Millimeter wave radar power transmission line icing monitoring system and method

Abstract

The invention relates to the technical field of power system safety monitoring, and provides a millimeter wave radar power transmission line icing monitoring system and method, which can perform all-weather icing monitoring under complex meteorological conditions (such as rain, snow and fog). Frequency domain features are extracted through fast Fourier transform (FFT), inversion of the icing thickness is carried out in combination with algorithms such as support vector regression (SVR), and the icing thickness on the power transmission line can be accurately obtained in real time. Through the wide coverage characteristic of the millimeter wave radar, a large-range power transmission line can be monitored. Compared with a locally installed optical fiber sensor, the system can cover a wider line area by arranging a small amount of radar equipment, the monitoring range is expanded to tens of kilometers, and the installation and maintenance cost of the equipment is greatly reduced; when the icing thickness of the power transmission line and the icing thickness increasing speed of the power transmission line exceed a set safety threshold value, an alarm is triggered to remind a maintainer to clean the line.

Description

Technical Field

[0001] The present invention relates to the technical field of power system safety monitoring, and in particular to a millimeter wave radar transmission line icing monitoring system and method. Background Art

[0002] In the power transmission system, the safe and stable operation of the transmission line is crucial to the power supply. However, the transmission lines are usually erected in outdoor environments and exposed to severe weather conditions for a long time. When encountering low temperature and humid weather conditions, the transmission lines are very easy to be covered with ice. The icing of the transmission line increases the weight of the transmission line, which will cause serious accidents such as line breakage and tower collapse. In addition, the icing of the transmission line will also increase the resistance of the transmission line, resulting in a decrease in transmission efficiency. Therefore, the monitoring and early warning of the icing of the transmission line is very important for the power industry.

[0003] In the prior art, there are mainly the following methods for detecting ice coating on transmission lines:

[0004] 1. Traditional manual inspection method: through patrol or infrared thermal imaging technology to determine the icing condition of transmission lines; this method has the defects of low efficiency, poor real-time performance and being limited by environmental conditions. In addition, the reason for icing of transmission lines is the bad weather. Manual inspection in bad weather is prone to unexpected situations.

[0005] 2. Video surveillance and image recognition technology: Some systems use video surveillance equipment to monitor transmission lines in real time, and combine image processing algorithms to analyze ice coverage; however, video surveillance systems are prone to failure in weather conditions with low visibility such as fog, rain and snow, and have limited coverage, making it difficult to meet the detection needs of large-scale transmission lines.

[0006] 3. Fiber optic sensing technology: By installing fiber optic sensors on the transmission line, line deformation caused by icing can be detected; however, fiber optic sensors are complex to install and have high maintenance costs. In addition, since fiber optic sensors can only monitor locally, they cannot cover the entire transmission line.

[0007] Although these existing technologies have solved the ice detection problem to a certain extent, there are still problems and defects in practical applications, such as poor real-time performance, that is, manual and video monitoring depends on weather and personnel conditions, and cannot achieve all-weather monitoring, limited monitoring range, that is, traditional methods are difficult to conduct all-round monitoring of transmission lines in a wide area, there are monitoring blind spots, poor adaptability to severe weather, that is, under severe weather conditions such as rain, snow, fog and haze, the detection effect of technologies such as video monitoring and fiber optic sensors is significantly reduced. High cost and complex maintenance, that is, the installation and maintenance costs of fiber optic sensors and other equipment are high, which increases the difficulty of overall operation and maintenance.

[0008] The existing ice monitoring technology is difficult to fully meet the actual application needs, especially under severe weather conditions. Traditional methods are ineffective and difficult to provide efficient and accurate real-time monitoring. Therefore, there is an urgent need for a transmission line ice monitoring system that can operate stably and effectively under various weather conditions and has high precision and low cost.

[0009] Based on this, the present invention proposes a transmission line icing monitoring method and system based on millimeter-wave radar, which utilizes the penetration ability and high-resolution characteristics of millimeter-wave radar and combines signal processing technology to overcome the shortcomings of the prior art and can realize real-time monitoring and early warning of transmission line icing under severe weather conditions. Summary of the invention

[0010] The purpose of the present invention is to overcome the shortcomings of the prior art and to provide a millimeter-wave radar transmission line icing monitoring system and method. The system and method utilize the penetration ability and high-resolution characteristics of millimeter-wave radar, combined with signal processing technology, to overcome the shortcomings of the prior art and to achieve real-time monitoring and early warning of icing on transmission lines under severe weather conditions.

[0011] In order to achieve the above object, the present invention adopts the following technical solutions:

[0012] A millimeter wave radar transmission line icing monitoring system, comprising: a millimeter wave radar module, a signal processing module, an ice thickness inversion module, a real-time monitoring module, a communication module and a visualization module;

[0013] The millimeter wave radar module is used to transmit millimeter wave electromagnetic signals and receive echo signals reflected from the surface of the transmission line, and output the echo signals reflected from the surface of the transmission line to the signal processing module:

[0014] The signal processing module is used to receive the echo signal output by the millimeter wave radar module, pre-process the echo signal and extract the backscattering coefficient, phase angle and amplitude of the echo signal, and output the backscattering coefficient, phase angle and amplitude of the echo signal to the ice thickness inversion module;

[0015] The ice thickness inversion module is used to output the ice thickness on the transmission line according to the scattering coefficient, phase angle and amplitude of the echo signal output by the signal processing module in combination with the ice thickness inversion model, and output the ice thickness data on the transmission line to the real-time monitoring module;

[0016] The real-time monitoring module is used to determine whether there is abnormal icing based on the ice thickness data output by the ice thickness inversion module, and trigger an alarm if abnormal icing exists, and output the alarm information and ice thickness data to the communication module;

[0017] The communication module is used to transmit the alarm information and ice thickness data to the remote monitoring center in real time through wireless communication so as to enable the power system management personnel to monitor and analyze;

[0018] The visualization module is used to display alarm information and ice thickness data.

[0019] Preferably, the millimeter wave radar module is carried by a drone or other flying platform.

[0020] Preferably, the ice thickness inversion model is obtained based on the following method:

[0021] Step 1: Data collection: collecting echo signals of transmission lines under different ice thicknesses to form a sample set;

[0022] Step 2: Data preprocessing: cleaning and standardizing the collected echo signals;

[0023] Step 3, echo signal feature extraction: extract the backscattering coefficient, phase angle and amplitude of the pre-processed echo signal; assemble the backscattering coefficient, frequency domain phase and amplitude information features into a feature vector as the input of the subsequent model;

[0024] Step 4, training an ice thickness inversion model; using a support vector regression model, training an ice thickness inversion model whose input is a feature vector and output is ice thickness, and cross-validation is used to optimize hyperparameters during the training process;

[0025] Step 5: Use the validation set to test the inversion effect of the ice thickness inversion model; set the target accuracy of the test set to more than 95%.

[0026] Preferably, the feature extraction in step 3 comprises the following steps:

[0027] The echo signal is converted into backscatter coefficient through time-frequency analysis and radar equation. The specific formula is as follows:

[0028]

[0029] Where P r is the received signal power, P t : The transmitted signal power, R is the distance from the radar to the target, G t , G r are the transmitting and receiving antenna gains, λ is the radar wavelength;

[0030] The preprocessed time domain echo signal is subjected to Fourier transform to generate a frequency domain echo signal, and the phase angle and amplitude information of the echo signal are extracted from the spectrum.

[0031] Preferably, the objective function of the support vector regression model in step 4 is as follows:

[0032] f(x)=w·φ(x)+b;

[0033] Where x is the feature vector, w is the weight, φ(x) is the nonlinear mapping function, and b is the bias; during the training process, the optimal w and b are found by minimizing the loss function.

[0034] Preferably, after step 5 is completed, actual field operation data are collected regularly and used to retrain the current inversion model; the existing model is slightly updated using new data, and the existing model weights or support vectors are fine-tuned using the newly added data.

[0035] Preferably, the real-time monitoring module analyzes the changes in ice thickness of the transmission line in real time during the monitoring process, and triggers an alarm when the thickness of ice thickness of the transmission line and the growth rate of ice thickness of the transmission line exceed a set safety threshold.

[0036] Another object of the present invention is to provide a millimeter wave radar transmission line icing monitoring method, using the above-mentioned millimeter wave radar transmission line icing monitoring system, comprising the following steps:

[0037] S1, inspection starts; the UAV millimeter wave radar module starts to inspect along the power transmission line and collect echo signals in real time;

[0038] S2, signal processing: pre-processing the collected echo signal through the signal processing module, removing noise and interference, and performing feature extraction;

[0039] S3, data analysis: passing the information to the ice thickness inversion module, and calculating the ice thickness through the ice thickness inversion model;

[0040] S4, monitoring and alarm; the real-time monitoring module updates the transmission line ice thickness data in real time, performs transmission line ice thickness trend analysis, and calculates the growth rate of transmission line ice thickness. Once the preset threshold is exceeded, the real-time monitoring module automatically triggers an alarm and sends information to the monitoring center through the communication module;

[0041] S5. Data transmission and feedback: All monitoring data and alarm information are transmitted to the remote monitoring center in real time, and operation and maintenance personnel obtain information through a visual interface.

[0042] Preferably, step S2 comprises the following steps:

[0043] S2.1, denoising processing; using a bandpass filter to remove out-of-band noise, and using wavelet transform to remove high-frequency noise in the echo signal; normalizing the signal amplitude to standardize the signal in each time period;

[0044] S2.2, feature extraction; the extracted features include backscattering coefficient, frequency domain phase, and amplitude information;

[0045] Backscatter coefficient, the echo signal is converted into the backscatter coefficient through time-frequency analysis and radar equation. The specific formula is as follows:

[0046]

[0047] Where P r is the received signal power, P t : The transmitted signal power, R is the distance from the radar to the target, G t , G r are the transmitting and receiving antenna gains, λ is the radar wavelength;

[0048] Frequency domain phase, by performing fast Fourier transform on the preprocessed signal, extracting frequency domain information, and calculating the frequency domain phase. The specific formula is as follows:

[0049] φ(f)=arg{X(f)};

[0050] Where X(f) is the complex spectrum obtained after FFT;

[0051] Amplitude information, calculate the amplitude information of the signal, as the intensity feature of the target, the amplitude can be directly extracted from the FFT result in the following form:

[0052] A(f) = |X(f)|;

[0053] S2.3, feature vector assembly: combine the backscatter coefficient, frequency domain phase and amplitude information into a feature vector; the number of extracted features is n, and the feature vector is expressed as:

[0054] F=[σ,φ(f1),A(f1),φ(f2),A(f2),…,φ(f n ),A(f n )] T ;

[0055] Among them, F is the feature vector, σ is the backscattering coefficient, φ(fi) is the phase angle of the i-th frequency domain signal; A(fi) is the amplitude information of the i-th frequency domain signal; n is the number of extracted features, which represents the resolution of the signal in the frequency domain.

[0056] The present invention discloses a millimeter wave radar transmission line icing monitoring system and method having the following beneficial effects.

[0057] The present invention can perform all-weather ice monitoring under complex meteorological conditions (such as rain, snow, fog, etc.). By extracting frequency domain features through fast Fourier transform (FFT), and combining support vector regression (SVR) and other algorithms to invert ice thickness, the ice thickness on the transmission line can be obtained in real time and accurately; the present invention can monitor a large range of transmission lines through the wide coverage characteristics of millimeter wave radar. Compared with locally installed fiber optic sensors, this system can cover a wider line area by deploying a small number of radar equipment, and the monitoring range is expanded to tens of kilometers, greatly reducing the installation and maintenance costs of the equipment; when the thickness of the ice on the transmission line and the growth rate of the ice on the transmission line exceed the set safety threshold, the present invention triggers an alarm to remind maintenance personnel to clean the line. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a structural schematic diagram of the millimeter wave radar transmission line icing monitoring system of the present invention.

[0059] Figure 2 This is a flow chart of the millimeter wave radar transmission line icing monitoring method of the present invention.

[0060] In the attached figure: 1. Wearable part; 11. Back buckle; 2. Safety rope; 3. Hook; 4. Monitoring host; 5. Monitoring auxiliary machine; 51. Array displacement sensor; 6. Handheld monitoring terminal. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0062] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0063] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0064] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0065] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0066] Example 1

[0067] Please refer to Figure 2 , a millimeter wave radar transmission line icing monitoring system, comprising: a millimeter wave radar module, a signal processing module, an ice thickness inversion module, a real-time monitoring module, a communication module and a visualization module;

[0068] The millimeter wave radar module is used to transmit millimeter wave electromagnetic signals and receive echo signals reflected from the surface of the transmission line, and output the echo signals reflected from the surface of the transmission line to the signal processing module: In the present application, SAR equipment is carried out on a drone or other flying platform to inspect above the transmission line to provide wide-area coverage of the entire line. The signal acquisition module of the SAR radar transmits electromagnetic waves to receive reflected signals from the surface of the transmission line and the surrounding environment. In particular, when ice is formed or foreign objects are attached, the reflection intensity and scattering characteristics of the signal will change. The echo data collected by the SAR radar has high spatial resolution and can accurately depict the geometry and surface state of the transmission line.

[0069] A signal processing module is used to receive the echo signal output by the millimeter wave radar module, pre-process the echo signal and extract the backscattering coefficient, phase angle and amplitude of the echo signal, and output the backscattering coefficient, phase angle and amplitude of the echo signal to the ice thickness inversion module;

[0070] An ice thickness inversion module is used to output the ice thickness on the transmission line according to the scattering coefficient, phase angle and amplitude of the echo signal output by the signal processing module in combination with the ice thickness inversion model, and output the ice thickness data on the transmission line to the real-time monitoring module;

[0071] A real-time monitoring module is used to determine whether there is abnormal icing based on the ice thickness data output by the ice thickness inversion module. If there is abnormal icing, an alarm is triggered and the alarm information and ice thickness data are output to the communication module.

[0072] In this embodiment, as a preferred real-time monitoring module, the change of ice thickness of the transmission line is analyzed in real time during the monitoring process. When the thickness of the ice thickness of the transmission line and the growth rate of the ice thickness of the transmission line exceed the set safety threshold, an alarm is triggered. When setting the threshold in this application, the ice thickness data of the historical transmission line is collected, a sample library is constructed, the distribution characteristics of the ice thickness in the sample library are analyzed, and the normal range and abnormal range are identified; the mean, standard deviation and extreme value of the sample data are calculated, and a statistical model of ice thickness is established; the normal thickness upper limit threshold Tupper is set according to the statistical results, and the mean plus 1 to 2 standard deviations represents the upper limit of the ice thickness under normal conditions; the abnormal thickness alarm threshold Talarm is the mean plus 3 standard deviations. If the ice thickness exceeds this value, it is considered abnormal; the growth rate threshold is set, by analyzing the change rate of ice thickness in historical data, the average growth rate of different time intervals (for example, 1 hour, 3 hours and 24 hours) is calculated, and the growth rate threshold Vthreshold is set. The calculation formula is:

[0073] Vthreshold = mean(Vhistorical) + k·std(Vhistorical); k is a user-defined empirical value ranging from 1 to 2;

[0074] Once the detected ice thickness or its growth rate exceeds the set threshold, the real-time monitoring module will trigger an alarm according to the following strategy:

[0075] When the ice thickness reaches the upper limit of normal thickness, Tupper, the system will send out an alarm signal indicating possible abnormal ice cover, prompting the monitoring personnel to pay attention.

[0076] When the ice thickness exceeds the abnormal thickness alarm threshold Talarm or the growth rate exceeds Vthreshold, the system automatically triggers an ice abnormality and immediately notifies the relevant maintenance personnel to conduct on-site inspections;

[0077] The communication module is used to transmit the alarm information and ice thickness data to the remote monitoring center in real time through wireless communication so as to monitor and analyze it for power system managers;

[0078] The visualization module is used to display alarm information and ice thickness data. In this embodiment, the visualization module is displayed in the form of a visualization chart, including a real-time thickness change curve, historical data comparison, and trend prediction chart. Users can intuitively view the ice status of the line through the interface. An alarm prompt pops up on the user interface, showing the abnormal ice area and providing specific time, thickness and other information to help operation and maintenance personnel handle it in a timely manner.

[0079] In this embodiment, the millimeter wave radar module is preferably carried by a drone or other flying platform.

[0080] In this embodiment, the preferred ice thickness inversion model is obtained based on the following method:

[0081] Step 1: Data collection: collecting echo signals of transmission lines under different ice thicknesses to form a sample set;

[0082] Step 2, data preprocessing; cleaning and standardizing the collected echo signals; in the present application, the echo signals are converted into digital signals by a high-speed analog-to-digital converter, and the environmental noise and non-target signals are removed by wavelet transform and adaptive filter, and the signal amplitude changes in different time periods are reduced by normalization processing.

[0083] Step 3: Extract echo signal features; extract the backscattering coefficient, phase angle and amplitude of the echo signal after preprocessing; assemble the backscattering coefficient, frequency domain phase and amplitude information features into a feature vector as the input of the subsequent model; define the target variable as the ice thickness H on the transmission line, calibrate it through field measurement, and establish a mapping relationship between the feature and the target variable;

[0084] In this embodiment, the feature extraction in step 3 preferably includes the following steps:

[0085] The echo signal is converted into backscatter coefficient through time-frequency analysis and radar equation. The specific formula is as follows:

[0086]

[0087] Where P r is the received signal power, P t : The transmitted signal power, R is the distance from the radar to the target, G t , G r are the transmitting and receiving antenna gains, λ is the radar wavelength;

[0088] The preprocessed time domain echo signal is subjected to Fourier transform to generate a frequency domain echo signal, and the phase angle and amplitude information of the echo signal are extracted from the spectrum. In this embodiment, the main calculation process of the Fourier transform (FFT) is to divide a long time domain signal sequence into two subsequences of even and odd positions. The Fourier transforms of these two subsequences are calculated separately (recursively). The Fourier transform results of the original sequence are obtained by weighted combination of the Fourier transform results of the even sequence and the odd sequence. The purpose of this part of the processing is to retain the signal characteristics related to ice coverage as much as possible, and to filter out irrelevant information such as noise and interference. The extracted features provide a reliable data basis for the subsequent inversion of ice thickness.

[0089] Step 4, training the ice thickness inversion model; using the support vector regression model, training an ice thickness inversion model with the input as the feature vector and the output as the ice thickness, cross-validation is used to optimize the hyperparameters during the training process; SVR has good generalization ability and is suitable for dealing with nonlinear problems; the collected sample data is divided into a training set, a validation set, and a test set with a ratio of 7:2:1; the SVR model is trained using the training set;

[0090] In this embodiment, the objective function of the support vector regression model in the preferred step 4 is as follows:

[0091] f(x)=w·φ(x)+b;

[0092] Where x is the feature vector, w is the weight, φ(x) is the nonlinear mapping function, and b is the bias. During the training process, the optimal w and b are found by minimizing the loss function.

[0093] Step 5: Use the validation set to test the inversion effect of the ice thickness inversion model; set the target accuracy of the test set to more than 95%.

[0094] In this embodiment, after the preferred step 5 is completed, the actual operation data of the field is collected regularly, and the current inversion model is retrained using the dynamic model update module using these data; the existing model is slightly updated using the new data, and the existing model weights or support vectors are fine-tuned using the newly added data. The actual ice cover conditions monitored (such as manually verified data) are compared with the prediction results of the ice thickness inversion model. If the prediction results of the ice thickness inversion model deviate greatly from the actual situation, the weights of the ice thickness inversion model are automatically updated to ensure that the ice thickness inversion model can always accurately reflect the actual situation on site; when large fluctuations or abnormal trends are detected in the ice monitoring results (such as a sudden increase or decrease in ice thickness), the abnormal detection mechanism will be triggered, and the ice thickness inversion model update program will be automatically started. The abnormal detection monitors the changing trend of the data in real time, and finds that the output of the ice thickness inversion model does not match the current environment. Then, the ice thickness inversion model is corrected through adaptive adjustment or model retraining to adapt it to the new environmental conditions.

[0095] Example 2

[0096] Based on Example 1, please refer to Figure 1 This embodiment provides a millimeter wave radar transmission line icing monitoring method, using the millimeter wave radar transmission line icing monitoring system in Example 1, including the following steps:

[0097] S1. Inspection starts; the UAV millimeter-wave radar module starts to inspect along the transmission line and collects echo signals in real time; in this application, GIS is used to plan the inspection route of the UAV to ensure that all transmission lines are covered. During the flight of the UAV, the SAR device transmits millimeter-wave signals, collects echo signals reflected from the transmission line and its surrounding environment, records data, and outputs the echo signals to the signal processing module;

[0098] S2, signal processing: pre-processing the collected echo signal through the signal processing module, removing noise and interference, and performing feature extraction;

[0099] In this embodiment, as a preferred step S2, the following steps are included:

[0100] S2.1, denoising processing; using a bandpass filter to remove out-of-band noise, and using wavelet transform to remove high-frequency noise in the echo signal; normalizing the signal amplitude to standardize the signal in each time period;

[0101] S2.2, feature extraction; the extracted features include backscattering coefficient, frequency domain phase, and amplitude information;

[0102] Backscatter coefficient, the echo signal is converted into the backscatter coefficient through time-frequency analysis and radar equation. The specific formula is as follows:

[0103]

[0104] Where P r is the received signal power, P t : The transmitted signal power, R is the distance from the radar to the target, G t , G r are the transmitting and receiving antenna gains, λ is the radar wavelength;

[0105] Frequency domain phase, by performing fast Fourier transform on the preprocessed signal, extracting frequency domain information, and calculating the frequency domain phase. The specific formula is as follows:

[0106] φ(f)=arg{X(f)};

[0107] Where X(f) is the complex spectrum obtained after FFT;

[0108] Amplitude information, calculate the amplitude information of the signal, as the intensity feature of the target, the amplitude can be directly extracted from the FFT result in the following form:

[0109] A(f) = |X(f)|;

[0110] S2.3, feature vector assembly: combine the backscatter coefficient, frequency domain phase and amplitude information into a feature vector; the number of extracted features is n, and the feature vector is expressed as:

[0111] F=[σ,φ(f1),A(f1),φ(f2),A(f2),…,φ(f n ),A(f n )] T ;

[0112] Among them, F is the feature vector, σ is the backscattering coefficient, φ(fi) is the phase angle of the i-th frequency domain signal; A(fi) is the amplitude information of the i-th frequency domain signal; n is the number of extracted features, indicating the resolution of the signal in the frequency domain; T represents the transposition operation, indicating that the feature vector F is in the form of a column vector;

[0113] S3, data analysis: passing the information to the ice thickness inversion module, calculating the ice thickness through the ice thickness inversion model, and filtering the ice thickness at each time point using the Kalman filter; the Kalman filter recursively calculates the optimal estimate of the current state; combining historical data and current measurements to provide a more accurate thickness prediction;

[0114] S4, monitoring and alarm; the real-time monitoring module updates the transmission line ice thickness data in real time, performs transmission line ice thickness trend analysis, and calculates the growth rate of transmission line ice thickness. Once the preset threshold is exceeded, the real-time monitoring module automatically triggers an alarm and sends information to the monitoring center through the communication module;

[0115] S5. Data transmission and feedback: All monitoring data and alarm information are transmitted to the remote monitoring center in real time, and operation and maintenance personnel obtain information through a visual interface.

[0116] Example 3

[0117] Based on Example 1-2, in this embodiment, a millimeter wave radar transmission line icing monitoring system is provided, and a foreign object recognition module is provided in the ice thickness inversion module, and the foreign object recognition module is used to identify foreign objects attached to the transmission line according to the echo data output by the millimeter wave radar module after being processed by the signal processing module, and output the identified foreign object information to the real-time monitoring module, and the real-time monitoring module transmits the foreign object information to the communication module, and the communication module transmits the foreign object information to the monitoring center;

[0118] In this embodiment, the signal processing module extracts geometric feature information of foreign objects and outputs it to the ice thickness inversion module;

[0119] The ice thickness inversion module is used to output the ice thickness and foreign object attachment information on the transmission line based on the scattering coefficient, phase angle and amplitude of the echo signal output by the signal processing module and the geometric characteristic information of the foreign object, combined with the ice thickness inversion model.

[0120] In this embodiment, based on the embodiment 1, the ice thickness inversion model is implemented by sharing features and multi-task learning to output the ice thickness and foreign matter adhesion information on the transmission line, which specifically includes the following steps:

[0121] Step 1: Feature selection: In the data preprocessing stage, distinguishing features are extracted through clustering, principal component analysis (PCA) and other methods, so as to jointly construct a more representative feature vector for ice thickness and foreign body attachment information;

[0122] F=[σ,φ(f1),A(f1),…,σ ice ,σ foreign ,…];

[0123] Among them, σice represents the characteristics related to ice layer, and σforeign represents the characteristics related to foreign matter;

[0124] Step 2: Joint model: use a shared neural network front end and then use two different output branches, one for ice thickness prediction and the other for foreign object identification.

[0125] During training, the loss function is a composite loss function, which includes two parts: mean square error and cross entropy, which are used for ice thickness inversion and foreign body recognition respectively. The details are as follows:

[0126] L=L ice +λL foreign ; Where Lice is the loss of ice thickness, Lforeign is the loss of foreign object recognition, and λ is the weight coefficient used to balance the impact of the two tasks;

[0127] Step 3, data set and training; data set preparation. During training, the data set contains the labeled ice thickness and foreign body type. Multiple measurements are performed to collect data in the same time period. The data set is divided into training set, validation set and test set in a ratio of 7:2:1.

[0128] The alternating training method is adopted to optimize the ice thickness and foreign object recognition loss in each training round. The output of the ice thickness inversion model after training includes: ice thickness, foreign object type (such as branches, plastic bags, etc.). The ice thickness inversion model can ensure that foreign objects are not confused with ice.

[0129] Example 4

[0130] Based on Embodiments 1-3, this embodiment provides a millimeter wave radar transmission line icing monitoring method, using the millimeter wave radar transmission line icing monitoring system in Embodiments 1-3, including the following steps:

[0131] S1. Inspection starts; the UAV millimeter-wave radar module starts to inspect along the transmission line and collects echo signals in real time; in this application, GIS is used to plan the inspection route of the UAV to ensure that all transmission lines are covered. During the flight of the UAV, the SAR device transmits millimeter-wave signals, collects echo signals reflected from the transmission line and its surrounding environment, records data, and outputs the echo signals to the signal processing module;

[0132] S2, signal processing: pre-processing the collected echo signal through the signal processing module, removing noise and interference, and performing feature extraction;

[0133] S3, data analysis: passing the information to the ice thickness inversion module, calculating the ice thickness through the ice thickness inversion model, and performing foreign body identification;

[0134] S4, monitoring and alarm; the real-time monitoring module updates the transmission line ice thickness data and foreign body attachment information in real time, performs transmission line ice thickness trend analysis, and calculates the growth rate of transmission line ice thickness. Once the preset threshold is exceeded, the real-time monitoring module automatically triggers an alarm and sends information to the monitoring center through the communication module; at the same time, if there is foreign body attachment information, the real-time monitoring module sends the foreign body category information to the monitoring center through the communication module;

[0135] S5. Data transmission and feedback: All monitoring data and alarm information are transmitted to the remote monitoring center in real time, and operation and maintenance personnel obtain information through a visual interface.

[0136] The above are only preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The substitution may be a substitution of a part of the structure, device, method step, or a complete technical solution. The equivalent replacement or change according to the technical solution and the inventive concept of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A millimeter wave radar transmission line ice monitoring system, characterized in that: include: Millimeter wave radar module, signal processing module, ice thickness inversion module, real-time monitoring module, communication module and visualization module; The millimeter wave radar module is used to transmit millimeter wave electromagnetic signals and receive echo signals reflected from the surface of the transmission line, and output the echo signals reflected from the surface of the transmission line to the signal processing module: The signal processing module is used to receive the echo signal output by the millimeter wave radar module, pre-process the echo signal and extract the backscattering coefficient, phase angle and amplitude of the echo signal, and output the backscattering coefficient, phase angle and amplitude of the echo signal to the ice thickness inversion module; The ice thickness inversion module is used to output the ice thickness on the transmission line according to the scattering coefficient, phase angle and amplitude of the echo signal output by the signal processing module in combination with the ice thickness inversion model, and output the ice thickness data on the transmission line to the real-time monitoring module; The real-time monitoring module is used to determine whether there is abnormal icing based on the ice thickness data output by the ice thickness inversion module, and trigger an alarm if abnormal icing exists, and output the alarm information and ice thickness data to the communication module; The communication module is used to transmit the alarm information and ice thickness data to the remote monitoring center in real time through wireless communication so as to enable the power system management personnel to monitor and analyze; The visualization module is used to display alarm information and ice thickness data.

2. The millimeter wave radar transmission line icing monitoring system according to claim 1, characterized in that: The millimeter wave radar module is carried by a drone or other flying platform.

3. The millimeter wave radar transmission line icing monitoring system according to claim 1, characterized in that: The ice thickness inversion model is obtained based on the following method: Step 1: Data collection: collecting echo signals of transmission lines under different ice thicknesses to form a sample set; Step 2: Data preprocessing: cleaning and standardizing the collected echo signals; Step 3, echo signal feature extraction: extract the backscattering coefficient, phase angle and amplitude of the pre-processed echo signal; assemble the backscattering coefficient, frequency domain phase and amplitude information features into a feature vector as the input of the subsequent model; Step 4, training an ice thickness inversion model; using a support vector regression model, training an ice thickness inversion model whose input is a feature vector and output is ice thickness, and cross-validation is used to optimize hyperparameters during the training process; Step 5: Use the validation set to test the inversion effect of the ice thickness inversion model; set the target accuracy of the test set to more than 95%.

4. The millimeter wave radar transmission line icing monitoring system according to claim 3, characterized in that: The feature extraction in step 3 includes the following steps: The echo signal is converted into backscatter coefficient through time-frequency analysis and radar equation. The specific formula is as follows: Where P r is the received signal power, P t : The transmitted signal power, R is the distance from the radar to the target, G t , G r are the transmitting and receiving antenna gains, λ is the radar wavelength; The preprocessed time domain echo signal is subjected to Fourier transform to generate a frequency domain echo signal, and the phase angle and amplitude information of the echo signal are extracted from the spectrum.

5. The millimeter wave radar transmission line icing monitoring system according to claim 3, characterized in that: The objective function of the support vector regression model in step 4 is as follows: f(x)=w·φ(x))+b; Where x is the feature vector, w is the weight, φ(x) is the nonlinear mapping function, and b is the bias; During the training process, the optimal w and b are found by minimizing the loss function.

6. The millimeter wave radar transmission line icing monitoring system according to claim 3, characterized in that: After step 5 is completed, actual field operation data is collected regularly and used to retrain the current inversion model; the existing model is slightly updated using new data, and the existing model weights or support vectors are fine-tuned using the newly added data.

7. The millimeter wave radar transmission line icing monitoring system according to claim 1, characterized in that: The real-time monitoring module analyzes the changes in the ice thickness of the transmission line in real time during the monitoring process, and triggers an alarm when the thickness of the ice thickness of the transmission line and the growth rate of the ice thickness of the transmission line exceed a set safety threshold.

8. A method for monitoring ice coating on a transmission line using a millimeter wave radar, using the millimeter wave radar monitoring ice coating on a transmission line according to any one of claims 1 to 7, characterized in that: The steps include: S1, inspection starts; the UAV millimeter wave radar module starts to inspect along the power transmission line and collect echo signals in real time; S2, signal processing: pre-processing the collected echo signal through the signal processing module, removing noise and interference, and performing feature extraction; S3, data analysis: passing the information to the ice thickness inversion module, and calculating the ice thickness through the ice thickness inversion model; S4, monitoring and alarm; The real-time monitoring module updates the transmission line ice thickness data in real time, performs transmission line ice thickness trend analysis, and calculates the growth rate of transmission line ice thickness. Once the preset threshold is exceeded, the real-time monitoring module automatically triggers an alarm and sends information to the monitoring center through the communication module; S5. Data transmission and feedback: All monitoring data and alarm information are transmitted to the remote monitoring center in real time, and operation and maintenance personnel obtain information through a visual interface.

9. The millimeter wave radar transmission line icing monitoring system according to claim 8, characterized in that: The step S2 comprises the following steps: S2.1, denoising processing; using a bandpass filter to remove out-of-band noise, and using wavelet transform to remove high-frequency noise in the echo signal; normalizing the signal amplitude to standardize the signal in each time period; S2.2, feature extraction; the extracted features include backscattering coefficient, frequency domain phase, and amplitude information; Backscatter coefficient, the echo signal is converted into the backscatter coefficient through time-frequency analysis and radar equation. The specific formula is as follows: Where P r is the received signal power, P t : The transmitted signal power, R is the distance from the radar to the target, G t , G r are the transmitting and receiving antenna gains, λ is the radar wavelength; Frequency domain phase, by performing fast Fourier transform on the preprocessed signal, extracting frequency domain information, and calculating the frequency domain phase. The specific formula is as follows: φ(f)=arg{X(f)}; Where X(f) is the complex spectrum obtained after FFT; Amplitude information, calculate the amplitude information of the signal, as the intensity feature of the target, the amplitude can be directly extracted from the FFT result in the following form: A(f) = |X(f)|; S2.3, feature vector assembly: combine the backscatter coefficient, frequency domain phase and amplitude information into a feature vector; the number of extracted features is n, and the feature vector is expressed as: F=[σ,φ(f1),A(f1),φ(f2),A(f2),...,φ(f n ),A(f n )] T ; Among them, F is the feature vector, σ is the backscattering coefficient, φ(fi) is the phase angle of the i-th frequency domain signal; A(fi) is the amplitude information of the i-th frequency domain signal; n is the number of extracted features, which represents the resolution of the signal in the frequency domain.

Images