Intelligent spacer integrated with high-precision galloping amplitude and vibration frequency sensor

Abstract

The invention relates to the technical field of power transmission line monitoring, discloses an intelligent spacer integrated with a high-precision galloping amplitude and vibration frequency sensor, and aims to solve the problem of online monitoring of windage yaw and galloping frequency of an existing power transmission line. The intelligent spacer is composed of a spacer body, a supporting rod and a power transmission line buckle, and is equipped with a sensor, a Bluetooth device, a GPS device, a battery and a laser range finder. And the system can communicate with a background management system to realize real-time transmission and analysis of data. During monitoring, a plurality of intelligent spacers are installed to cover key monitoring points, vibration, position information and height changes of a power transmission line are obtained through a sensor, a GPS and a laser range finder, a background management system preprocesses collected data, a spectrogram is generated through time domain and frequency domain analysis, and the spectrogram is used for monitoring the power transmission line. And the variation trend of the galloping amplitude and the vibration frequency is analyzed, and a detailed monitoring report is finally formed, so that the precision and efficiency of state monitoring of the power transmission line are improved, and the method has important significance on safe operation of the power transmission line.

Description

Technical Field

[0001] The invention relates to the technical field of power transmission line monitoring, and in particular to an intelligent spacer rod integrated with high-precision dancing amplitude and vibration frequency sensors. Background Art

[0002] The intelligent spacer is a highly integrated device specially designed for online monitoring of the status of power transmission lines. The device not only integrates intelligent wireless sensors, but also monitors multiple key parameters in real time, including: Dancing monitoring: monitors the dancing of power transmission lines under wind power, so as to promptly detect potential safety hazards caused by dancing. Conductor temperature monitoring: real-time monitoring of the temperature changes of the conductor to ensure that it is within the safe working range to avoid damage caused by overheating. Conductor sag (distance to the ground) monitoring: ensure a safe distance between the conductor and the ground to prevent electric shock or short circuit accidents caused by too low sag.

[0003] As the scale of transmission lines continues to expand, traditional online monitoring systems for wind deviation and dancing frequency face a series of challenges, including: Complex device types: Existing systems usually include many different types of monitoring equipment, making the overall system complex and difficult to manage. Large and bulky size: Traditional monitoring equipment is often large and heavy, which adds an extra burden to the transmission line and may affect the overall stability of the line. Difficult installation: The presence of multiple devices makes the installation process complicated, time-consuming and human resources. Frequent maintenance: Different types of equipment have different repair and maintenance requirements, which increases the complexity and frequency of maintenance work. Huge power consumption: Traditional equipment usually consumes more electricity, affecting the overall energy efficiency of the transmission line.

[0004] Therefore, the development of intelligent spacers that integrate high-precision dancing amplitude and vibration frequency sensors will greatly improve the performance stability of the device, increase convenience and safety, provide effective assistance for the daily operation and maintenance of transmission lines, while improving monitoring performance and transmission efficiency, and enhancing the power supply reliability of transmission lines. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent spacer rod integrated with high-precision dancing amplitude and vibration frequency sensors, which solves the problems raised in the above-mentioned background technology.

[0006] The technical solution adopted by the present invention is:

[0007] An intelligent spacer with integrated high-precision dancing amplitude and vibration frequency sensors, comprising a spacer body, a support rod installed on the spacer body and extending outward, and a transmission line buckle installed at one end of the support rod away from the spacer body, wherein the spacer body can be installed on the transmission line through the buckle;

[0008] A sensor body and a Bluetooth device are installed on one side of the spacer body, a GPS device and a battery are installed on the other side, and a laser rangefinder is installed at the bottom; the sensor body, the GPS device and the laser rangefinder are all electrically connected to the Bluetooth device and the battery, are powered by the battery, and are communicated with the background management system through the Bluetooth device.

[0009] Furthermore, the spacer rod body is in the shape of a rectangular plate, and the support rod is installed at the four corners of the spacer rod body; the power transmission line buckle on the support rod includes a fixed buckle and a movable buckle, and the movable buckle is bolted to the fixed buckle.

[0010] Furthermore, the buckle is installed with a current transformer, and an electric energy metering device is installed on the other side of the spacer rod body. The current transformer is electrically connected to the electric energy metering device and the battery, and the electric energy metering device is communicated with the background management system via a Bluetooth device.

[0011] Furthermore, a photovoltaic power generation system is also provided on the spacer body; the photovoltaic power generation system includes a photovoltaic panel fixedly installed above the spacer body through a connecting rod, and an inverter and a power controller fixedly installed on the spacer body; the photovoltaic panel is electrically connected to the inverter, and the inverter is electrically connected to the power controller; the power controller is installed on the power supply line between the battery and the sensor body, the GPS device, and the laser rangefinder.

[0012] An online monitoring method for the state of a power transmission line, the online monitoring method for the state of a power transmission line is based on the above-mentioned intelligent spacer integrating high-precision dancing amplitude and vibration frequency sensors, and a background management system; and comprises the following steps:

[0013] Step 1: Install multiple intelligent spacers with integrated high-precision dancing amplitude and vibration frequency sensors on the transmission line to ensure that all important monitoring points are covered;

[0014] Step 2: Detect corresponding data through the sensor body, GPS device and laser rangefinder of the intelligent spacer at each detection point and transmit it to the background management system;

[0015] Step 3: The backend management system performs data preprocessing, time domain analysis and frequency domain analysis based on the data detected by the sensor body, GPS device and laser rangefinder, and finally generates a spectrum diagram;

[0016] Step 4: The background management system analyzes the changing trends of the dancing amplitude and vibration frequency based on the spectrum diagram, and generates a corresponding report based on the analysis results.

[0017] Further, in step 2, the sensor body of each intelligent spacer detects the vibration data of the power transmission line, the GPS device detects the longitude, latitude, and altitude data, and the laser rangefinder detects the straight-line distance and angle from the monitoring point to the ground;

[0018] The backend management system calculates the deviation between the actual moving direction of the object and the predetermined heading by analyzing the moving GPS trajectory, thereby obtaining the wind deviation data; based on the sensor body, it captures the acceleration and angular velocity of the transmission line in all directions, provides the dynamic characteristics of the transmission line when it is dancing, and cooperates with the height data detected by the laser rangefinder to monitor the changes in the height of the transmission line, and then calculates its up and down dancing data.

[0019] Further, in step 3, the data preprocessing process is as follows:

[0020] Step 1, continuous wavelet transform: by transforming the vibration signal of the transmission line on a continuous scale and a continuous translation, the formula is as follows:

[0021]

[0022] Among them, W x (a, b) are the wavelet coefficients of the transmission line vibration signal x(t) at scales a and b; x(t) is the original signal of the transmission line vibration signal; ψ * a,b (t) is the complex conjugate form of the mother wavelet function; t represents the time variable, usually the time of signal measurement;

[0023] It is defined as:

[0024]

[0025] Among them, a is the scale parameter, which is used to control the stretching or compression of the wavelet; b is the translation parameter, which is used to control the displacement of the wavelet in time; ψ(t) is the mother wavelet, and choosing different mother wavelets will affect the effect of the transformation;

[0026] Step 2, discrete wavelet transform DWT: Discrete wavelet transform DWT decomposes the signal into low-frequency and high-frequency parts of different frequency bands through multi-resolution analysis MRA. The decomposition process is based on the filter bank, and the formula is as follows:

[0027]

[0028] Where x[n] is the discrete input signal, c j [k] is the low-frequency component at the jth scale, i.e., the approximate coefficient; φ j,k (n) is the scaling function, corresponding to the output of the low-pass filter; d j [k] high-frequency component at the jth scale, i.e. detail coefficient; ψ j.k (n) is the wavelet function, corresponding to the output of the high-pass filter;

[0029] The calculation of discrete wavelet transform DWT is performed by Mallat algorithm, which gradually decomposes the signal into approximate signal and high detail signal. The formula is as follows:

[0030]

[0031] Among them, is the low-pass filter coefficient, used to extract the approximate signal; is the high-pass filter coefficient, used to extract the detail signal; is the low-frequency component of the j-th scale; is the high-frequency component of the j-th scale; k is the index of the filter, and the range depends on the filter length; n is the discrete time index, indicating the sample point position of the signal; j is the decomposition level or scale level;

[0032] Step 3, Inverse Discrete Wavelet Transform IDWT: To reconstruct the original signal from the discrete wavelet transform DWT decomposition result, an inverse discrete wavelet transform IDWT is required. The formula is as follows:

[0033]

[0034] Among them, c j+1 [n] is the reconstructed low-frequency component; c j [k] represents the low-frequency component of the j-th scale, i.e., the approximate signal; d j [k] represents the high-frequency component of the jth scale, i.e., the detail signal; n is the discrete time index of the reconstructed signal;

[0035] Step 4, data preprocessing and denoising: When using discrete wavelet transform DWT to denoise the transmission line vibration signal, the noise is removed by value processing of the detail coefficients. The formula is as follows:

[0036]

[0037] Among them, d j [k] is the high-frequency component after processing; λ is the set threshold, which is used to filter out noise smaller than this value.

[0038] Furthermore, in step 4, the background management system analyzes the changing trends of the dancing amplitude and vibration frequency based on the spectrum diagram, and comprehensively processes various monitoring data of the transmission line including vibration, position, and distance through multi-sensor data fusion and intelligent analysis; through data fusion, it can integrate data from the sensor body, GPS equipment and laser rangefinder to realize comprehensive analysis of information.

[0039] Further, multi-sensor data fusion includes the following steps:

[0040] Step 1, multi-sensor data collection: collect different types of data through the sensor body, GPS device and laser rangefinder respectively; suppose x1(t), x2(t), ...xn (t) are the observation values ​​of the sensor body, GPS device and laser rangefinder at time t respectively;

[0041] Step 2, data preprocessing: normalize the data collected by the sensor body, GPS device and laser rangefinder to eliminate the dimensional differences between different data sources. The formula is as follows:

[0042]

[0043] Among them, x i (t) is the standardized data; μ i is the mean value of the i-th sensor data; σ i is the standard deviation of the i-th sensor data;

[0044] Step 3: Weighted average fusion: Use the weighted average method to fuse data. The formula is as follows:

[0045]

[0046] Among them, x fused (t) is the fused data; ω i is the weight of the i-th sensor, satisfying

[0047] Step 4, Kalman filter fusion:

[0048] predict:

[0049] x k|k-1 =Ax k-1 +Bu k

[0050] P k|k-1 =AP k-1 A T +Q

[0051] Among them, x k|k-1 is the state prediction value at time k; A is the state transfer matrix; B is the control input matrix; uk is the control input; P k|k-1 is the prediction covariance matrix; Q is the process noise covariance matrix; A T for?

[0052] renew:

[0053] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0054] x k =xk|k-1 +K k (z k -Hx k|k-1 )

[0055] P k =(IK k H)P k|k-1

[0056] Among them, K k is the Kalman gain; H is the observation matrix; R is the observation noise covariance matrix; H T is the transpose of the observation matrix H; x k is the estimated value of the state at time k; z k is the sensor measurement value at the kth moment; P k is the estimated error covariance matrix at time k; I is the identity matrix;

[0057] Step 5: Feature extraction and data dimensionality reduction: fused (t) performing feature extraction, extracting time domain features including mean and variance, and frequency domain features including spectrum, amplitude, and frequency center;

[0058] Use principal component analysis PCA to reduce data dimension and reduce data redundancy. The formula is as follows:

[0059] Z=XW

[0060] Among them, Z is the data matrix after dimension reduction; X is the original data matrix; W is the principal component matrix, which is composed of the eigenvectors corresponding to the largest eigenvalue;

[0061] Step 6: Anomaly detection based on machine learning: Use the machine learning model to detect anomalies in the feature data and find a hyperplane to distinguish between normal and normal states. The formula is as follows:

[0062]

[0063] Among them, f(x) is the classification function, which is used to determine whether it is abnormal; α i is the Lagrange multiplier; y i is the category label of the i-th sample; K(x i ,x) is the kernel function, which is used to calculate the input data x and sample x i The similarity between them; b is the bias term;

[0064] Step 7, generate reports and decision support: Generate reports based on the analysis results, record the changing trend of the data, the location and time of the abnormal points; combine the historical data of the transmission line to provide fault prediction and alarm functions to help maintenance personnel make timely decisions.

[0065] Further, for the fused data x fused (t) When extracting features, start from the time domain features and frequency domain features; the time domain features can directly reflect the statistical characteristics of the signal in time, while the frequency domain features reveal the frequency distribution characteristics of the signal; including the following steps:

[0066] Step 1, time domain feature extraction: The time domain feature is a direct description of the signal in the time series, including mean, variance, root mean square value, skewness, kurtosis, and time domain features;

[0067] The mean is used to describe the central trend of the signal, and the formula is as follows:

[0068]

[0069] Where, μ is the mean value of the signal; N is the total number of sampling points of the signal; x fused (t) is the signal value at time t;

[0070] Variance is used to describe the degree of fluctuation or dispersion of a signal. The formula is as follows:

[0071]

[0072] Among them, σ 2 is the variance of the signal;

[0073] The root mean square value is used to measure the energy of the signal. The formula is as follows:

[0074]

[0075] Among them, RMS is the root mean square value of the signal;

[0076] Skewness is used to describe the symmetry of the signal distribution, and the formula is as follows:

[0077]

[0078] Among them, Skewness is the skewness of the signal; σ is the standard deviation of the signal;

[0079] Kurtosis is used to describe the sharpness of a signal, and the formula is as follows:

[0080]

[0081] Among them, Kurtosis is the kurtosis of the signal;

[0082] Step 2, frequency domain feature extraction: The frequency domain features reveal the components of the signal at different frequencies, which are obtained by Fourier transforming the signal; the frequency domain features include spectrum amplitude, frequency center, and bandwidth;

[0083] First, perform fast Fourier transform on the signal, the formula is as follows:

[0084]

[0085] Where X(f) is the spectrum of the signal at frequency f; N is the number of sampling points of the signal; j is the imaginary unit;

[0086] The spectrum amplitude is used to describe the amplitude of the signal at each frequency. The formula is as follows:

[0087]

[0088] Where, |X(f)| is the spectrum amplitude; is the real part of the spectrum X(f); is the imaginary part of the spectrum X(f);

[0089] The frequency center is used to describe the center position of the signal frequency distribution. The formula is as follows:

[0090]

[0091] Among them, f centroid is the frequency center; f is the frequency component;

[0092] Bandwidth is used to describe the discreteness of the signal frequency distribution. The formula is as follows:

[0093]

[0094] Bandwidth is the spectrum bandwidth.

[0095] The beneficial effects of the present invention are:

[0096] 1. High-precision monitoring: Intelligent spacers with integrated high-precision dancing amplitude and vibration frequency sensors can provide real-time and accurate analysis of the dynamic characteristics of power transmission lines. This helps to timely detect changes in the line under external factors such as wind deviation and vibration, and ensure the safe operation of the transmission line.

[0097] 2. Simplified installation and maintenance: Compared with traditional monitoring equipment, the intelligent spacer has a compact design and is easy to install on the transmission line, reducing the extra burden and improving the flexibility of installation. At the same time, its integrated design helps to reduce the maintenance frequency and save manpower and material resources.

[0098] 3. Energy saving and environmental protection: By equipping with a photovoltaic power generation system, the intelligent spacer can use solar energy to power itself and monitoring equipment, reducing dependence on external power supplies, reducing energy consumption, and embodying the concept of green environmental protection.

[0099] 4. Remote data transmission and real-time monitoring: The application of Bluetooth devices realizes wireless transmission of data, enabling the background management system to obtain monitoring data in real time, thereby improving the convenience and real-time nature of monitoring and providing a basis for decision-making.

[0100] 5. Diversified data collection: The intelligent spacer not only detects vibration data, but also contains GPS and laser rangefinders, which can comprehensively monitor the location, geographic information and height changes of the transmission line, providing more comprehensive data support for line status analysis.

[0101] 6. Trend analysis and early warning capabilities: The background management system can pre-process and analyze the acquired data, generate spectrum graphs and trend reports, and provide engineers with early warning capabilities so that they can take timely measures to prevent potential line failures.

[0102] 7. Optimized decision support: Through detailed data analysis and reporting, management can make scientific decisions based on specific monitoring results, optimize the line's operation and maintenance plans and response strategies, and improve overall management efficiency.

[0103] 8. Enhanced reliability and safety: The integrated monitoring system continuously monitors the status of the transmission lines, reducing the risk of accidents caused by equipment failure and enhancing the safety and reliability of the entire transmission system.

[0104] The above beneficial effects jointly improve the monitoring efficiency and safety management level of transmission lines, and provide support for the healthy development of the power industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] 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.

[0106] Figure 1 It is a schematic diagram of the overall structure of the intelligent spacer of the present invention;

[0107] Figure 2 This is a top view of the overall structure of the intelligent spacer of the present invention;

[0108] Figure 3 This is a bottom view of the overall structure of the intelligent spacer of the present invention;

[0109] Figure 4 This is a right view of the overall structure of the intelligent spacer of the present invention;

[0110] In the figure, 1. spacer bar body; 2. buckle; 201. fixed buckle; 202. movable buckle; 203. current transformer; 204. electric energy metering equipment; 3. sensor body; 4. laser rangefinder; 5. GPS equipment; 6. battery; 7. Bluetooth equipment; 8. photovoltaic power generation system; 801. photovoltaic panel; 802. inverter; 803. power controller. DETAILED DESCRIPTION

[0111] To make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0112] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the claimed invention, but merely represents some embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should be noted that the embodiments of the present invention and the features and technical solutions in the embodiments can be combined with each other without conflict. It should be noted that similar numbers and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0113] Example 1

[0114] For online monitoring of windage and dancing frequency of power transmission lines, this embodiment provides an intelligent spacer bar with integrated high-precision dancing amplitude and vibration frequency sensors; Figure 1 As shown, the intelligent spacer includes a spacer body 1, a support rod installed on the spacer body 1 and extending outward, and a transmission line buckle 2 installed on one end of the support rod away from the spacer body 1, and the spacer body can be installed on the transmission line through the buckle 2. Figure 1 and Figure 2 As shown, a sensor body 3 and a Bluetooth device 7 are installed on one side of the spacer body 1. Figure 3 and Figure 4 As shown, a GPS device 5 and a battery 6 are installed on the other side of the spacer body 1; Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown, a laser rangefinder 4 is installed at the bottom of the spacer body 1; wherein, the sensor body 3, the GPS device 5 and the laser rangefinder 4 are all electrically connected to the Bluetooth device 7 and the battery 6, the sensor body 3, the GPS device 5 and the laser rangefinder 4 are powered by the battery 6, and are communicated with the background management system through the Bluetooth device 7.

[0115] Further, if Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown, the spacer body 1 is in the shape of a rectangular plate, and the support rods are installed at the four corners of the spacer body 1; the power transmission line buckle 2 on the support rod includes a fixed buckle 201 and a movable buckle 202, and the movable buckle 202 is bolted to the fixed buckle 201, so as to realize the rapid installation of the intelligent spacer on the power transmission line.

[0116] After the smart spacer is installed on the transmission line, the sensor body 3 of the smart spacer detects the vibration data of the transmission line, the GPS device 5 detects the longitude, latitude, and altitude data, and the laser rangefinder 4 detects the straight-line distance and angle from the monitoring point to the ground. The above data are transmitted to the background management system through the Bluetooth device 7, so that the background technicians can obtain the wind deviation and dancing frequency of the transmission line based on the above data.

[0117] The intelligent spacer bar is combined with sensors, GPS equipment 5 and laser rangefinder 4, which can obtain the vibration data, geographical location information and distance information of the transmission line in real time to ensure the monitoring accuracy. Through the Bluetooth device 7, the monitoring data can be quickly transmitted to the background management system to achieve instant analysis and response, thereby improving management efficiency. The spacer bar is designed as a rectangular plate, and the configuration of the four-corner support rods and the combination of the fixed buckle 201 and the movable buckle 202 are convenient for quick and stable installation on the transmission line. The monitoring system can integrate and analyze multi-dimensional data such as vibration, positioning, and distance, and provide comprehensive support for evaluating the safety of the transmission line under the action of wind. Therefore, the intelligent spacer bar improves the monitoring capability of the wind deviation and dancing frequency of the transmission line through an efficient monitoring device and a convenient data transmission method, providing effective protection for the safety of the power grid.

[0118] Example 2

[0119] Based on Example 1, this example also makes the following improvements:

[0120] First, as Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown, in this embodiment, a current transformer 203 is also installed in the buckle 2, and an electric energy metering device 204 is installed on the other side of the spacer rod body 1. The current transformer 203 is electrically connected to the electric energy metering device 204 and the battery 6, and the electric energy metering device 204 is communicated with the background management system via the Bluetooth device 7.

[0121] After the current transformer 203 is powered by the battery 6, it can detect the current of the transmission line, and the detection data is transmitted to the background management system through the Bluetooth device 7. First, the current transformer 203 can monitor the current changes of the transmission line in real time and provide important operating status information for the power system. This real-time monitoring helps to timely discover potential risks such as abnormal line load, overload or short circuit, thereby improving the safety and stability of the transmission system. Secondly, the combination of the current transformer 203 and the electric energy metering device 204 can achieve accurate electric energy metering. In addition, the current data can be visualized and remotely monitored by communicating with the background management system through the Bluetooth device 7, so that operation and maintenance personnel can obtain line status information anytime and anywhere and respond in time.

[0122] Second, if Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown, in this embodiment, a photovoltaic power generation system 8 is also provided on the spacer body 1; the photovoltaic power generation system 8 includes a photovoltaic panel 801 fixedly installed above the spacer body 1 through a connecting rod, an inverter 802 and a power controller 803 fixedly installed on the spacer body 1; the photovoltaic panel 801 is electrically connected to the inverter 802, and the inverter 802 is electrically connected to the power controller 803; the power controller 803 is installed on the power supply line between the battery 6 and the sensor body 3, the GPS device 5, and the laser rangefinder 4.

[0123] The photovoltaic panel 801 can convert solar energy into electrical energy, and after AC-DC conversion through the inverter 802, power the sensor body 3, GPS device 5, and laser rangefinder 4; when the photovoltaic panel 801 can supply power, the power controller 803 cuts off the power supply of the battery 6; when the photovoltaic panel 801 cannot supply power, the power controller 803 cuts off the power supply of the photovoltaic panel 801 and converts it to power supply of the battery 6.

[0124] First, by converting solar energy into electrical energy, the photovoltaic system effectively improves the self-sufficiency of the equipment and reduces the overall energy consumption of the series monitoring equipment. This independent power supply method ensures the continuous and stable operation of the sensor, GPS device 5 and laser rangefinder 4 in the field environment, and enhances the reliability and service life of the equipment. Secondly, the design of the photovoltaic system can realize automatic switching of power supply. When the photovoltaic panel 801 is able to provide power, the system will give priority to solar energy, reduce dependence on the battery 6, and thus extend the service life of the battery 6; and when solar energy is insufficient, it can quickly switch to battery 6 for power supply, ensuring that the equipment always has electricity available and ensuring the continuity of online monitoring. In addition, the integration of the photovoltaic power generation system 8 simplifies the maintenance and operation process, reduces the cost of manual maintenance, and improves the intelligence level of the system.

[0125] Example 3

[0126] On the basis of Example 1, this embodiment provides an online monitoring method for the state of a power transmission line. The online monitoring method for the state of a power transmission line is based on the above-mentioned intelligent spacer with integrated high-precision dancing amplitude and vibration frequency sensors, and a background management system; and comprises the following steps:

[0127] Step 1: Install multiple intelligent spacers with integrated high-precision dancing amplitude and vibration frequency sensors on the transmission line to ensure coverage of all important monitoring points.

[0128] Step 2, the sensor body 3, GPS device 5 and laser rangefinder 4 of the intelligent spacer at each detection point detect the corresponding data and transmit it to the background management system.

[0129] The sensor body 3 of each intelligent spacer detects the vibration data of the power transmission line, the GPS device 5 detects the longitude, latitude, and altitude data, and the laser rangefinder 4 detects the straight-line distance and angle from the monitoring point to the ground;

[0130] The background management system calculates the deviation between the actual moving direction of the object and the predetermined heading by analyzing the moving GPS trajectory, thereby obtaining the wind deviation data; based on the sensor body 3, the acceleration and angular velocity of the transmission line in all directions are captured, and the dynamic characteristics of the transmission line when it is dancing are provided. At the same time, the height data detected by the laser rangefinder 4 is used to monitor the changes in the height of the transmission line, and then calculate its up and down dancing data.

[0131] Step 3, the background management system performs data preprocessing, time domain analysis and frequency domain analysis based on the detection data of the sensor body 3, GPS device 5 and laser rangefinder 4, and finally generates a spectrum diagram.

[0132] After completing data collection, the background management system generates a vibration waveform diagram based on the selected data by selecting the data of the vibration signal and setting the required parameters, such as the displayed time range and axis labels. Then, by setting the frequency range, resolution, and axis labels, the fast Fourier transform FFT is applied to the time domain signal, and the sample points of the input signal are divided into even and odd parts. These two parts are then calculated separately, and the results are finally combined to generate a spectrum diagram.

[0133] Step 4: The background management system analyzes the changing trends of the dancing amplitude and vibration frequency based on the spectrum diagram, and generates a corresponding report based on the analysis results.

[0134] View the generated waveform and spectrum diagram to observe the characteristics of the vibration signal. You can capture, zoom in, zoom out or pan to get a clearer view so as to analyze the changing trend of the dancing amplitude and vibration frequency. Generate a corresponding report based on the analysis results.

[0135] In the online monitoring method of the transmission line status, the intelligent spacer installed on the transmission line collects vibration data, GPS positioning information and laser ranging data in real time, realizes continuous monitoring of the line status, and greatly improves the response efficiency of the system. The integrated high-precision sensor can capture the acceleration and angular velocity of the line, and combined with the height data provided by the laser rangefinder 4, accurately calculates the dancing amplitude and vibration frequency, and provides a comprehensive dynamic characteristic analysis. Through the background management system, the collected data of multiple monitoring points are comprehensively analyzed, and the wind deviation and dancing rules can be effectively identified. The generated waveform and spectrum diagram enable users to easily observe the characteristics of the vibration signal. Through interactive operations (zoom in, zoom out, and pan), it is easy to analyze trend changes and generate reports in a timely manner, thereby improving decision-making support capabilities. By identifying potential problems in advance, the risk of sudden failures can be effectively reduced, the frequency of manual inspections can be reduced, thereby saving maintenance costs and improving the reliability and safety of transmission lines.

[0136] Example 4

[0137] On the basis of Example 3, since the background management system detects data based on the sensor body 3, GPS device 5 and laser rangefinder 4, it is necessary to perform data preprocessing first, and then perform time domain analysis and frequency domain analysis; therefore, this embodiment gives the following sensor data preprocessing process for the sensor body 3, GPS device 5 and laser rangefinder 4:

[0138] Step 1, continuous wavelet transform: by transforming the vibration signal of the transmission line on a continuous scale and a continuous translation, the formula is as follows:

[0139]

[0140] Among them, W x (a, b) are the wavelet coefficients of the transmission line vibration signal x(t) at scales a and b; x(t) is the original signal of the transmission line vibration signal; ψ * a,b (t) is the complex conjugate form of the mother wavelet function, where a represents the scale parameter, b represents the translation parameter, and t represents the time variable, usually the time of signal measurement.

[0141] It is defined as:

[0142]

[0143] Among them, a is the scale parameter, which is used to control the stretching or compression of the wavelet; b is the translation parameter, which is used to control the displacement of the wavelet in time; ψ(t) is the mother wavelet. Choosing different mother wavelets will affect the effect of the transformation.

[0144] Step 2, discrete wavelet transform DWT: Discrete wavelet transform DWT decomposes the signal into low-frequency and high-frequency parts of different frequency bands through multi-resolution analysis MRA. The decomposition process is based on the filter bank, and the formula is as follows:

[0145]

[0146] Where x[n] is the discrete input signal, c j [k] is the low-frequency component at the jth scale, i.e., the approximate coefficient; φ j,k (n) is the scaling function, corresponding to the output of the low-pass filter; d j [k] high-frequency component at the jth scale, i.e. detail coefficient; ψ j.k (n) is the wavelet function, corresponding to the output of the high-pass filter.

[0147] The calculation of discrete wavelet transform DWT is performed by Mallat algorithm, which gradually decomposes the signal into approximate signal and high detail signal. The formula is as follows:

[0148]

[0149] Among them, h[k] is the low-pass filter coefficient, which is used to extract the approximate signal; g[k] is the high-pass filter coefficient, which is used to extract the detail signal; c j [n] is the low-frequency component of the jth scale; d j [n] is the high-frequency component of the jth scale; k is the index of the filter, and its range depends on the length of the filter; n is the discrete time index, indicating the sample point position of the signal; j is the decomposition level or scale level.

[0150] Step 3, Inverse Discrete Wavelet Transform IDWT: To reconstruct the original signal from the discrete wavelet transform DWT decomposition result, an inverse discrete wavelet transform IDWT is required. The formula is as follows:

[0151]

[0152] Among them, c j+1 [n] is the reconstructed low-frequency component; c j [k] represents the low-frequency component of the j-th scale, i.e., the approximate signal; d j [k] represents the high-frequency component of the j-th scale, that is, the detail signal; n is the discrete time index of the reconstructed signal.

[0153] Step 4, data preprocessing and denoising: When using discrete wavelet transform DWT to denoise the transmission line vibration signal, the noise is removed by value processing of the detail coefficients. The formula is as follows:

[0154]

[0155] Among them, d j [k] is the high-frequency component after processing; λ is the set threshold, which is used to filter out noise smaller than this value.

[0156] Through continuous wavelet transform CWT and discrete wavelet transform DWT, the low-frequency and high-frequency components in the signal are effectively separated, thereby reducing the impact of noise on data analysis. This process enables the signal to more truly reflect the vibration characteristics of the transmission line. The spectrum diagram generated after preprocessing can clearly show the trend of the change of vibration frequency over time, which is convenient for analyzing and judging the status of the transmission line. The multi-resolution characteristics of the wavelet transform enable the details of the signal, such as emergencies or abnormal vibrations, to be effectively retained, which is crucial for accurately identifying potential risk points. The sensor data preprocessing process of the sensor body 3, GPS device 5 and laser rangefinder 4 has good adaptability to various types of signals, can operate stably under different environments and conditions, and improves the reliability of monitoring.

[0157] In summary, wavelet transform not only improves data quality, but also enhances the system's ability to monitor the real-time status of transmission lines, providing support for subsequent trend analysis and decision-making.

[0158] Example 5

[0159] On the basis of Example 3, in step 4, the background management system of this embodiment analyzes the changing trend of the dancing amplitude and the vibration frequency based on the spectrum diagram, and comprehensively processes various monitoring data of the transmission line including vibration, position, and distance through multi-sensor data fusion and intelligent analysis; through data fusion, the data from the sensor body 3, the GPS device 5 and the laser rangefinder 4 can be integrated to realize comprehensive analysis of information.

[0160] Multi-sensor data fusion includes the following steps:

[0161] Step 1, multi-sensor data collection: collect different types of data through the sensor body 3, GPS device 5 and laser rangefinder 4 respectively; suppose x1(t), x2(t), ...x n (t) are the observation values ​​of the sensor body 3, GPS device 5 and laser rangefinder 4 at time t respectively.

[0162] Step 2, data preprocessing: normalize the data collected by the sensor body 3, GPS device 5 and laser rangefinder 4 to eliminate the dimensional differences between different data sources. The formula is as follows:

[0163]

[0164] Among them, x i(t) is the standardized data; μ i is the mean value of the i-th sensor data; σ i is the standard deviation of the i-th sensor data.

[0165] Step 3: Weighted average fusion: Use the weighted average method to fuse data. The formula is as follows:

[0166]

[0167] Among them, x fused (t) is the fused data; ω i is the weight of the i-th sensor, satisfying

[0168] Step 4, Kalman filter fusion:

[0169] predict:

[0170] x k|k-1 =Ax k-1 +Bu k

[0171] P k|k-1 =AP k-1 A T +Q

[0172] Among them, x k|k-1 is the predicted value of the state at time k; x k-1 is the state estimate at time k-1; A is the state transfer matrix; B is the control input matrix; u k is the control input; P k|k-1 is the prediction covariance matrix; P k-1 is the estimated error covariance matrix at time k-1; Q is the process noise covariance matrix; A T represents the transpose of the state transfer matrix A.

[0173] renew:

[0174] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0175] x k =x k|k-1 +K k (z k -Hx k|k-1 )

[0176] P k =(IK k H)P k|k-1

[0177] Among them, K k is the Kalman gain; H is the observation matrix; R is the observation noise covariance matrix; H T is the transpose of the observation matrix H; x k is the estimated value of the state at time k; z k is the sensor measurement value at the kth moment; P k is the estimated error covariance matrix at time k; I is the identity matrix.

[0178] Step 5: Feature extraction and data dimensionality reduction: fused (t) performing feature extraction, extracting time domain features including mean and variance, and frequency domain features including spectrum, amplitude, and frequency center;

[0179] Use principal component analysis PCA to reduce data dimension and reduce data redundancy. The formula is as follows:

[0180] Z=XW

[0181] Among them, Z is the data matrix after dimensionality reduction; X is the original data matrix; W is the principal component matrix, which is composed of the eigenvectors corresponding to the largest eigenvalue.

[0182] Step 6: Anomaly detection based on machine learning: Use the machine learning model to detect anomalies in the feature data and find a hyperplane to distinguish between normal and normal states. The formula is as follows:

[0183]

[0184] Among them, f(x) is the classification function, which is used to determine whether it is abnormal; α i is the Lagrange multiplier; y i is the category label of the i-th sample; K(x i ,x) is the kernel function, which is used to calculate the input data x and sample x i The similarity between them; b is the bias term.

[0185] Step 7, generate reports and decision support: Generate reports based on the analysis results, record the changing trend of the data, the location and time of the abnormal points; combine the historical data of the transmission line to provide fault prediction and alarm functions to help maintenance personnel make timely decisions.

[0186] By integrating data from multiple sensors, such as vibration, position, and distance, the errors that may be caused by a single sensor are eliminated, and the comprehensiveness and accuracy of the data are improved. The application of Kalman filtering provides prediction and update of real-time status, ensuring that the system can respond to environmental changes in a timely manner and capture small changes in the amplitude and frequency of the dancing. By extracting time domain and frequency domain features and using principal component analysis PCA for data dimensionality reduction, the computational complexity is effectively reduced while retaining key state change information. Using machine learning models for anomaly detection can quickly identify potential fault risks, and provide accurate fault prediction and alarm based on historical data to ensure the safety and stability of the line.

[0187] In summary, the combination of multi-sensor data fusion and intelligent analysis in step 4 provides strong technical support for the condition monitoring of transmission lines.

[0188] Further, for the fused data x fused (t) When extracting features, start from the time domain features and frequency domain features; the time domain features can directly reflect the statistical characteristics of the signal in time, while the frequency domain features reveal the frequency distribution characteristics of the signal; including the following steps:

[0189] Step 1, time domain feature extraction: The time domain feature is a direct description of the signal in the time series, including mean, variance, root mean square value, skewness, kurtosis, and time domain features;

[0190] The mean is used to describe the central trend of the signal, and the formula is as follows:

[0191]

[0192] Where, μ is the mean value of the signal; N is the total number of sampling points of the signal; x fused (t) is the signal value at time t;

[0193] Variance is used to describe the degree of fluctuation or dispersion of a signal. The formula is as follows:

[0194]

[0195] Among them, σ 2 is the variance of the signal;

[0196] The root mean square value is used to measure the energy of the signal. The formula is as follows:

[0197]

[0198] Among them, RMS is the root mean square value of the signal;

[0199] Skewness is used to describe the symmetry of the signal distribution, and the formula is as follows:

[0200]

[0201] Among them, Skewness is the skewness of the signal; σ is the standard deviation of the signal;

[0202] Kurtosis is used to describe the sharpness of a signal, and the formula is as follows:

[0203]

[0204] Among them, Kurtosis is the kurtosis of the signal;

[0205] Step 2, frequency domain feature extraction: The frequency domain features reveal the components of the signal at different frequencies, which are obtained by Fourier transforming the signal; the frequency domain features include spectrum amplitude, frequency center, and bandwidth;

[0206] First, perform fast Fourier transform on the signal, the formula is as follows:

[0207]

[0208] Where X(f) is the spectrum of the signal at frequency f; N is the number of sampling points of the signal; j is the imaginary unit;

[0209] The spectrum amplitude is used to describe the amplitude of the signal at each frequency. The formula is as follows:

[0210]

[0211] Where, |X(f)| is the spectrum amplitude; is the real part of the spectrum X(f); is the imaginary part of the spectrum X(f);

[0212] The frequency center is used to describe the center position of the signal frequency distribution. The formula is as follows:

[0213]

[0214] Among them, f centroid is the frequency center; f is the frequency component;

[0215] Bandwidth is used to describe the discreteness of the signal frequency distribution. The formula is as follows:

[0216]

[0217] Bandwidth is the spectrum bandwidth.

[0218] The online monitoring method of the transmission line status can realize comprehensive and accurate monitoring of the transmission line status by integrating intelligent spacers with high-precision dancing amplitude and vibration frequency sensors, as well as a background management system. Specific technical effects include: High-precision monitoring: The use of high-precision sensors can obtain multi-dimensional data such as deflection and vibration, which improves the monitoring accuracy of the transmission line status; accurate dancing amplitude and vibration frequency data provide a reliable basis for subsequent analysis. Data fusion and comprehensive analysis: Multi-sensor data fusion integrates a variety of monitoring data such as vibration, position, and distance, which can fully reflect the state changes of the transmission line; by integrating data from different sources, it reduces the errors and limitations that may be caused by a single sensor, and improves the reliability of the monitoring system. Time domain and frequency domain feature extraction: Time domain features (such as mean, variance, root mean square value, etc.) provide statistical characteristics of the signal, which helps to identify fluctuations and anomalies in daily operation; frequency domain features (such as spectrum amplitude, frequency center, bandwidth, etc.) help identify potential frequency anomalies and can promptly detect resonance or other problems that may exist in the transmission line. Intelligence and automation: The background management system uses spectrum graphs to analyze the changing trends of the dancing amplitude and vibration frequency, and generates corresponding reports to achieve intelligent data analysis and automatic report generation; it reduces the need for human intervention, improves monitoring efficiency, and enables maintenance personnel to make maintenance decisions in a timely manner. Early warning and maintenance decision support: Through real-time analysis of monitoring data, early warnings can be provided before problems occur, reducing potential risks and losses; the resulting reports provide a scientific basis for subsequent maintenance and overhaul decisions, and can optimize resource allocation and planning. Enhance line safety and stability: Continuous online monitoring can effectively improve the safety of transmission lines, identify and handle various anomalies in a timely manner, and prevent safety hazards caused by dancing or wind deviation; it improves the overall stability of the power system, reduces the frequency of failures, and improves power supply reliability.

[0219] In summary, this online monitoring method significantly improves the monitoring capability of transmission lines through efficient data collection and analysis, and provides a strong guarantee for the safe and stable operation of the power system.

[0220] At the same time, it should be pointed out that the above description is only a typical embodiment of the present invention and does not limit the present invention in any form. Any changes made to the above embodiments based on the ideas and technical essence of the present invention are within the protection scope of the present invention.

Claims

1. An intelligent spacer bar with integrated high-precision dancing amplitude and vibration frequency sensor, characterized in that: It includes a spacer bar body, a support rod installed on the spacer bar body and extending outward, and a transmission line buckle installed at one end of the support rod away from the spacer bar body, and the spacer bar body can be installed on the transmission line through the buckle; A sensor body and a Bluetooth device are installed on one side of the spacer body, a GPS device and a battery are installed on the other side, and a laser rangefinder is installed at the bottom; the sensor body, the GPS device and the laser rangefinder are all electrically connected to the Bluetooth device and the battery, are powered by the battery, and are communicated with the background management system through the Bluetooth device.

2. The intelligent spacer with integrated high-precision dancing amplitude and vibration frequency sensor according to claim 1 is characterized in that: The spacer rod body is in the shape of a rectangular plate, and the support rod is installed at the four corners of the spacer rod body; the transmission line buckle on the support rod includes a fixed buckle and a movable buckle, and the movable buckle is bolted to the fixed buckle.

3. The intelligent spacer with integrated high-precision dancing amplitude and vibration frequency sensor according to claim 1 is characterized in that: The buckle is installed with a current transformer, and an electric energy metering device is installed on the other side of the spacer rod body. The current transformer is electrically connected to the electric energy metering device and the battery, and the electric energy metering device is communicated with the background management system through a Bluetooth device.

4. The intelligent spacer with integrated high-precision dancing amplitude and vibration frequency sensor according to claim 1 is characterized in that: A photovoltaic power generation system is also provided on the spacer body; the photovoltaic power generation system includes a photovoltaic panel fixedly installed above the spacer body through a connecting rod, and an inverter and a power controller fixedly installed on the spacer body; the photovoltaic panel is electrically connected to the inverter, and the inverter is electrically connected to the power controller; the power controller is installed on the power supply line between the battery and the sensor body, the GPS device, and the laser rangefinder.

5. An online monitoring method for the state of a power transmission line, the online monitoring method for the state of a power transmission line is based on the intelligent spacer with integrated high-precision dancing amplitude and vibration frequency sensors as described in any one of claims 1 to 4, and a background management system; characterized in that: The following steps are involved: Step 1: Install multiple intelligent spacers with integrated high-precision dancing amplitude and vibration frequency sensors on the transmission line to ensure that all important monitoring points are covered; Step 2: Detect corresponding data through the sensor body, GPS device and laser rangefinder of the intelligent spacer at each detection point and transmit it to the background management system; Step 3: The backend management system performs data preprocessing, time domain analysis and frequency domain analysis based on the data detected by the sensor body, GPS device and laser rangefinder, and finally generates a spectrum diagram; Step 4: The background management system analyzes the changing trends of the dancing amplitude and vibration frequency based on the spectrum diagram, and generates a corresponding report based on the analysis results.

6. The method for online monitoring of the state of a power transmission line according to claim 5, characterized in that: In step 2, the sensor body of each intelligent spacer detects the vibration data of the transmission line, the GPS device detects the longitude, latitude, and altitude data, and the laser rangefinder detects the straight-line distance and angle from the monitoring point to the ground; The backend management system calculates the deviation between the actual moving direction of the object and the predetermined heading by analyzing the moving GPS trajectory, thereby obtaining the wind deviation data; based on the sensor body, it captures the acceleration and angular velocity of the transmission line in all directions, provides the dynamic characteristics of the transmission line when it is dancing, and cooperates with the height data detected by the laser rangefinder to monitor the changes in the height of the transmission line, and then calculates its up and down dancing data.

7. The method for online monitoring of power transmission line status according to claim 5, characterized in that: In step 3, the data preprocessing process is as follows: Step 1, continuous wavelet transform: by transforming the vibration signal of the transmission line on a continuous scale and a continuous translation, the formula is as follows: Among them, W x (a, b) are the wavelet coefficients of the transmission line vibration signal x(t) at scales a and b; x(t) is the original signal of the transmission line vibration signal; ψ * a,b (t) is the complex conjugate form of the mother wavelet function, where a represents the scale parameter, b represents the translation parameter; t represents the time variable, usually the time of signal measurement; It is defined as: Among them, a is the scale parameter, which is used to control the stretching or compression of the wavelet; b is the translation parameter, which is used to control the displacement of the wavelet in time; ψ(t) is the mother wavelet, and choosing different mother wavelets will affect the effect of the transformation; Step 2, discrete wavelet transform DWT: Discrete wavelet transform DWT decomposes the signal into low-frequency and high-frequency parts of different frequency bands through multi-resolution analysis MRA. The decomposition process is based on the filter bank, and the formula is as follows: Where x[n] is the discrete input signal, c j [k] is the low-frequency component at the jth scale, i.e., the approximate coefficient; φ j,k (n) is the scaling function, corresponding to the output of the low-pass filter; d j [k] high-frequency component at the jth scale, i.e. detail coefficient; ψ j.k (n) is the wavelet function, corresponding to the output of the high-pass filter; The calculation of discrete wavelet transform DWT is performed by Mallat algorithm, which gradually decomposes the signal into approximate signal and high detail signal. The formula is as follows: Among them, h[k] is the low-pass filter coefficient, which is used to extract the approximate signal; g[k] is the high-pass filter coefficient, which is used to extract the detail signal; c j [n] is the low-frequency component of the jth scale; d j [n] is the high-frequency component of the jth scale; k is the index of the filter, and its range depends on the length of the filter; n is a discrete time index, indicating the sample point position of the signal; j is the decomposition level or scale level; Step 3, Inverse Discrete Wavelet Transform IDWT: To reconstruct the original signal from the discrete wavelet transform DWT decomposition result, an inverse discrete wavelet transform IDWT is required. The formula is as follows: Among them, c j+1 [n] is the reconstructed low-frequency component; c j [k] represents the low-frequency component of the j-th scale, i.e., the approximate signal; d j [k] represents the high-frequency component of the jth scale, i.e., the detail signal; n is the discrete time index of the reconstructed signal; Step 4, data preprocessing and denoising: When using discrete wavelet transform DWT to denoise the transmission line vibration signal, the noise is removed by value processing of the detail coefficients. The formula is as follows: Among them, d j [k] is the high-frequency component after processing; λ is the set threshold, which is used to filter out noise smaller than this value.

8. The method for online monitoring of power transmission line status according to claim 5, characterized in that: Step 4. In the process of analyzing the changing trends of the dancing amplitude and vibration frequency based on the spectrum diagram, the background management system comprehensively processes various monitoring data of the transmission line including vibration, position, and distance through multi-sensor data fusion and intelligent analysis; through data fusion, it can integrate data from the sensor body, GPS equipment and laser rangefinder to realize comprehensive analysis of information.

9. The method for online monitoring of the state of a power transmission line according to claim 8, characterized in that: Multi-sensor data fusion includes the following steps: Step 1, multi-sensor data collection: collect different types of data through the sensor body, GPS device and laser rangefinder respectively; suppose x1(t), x2(t), ...x n (t) are the observation values ​​of the sensor body, GPS device and laser rangefinder at time t respectively; Step 2, data preprocessing: normalize the data collected by the sensor body, GPS device and laser rangefinder to eliminate the dimensional differences between different data sources. The formula is as follows: Among them, x i (t) is the standardized data; μ i is the mean value of the i-th sensor data; σ i is the standard deviation of the i-th sensor data; Step 3: Weighted average fusion: Use the weighted average method to fuse data. The formula is as follows: Among them, x fused (t) is the fused data; ω i is the weight of the i-th sensor, satisfying Step 4, Kalman filter fusion: predict: x kk-1 =Ax k-1 +Bu k P kk-1 =AP k-1 From T +Q Among them, x k|k-1 is the state prediction value at time k; A is the state transfer matrix; B is the control input matrix; u k is the control input; P k|k-1 is the prediction covariance matrix; Q is the process noise covariance matrix; A T for? renew: K k =P k|k-1 H T (HP k|k-1 H T +R) -1 x k =x k|k-1 +K k (z k -Hx k|k-1 ) P k =(I-K k H)P kk-1 Among them, K k is the Kalman gain; H is the observation matrix; R is the observation noise covariance matrix; H T is the transpose of the observation matrix H; x k is the estimated value of the state at time k; z k is the sensor measurement value at the kth moment; P k is the estimated error covariance matrix at time k; I is the identity matrix; Step 5: Feature extraction and data dimensionality reduction: fused (t) performing feature extraction, extracting time domain features including mean and variance, and frequency domain features including spectrum, amplitude, and frequency center; Use principal component analysis PCA to reduce data dimension and reduce data redundancy. The formula is as follows: Z=XW Among them, Z is the data matrix after dimension reduction; X is the original data matrix; W is the principal component matrix, which is composed of the eigenvectors corresponding to the largest eigenvalue; Step 6: Anomaly detection based on machine learning: Use the machine learning model to detect anomalies in the feature data and find a hyperplane to distinguish between normal and normal states. The formula is as follows: Among them, f(x) is the classification function, which is used to determine whether it is abnormal; α i is the Lagrange multiplier; y i is the category label of the i-th sample; K(x i ,x) is the kernel function, which is used to calculate the input data x and sample x i The similarity between them; b is the bias term; Step 7, generate reports and decision support: Generate reports based on the analysis results, record the changing trend of the data, the location and time of the abnormal points; combine the historical data of the transmission line to provide fault prediction and alarm functions to help maintenance personnel make timely decisions.

10. The method for online monitoring of power transmission line status according to claim 9, characterized in that: For the fused data x fused (t) When extracting features, start from both time domain features and frequency domain features; The time domain features can directly reflect the statistical characteristics of the signal in time, while the frequency domain features reveal the frequency distribution characteristics of the signal; including the following steps: Step 1, time domain feature extraction: The time domain feature is a direct description of the signal in the time series, including mean, variance, root mean square value, skewness, kurtosis, and time domain features; The mean is used to describe the central trend of the signal, and the formula is as follows: Where, μ is the mean value of the signal; N is the total number of sampling points of the signal; x fused (t) is the signal value at time t; Variance is used to describe the degree of fluctuation or dispersion of a signal. The formula is as follows: Among them, σ 2 is the variance of the signal; The root mean square value is used to measure the energy of the signal. The formula is as follows: Among them, RMS is the root mean square value of the signal; Skewness is used to describe the symmetry of the signal distribution, and the formula is as follows: Among them, Skewness is the skewness of the signal; σ is the standard deviation of the signal; Kurtosis is used to describe the sharpness of a signal, and the formula is as follows: Among them, Kurtosis is the kurtosis of the signal; Step 2, frequency domain feature extraction: The frequency domain features reveal the components of the signal at different frequencies, which are obtained by Fourier transforming the signal; the frequency domain features include spectrum amplitude, frequency center, and bandwidth; First, perform fast Fourier transform on the signal, the formula is as follows: Where X(f) is the spectrum of the signal at frequency f; N is the number of sampling points of the signal; j is the imaginary unit; The spectrum amplitude is used to describe the amplitude of the signal at each frequency. The formula is as follows: Where, |X(f)| is the spectrum amplitude; is the real part of the spectrum X(f); is the imaginary part of the spectrum X(f); The frequency center is used to describe the center position of the signal frequency distribution. The formula is as follows: Among them, f centroid is the frequency center; f is the frequency component; Bandwidth is used to describe the discreteness of the signal frequency distribution. The formula is as follows: Bandwidth is the spectrum bandwidth.

Images