Self-powered power transmission online monitoring method based on Internet of Things

Abstract

The invention relates to the technical field of power transmission, in particular to a self-powered power transmission online monitoring method based on the Internet of Things, which comprises the steps of system construction and equipment deployment, data acquisition and transmission, data processing and analysis, monitoring and alarming and emergency response. By constructing a system framework comprising an acquisition layer, a network layer, a data layer and an application layer, comprehensive and real-time acquisition and efficient transmission of parameters of the power transmission line are realized, meanwhile, continuous and stable energy supply is provided for the system through renewable energy sources, long-term stable operation of the monitoring system is ensured, and the power transmission line monitoring system has a wide application prospect. Therefore, powerful technical support is provided for safety monitoring and emergency response of the power system, data of other parallel monitoring systems can be counted and collected through the data acquisition center, unified management is performed, communication protocols and data models of various sensing devices are unified, and various online monitoring devices are managed in a unified manner.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission, and in particular to an online monitoring method for self-powered power transmission based on the Internet of Things. Background Art

[0002] With the continuous development of power systems and the improvement of their intelligence levels, the demand for real-time monitoring and efficient transmission of transmission line parameters is increasing. Traditional monitoring systems often have problems such as incomplete data collection and low transmission efficiency, and cannot meet the urgent needs of modern power systems for safety monitoring and emergency response.

[0003] Secondly, in the existing monitoring systems, the data collection and processing capabilities of the acquisition layer are limited, and often can only monitor specific parameters, and the data accuracy and reliability need to be improved. At the same time, these systems often lack unified communication protocols and data models, resulting in the inability to effectively communicate and uniformly manage different monitoring systems, thereby reducing the utilization efficiency of monitoring equipment.

[0004] In addition, the energy supply method of traditional monitoring systems usually relies on external power supplies or batteries, which not only increases the operation and maintenance costs of the system, but also limits the deployment scope and stability of the system. Especially in some remote areas or harsh environments, traditional energy supply methods often cannot meet the long-term stable operation requirements of the monitoring system.

[0005] In response to the above problems, this invention patent proposes an online monitoring method for self-powered power transmission based on the Internet of Things. By constructing a system architecture including the collection layer, network layer, data layer and application layer, it realizes the comprehensive and real-time collection and efficient transmission of transmission line parameters. At the same time, the sensor network, data collection center and self-powered module in the collection layer not only improve the comprehensiveness and accuracy of data collection, but also provide the system with a continuous and stable energy supply through renewable energy, ensuring the long-term stable operation of the monitoring system. This method not only solves the problem of multiple monitoring systems coexisting and overlapping each other and monitoring equipment not being effectively utilized in the prior art, but also provides strong technical support for the safety monitoring and emergency response of the power system. Summary of the invention

[0006] In order to solve the problems raised in the above background technology, the present invention proposes an online monitoring method for self-powered power transmission based on the Internet of Things.

[0007] The technical solution of the present invention is: a method for online monitoring of self-powered power transmission based on the Internet of Things, comprising the following steps:

[0008] S11: System construction and equipment deployment, including system architecture design and equipment selection and deployment. When selecting and deploying equipment, sensors and monitoring equipment are installed on the transmission line. The installed sensors include current sensors, voltage sensors, temperature sensors and humidity sensors.

[0009] S12: Data collection and transmission: using sensors installed on the transmission line to collect the working parameters of the transmission line in real time, and transmit the collected data to the monitoring equipment, which transmits the received data to the remote data center through the network;

[0010] S13: Data processing and analysis: first, preprocessing the received raw data to improve the quality and availability of the data. After preprocessing, the data is analyzed in depth using a data analysis algorithm. The in-depth analysis of the data includes real-time monitoring of the status of the transmission line, identification of abnormal data, and prediction of potential faults.

[0011] S14: Monitoring and alarm, which displays the status information of the transmission line in real time through the user interface. When abnormal data and potential faults are detected, the alarm mechanism is immediately triggered to notify relevant personnel;

[0012] S15: Emergency response. When the monitoring system detects faults and abnormalities in the transmission line, it notifies the staff to immediately start the emergency response mechanism to ensure the safe and stable operation of the transmission system. The emergency response mechanism adopted includes notifying relevant personnel, starting the backup power supply and cutting off the faulty line.

[0013] Preferably, when designing the system architecture, the system architecture includes:

[0014] A11: Collection layer, responsible for real-time collection of transmission line parameters and data, including current, voltage, temperature and humidity;

[0015] A12: Network layer, responsible for transmitting the data collected by the collection layer to the remote data center in real time;

[0016] A13: Data layer, responsible for preprocessing the received raw data and storing and managing the processed data;

[0017] A14: Application layer, responsible for displaying the processed data to users in an intuitive and easy-to-understand manner, and providing various monitoring, alarm, analysis and decision support functions.

[0018] Preferably, the acquisition layer includes:

[0019] A21: Sensor network, used to build a monitoring network using multiple sensors, including current sensors, voltage sensors, temperature sensors, and humidity sensors;

[0020] A22: Data collection center, used to collect statistics on the data of the sensor network and other parallel monitoring systems, and send them to the data layer using the network layer;

[0021] A23: Self-powered module, used to provide continuous energy supply for sensor networks and data collection centers using renewable energy, including solar energy, wind energy and hydropower.

[0022] Preferably, the data collection center of the collection layer also has the following functions:

[0023] A31: Data decoding and repackaging: Decode the received data using different encoding methods, and repack the decoded data according to the requirements of subsequent processing and transmission to ensure the integrity and consistency of the data;

[0024] A32: Data integrity check, using different verification methods to verify the integrity of the data to ensure the accuracy and reliability of the data;

[0025] A33: Data correctness verification verifies the logical correctness of the data, including the verification of the data range, format and consistency.

[0026] Preferably, when the data collection center of the collection layer performs data integrity verification, the verification methods adopted include:

[0027] A41: Count check, which verifies data integrity by counting the total number of records and the number of non-null values ​​in a specific field;

[0028] A42: Uniqueness check, ensuring that the specified special field is unique in the data;

[0029] A43: Checksum check: the integrity of the data is checked using the checksum calculated based on the data content. The calculation formula for the checksum includes:

[0030] Checksum = ((SUM1MOD255) + (SUM2MOD255) * 256) MOD255;

[0031] Where SUM1 is the sum of the data bytes, and SUM2 is the sum of the digits in SUM1.

[0032] Preferably, when the data collection center of the collection layer verifies the data correctness, the verification methods adopted include:

[0033] A51: Range check, verifying whether the data is within a specific range. For numerical data, a statistical method is used to determine whether the data is within a specific range. The principle formula of the statistical method is:

[0034]

[0035] Where X is the data point, μ is the mean, and σ is the standard deviation. When identifying outliers, when the size of Z calculated from data point X is greater than the set threshold, the data point X is marked as an outlier.

[0036] A52: Logical verification, using logical expressions to verify the logical relationship between data, thereby verifying the correctness of the data;

[0037] A53: Checksum verification, using the checksum to verify the data, so as to verify the correctness of the data;

[0038] A54: Customized verification formula: Write a customized verification formula based on specific business needs, and use the customized verification formula to verify the correctness of the data.

[0039] Preferably, when preprocessing the received raw data to improve the quality and usability of the data, the following steps are included:

[0040] S21: Data filtering. First, the collected data is filtered to remove high-frequency noise and interference signals. The principle formula of the filtering process is:

[0041]

[0042] Among them, X(k) represents the frequency, x(n) represents the time domain signal, N represents the signal length, and k represents the frequency domain index;

[0043] S22: Data denoising processing, denoising the filtered data to further reduce the noise components in the data, wherein the principle formula of the denoising algorithm used is:

[0044]

[0045] Among them, W ψ (j,k) is the wavelet coefficient, M is the signal length, x[n] is the input signal, ψ j,k (n) is the wavelet function after scaling and translation, j is the scale parameter, and k is the translation parameter;

[0046] S23: Data standardization, including converting data into dimensionless form to ensure the accuracy and consistency of subsequent analysis;

[0047] S24: Data normalization processing, converting the data into data under a unified standard unit, wherein the principle formula of data normalization processing is:

[0048]

[0049] Among them, X ‘’ Represents the normalized value of data point X, X min represents the minimum value in the data set, X max Represents the maximum value in the data set.

[0050] Preferably, after preprocessing, the data is analyzed in depth using a data analysis algorithm, including the following steps:

[0051] S31: real-time monitoring of the state of the transmission line, by receiving the operation data of the transmission line collected by the sensor network, and real-time monitoring of the operation state of the transmission line;

[0052] S32: Abnormal data identification, using the method of setting thresholds and using machine learning algorithms to identify abnormal data points and abnormal patterns;

[0053] S33: Predict potential failures, based on historical data and real-time monitoring data, using one of data mining algorithms, machine learning algorithms and deep learning algorithms to establish a prediction model to predict potential failures.

[0054] Preferably, when using a machine learning algorithm to identify abnormal data points and abnormal patterns, the following steps are included:

[0055] S41: Data preparation and preprocessing, first obtain the real-time monitoring data of the transmission line from the IoT system, including current, voltage, temperature and humidity data, and preprocess the data to improve the quality and availability of the data;

[0056] S42: extracting useful features from the preprocessed raw data, including statistical features, time domain features, and frequency domain features, to obtain a training data set;

[0057] S43: Model selection and training: Select a suitable machine learning algorithm based on the characteristics of the data and the needs of anomaly detection, and use the training data set to train the selected machine learning algorithm and adjust the algorithm's hyperparameters to obtain the best performance;

[0058] S44: Anomaly detection and identification, apply the trained model to real-time monitoring data, calculate the anomaly score of each data point, set the anomaly score threshold according to actual needs, and mark the data point as an abnormal data point when the anomaly score exceeds the threshold. By analyzing the distribution and correlation characteristics of the abnormal data points, potential abnormal patterns can be identified.

[0059] Preferably, when extracting useful features from the raw data after preprocessing, the feature extraction method used includes a hyperparameter method, wherein the principle formula of the hyperparameter method used is:

[0060] EMAt=αXt+(1-α)EMAt-1EMA t =αX t +(1-α)EMA t-1 EMAt=

[0061] αXt+(1-α)EMAt-1;

[0062] Among them, EMAt represents the exponential moving average at time t, α is a smoothing coefficient between 0 and 1, Xt represents the observed value at time t, and EMA t-1 represents the exponential moving average at time t-1, and 1-α represents the previous exponential moving average EMA t-1 Importance in calculating the current EMAt.

[0063] Beneficial effects of the present invention:

[0064] 1. By building a system architecture including the collection layer, network layer, data layer and application layer, comprehensive and real-time collection and efficient transmission of transmission line parameters are achieved. At the same time, the sensor network, data collection center and self-powered module in the collection layer not only improve the comprehensiveness and accuracy of data collection, but also provide a continuous and stable energy supply for the system through renewable energy, ensuring the long-term stable operation of the monitoring system, thereby providing strong technical support for the safety monitoring and emergency response of the power system. In addition, the data of other parallel monitoring systems can be counted and collected through the data collection center for unified management, realizing the unification of communication protocols and data models of various sensing devices, and unified management of various online monitoring devices;

[0065] 2. The data acquisition center in the present invention not only ensures that the received data can be processed and transmitted completely and accurately through functions such as data decoding and repackaging, data integrity verification and data correctness verification, but also greatly improves the reliability and consistency of the data, providing a solid foundation for subsequent data analysis and decision-making, thereby further improving the overall performance and accuracy of the transmission line monitoring system;

[0066] 3. Ensure data integrity by adopting counting check, uniqueness check and checksum-based check value check, and use range check (combined with statistical methods to identify abnormal values), logic check, check code check and custom check formulas to verify data correctness. This greatly enhances the data collection center's ability to ensure data accuracy and consistency, provides a high-quality data foundation for transmission line monitoring, and effectively improves the reliability and accuracy of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a flow chart of the online monitoring method of self-powered power transmission based on the Internet of Things of the present invention;

[0068] Figure 2 It is a structural schematic diagram of the system architecture in the online monitoring method of self-powered power transmission based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0069] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0070] See also Figure 1-2 The present invention provides an embodiment: a method for online monitoring of self-powered power transmission based on the Internet of Things, comprising the following steps:

[0071] S11: System construction and equipment deployment, including system architecture design and equipment selection and deployment. When selecting and deploying equipment, sensors and monitoring equipment are installed on the transmission line. The installed sensors include current sensors, voltage sensors, temperature sensors and humidity sensors.

[0072] S12: Data collection and transmission: using sensors installed on the transmission line to collect the working parameters of the transmission line in real time, and transmit the collected data to the monitoring equipment, which transmits the received data to the remote data center through the network;

[0073] S13: Data processing and analysis: first, preprocessing the received raw data to improve the quality and availability of the data. After preprocessing, the data is analyzed in depth using a data analysis algorithm. The in-depth analysis of the data includes real-time monitoring of the status of the transmission line, identification of abnormal data, and prediction of potential faults.

[0074] S14: Monitoring and alarm, which displays the status information of the transmission line in real time through the user interface. When abnormal data and potential faults are detected, the alarm mechanism is immediately triggered to notify relevant personnel;

[0075] S15: Emergency response. When the monitoring system detects faults and abnormalities in the transmission line, it notifies the staff to immediately start the emergency response mechanism to ensure the safe and stable operation of the transmission system. The emergency response mechanism adopted includes notifying relevant personnel, starting the backup power supply and cutting off the faulty line.

[0076] As described above, the present invention effectively improves the monitoring efficiency and accuracy of transmission lines through the steps of system construction, data collection and transmission, data processing and analysis, real-time monitoring and alarm, and emergency response. It can identify abnormal data and predict potential faults in real time, trigger alarms in time and start emergency response mechanisms, thereby ensuring the safe and stable operation of the transmission system and significantly improving the reliability and safety of the power system.

[0077] Preferably, when designing the system architecture, the system architecture includes:

[0078] A11: Collection layer, responsible for real-time collection of transmission line parameters and data, including current, voltage, temperature and humidity;

[0079] A12: Network layer, responsible for transmitting the data collected by the collection layer to the remote data center in real time;

[0080] A13: Data layer, responsible for preprocessing the received raw data and storing and managing the processed data;

[0081] A14: Application layer, responsible for displaying the processed data to users in an intuitive and easy-to-understand manner, and providing various monitoring, alarm, analysis and decision support functions.

[0082] Preferably, the acquisition layer includes:

[0083] A21: Sensor network, used to build a monitoring network using multiple sensors, including current sensors, voltage sensors, temperature sensors, and humidity sensors;

[0084] A22: Data collection center, used to collect statistics on the data of the sensor network and other parallel monitoring systems, and send them to the data layer using the network layer;

[0085] A23: Self-powered module, used to provide continuous energy supply for sensor networks and data collection centers using renewable energy, including solar energy, wind energy and hydropower.

[0086] As described above, the present invention realizes comprehensive, real-time collection and efficient transmission of transmission line parameters by constructing a system architecture including an acquisition layer, a network layer, a data layer and an application layer. At the same time, the sensor network, the data acquisition center and the self-powered module in the acquisition layer not only improve the comprehensiveness and accuracy of data collection, but also provide a continuous and stable energy supply for the system through renewable energy, ensuring the long-term stable operation of the monitoring system, thereby providing strong technical support for the safety monitoring and emergency response of the power system. In addition, the data of other parallel monitoring systems can be counted and collected through the data acquisition center for unified management, thereby realizing the unification of communication protocols and data models of various sensing devices and the unified management of various online monitoring devices.

[0087] Preferably, the data collection center of the collection layer also has the following functions:

[0088] A31: Data decoding and repackaging: Decode the received data using different encoding methods, and repack the decoded data according to the requirements of subsequent processing and transmission to ensure the integrity and consistency of the data;

[0089] A32: Data integrity check, using different verification methods to verify the integrity of the data to ensure the accuracy and reliability of the data;

[0090] A33: Data correctness verification verifies the logical correctness of the data, including the verification of the data range, format and consistency.

[0091] As described above, the data acquisition center in the present invention not only ensures that the received data can be processed and transmitted completely and accurately through functions such as data decoding and repackaging, data integrity verification, and data correctness verification, but also greatly improves the reliability and consistency of the data, providing a solid foundation for subsequent data analysis and decision-making, thereby further improving the overall performance and accuracy of the transmission line monitoring system.

[0092] Preferably, when the data collection center of the collection layer performs data integrity verification, the verification methods adopted include:

[0093] A41: Count check, which verifies data integrity by counting the total number of records and the number of non-null values ​​in a specific field;

[0094] A42: Uniqueness check, ensuring that the specified special field is unique in the data;

[0095] A43: Checksum check: the integrity of the data is checked using the checksum calculated based on the data content. The calculation formula for the checksum includes:

[0096] Checksum = ((SUM1MOD255) + (SUM2MOD255) * 256) MOD255;

[0097] Where SUM1 is the sum of the data bytes, and SUM2 is the sum of the digits in SUM1.

[0098] Preferably, when the data collection center of the collection layer verifies the data correctness, the verification methods adopted include:

[0099] A51: Range check, verifying whether the data is within a specific range. For numerical data, a statistical method is used to determine whether the data is within a specific range. The principle formula of the statistical method is:

[0100]

[0101] Where X is the data point, μ is the mean, and σ is the standard deviation. When identifying outliers, when the size of Z calculated from data point X is greater than the set threshold, the data point X is marked as an outlier.

[0102] A52: Logical verification, using logical expressions to verify the logical relationship between data, thereby verifying the correctness of the data;

[0103] A53: Checksum verification, using the checksum to verify the data, so as to verify the correctness of the data;

[0104] A54: Customized verification formula: Write a customized verification formula based on specific business needs, and use the customized verification formula to verify the correctness of the data.

[0105] As described above, the present invention ensures data integrity by adopting counting verification, uniqueness verification and checksum-based verification value verification, and at the same time uses range verification (combined with statistical methods to identify abnormal values), logic verification, check code verification and custom verification formulas and other means to verify data correctness, which greatly enhances the data acquisition center's ability to ensure data accuracy and consistency, provides a high-quality data foundation for transmission line monitoring, and effectively improves the reliability and accuracy of the monitoring system.

[0106] Preferably, when preprocessing the received raw data to improve the quality and usability of the data, the following steps are included:

[0107] S21: Data filtering. First, the collected data is filtered to remove high-frequency noise and interference signals. The principle formula of the filtering process is:

[0108]

[0109] Among them, X(k) represents the frequency, x(n) represents the time domain signal, N represents the signal length, and k represents the frequency domain index;

[0110] S22: Data denoising processing, denoising the filtered data to further reduce the noise components in the data, wherein the principle formula of the denoising algorithm used is:

[0111]

[0112] Among them, W ψ (j,k) is the wavelet coefficient, M is the signal length, x[n] is the input signal, ψ j,k (n) is the wavelet function after scaling and translation, j is the scale parameter, and k is the translation parameter;

[0113] S23: Data standardization, including converting data into dimensionless form to ensure the accuracy and consistency of subsequent analysis;

[0114] S24: Data normalization processing, converting the data into data under a unified standard unit, wherein the principle formula of data normalization processing is:

[0115]

[0116] Among them, X ‘’ Represents the normalized value of data point X, X min represents the minimum value in the data set, X max Represents the maximum value in the data set.

[0117] As described above, the present invention effectively reduces high-frequency noise and interference signals in the original data through data filtering and denoising processing, and further converts the data into a dimensionless form and a unified standard unit through data standardization and normalization processing, which significantly improves the quality and availability of the data, and provides a more accurate and consistent data basis for subsequent data analysis and decision-making, thereby enhancing the performance and reliability of the transmission line monitoring system.

[0118] Preferably, after preprocessing, the data is analyzed in depth using a data analysis algorithm, including the following steps:

[0119] S31: real-time monitoring of the state of the transmission line, by receiving the operation data of the transmission line collected by the sensor network, and real-time monitoring of the operation state of the transmission line;

[0120] S32: Abnormal data identification, using the method of setting thresholds and using machine learning algorithms to identify abnormal data points and abnormal patterns;

[0121] S33: Predict potential failures, based on historical data and real-time monitoring data, using one of data mining algorithms, machine learning algorithms and deep learning algorithms to establish a prediction model to predict potential failures.

[0122] As described above, the present invention realizes a comprehensive and in-depth analysis of the operating status of transmission lines and fault warning by real-time monitoring of the status of transmission lines, identifying abnormal data using threshold setting and machine learning algorithms, and building a prediction model based on historical and real-time monitoring data to predict potential faults, thereby effectively improving the safety, stability and fault prevention capabilities of the power system.

[0123] Preferably, when using a machine learning algorithm to identify abnormal data points and abnormal patterns, the following steps are included:

[0124] S41: Data preparation and preprocessing, first obtain the real-time monitoring data of the transmission line from the IoT system, including current, voltage, temperature and humidity data, and preprocess the data to improve the quality and availability of the data;

[0125] S42: extracting useful features from the preprocessed raw data, including statistical features, time domain features, and frequency domain features, to obtain a training data set;

[0126] S43: Model selection and training: Select a suitable machine learning algorithm based on the characteristics of the data and the needs of anomaly detection, and use the training data set to train the selected machine learning algorithm and adjust the algorithm's hyperparameters to obtain the best performance;

[0127] S44: Anomaly detection and identification, apply the trained model to real-time monitoring data, calculate the anomaly score of each data point, set the anomaly score threshold according to actual needs, and mark the data point as an abnormal data point when the anomaly score exceeds the threshold. By analyzing the distribution and correlation characteristics of the abnormal data points, potential abnormal patterns can be identified.

[0128] As described above, the present invention uses machine learning algorithms to effectively identify abnormal data points and abnormal patterns in real-time monitoring data of transmission lines through steps such as data preparation, feature extraction, model selection and training, and anomaly detection and identification. This not only improves the accuracy and efficiency of anomaly detection, but also provides strong support for timely discovery of potential faults, further enhancing the safety and stability of the power system.

[0129] Preferably, when extracting useful features from the raw data after preprocessing, the feature extraction method used includes a hyperparameter method, wherein the principle formula of the hyperparameter method used is:

[0130] EMAt=αXt+(1-α)EMAt-1EMA t =αX t +(1-α)EMA t-1 EMAt=

[0131] αXt+(1-α)EMAt-1;

[0132] Among them, EMAt represents the exponential moving average at time t, α is a smoothing coefficient between 0 and 1, Xt represents the observed value at time t, and EMA t-1 represents the exponential moving average at time t-1, and 1-α represents the previous exponential moving average EMA t-1 Importance in calculating the current EMAt.

[0133] As described above, the present invention extracts features by adopting a hyperparameter method and calculates the exponential moving average, which can smooth the fluctuations in the original data, effectively capture the trends and periodic characteristics of time series data, improve the accuracy and efficiency of feature extraction, and provide more abundant and valuable information for subsequent machine learning model training and anomaly detection, thereby enhancing the performance of the transmission line monitoring system.

[0134] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. A self-powered power transmission online monitoring method based on the Internet of Things; characterized in that: The following steps are included: S11: System construction and equipment deployment, including system architecture design and equipment selection and deployment. When selecting and deploying equipment, sensors and monitoring equipment are installed on the transmission line. The installed sensors include current sensors, voltage sensors, temperature sensors and humidity sensors. S12: Data collection and transmission: using sensors installed on the transmission line to collect the working parameters of the transmission line in real time, and transmit the collected data to the monitoring equipment, which transmits the received data to the remote data center through the network; S13: Data processing and analysis: first, preprocessing the received raw data to improve the quality and availability of the data. After preprocessing, the data is analyzed in depth using a data analysis algorithm. The in-depth analysis of the data includes real-time monitoring of the status of the transmission line, identification of abnormal data, and prediction of potential faults. S14: Monitoring and alarm, which displays the status information of the transmission line in real time through the user interface. When abnormal data and potential faults are detected, the alarm mechanism is immediately triggered to notify relevant personnel; S15: Emergency response. When the monitoring system detects faults and abnormalities in the transmission line, it notifies the staff to immediately start the emergency response mechanism to ensure the safe and stable operation of the transmission system. The emergency response mechanism adopted includes notifying relevant personnel, starting the backup power supply and cutting off the faulty line.

2. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 1 is characterized in that: When designing the system architecture, the system architecture includes: A11: Collection layer, responsible for real-time collection of transmission line parameters and data, including current, voltage, temperature and humidity; A12: Network layer, responsible for transmitting the data collected by the collection layer to the remote data center in real time; A13: Data layer, responsible for preprocessing the received raw data and storing and managing the processed data; A14: Application layer, responsible for displaying the processed data to users in an intuitive and easy-to-understand manner, and providing various monitoring, alarm, analysis and decision support functions.

3. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 2 is characterized in that: The collection layer includes: A21: Sensor network, used to build a monitoring network using multiple sensors, including current sensors, voltage sensors, temperature sensors, and humidity sensors; A22: Data collection center, used to collect statistics on the data of the sensor network and other parallel monitoring systems, and send them to the data layer using the network layer; A23: Self-powered module, used to provide continuous energy supply for sensor networks and data collection centers using renewable energy, including solar energy, wind energy and hydropower.

4. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 3 is characterized in that: The data collection center of the collection layer also has the following functions: A31: Data decoding and repackaging: Decode the received data using different encoding methods, and repack the decoded data according to the requirements of subsequent processing and transmission to ensure the integrity and consistency of the data; A32: Data integrity check, using different verification methods to verify the integrity of the data to ensure the accuracy and reliability of the data; A33: Data correctness verification, verifying the logical correctness of the data, including verification of the data range, format and consistency.

5. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 4 is characterized in that: The data collection center of the collection layer uses the following verification methods when performing data integrity verification: A41: Count check, which verifies data integrity by counting the total number of records and the number of non-null values ​​in a specific field; A42: Uniqueness check, ensuring that the specified special field is unique in the data; A43: Checksum check: the integrity of the data is checked using the checksum calculated based on the data content. The calculation formula for the checksum includes: Checksum = ((SUM1MOD255) + (SUM2MOD255) * 256) MOD255; Where SUM1 is the sum of the data bytes, and SUM2 is the sum of the digits in SUM1.

6. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 5 is characterized in that: The data collection center of the collection layer uses the following verification methods when verifying the correctness of data: A51: Range check, verifying whether the data is within a specific range. For numerical data, a statistical method is used to determine whether the data is within a specific range. The principle formula of the statistical method is: Where X is the data point, μ is the mean, and σ is the standard deviation. When identifying outliers, when the size of Z calculated from data point X is greater than the set threshold, the data point X is marked as an outlier. A52: Logical verification, using logical expressions to verify the logical relationship between data, thereby verifying the correctness of the data; A53: Checksum verification, using the checksum to verify the data, so as to verify the correctness of the data; A54: Customized verification formula: Write a customized verification formula based on specific business needs, and use the customized verification formula to verify the correctness of the data.

7. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 6 is characterized in that: When preprocessing the received raw data to improve the quality and usability of the data, the following steps are included: S21: Data filtering. First, the collected data is filtered to remove high-frequency noise and interference signals. The principle formula of the filtering process is: Among them, X(k) represents the frequency, x(n) represents the time domain signal, N represents the signal length, and k represents the frequency domain index; S22: Data denoising processing, denoising the filtered data to further reduce the noise components in the data, wherein the principle formula of the denoising algorithm used is: Among them, W ψ (j,k) is the wavelet coefficient, M is the signal length, x[n] is the input signal, ψ j,k (n) is the wavelet function after scaling and translation, j is the scale parameter, and k is the translation parameter; S23: Data standardization, including converting data into dimensionless form to ensure the accuracy and consistency of subsequent analysis; S24: Data normalization processing, converting the data into data under a unified standard unit, wherein the principle formula of data normalization processing is: Among them, X ‘’ Represents the normalized value of data point X, X min represents the minimum value in the data set, X max Represents the maximum value in the data set.

8. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 7 is characterized in that: When using data analysis algorithms to conduct in-depth analysis of data after preprocessing, the following steps are included: S31: real-time monitoring of the state of the transmission line, by receiving the operation data of the transmission line collected by the sensor network, and real-time monitoring of the operation state of the transmission line; S32: Abnormal data identification, using the method of setting thresholds and using machine learning algorithms to identify abnormal data points and abnormal patterns; S33: Predict potential failures, based on historical data and real-time monitoring data, using one of data mining algorithms, machine learning algorithms and deep learning algorithms to establish a prediction model to predict potential failures.

9. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 8, characterized in that: When using machine learning algorithms to identify abnormal data points and abnormal patterns, the following steps are included: S41: Data preparation and preprocessing, first obtain the real-time monitoring data of the transmission line from the IoT system, including current, voltage, temperature and humidity data, and preprocess the data to improve the quality and availability of the data; S42: extracting useful features from the preprocessed raw data, including statistical features, time domain features, and frequency domain features, to obtain a training data set; S43: Model selection and training: Select a suitable machine learning algorithm based on the characteristics of the data and the needs of anomaly detection, and use the training data set to train the selected machine learning algorithm and adjust the algorithm's hyperparameters to obtain the best performance; S44: Anomaly detection and identification, apply the trained model to real-time monitoring data, calculate the anomaly score of each data point, set the anomaly score threshold according to actual needs, and mark the data point as an abnormal data point when the anomaly score exceeds the threshold. By analyzing the distribution and correlation characteristics of the abnormal data points, potential abnormal patterns can be identified.

10. The method for online monitoring of self-powered power transmission based on the Internet of Things according to claim 9, characterized in that: When extracting useful features from the raw data after preprocessing, the feature extraction method used includes a hyperparameter method, wherein the principle formula of the hyperparameter method used is: EMAt=αXt+(1-α)EMAt-1EMA t =αX t +(1-α)EMA t-1 EMAt= αXt+(1-α)EMAt-1; Among them, EMAt represents the exponential moving average at time t, α is a smoothing coefficient between 0 and 1, Xt represents the observed value at time t, and EMA t-1 represents the exponential moving average at time t-1, and 1-α represents the previous exponential moving average EMA t-1 Importance in calculating the current EMAt.

Images