation intensity.

[0044] In some embodiments, the system is configured to: Obtaining a basic tension of the line to be detected based on the tension sensor, and obtaining a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity, including: Based on historical data, multiple sets of corresponding basic tension, actual first oscillation intensity, and actual second oscillation intensity are obtained when different maximum ice thicknesses are present on the line to be tested; Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated, and the trained target neural network model is output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension.

[0045] In some embodiments, the system is configured to: Obtaining a basic tension of the line to be detected based on the tension sensor, and obtaining a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity, including: Based on historical data, the corresponding basic tension, actual first oscillation intensity, and actual second oscillation intensity are obtained when the maximum ice thickness on the line to be tested is 0; Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated, and the trained target neural network model is output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension, and also includes: When the maximum ice thickness on the line to be tested is 0, the corresponding basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed.

[0046] In some embodiments, the system is configured to: Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated. The trained target neural network model is then output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, actual second oscillation intensity, and basic tension, including: The actual first oscillation intensity, the actual second oscillation intensity, and the basic tension are taken as three different dimensions, and the dimension vectors are retained for connection. The three dimensions are connected to form a characteristic vector corresponding to the maximum ice thickness; Multiple sets of basic tension, actual first oscillation intensity and actual second oscillation intensity are imported into the neural network training model and iterative calculation is performed. When the preset conditions are met during the iterative calculation process, the calculation is stopped and the trained target neural network model is output.

[0047] In some embodiments, the system is configured to: Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are imported into the neural network training model and iteratively calculated. When the preset conditions are met during the iterative calculation process, the calculation is stopped and the trained target neural network model is output, including: Multiple sets of basic tension, actual first shock intensity and actual second shock intensity are divided into two sets: training set and validation set; The neural network model is trained based on the data in the training set, and is verified based on the data in the verification set. When the verification result meets the preset conditions, the target neural network model is output.

[0048] In some embodiments, the system is configured to: Multiple sets of basic tension, actual first oscillation intensity, and actual second oscillation intensity are divided into two sets: a training set and a validation set, wherein the data in the training set and the validation set are different.

[0049] In some embodiments, the system is configured to: The neural network model is trained based on the data in the training set, and is verified based on the data in the validation set. When the verification result meets the preset conditions, the target neural network model is output, including: Perform iterative calculations based on the data in the training set, and generate a conditional neural network model during each iterative calculation process; Import the data in the validation set into the conditional neural network model and obtain multiple error values; Get multiple error values ​​corresponding to the validation set and get the average error value of the multiple error values; When the average error value is less than the preset value, the calculation is stopped and the conditional neural network model is used as the target neural network model and output.

[0050] An embodiment of the present application proposes an online monitoring system for transmission line icing based on multi-sensor fusion. Dual-polarization mechanical shear waves are formed by an oscillation generator and an oscillation receiver arranged at both ends of the transmission line to be detected. The system is combined with a tension sensor to train a neural network to achieve the purpose of predicting the maximum ice thickness.

[0051] Based on the same inventive concept, an embodiment of the present application further provides an electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the online monitoring method for transmission line icing based on multi-sensor fusion according to an embodiment of the present application.

[0052] In addition, to achieve the above-mentioned purpose, an embodiment of the present application also proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the online monitoring method for icing of transmission lines based on multi-sensor fusion of the embodiment of the present application is implemented.

[0053] The following is a detailed introduction to the various components of electronic equipment: The term "processor" refers to the control center of an electronic device and can be a single processor or a collective term for multiple processing elements. For example, the processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0054] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0055] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0056] Alternatively, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and be coupled to the processor via an interface circuit of the electronic device, and this is not specifically limited in the embodiments of the present invention.

[0057] A transceiver is used to communicate with network devices or terminal devices.

[0058] Optionally, the transceiver may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0059] Optionally, the transceiver may be integrated with the processor, or may exist independently and be coupled to the processor via an interface circuit of the router, which is not specifically limited in the embodiment of the present invention.

[0060] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiment, and will not be repeated here.

[0061] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), but may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0062] It should also be understood that the memory in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0063] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). A computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0064] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0065] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0066] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0067] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of 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. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

Claims

1. A method for online monitoring of ice coating on power transmission lines based on multi-sensor fusion, characterized in that: Applicable to a transmission line icing monitoring device, the transmission line icing monitoring device includes an oscillation generator, an oscillation receiver, a tension sensor and a control terminal. The method is applicable to the control terminal and includes: controlling the oscillation generator disposed at one end of the line to be inspected to generate a first mechanical shear wave and a second mechanical shear wave transmitted along the line to be inspected, wherein the directions of perpendicular lines between the peaks of the first mechanical shear wave and the second mechanical shear wave and the central axis of the line to be inspected are first and second directions, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity, and the oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities; receiving the first mechanical shear wave and the second mechanical shear wave based on the oscillation receiver disposed at the other end away from the oscillation generator, and obtaining an actual first oscillation intensity and an actual second oscillation intensity corresponding to the first mechanical shear wave and the second mechanical shear wave, respectively; A basic tension of the line to be detected is obtained based on the tension sensor, and a corresponding maximum ice thickness of the line to be detected is obtained based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity.

2. The method for online monitoring of ice coating on power transmission lines based on multi-sensor fusion according to claim 1, characterized in that: Obtaining a basic tension of the line to be detected based on the tension sensor, and obtaining a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity, including: Acquire, based on historical data, multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity corresponding to different maximum ice thicknesses on the line to be detected; Multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity are imported into a neural network training model and iteratively calculated, and a trained target neural network model is output. The target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, the actual second oscillation intensity, and the basic tension.

3. The method for online monitoring of ice coating on power transmission lines based on multi-sensor fusion according to claim 2, characterized in that: Obtaining a basic tension of the line to be detected based on the tension sensor, and obtaining a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity, including: Acquire, based on historical data, the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity corresponding to when the maximum ice thickness on the line to be detected is 0; Importing multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity into a neural network training model and performing iterative calculations, and outputting a trained target neural network model, wherein the target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, the actual second oscillation intensity, and the basic tension, further comprising: When the maximum ice thickness on the line to be detected is 0, the corresponding basic tension, the actual first oscillation intensity, and the actual second oscillation intensity are introduced into the neural network training model and iterative calculation is performed.

4. The method for online monitoring of ice coating on power transmission lines based on multi-sensor fusion according to claim 3 is characterized in that: Importing multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity into a neural network training model and performing iterative calculations, and outputting a trained target neural network model, wherein the target neural network model is used to output the predicted maximum ice thickness based on the input actual first oscillation intensity, the actual second oscillation intensity, and the basic tension, including: The actual first oscillation intensity, the actual second oscillation intensity, and the basic tension are taken as three different dimensions, and the dimension vectors are retained for connection, and the three dimensions are connected to form a characteristic vector corresponding to the maximum ice cover thickness; Multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity are imported into a neural network training model and iteratively calculated. When a preset condition is met during the iterative calculation, the calculation is stopped and the trained target neural network model is output.

5. The method for online monitoring of ice coating on power transmission lines based on multi-sensor fusion according to claim 4, characterized in that: Importing multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity into a neural network training model and performing iterative calculations, and when a preset condition is met during the iterative calculation, stopping the calculation and outputting the trained target neural network model, including: Dividing the multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity into two sets: a training set and a validation set; The neural network model is trained based on the data in the training set, and the neural network model is verified based on the data in the verification set. When the verification result meets the preset conditions, the target neural network model is output.

6. The method for online monitoring of ice coating on power transmission lines based on multi-sensor fusion according to claim 5, characterized in that: The multiple sets of the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity are divided into two sets: a training set and a validation set, wherein the data in the training set is different from the data in the validation set.

7. The method for online monitoring of ice coating on power transmission lines based on multi-sensor fusion according to claim 5, characterized in that: The neural network model is trained based on the data in the training set, and the neural network model is verified based on the data in the verification set. When the verification result meets the preset conditions, the target neural network model is output, including: Performing iterative calculations based on the data in the training set, and generating a conditional neural network model during each iterative calculation; Importing the data in the validation set into the conditional neural network model and obtaining multiple error values; Obtaining a plurality of error values ​​corresponding to the validation set, and obtaining an average error value of the plurality of error values; When the average error value is less than a preset value, the calculation is stopped, and the conditional neural network model is used as the target neural network model and output.

8. A transmission line icing monitoring device, characterized in that: The transmission line icing monitoring device includes: A tension sensor is provided at one end of the power transmission line to be detected and is used to monitor the tension of the power transmission line to be detected; an oscillation generator and an oscillation receiver, wherein the oscillation generator is disposed at one end of the power transmission line to be detected, and the oscillation receiver is disposed at an end of the power transmission line to be detected away from the oscillation generator, the oscillation generator being configured to generate a first mechanical shear wave and a second mechanical shear wave transmitted along the direction of the power transmission line to be detected, wherein the directions of perpendicular lines between the crests of the first mechanical shear wave and the second mechanical shear wave and the central axis of the power transmission line to be detected are first and second directions, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity, the oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities, and the oscillation receiver receives the first mechanical shear wave and the second mechanical shear wave; and A control terminal is communicatively connected to the tension sensor, the vibration receiver, and the vibration generator, and is used to execute the method according to any one of claims 1 to 7.

9. An online monitoring system for ice coating on power transmission lines based on multi-sensor fusion, characterized in that: The system comprises an oscillation generator, an oscillation receiver, a tension sensor and a control terminal, and is configured as follows: The control terminal controls the oscillation generator disposed at one end of the line to be detected to generate a first mechanical shear wave and a second mechanical shear wave transmitted along the line to be detected, wherein perpendicular directions between the crests of the first mechanical shear wave and the second mechanical shear wave and the central axis of the line to be detected are a first direction and a second direction, the first direction is opposite to the direction of gravity, and the second direction is perpendicular to the direction of gravity, and the oscillation intensities of the first mechanical shear wave and the second mechanical shear wave are both initial oscillation intensities; The control terminal receives the first mechanical shear wave and the second mechanical shear wave based on the oscillation receiver disposed at the other end away from the oscillation generator, and obtains an actual first oscillation intensity and an actual second oscillation intensity corresponding to the first mechanical shear wave and the second mechanical shear wave, respectively; The control terminal obtains a basic tension of the line to be detected based on the tension sensor, and obtains a corresponding maximum ice thickness of the line to be detected based on the basic tension, the actual first oscillation intensity, and the actual second oscillation intensity.

10. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to at least one of the processors; The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors to enable the at least one processor to execute the method according to any one of claims 1 to 7.

Images