Millimeter wave radar power transmission line clustering system and method

Abstract

The invention discloses a millimeter wave radar power transmission line clustering system and method, relates to the technical field of radar signal processing and power transmission line monitoring, and aims to solve the defects of the prior art in the aspects of monitoring precision, efficiency, all-weather monitoring and the like and improve the reliability and intelligent level of a power transmission line monitoring system. The system comprises a millimeter wave radar module, a signal processing module, a clustering and classification module and a risk early warning module. Foreign matter identification and icing monitoring of the power transmission line are carried out based on the millimeter wave radar, and the system has high resolution and strong penetrating power and can work stably under complex weather conditions. By combining a K-means + + algorithm, a mahalanobis distance and other methods, foreign matters and ice coating on the power transmission line can be accurately classified and identified; according to the system, the recognition accuracy of different targets in a complex scene is improved, the problems of false detection and missing detection in a traditional method are reduced, meanwhile, automatic real-time monitoring can be achieved, the manual intervention requirement is reduced, and the monitoring efficiency and the power transmission line maintenance safety are greatly improved.

Description

Technical Field

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

[0002] As electricity demand continues to grow, the safe operation and efficient monitoring of transmission lines have become increasingly important. Currently, traditional transmission line monitoring methods mainly rely on optical sensors, video surveillance systems, and manual inspections. These methods can meet basic monitoring needs to a certain extent, but there are many limitations in practical applications.

[0003] Optical sensors and video surveillance systems perform poorly in adverse weather conditions (such as fog, rain, snow, etc.), resulting in a significant decrease in monitoring effectiveness. This environmental impact makes it difficult for the monitoring system to achieve all-weather real-time monitoring, which in turn affects the safety of transmission lines. This limitation is particularly prominent in complex or changeable natural environments, where potential safety hazards cannot be discovered in a timely manner.

[0004] On the other hand, manual inspection as a traditional monitoring method, although it can provide direct detection and feedback, is inefficient and time-consuming, especially in rugged terrain or adverse weather conditions, where inspectors face greater safety risks. This not only increases operating and maintenance costs, but also exposes inspectors to potential dangers.

[0005] Although the existing low-frequency radar monitoring system has a certain degree of penetration and can provide valuable monitoring information in some cases, its resolution is relatively low, making it difficult to effectively identify small foreign objects or ice on the transmission line, especially in complex environments, and prone to missed detection or misjudgment. This problem of insufficient resolution directly leads to the monitoring system's insufficient ability to deal with small targets and cannot meet the safety supervision needs of modern power transmission.

[0006] In addition, the existing monitoring system still lacks intelligent clustering and classification algorithms, making it difficult to effectively distinguish between multiple types of risks. For example, there are obvious differences between different types of foreign objects and snow and ice, but due to the limitations of conventional monitoring methods, it is difficult for the system to quickly and accurately identify and classify them. This makes the monitoring system insufficient in processing power when facing complex scenarios, and it cannot automatically and real-time classify and respond to possible threats.

[0007] In summary, the current transmission line monitoring technology has the following key technical problems:

[0008] Poor environmental adaptability: Traditional optical sensors and video surveillance have poor monitoring effects in bad weather conditions, affecting safety. Inefficiency: Manual inspections are time-consuming, inefficient, and pose safety risks. Insufficient resolution: Low-frequency radar monitoring systems have low resolution and are difficult to identify small foreign objects or ice in complex environments. Insufficient intelligence: Lack of effective clustering and classification algorithms makes it impossible to quickly and accurately identify and classify different types of risks.

[0009] The existence of these technical problems urgently needs to be solved through innovative monitoring technologies and intelligent algorithms to improve the safety monitoring level of transmission lines. Summary of the invention

[0010] To solve the above problems, the present invention proposes a millimeter wave radar transmission line clustering system and method, which performs foreign body identification and ice coverage monitoring on transmission lines based on millimeter wave radar, has high resolution and strong penetration ability, can work stably under complex weather conditions such as clouds, fog, rain, snow, etc., and provides all-weather and all-time monitoring capabilities; by combining millimeter wave radar with intelligent clustering algorithm, using methods such as K-means++ algorithm and Mahalanobis distance, it can accurately classify and identify foreign bodies and ice coverage on transmission lines; through this system, the distance metric and clustering method can be adaptively adjusted to improve the recognition accuracy of different targets (such as bird nests, plastic bags, ice coverage, etc.) in complex scenes, reduce the problems of false detection and missed detection in traditional methods, and at the same time, the system can realize automatic real-time monitoring, reduce the need for manual intervention, and greatly improve the monitoring efficiency and the safety of transmission line maintenance; solve the deficiencies of the existing technology in monitoring accuracy, efficiency and all-weather monitoring, and improve the reliability and intelligence level of the transmission line monitoring system.

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

[0012] A millimeter wave radar power transmission line clustering system, the millimeter wave radar power transmission line clustering system comprising a millimeter wave radar module, a signal processing module, a clustering and classification module and a risk warning module;

[0013] The millimeter-wave radar module is electrically connected to the external antenna, and includes a millimeter-wave radar antenna, a receiving module and a transmitter; the signal processing module is electrically connected to the millimeter-wave radar module, and includes an amplifier, a filter, and a signal preprocessing circuit; the clustering and classification module is electrically connected to the signal processing module, and includes a K-means++ algorithm module, a DBSCAN algorithm module, and an analog-to-digital converter ADC; the risk warning module is electrically connected to the clustering and classification module, and is internally provided with a risk assessment calculation circuit, an alarm mechanism module, a storage unit, and a wireless communication module, and the risk warning module is connected to the remote monitoring center through a signal interface.

[0014] A millimeter wave radar transmission line clustering method, which is based on the above-mentioned millimeter wave radar transmission line clustering system, comprises the following steps:

[0015] Step 1: Data collection: The millimeter-wave radar module continuously monitors foreign objects or ice on the transmission line under severe weather conditions based on the high-frequency band. The millimeter-wave radar module transmits millimeter-wave signals and receives echo signals reflected from the target.

[0016] Step 2: Signal preprocessing: sending the received radar echo signal to the signal processing module for denoising, enhancement and feature extraction; the signal processing module uses amplifiers and filters to process the signal to remove environmental noise and enhance the target echo signal;

[0017] Step 3: Convert analog signal to digital signal. The clustering and classification module converts the processed analog signal into a digital signal through an analog-to-digital converter (ADC).

[0018] Step 4: Feature extraction: The signal processing module extracts important features from the digital signal, including signal strength, time delay, and spectrum features. Feature extraction reduces the dimension of the original data and retains the features that have the greatest impact on the clustering results.

[0019] Step 5 Cluster analysis: The clustering and classification module applies the K-means++ algorithm to perform preliminary clustering and divide the data into different clusters based on features such as intensity and time delay. Then, the clustering results are further processed using the DBSCAN algorithm to identify areas with lower density and filter out noise.

[0020] Step 6: Accurate classification: The clustering and classification module uses Mahalanobis distance to accurately classify the clustering results to further distinguish the differences between foreign objects and ice cover characteristics, and compares the statistical characteristics of each cluster with the known categories to determine the target type; the Mahalanobis distance is used to evaluate the similarities and differences between different clusters, so that the system can effectively distinguish and classify data in high-dimensional space and improve the accuracy of classification;

[0021] Step 7: Risk assessment and early warning: The classification results are passed to the risk early warning module to evaluate the risk level of each target and conduct a comprehensive analysis based on historical data. Once a high-risk target is detected, the system immediately triggers the alarm mechanism and records detailed information. Through real-time risk assessment, potential dangers can be discovered in a timely manner to ensure the safety of transmission lines and reduce the possibility of accidents.

[0022] Furthermore, the echo signal collected in step 1 contains characteristics such as the location information and intensity information of the target, providing basic information for subsequent data processing and analysis.

[0023] Furthermore, in the signal preprocessing process of step 2, the filter is a Butterworth, Chebyshev or elliptic filter, and the transfer function of the low-pass filter is:

[0024]

[0025] Where H(f) is the frequency response of the filter; f is the frequency; f c is the cut-off frequency; n is the filter order;

[0026] Apply a filter to perform a convolution filter on a signal:

[0027] x'(t)=∫x(τ)·h(t-τ)dτ

[0028] In the formula, x'(t) is the output signal after filtering; x(τ) is the input signal; h(t-τ) is the impulse response of the filter; τ is the integral variable, which represents a delay in time; dτ is the integral element, which represents a small change in the time variable τ;

[0029] After filtering, the low-frequency part of the signal is retained.

[0030] Furthermore, in the signal preprocessing process of step 2, the environmental noise is removed by using wavelet denoising, which includes the following steps:

[0031] Step 2.1 Signal decomposition: Perform discrete wavelet transform on the input signal x(t) and decompose it into wavelet coefficients of different scales, including approximate component A and detail component D; the formula is:

[0032]

[0033] In the formula, c j,k is the wavelet coefficient; x(t) is the input signal; is the mother wavelet function of the jth layer, and k is the translation factor;

[0034] Step 2.2 Threshold processing: Apply soft threshold or hard threshold rule to the detail component D to remove noise:

[0035] Soft Thresholding:

[0036]

[0037] Hard Threshold:

[0038]

[0039] Where D' is the detail component after threshold processing; sign(D) represents the sign function of D; |D| is the amplitude of the detail component; λ is the threshold value, which is set according to the noise level or signal-to-noise ratio; D represents the detail component of the input signal or image;

[0040] Step 2.3 Signal reconstruction: Use the denoised wavelet coefficients to perform inverse wavelet transform and reconstruct the denoised signal:

[0041]

[0042] Where x'(t) is the signal generated based on the denoised wavelet coefficients; c j,k is the wavelet coefficient; is the mother wavelet function of the jth layer, k is the translation factor; t is the time; represents the summation over all scales j and positions k.

[0043] Further, in the signal preprocessing process of step 2, the target echo signal is enhanced, including the following steps:

[0044] Step 201 Adaptive gain control AGC: AGC enhances weak echo signals by dynamically adjusting signal gain; the gain function is:

[0045]

[0046] Where G(t) is the gain; α is the gain adjustment coefficient; x(t) is the input signal; |x(t)| is the amplitude of the signal x(t);

[0047] Enhanced signal:

[0048] x′(t)=G(t)·x(t)

[0049] In the formula, x'(t) is the enhanced signal; G(t) is the gain; x(t) is the input signal;

[0050] Optimize dynamic range to ensure that the enhanced signal does not exceed the system dynamic range;

[0051] Step 202 Fourier transform enhancement: enhancing specific frequency components of the echo signal through frequency domain analysis;

[0052] Through Fourier transform, the signal is transformed from the time domain to the frequency domain;

[0053] X(f)=∫x(t)e -j2πft dt

[0054] Where X(f) is the frequency domain signal; x(t) is the input signal; e -j2πft is a complex exponential function; e is the base of the natural logarithm; j is the imaginary unit; f is the frequency; t is the time;

[0055] Enhance specific frequency components:

[0056] X'(f)=W(f)·X(f)

[0057] Where X'(f) is the enhanced frequency domain signal; W(f) is the gain function; X(f) is the frequency domain signal;

[0058] The calculation formula of the gain function W(f) is as follows:

[0059]

[0060] Where, f is the frequency; exp() is the exponential function; f0 is the target frequency; σ is the bandwidth;

[0061] The enhanced signal is converted from the frequency domain back to the time domain by inverse Fourier transform:

[0062] x'(t)=∫X'(f)e j2πft df

[0063] Where x'(t) is the enhanced signal; X'(f) is the enhanced frequency domain signal e j2πft is a complex exponential function; f is the frequency.

[0064] Furthermore, in step 5, during the cluster analysis, the K-means++ algorithm is applied for preliminary clustering to divide the data into different clusters based on features such as intensity and time delay, including the following steps:

[0065] Step 5.1, randomly select a data point as the first cluster center;

[0066] Step 5.2, calculate the square distance between each data point and the nearest selected cluster center to generate a probability distribution;

[0067] Step 5.3, select the next cluster center according to the probability distribution of distance, and points with farther distance are given higher weights;

[0068] Step 5.4, repeat steps 5.2 and 5.3 until k initial cluster centers are selected;

[0069] Step 5.5, use the K-means algorithm to optimize the clustering results according to the preset iterative formula; the calculation formula of the K-means algorithm is as follows:

[0070]

[0071] In the formula, μ j is the centroid of the jth cluster; |C j | is the number of points in the cluster; Indicates that it belongs to the jth cluster C j All sample points x in i Perform summation; x i is the jth cluster C j The sample points in .

[0072] Furthermore, in the cluster analysis process of step 5, the DBSCAN algorithm can identify dense areas in the data and identify discrete points as noise, effectively processing outliers in millimeter wave data and improving monitoring effects under severe weather conditions;

[0073] Use the DBSCAN algorithm to process the clustering results, identify areas with lower density and filter out noise, including the following steps:

[0074] Step 501, randomly select an unvisited data point from the data set;

[0075] Step 502, calculating the number of all data points within the neighborhood of the data point with a radius of ε;

[0076] Step 503, MinPts is the minimum number of neighboring points that form a core point; if the number of neighboring points is greater than or equal to MinPts, the point is marked as a core point and a new cluster is created;

[0077] Step 504, if the number of neighbor points is less than MinPts, the point is marked as a noise point;

[0078] Step 505, check all the neighboring points of the core point, if a point in the neighborhood is also a core point, then add the neighboring points of the core point to the same cluster; in this way, gradually expand the cluster until no more points can be added;

[0079] Step 506, repeating steps 501 to 503, and continuing to select unvisited data points until all points are visited and marked as belonging to a cluster or noise.

[0080] Furthermore, in the precise classification process of step 6, the Mahalanobis distance is introduced as a new distance measurement method. The Mahalanobis distance takes into account the correlation between various features and can better handle non-spherical data distribution. By calculating the Mahalanobis distance between each data point and the cluster center, the classification accuracy of foreign matter and ice cover is effectively improved.

[0081] The calculation formula of Mahalanobis distance is as follows:

[0082]

[0083] Where, d M (x,μ) represents the Mahalanobis distance between the sample point vector x and the mean vector μ; x is the sample point vector to be classified; μ is the mean vector of the data, which is the center of the cluster or the mean of the category; Σ is the covariance matrix of the data; Σ -1 is the inverse of the covariance matrix; (x-μ) T Represents the transpose of the difference vector between x and the mean μ.

[0084] Furthermore, in step 7, risk assessment and early warning, the specific implementation of the risk early warning module is as follows:

[0085] Step 7.1 Data reception and processing: Data reception and processing is the starting point of the risk warning module; the risk warning module continuously receives analysis data from the clustering and classification module through the interface. The analysis data includes:

[0086] Target type, target size, target location, and reflection characteristics; the risk warning module performs data verification and preprocessing to remove possible noise and erroneous data;

[0087] Step 7.2 Risk Assessment: The early warning module uses a risk assessment algorithm to analyze the current situation based on the received data; the risk assessment algorithm is as follows:

[0088] R=ω1·S+ω2·P+ω3·E

[0089] Where R is the generated risk score; S is the target size; P is the relative distance between the target location and the transmission line; E is the environmental condition; ω1, ω2, ω3 are weight coefficients;

[0090] Determine the risk score based on the risk assessment algorithm and express the assessment result in a numerical way;

[0091] Step 7.3 Risk level classification: After generating the risk score, the early warning module classifies the risk level, including:

[0092] High risk: large bird nests or ice cover, immediate action is required;

[0093] Medium risk: Generates a prompt message to notify maintenance personnel to conduct a careful inspection;

[0094] Low risk: Recorded, no active notification for the time being;

[0095] Step 7.4 Report generation and historical data management: The early warning module can automatically generate a detailed detection report based on the detected targets and risk assessment results; the report will include: the specific location of the target, type information, occurrence time, risk level, and recommended treatment measures; the report is output in PDF or other electronic format for management personnel to review;

[0096] In addition, the warning module stores all warning records in the database to form a historical data management system; the historical data management system supports storage and retrieval; based on the historical data management system, maintenance personnel analyze the line conditions in different time periods according to historical data and optimize inspection and maintenance strategies.

[0097] Compared with the prior art, the millimeter wave radar transmission line clustering system and method has the following beneficial effects:

[0098] The present invention significantly improves the efficiency and accuracy of detecting foreign objects and ice on power transmission lines by introducing millimeter wave radar technology combined with intelligent clustering algorithms. Millimeter wave radar has high resolution and strong penetration ability, can work stably in severe weather such as fog, rain, and snow, and is not affected by light and environment, ensuring that the system can achieve all-weather and all-time monitoring to ensure the safety of power transmission lines.

[0099] Compared with traditional optical sensors or low-frequency radars, the present invention is more accurate and can accurately distinguish between foreign objects such as bird nests and plastic bags and targets such as ice through the backscattered signals collected by the millimeter-wave radar, effectively reducing missed detections and misjudgments and improving the reliability of monitoring.

[0100] In terms of intelligent algorithms, the present invention combines the K-means++ algorithm with the Mahalanobis distance, adaptively adjusts the classification criteria, and processes non-spherical data distribution, thus improving the accuracy of foreign matter and ice classification. The introduction of the DBSCAN algorithm further enhances the system's ability to handle noise and abnormal data, ensuring the stability of monitoring results in complex scenarios.

[0101] The present invention not only reduces the need for manual inspections and reduces maintenance costs, but also improves the safety and operating efficiency of transmission lines. In particular, it can still provide efficient and accurate monitoring under extreme weather conditions, and has significant social and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0103] Figure 1 It is a schematic diagram of the overall structure of the millimeter wave radar transmission line clustering system of the present invention;

[0104] Figure 2 This is a flow chart of the millimeter wave radar transmission line clustering method of the present invention;

[0105] Figure 3 This is a working flow chart of the risk warning module of the millimeter wave radar transmission line clustering system of the present invention. DETAILED DESCRIPTION

[0106] The following will be combined with the drawings of the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without creative work are within the scope of protection of the present invention.

[0107] Example 1

[0108] In view of several key issues in the existing power transmission line monitoring technology, this embodiment provides a millimeter wave radar power transmission line clustering system, such as Figure 1 As shown, the millimeter wave radar transmission line clustering system includes a millimeter wave radar module, a signal processing module, a clustering and classification module and a risk warning module;

[0109] Among them, the millimeter-wave radar module is electrically connected to the external antenna, and includes a millimeter-wave radar antenna, a receiving module and a transmitter; the signal processing module is electrically connected to the millimeter-wave radar module, and includes an amplifier, a filter, and a signal preprocessing circuit; the clustering and classification module is electrically connected to the signal processing module, and includes a K-means++ algorithm module, a DBSCAN algorithm module, and an analog-to-digital converter ADC; the risk warning module is electrically connected to the clustering and classification module, and is internally provided with a risk assessment calculation circuit, an alarm mechanism module, a storage unit, and a wireless communication module, and the risk warning module is connected to the remote monitoring center through a signal interface.

[0110] Millimeter-wave radar module: The millimeter-wave radar module is responsible for continuously collecting echo signals on the transmission line. The module is electrically connected to the external antenna, and the antenna transmits the echo signal to the receiving module of the millimeter-wave radar module. The millimeter-wave radar module operates in the high-frequency band, has high resolution and strong penetration ability, and can monitor foreign objects or ice on the transmission line under severe weather conditions (such as rain, snow, fog, etc.). The signal transmission path is: radar antenna → millimeter-wave radar module → signal processing module.

[0111] Signal processing module: The received radar echo signal is first transmitted to the signal processing module, which performs signal preprocessing, including: denoising, echo enhancement and feature extraction. The core circuit of the signal processing module includes an amplifier, a filter, and a signal preprocessing circuit, which is used to enhance the target echo signal and filter the interference signal. The processed data is electrically connected to the interface of the clustering and classification module, and the cleaned signal is transmitted to the clustering and classification module.

[0112] Clustering and classification module: The clustering and classification module includes K-means++ algorithm module, DBSCAN algorithm module, and analog-to-digital converter ADC; K-means++ algorithm is an improved K-means clustering algorithm, which is mainly used for preliminary clustering; DBSCAN algorithm (Density-Based Spatial Clustering of Applications with Noise) is a density-based spatial clustering algorithm that can effectively process noise data algorithms, which are used for preliminary clustering and identification of density anomaly areas respectively. The clustering and classification module converts analog signals into digital signals through the analog-to-digital converter ADC to facilitate subsequent digital processing. The analog signals output by the signal processing module are converted into digital signals and input into the clustering algorithm. The K-means++ algorithm performs clustering analysis based on the echo characteristics of the target, such as intensity and time delay, and the DBSCAN algorithm is used to filter abnormal noise. Finally, the Mahalanobis distance is used to further distinguish the characteristic differences between foreign objects and ice cover, so as to achieve accurate classification; Mahalanobis distance is a way to measure the distance between different sample points, which is particularly suitable for processing data related to different dimensions. The output data of this clustering and classification module is transmitted to the risk warning module through the communication interface.

[0113] Risk warning module: The risk warning module is equipped with a risk assessment calculation circuit, an alarm mechanism module, a storage unit, and a wireless communication module; it receives the output of the clustering and classification module and evaluates the risk level of the target based on the classification result. The module uses the internal calculation circuit and historical data to conduct a comprehensive analysis of the danger of the target. The risk warning module is connected to the remote monitoring center through a signal interface. When a high-risk target is detected, the module will immediately trigger the alarm mechanism and send a warning signal to the remote monitoring center. At the same time, the system generates a detailed detection report, records the target type, location and risk level, and transmits the report to the maintenance team through the wireless communication module. In addition, the internal storage unit of the module saves all historical data for future analysis.

[0114] The workflow of the millimeter-wave radar transmission line clustering system is as follows: the millimeter-wave radar module first collects the reflected signal on the transmission line and pre-processes it through the signal processing module. The processed data is input into the clustering and classification module, and the algorithm is used to extract features and classify and analyze them, and finally transmitted to the risk warning module for evaluation and warning. Each module is electrically connected to form a complete closed-loop system, which can automatically and real-time monitor and warn of foreign objects and ice on the transmission line in the actual environment.

[0115] The high-resolution characteristics of the millimeter-wave radar ensure the effective identification of small targets on the transmission line, while the denoising and enhancement functions of the signal processing module greatly reduce the interference of environmental noise on the system. The intelligent algorithm in the clustering and classification module further ensures the accurate classification of foreign objects and ice in complex scenes, and the Mahalanobis distance plays an important role in distinguishing foreign objects from ice. The risk warning module generates warning signals in real time through comprehensive analysis of system output data, and records and analyzes historical data, which greatly improves the safety and monitoring efficiency of transmission lines.

[0116] Example 2

[0117] Based on the millimeter wave radar transmission line clustering system provided in Example 1, this embodiment provides a millimeter wave radar transmission line clustering method, such as Figure 2 As shown, the millimeter wave radar transmission line clustering method includes the following steps:

[0118] Step 1: Data collection: The millimeter wave radar module continuously monitors foreign objects or ice on the transmission line based on the high frequency band under severe weather conditions. The millimeter wave radar module transmits millimeter wave signals and receives echo signals reflected from the target. The collected echo signals contain the location information, intensity information and other characteristics of the target, providing basic information for subsequent data processing and analysis.

[0119] Step 2: Signal preprocessing: the received radar echo signal is sent to the signal processing module for denoising, enhancement and feature extraction; the signal processing module uses amplifiers and filters to process the signal to remove environmental noise and enhance the target echo signal.

[0120] During the signal preprocessing, the filter is a Butterworth, Chebyshev or elliptic filter, and the transfer function of the low-pass filter is:

[0121]

[0122] Where H(f) is the frequency response of the filter; f is the frequency; f c is the cut-off frequency; n is the filter order;

[0123] Apply a filter to perform a convolution filter on a signal:

[0124] x'(t)=∫x(τ)·h(t-τ)dτ

[0125] In the formula, x'(t) is the output signal after filtering; x(τ) is the input signal; h(t-τ) is the impulse response of the filter; τ is the integral variable, which represents a delay in time; dτ is the integral element, which represents a small change in the time variable τ;

[0126] After filtering, the low-frequency part of the signal is retained.

[0127] Furthermore, in the signal preprocessing process, wavelet denoising is used to remove environmental noise, including the following steps:

[0128] Step 2.1 Signal decomposition: Perform discrete wavelet transform on the input signal x(t) and decompose it into wavelet coefficients of different scales, including approximate component A and detail component D; the formula is:

[0129]

[0130] In the formula, c j,k is the wavelet coefficient; x(t) is the input signal; is the mother wavelet function of the jth layer, and k is the translation factor;

[0131] Step 2.2 Threshold processing: Apply soft threshold or hard threshold rule to the detail component D to remove noise:

[0132] Soft Thresholding:

[0133]

[0134] Hard Threshold:

[0135]

[0136] Where D' is the detail component after threshold processing; sign(D) represents the sign function of D; |D| is the amplitude of the detail component; λ is the threshold value, which is set according to the noise level or signal-to-noise ratio; D represents the detail component of the input signal or image;

[0137] Step 2.3 Signal reconstruction: Use the denoised wavelet coefficients to perform inverse wavelet transform and reconstruct the denoised signal:

[0138]

[0139] Where x'(t) is the signal generated based on the denoised wavelet coefficients; c j,k is the wavelet coefficient; is the mother wavelet function of the jth layer, k is the translation factor; t is the time; represents the summation over all scales j and positions k.

[0140] Furthermore, in the signal preprocessing process, the target echo signal is enhanced, including the following steps:

[0141] Step 201 Adaptive gain control AGC: AGC enhances weak echo signals by dynamically adjusting signal gain; the gain function is:

[0142]

[0143] Where G(t) is the gain; α is the gain adjustment coefficient; x(t) is the input signal; |x(t)| is the amplitude of the signal x(t);

[0144] Enhanced signal:

[0145] x′(t)=G(t)·x(t)

[0146] In the formula, x'(t) is the enhanced signal; G(t) is the gain; x(t) is the input signal;

[0147] Optimize dynamic range to ensure that the enhanced signal does not exceed the system dynamic range;

[0148] Step 202 Fourier transform enhancement: enhancing specific frequency components of the echo signal through frequency domain analysis;

[0149] Through Fourier transform, the signal is transformed from the time domain to the frequency domain;

[0150] X(f)=∫x(t)e -j2πft dt

[0151] Where X(f) is the frequency domain signal; x(t) is the input signal; e -j2πft is a complex exponential function; e is the base of the natural logarithm; j is the imaginary unit; f is the frequency; t is the time;

[0152] Enhance specific frequency components:

[0153] X'(f)=W(f)·X(f)

[0154] Where X'(f) is the enhanced frequency domain signal; W(f) is the gain function; X(f) is the frequency domain signal;

[0155] The calculation formula of the gain function W(f) is as follows:

[0156]

[0157] Where, f is the frequency; exp() is the exponential function; f0 is the target frequency; σ is the bandwidth;

[0158] The enhanced signal is converted from the frequency domain back to the time domain by inverse Fourier transform:

[0159] x'(t)=∫X'(f)e j2πft df

[0160] Where x'(t) is the enhanced signal; X'(f) is the enhanced frequency domain signal e j2πft is a complex exponential function; f is the frequency.

[0161] Step 3: Convert analog signal to digital signal. The clustering and classification module converts the processed analog signal into a digital signal through an analog-to-digital converter (ADC).

[0162] Step 4: Feature extraction: The signal processing module extracts important features from the digital signal, including signal strength, time delay, and spectrum characteristics; feature extraction is used to reduce the dimension of the original data and retain the features that have the greatest impact on the clustering results.

[0163] Step 5 Cluster analysis: The clustering and classification module applies the K-means++ algorithm for preliminary clustering, dividing the data into different clusters based on features such as intensity and time delay; then, the clustering results are further processed using the DBSCAN algorithm to identify low-density areas and filter noise.

[0164] During the cluster analysis, the K-means++ algorithm was used for preliminary clustering to divide the data into different clusters based on features such as intensity and time delay, including the following steps:

[0165] Step 5.1, randomly select a data point as the first cluster center;

[0166] Step 5.2, calculate the square distance between each data point and the nearest selected cluster center to generate a probability distribution;

[0167] Step 5.3, select the next cluster center according to the probability distribution of distance, and points with farther distance are given higher weights;

[0168] Step 5.4, repeat steps 5.2 and 5.3 until k initial cluster centers are selected;

[0169] Step 5.5, use the K-means algorithm to optimize the clustering results according to the preset iterative formula; the calculation formula of the K-means algorithm is as follows:

[0170]

[0171] In the formula, μ j is the centroid of the jth cluster; |C j | is the number of points in the cluster; Indicates that it belongs to the jth cluster C j All sample points x in i Perform summation; x i is the jth cluster C j The sample points in .

[0172] During the cluster analysis process, the DBSCAN algorithm can identify dense areas in the data and identify discrete points as noise, effectively processing outliers in millimeter wave data and improving monitoring results under severe weather conditions;

[0173] Use the DBSCAN algorithm to process the clustering results, identify areas with lower density and filter out noise, including the following steps:

[0174] Step 501, randomly select an unvisited data point from the data set;

[0175] Step 502, calculating the number of all data points within the neighborhood of the data point with a radius of ;

[0176] Step 503, MinPts is the minimum number of neighboring points that form a core point; if the number of neighboring points is greater than or equal to MinPts, the point is marked as a core point and a new cluster is created;

[0177] Step 504, if the number of neighbor points is less than , then the point is marked as a noise point;

[0178] Step 505, check all the neighboring points of the core point, if a point in the neighborhood is also a core point, then add the neighboring points of the core point to the same cluster; in this way, gradually expand the cluster until no more points can be added;

[0179] Step 506, repeating steps 501 to 503, and continuing to select unvisited data points until all points are visited and marked as belonging to a cluster or noise.

[0180] Step 6: Accurate classification. The clustering and classification module uses the Mahalanobis distance to accurately classify the clustering results to further distinguish the differences in foreign objects and ice cover characteristics, and compares the statistical characteristics of each cluster with the known categories to determine the target type; the Mahalanobis distance is used to evaluate the similarities and differences between different clusters, so that the system can effectively distinguish and classify data in high-dimensional space and improve the accuracy of classification.

[0181] In the precise classification process, the Mahalanobis distance is introduced as a new distance measurement method. The Mahalanobis distance takes into account the correlation between various features and can better handle non-spherical data distribution. By calculating the Mahalanobis distance between each data point and the cluster center, the classification accuracy of foreign matter and ice cover is effectively improved.

[0182] The calculation formula of Mahalanobis distance is as follows:

[0183]

[0184] Where, d M (x,μ) represents the Mahalanobis distance between the sample point vector x and the mean vector μ; x is the sample point vector to be classified; μ is the mean vector of the data, which is the center of the cluster or the mean of the category; Σ is the covariance matrix of the data; Σ -1 is the inverse of the covariance matrix; (x-μ) TRepresents the transpose of the difference vector between x and the mean μ.

[0185] Step 7: Risk assessment and early warning: The classification results are passed to the risk early warning module to evaluate the risk level of each target and conduct a comprehensive analysis based on historical data. Once a high-risk target is detected, the system immediately triggers the alarm mechanism and records detailed information. Through real-time risk assessment, potential dangers can be discovered in a timely manner to ensure the safety of transmission lines and reduce the possibility of accidents.

[0186] In risk assessment and early warning, the specific implementation of the risk early warning module is as follows:

[0187] Step 7.1 Data reception and processing: Data reception and processing is the starting point of the risk warning module; the risk warning module continuously receives analysis data from the clustering and classification module through the interface. The analysis data includes:

[0188] Target type, target size, target location, and reflection characteristics; the risk warning module performs data verification and preprocessing to remove possible noise and erroneous data;

[0189] Step 7.2 Risk Assessment: Figure 3 As shown, the early warning module uses a risk assessment algorithm to analyze the current situation based on the received data; the risk assessment algorithm is as follows:

[0190] R=ω1·S+ω2·P+ω3·E

[0191] Where R is the generated risk score; S is the target size; P is the relative distance between the target location and the transmission line; E is the environmental condition; ω1, ω2, ω3 are weight coefficients;

[0192] Determine the risk score based on the risk assessment algorithm and express the assessment result in a numerical way;

[0193] Step 7.3 Risk level classification: After generating the risk score, the early warning module classifies the risk level, including:

[0194] High risk: large bird nests or ice cover, immediate action is required;

[0195] Medium risk: Generates a prompt message to notify maintenance personnel to conduct a careful inspection;

[0196] Low risk: Recorded, no active notification for the time being;

[0197] Step 7.4 Report generation and historical data management: The early warning module can automatically generate a detailed detection report based on the detected targets and risk assessment results; the report will include: the specific location of the target, type information, occurrence time, risk level, and recommended treatment measures; the report is output in PDF or other electronic format for management personnel to review;

[0198] In addition, the warning module stores all warning records in the database to form a historical data management system; the historical data management system supports storage and retrieval; based on the historical data management system, maintenance personnel analyze the line conditions in different time periods according to historical data and optimize inspection and maintenance strategies.

[0199] In summary, the method and system for foreign body identification and ice monitoring on power transmission lines based on millimeter wave radar can solve several key problems in existing power transmission line monitoring technology. Millimeter wave radar has high resolution and strong penetration ability, and can work stably under complex weather conditions such as clouds, fog, rain, and snow, providing all-weather and all-time monitoring capabilities. By combining millimeter wave radar with intelligent clustering algorithms, using methods such as K-means++ algorithm and Mahalanobis distance, it is possible to accurately classify and identify foreign bodies and ice on transmission lines.

[0200] Through this system, the distance metric and clustering method can be adaptively adjusted to improve the recognition accuracy of different targets in complex scenes (such as bird nests, plastic bags, ice covers, etc.), and reduce the problems of false detection and missed detection in traditional methods. At the same time, the system can realize automatic real-time monitoring, reduce the need for manual intervention, and greatly improve the monitoring efficiency and the safety of transmission line maintenance; improve the deficiencies in monitoring accuracy, efficiency and all-weather monitoring, and improve the reliability and intelligence level of the transmission line monitoring system.

[0201] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A millimeter wave radar transmission line clustering system, characterized by: The millimeter wave radar transmission line clustering system includes a millimeter wave radar module, a signal processing module, a clustering and classification module, and a risk warning module; The millimeter-wave radar module is electrically connected to the external antenna, and includes a millimeter-wave radar antenna, a receiving module and a transmitter; the signal processing module is electrically connected to the millimeter-wave radar module, and includes an amplifier, a filter, and a signal preprocessing circuit; the clustering and classification module is electrically connected to the signal processing module, and includes a K-means++ algorithm module, a DBSCAN algorithm module, and an analog-to-digital converter ADC; the risk warning module is electrically connected to the clustering and classification module, and is internally provided with a risk assessment calculation circuit, an alarm mechanism module, a storage unit, and a wireless communication module, and the risk warning module is connected to the remote monitoring center through a signal interface.

2. A millimeter wave radar transmission line clustering method, the millimeter wave radar transmission line clustering method is based on the millimeter wave radar transmission line clustering system according to claim 1, characterized in that: The following steps are involved: Step 1: Data collection: The millimeter-wave radar module continuously monitors foreign objects or ice on the transmission line under severe weather conditions based on the high-frequency band. The millimeter-wave radar module transmits millimeter-wave signals and receives echo signals reflected from the target. Step 2: Signal preprocessing: sending the received radar echo signal to the signal processing module for denoising, enhancement and feature extraction; the signal processing module uses amplifiers and filters to process the signal to remove environmental noise and enhance the target echo signal; Step 3: Convert analog signal to digital signal. The clustering and classification module converts the processed analog signal into a digital signal through an analog-to-digital converter (ADC). Step 4: Feature extraction: The signal processing module extracts important features from the digital signal, including signal strength, time delay, and spectrum features. Feature extraction reduces the dimension of the original data and retains the features that have the greatest impact on the clustering results. Step 5 Cluster analysis: The clustering and classification module applies the K-means++ algorithm to perform preliminary clustering and divide the data into different clusters based on features such as intensity and time delay. Then, the clustering results are further processed using the DBSCAN algorithm to identify areas with lower density and filter out noise. Step 6: Accurate classification: The clustering and classification module uses Mahalanobis distance to accurately classify the clustering results to further distinguish the differences between foreign objects and ice cover characteristics, and compares the statistical characteristics of each cluster with the known categories to determine the target type; the Mahalanobis distance is used to evaluate the similarities and differences between different clusters, so that the system can effectively distinguish and classify data in high-dimensional space and improve the accuracy of classification; Step 7: Risk assessment and early warning: The classification results are passed to the risk early warning module to evaluate the risk level of each target and conduct a comprehensive analysis based on historical data. Once a high-risk target is detected, the system immediately triggers the alarm mechanism and records detailed information. Through real-time risk assessment, potential dangers can be discovered in a timely manner to ensure the safety of transmission lines and reduce the possibility of accidents.

3. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: The echo signal collected in step 1 contains the location information, intensity information and other characteristics of the target, providing basic information for subsequent data processing and analysis.

4. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: In the signal preprocessing process of step 2, the filter is a Butterworth, Chebyshev or elliptic filter, and the transfer function of the low-pass filter is: Where H(f) is the frequency response of the filter; f is the frequency; f c is the cut-off frequency; n is the filter order; Apply a filter to perform a convolution filter on a signal: In the formula, x'(t) is the output signal after filtering; x(τ) is the input signal; h(t-τ) is the impulse response of the filter; τ is the integral variable, which represents a delay in time; dτ is the integral element, which represents a small change in the time variable τ; After filtering, the low-frequency part of the signal is retained.

5. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: Step 2: In the signal preprocessing process, wavelet denoising is used to remove environmental noise, including the following steps: Step 2.1 Signal decomposition: Perform discrete wavelet transform on the input signal x(t) and decompose it into wavelet coefficients of different scales, including approximate component A and detail component D; the formula is: In the formula, c j,k is the wavelet coefficient; x(t) is the input signal; is the mother wavelet function of the jth layer, and k is the translation factor; Step 2.2 Threshold processing: Apply soft threshold or hard threshold rule to the detail component D to remove noise: Soft Thresholding: Hard Threshold: Where D' is the detail component after threshold processing; sign(D) represents the sign function of D; |D| is the amplitude of the detail component; λ is the threshold value, which is set according to the noise level or signal-to-noise ratio; D represents the detail component of the input signal or image; Step 2.3 Signal reconstruction: Use the denoised wavelet coefficients to perform inverse wavelet transform and reconstruct the denoised signal: Where x'(t) is the signal generated based on the denoised wavelet coefficients; c j,k is the wavelet coefficient; is the mother wavelet function of the jth layer, k is the translation factor; t is the time; represents the summation over all scales j and positions k.

6. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: Step 2: During the signal preprocessing process, the target echo signal is enhanced, including the following steps: Step 201 Adaptive gain control AGC: AGC enhances weak echo signals by dynamically adjusting signal gain; the gain function is: Where G(t) is the gain; α is the gain adjustment coefficient; x(t) is the input signal; |x(t)| is the amplitude of the signal x(t); Enhanced signal: x′(t)=G(t)·x(t) In the formula, x'(t) is the enhanced signal; G(t) is the gain; x(t) is the input signal; Optimize dynamic range to ensure that the enhanced signal does not exceed the system dynamic range; Step 202 Fourier transform enhancement: enhancing specific frequency components of the echo signal through frequency domain analysis; Through Fourier transform, the signal is transformed from the time domain to the frequency domain; X(f)=∫x(t)e -j2πft dt Where X(f) is the frequency domain signal; x(t) is the input signal; e -j2πft is a complex exponential function; e is the base of the natural logarithm; j is the imaginary unit; f is the frequency; t is the time; Enhance specific frequency components: X'(f)=W(f)·X(f) Where X'(f) is the enhanced frequency domain signal; W(f) is the gain function; X(f) is the frequency domain signal; The calculation formula of the gain function W(f) is as follows: Where, f is the frequency; exp() is the exponential function; f0 is the target frequency; σ is the bandwidth; The enhanced signal is converted from the frequency domain back to the time domain by inverse Fourier transform: x'(t)=∫X'(f)e j2πft df Where x'(t) is the enhanced signal; X'(f) is the enhanced frequency domain signal e j2πft is a complex exponential function; f is the frequency.

7. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: Step 5: In the cluster analysis process, the K-means++ algorithm is used for preliminary clustering to divide the data into different clusters based on features such as intensity and time delay, including the following steps: Step 5.1, randomly select a data point as the first cluster center; Step 5.2, calculate the square distance between each data point and the nearest selected cluster center to generate a probability distribution; Step 5.3, select the next cluster center according to the probability distribution of distance, and points with farther distance are given higher weights; Step 5.4, repeat steps 5.2 and 5.3 until k initial cluster centers are selected; Step 5.5, use the K-means algorithm to optimize the clustering results according to the preset iterative formula; the calculation formula of the K-means algorithm is as follows: In the formula, μ j is the centroid of the jth cluster; |C j | is the number of points in the cluster; Indicates that it belongs to the jth cluster C j All sample points x in i Perform summation; x i is the jth cluster C j The sample points in .

8. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: In step 5, during the cluster analysis, the DBSCAN algorithm can identify dense areas in the data and identify discrete points as noise, effectively processing outliers in millimeter wave data and improving monitoring results under severe weather conditions; Use the DBSCAN algorithm to process the clustering results, identify areas with lower density and filter out noise, including the following steps: Step 501, randomly select an unvisited data point from the data set; Step 502, calculating the number of all data points within the neighborhood of the data point with a radius of ε; Step 503, MinPts is the minimum number of neighboring points that form a core point; if the number of neighboring points is greater than or equal to MinPts, the point is marked as a core point and a new cluster is created; Step 504, if the number of neighbor points is less than MinPts, the point is marked as a noise point; Step 505, check all the neighboring points of the core point, if a point in the neighborhood is also a core point, then add the neighboring points of the core point to the same cluster; in this way, gradually expand the cluster until no more points can be added; Step 506, repeating steps 501 to 503, and continuing to select unvisited data points until all points are visited and marked as belonging to a cluster or noise.

9. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: In the precise classification process of step 6, the Mahalanobis distance is introduced as a new distance measurement method. The Mahalanobis distance takes into account the correlation between various features and can better handle non-spherical data distribution. By calculating the Mahalanobis distance between each data point and the cluster center, the classification accuracy of foreign matter and ice cover is effectively improved. The calculation formula of Mahalanobis distance is as follows: Where, d M (x,μ) represents the Mahalanobis distance between the sample point vector x and the mean vector μ; x is the sample point vector to be classified; μ is the mean vector of the data, which is the center of the cluster or the mean of the category; Σ is the covariance matrix of the data; Σ -1 is the inverse of the covariance matrix; (x-μ) T Represents the transpose of the difference vector between x and the mean μ.

10. The millimeter wave radar transmission line clustering method according to claim 2, characterized in that: In step 7, risk assessment and early warning, the specific implementation of the risk early warning module is as follows: Step 7.1 Data reception and processing: Data reception and processing is the starting point of the risk warning module; The risk warning module continuously receives analysis data from the clustering and classification module through the interface. The analysis data includes: target type, target size, target location, and reflection characteristics. The risk warning module performs data verification and preprocessing to remove possible noise and erroneous data. Step 7.2 Risk Assessment: The early warning module uses a risk assessment algorithm to analyze the current situation based on the received data; the risk assessment algorithm is as follows: R=ω1·S+ω2·P+ω3·E Where R is the generated risk score; S is the target size; P is the relative distance between the target location and the transmission line; E is the environmental condition; ω1, ω2, ω3 are weight coefficients; Determine the risk score based on the risk assessment algorithm and express the assessment result in a numerical way; Step 7.3 Risk level classification: After generating the risk score, the early warning module classifies the risk level, including: High risk: large bird nests or ice cover, immediate action is required; Medium risk: Generates a prompt message to notify maintenance personnel to conduct a careful inspection; Low risk: Recorded, no active notification for the time being; Step 7.4 Report generation and historical data management: The early warning module can automatically generate a detailed detection report based on the detected targets and risk assessment results; the report will include: the specific location of the target, type information, occurrence time, risk level, and recommended treatment measures; the report is output in PDF or other electronic format for management personnel to review; In addition, the warning module stores all warning records in the database to form a historical data management system; the historical data management system supports storage and retrieval; based on the historical data management system, maintenance personnel analyze the line conditions in different time periods according to historical data and optimize inspection and maintenance strategies.

Images