Integrated device for adding potential safety hazard to current collection line

Abstract

The invention, which relates to the field of power system monitoring and management, provides a power line installation potential safety hazard integrated device comprising a data acquisition unit, a signal processing unit, a data analysis unit, a positioning early warning unit, a data learning module and a big data unit. The data acquisition unit comprises a double-end traveling wave sensor module for acquiring traveling wave signals at the two ends of the power line in real time; by means of the design, a fault tower can be rapidly and accurately positioned, line operation and maintenance personnel can be guided to rapidly find a fault point, rapid and accurate fault positioning is achieved, the problem that the detection effect is low by means of manual inspection or using a simple instrument is solved, real-time monitoring, analysis and positioning can be conducted, the operation and maintenance personnel can be timely notified to go to the site for troubleshooting, and the working efficiency is improved. According to the method, line fault tripping is avoided, fault traveling waves collected each time can be compared with a big data expert database for analysis, and operation and maintenance personnel go to the site to handle faults, continuously learn and improve and adapt to continuously changing environmental conditions.

Description

Technical Field

[0001] The present invention relates to the field of power system monitoring and management, and in particular to a device for integrating safety hazards installed on a collector line. Background Art

[0002] The collector line is an important component of wind farms and photovoltaic power stations. Its function is to concentrate the scattered electricity and transmit it to the load through the construction of high-voltage transmission lines, and efficiently transmit the electricity of multiple wind turbines to the substation for further delivery to the power grid.

[0003] In life, collector lines are very susceptible to tripping accidents caused by various natural factors such as lightning, dirt, animals and plants, slight disturbances, external force damage, etc. Every tripping failure, in addition to bringing impact to the wind farm power network, will also cause damage to insulators, wires and other facilities, leaving safety hazards to the system operation. If the fault cannot be quickly eliminated, it will cause a large amount of wind turbine electricity to be unable to be delivered, causing direct losses to the wind farm's electricity production.

[0004] Therefore, the present invention provides an integrated device for removing safety hazards installed on the collector line. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and provide an integrated device for installing safety hazards on a collector line.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: the collector line is equipped with an integrated safety hazard device, including a data acquisition unit, a signal processing unit, a data analysis unit, a positioning warning unit, a data learning module and a big data unit;

[0007] The data acquisition unit includes a double-end traveling wave sensor module for real-time acquisition of traveling wave signals at both ends of the power line, and an environmental monitoring module for real-time monitoring of the operating status of the power system;

[0008] The signal processing unit includes a wavelet transform module for preprocessing received data and extracting key feature information, and a GPS synchronous clock module for ensuring the time accuracy of all operations and providing an accurate time reference for data analysis.

[0009] As a preferred embodiment, the environmental monitoring module includes a voltage sensor for measuring the voltage value in the electrical system, a current sensor for monitoring the current flow in the electrical system, a temperature sensor for monitoring the ambient temperature and the operating temperature of the equipment, and a humidity sensor for monitoring the ambient humidity level.

[0010] As a preferred embodiment, the analysis module includes a data comparison submodule for comparing current data with historical data to find out changing trends and abnormal points, an abnormality detection submodule for detecting abnormal conditions in data through algorithms, a data repair submodule for repairing and filling damaged or missing data, a predictive maintenance submodule for predicting possible future problems based on historical data and current data and performing maintenance in advance, and a fault construction submodule for constructing a fault model based on the data analysis results to provide a basis for subsequent fault diagnosis and location.

[0011] As a preferred embodiment, the positioning and warning unit includes a double-end traveling wave positioning module for quickly and accurately determining the fault location using double-end traveling wave positioning technology, a warning decision module for making corresponding response measures based on the positioning results, and a notification module for issuing an alarm to inform the fault situation and countermeasures.

[0012] As a preferred implementation, the data learning unit includes an optimization module for continuously adjusting optimization algorithm parameters according to new data, and a multi-source data fusion module for integrating data from different sensors.

[0013] As a preferred embodiment, the optimization module includes a time-frequency analysis submodule for analyzing data in the time domain and frequency domain to extract more useful feature information, a feature selection submodule for selecting the most representative and discriminative features from a large number of features to improve the accuracy and efficiency of the model, a model training submodule for training data using a machine learning algorithm to establish a prediction model, a model optimization submodule for optimizing the trained model, and an incremental learning submodule for dynamically updating and optimizing the model as new data is continuously added.

[0014] As a preferred implementation, the large number unit includes a fault traveling wave database for storing traveling wave data related to the fault, so as to facilitate fault analysis and location.

[0015] As a preferred embodiment, the guidance module includes a pattern matching submodule for matching current data with known patterns to find the most similar pattern, a classification submodule for classifying data, a decision submodule for making decision recommendations based on data analysis results, and a solution optimization submodule for optimizing and adjusting decision solutions.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are:

[0017] The present invention can quickly detect faults and abnormal conditions in the power system by setting up an integrated device for safety hazards on the collector line to collect the traveling wave signals and environmental monitoring data at both ends of the power line in real time through the data acquisition unit. The signal processing unit and the data analysis unit pre-process and deeply analyze the received data, thereby quickly identifying potential problems. This design can quickly and accurately locate the faulty tower, guide the line operation and maintenance personnel to quickly find the fault point, and realize fast and accurate fault location, thereby solving the problem of low detection effect by relying on manual inspection or using simple instruments.

[0018] Through multi-dimensional analysis of the collected data, including time domain and frequency domain analysis, feature selection, pattern recognition, etc., these analyses can not only identify the current fault point, but also predict possible problems in the future and perform maintenance in advance; such a design can perform real-time monitoring, analysis, and positioning, and promptly notify the operation and maintenance personnel to go to the site for investigation to avoid line fault tripping, thereby effectively reducing the probability of faults, extending the service life of the equipment, and reducing maintenance costs;

[0019] The data learning unit continuously adjusts and optimizes algorithm parameters based on new data, and integrates data from different sensors through multi-source data fusion technology to form a unified data set for subsequent analysis. The big data unit is used to store historical fault data to facilitate long-term trend analysis and fault location. With this design, the fault traveling waves collected each time will be compared and analyzed with the company's fault traveling wave big data expert library. For different types of line faults, the nature of the fault can be identified, the cause of the fault can be diagnosed, and technical guidance can be provided for operation and maintenance personnel to deal with the fault on site. Continuous learning and improvement can be achieved to adapt to changing environmental conditions and maintain efficient performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of installing an integrated device for potential safety hazards on a collector line provided by the present invention;

[0021] Figure 2 A schematic diagram of a data acquisition unit for installing a safety hazard integrated device on a collector line provided by the present invention;

[0022] Figure 3 A schematic diagram of a signal processing unit for installing a safety hazard integrated device on a collector line provided by the present invention;

[0023] Figure 4 A schematic diagram of a data analysis unit for installing a safety hazard integrated device on a collector line provided by the present invention;

[0024] Figure 5 A diagram of a positioning and early warning unit for installing an integrated device for potential safety hazards on a collector line provided by the present invention;

[0025] Figure 6 A schematic diagram of a data learning module for installing an integrated device for potential safety hazards on a collector line provided by the present invention;

[0026] Figure 7 A schematic diagram of a big data unit for installing a safety hazard integrated device on a collector line provided by the present invention;

[0027] Figure 8 Operation flow chart of the integrated device for installing safety hazards on the collector line provided by the present invention DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0029] like Figure 1 - Figure 7 As shown, this embodiment provides a technical solution: a safety hazard integrated device is installed on the collector line, including a data acquisition unit, a signal processing unit, a data analysis unit, a positioning warning unit, a data learning module and a big data unit;

[0030] The data acquisition unit includes a double-end traveling wave sensor module for real-time acquisition of traveling wave signals at both ends of the power line, and an environmental monitoring module for real-time monitoring of the operating status of the power system;

[0031] The double-ended traveling wave sensor module is built on the basis of Fourier transformation. The double-ended traveling wave sensor module collects the traveling wave signals at both ends of the power line in real time. These signals are used to detect faults and abnormal conditions in the power system. By monitoring the changes in the traveling wave signals, the fault point in the line can be quickly identified, thereby greatly shortening the fault location time;

[0032] The environmental monitoring module includes a voltage sensor for measuring the voltage value in the electrical system, a current sensor for monitoring the current flow in the electrical system, a temperature sensor for monitoring the ambient temperature and the operating temperature of the equipment, and a humidity sensor for monitoring the ambient humidity level;

[0033] The voltage sensor and current sensor included in the environmental monitoring module can comprehensively monitor the operating status of the power system and provide multi-dimensional environmental data to help operation and maintenance personnel better understand the working conditions of the system. The temperature sensor can monitor the temperature changes of the equipment to prevent equipment damage caused by overheating; the humidity sensor can monitor the humidity level in the environment to prevent electrical failures caused by moisture;

[0034] like Figure 1 , Figure 3 and Figure 8 As shown, the signal processing unit includes a wavelet transform module for preprocessing the received data and extracting key feature information, and a GPS synchronization clock module for ensuring the time accuracy of all operations and providing an accurate time reference for data analysis;

[0035] The wavelet transform module pre-processes the received data and extracts key feature information, which can effectively extract useful information from complex signals. The GPS synchronization clock module ensures the time accuracy of all operations and provides an accurate time reference for data analysis. High-precision time synchronization can also locate faults and ensure that data at different locations are accurately recorded and analyzed at the same time point, thereby improving the accuracy of fault detection.

[0036] like Figure 1 , Figure 4 and Figure 8 The data analysis unit shown includes a feature extraction module for extracting key information from the processed data, a pattern recognition module for analyzing the information to identify potential problems, and an analysis module for further in-depth analysis of the identified problems;

[0037] The feature extraction module is built on the basis of the linear discriminant analysis algorithm. The feature extraction module extracts key information from the processed data. This information usually includes characteristic parameters such as signal amplitude, frequency, and phase. The pattern recognition module is built on the basis of the neural network algorithm. Through machine learning algorithms or statistical methods, this module can automatically identify abnormal patterns in the data. The analysis module further analyzes the identified problems.

[0038] The analysis module includes a data comparison submodule for comparing current data with historical data to find out the trend of changes and abnormal points, an anomaly detection submodule for detecting abnormal conditions in data through algorithms, a data repair submodule for repairing and filling damaged or missing data, a predictive maintenance submodule for predicting possible problems in the future based on historical data and current data and performing maintenance in advance, and a fault construction submodule for constructing a fault model based on the data analysis results to provide a basis for subsequent fault diagnosis and location;

[0039] The data comparison submodule is built on the basis of the differential algorithm. It is responsible for comparing the current data with the historical data to find out the changing trends and anomalies. The anomaly detection submodule is built on the basis of the isolation forest and local anomaly factor algorithms to detect anomalies in the data, so as to timely discover potential faults. The data repair submodule is built on the basis of the interpolation algorithm and the fitting algorithm to repair and fill in the damaged or missing data. In practical applications, some data may be lost or damaged due to various reasons. The data repair submodule repairs and fills in these data to ensure the integrity of the data. The predictive maintenance submodule is built on the basis of time series prediction and machine learning prediction models. Based on historical data and current data, it predicts possible problems in the future, so as to take maintenance measures in advance to avoid the occurrence of faults. The fault construction submodule is built on the basis of the decision tree. According to the data analysis results, a fault model is constructed to provide a basis for subsequent fault diagnosis and location.

[0040] like Figure 1 , Figure 5 and Figure 8 The positioning and warning unit shown includes a double-end traveling wave positioning module for quickly and accurately determining the fault location using the double-end traveling wave positioning technology, a warning decision module for making corresponding response measures according to the positioning result, and a notification module for issuing an alarm to inform the fault situation and countermeasures;

[0041] The dual-end traveling wave positioning module is built on the basis of the least squares algorithm. It uses the dual-end traveling wave positioning technology to quickly and accurately determine the fault location. The early warning decision module makes corresponding response measures based on the positioning results. Once the fault location is determined, the module makes response measures according to the preset. The notification module is responsible for issuing an alarm to inform the fault situation and response measures. The module can send alarm information to relevant personnel through SMS, email, sound, etc.

[0042] like Figure 1 , Figure 6 and Figure 8 The data learning unit shown includes an optimization module for continuously adjusting optimization algorithm parameters according to new data, and a multi-source data fusion module for integrating data from different sensors;

[0043] The optimization module continuously adjusts the optimization algorithm parameters according to the new data. The multi-source data fusion module is built on the basis of Kalman filtering and particle filtering, integrating data from different sensors and fusing these data into a unified data set for subsequent analysis.

[0044] The optimization module includes a time-frequency analysis submodule for analyzing the data in the time domain and frequency domain to extract more useful feature information, a feature selection submodule for selecting the most representative and discriminative features from a large number of features to improve the accuracy and efficiency of the model, a model training submodule for training the data using a machine learning algorithm to establish a prediction model, a model optimization submodule for optimizing the trained model, and an incremental learning submodule for dynamically updating and optimizing the model as new data is continuously added;

[0045] The time-frequency analysis submodule is built on the basis of Fourier transform and short-time Fourier transform. It analyzes the data in time domain and frequency domain to extract more useful feature information. Time domain analysis focuses on the change law of the signal over time, while frequency domain analysis focuses on the frequency components of the signal and its distribution. By combining the analysis of time domain and frequency domain, we can have a more comprehensive understanding of the characteristics of the signal and extract more useful information. The feature selection submodule is built on the basis of PCA and LDA algorithms. It selects the most representative and discriminative features from many features to improve the accuracy of the model. In practical applications, due to the large number of sensors and the fact that each sensor may generate a large amount of data, it is necessary to select the most representative and discriminative features. The model training submodule is built on the basis of SVM and neural network algorithms, and uses machine learning algorithms to train data to establish a prediction model. The model optimization submodule is built on the basis of gradient descent and genetic algorithms, and optimizes the trained model to improve its performance and accuracy. The incremental learning submodule is built on the basis of transfer learning algorithms. As new data is continuously added, the model is dynamically updated and optimized. In actual applications, due to the continuous changes in the environment and conditions, the original model may no longer be applicable or its performance may degrade. This submodule can use incremental learning methods to dynamically update and optimize the model to adapt to the new environment and conditions, thereby improving the stability of the model.

[0046] like Figure 1 , Figure 7 and Figure 8 The large data unit shown includes a fault traveling wave database for storing traveling wave data related to faults to facilitate fault analysis and location;

[0047] The optimization module is built on the basis of gradient descent method and genetic algorithm, and the optimization algorithm parameters are continuously adjusted according to the new data. The multi-source data fusion module is built on the basis of Kalman filter and particle filter, which integrates the data from different sensors and fuses them into a unified data set for subsequent analysis.

[0048] The guidance module includes a pattern matching submodule for matching current data with known patterns to find the most similar pattern, a classification submodule for classifying data, a decision submodule for making decision suggestions based on data analysis results, and a solution optimization submodule for optimizing and adjusting decision solutions;

[0049] The fault traveling wave database is used to store traveling wave data related to the fault, which is convenient for fault analysis and location. The fault traveling wave database uses the NoSQL database management system to store and manage data. The pattern matching submodule matches the current data with the known pattern to find the most similar pattern. It is built on the basis of the nearest neighbor algorithm. The classification submodule classifies the data and makes decision suggestions based on the data analysis results. It is built on the basis of decision tree and support vector machine algorithms. The decision submodule makes decision suggestions based on the data analysis results. The solution optimization submodule: optimizes and adjusts the decision plan with the cooperation of temperature and humidity sensors to improve its feasibility and effectiveness. It is built on the basis of genetic algorithm and simulated annealing algorithm.

[0050] Working principle:

[0051] like Figure 1 - Figure 8 As shown:

[0052] When in use: First, the data acquisition unit obtains the traveling wave signals and system operation status data at both ends of the power line in real time through the double-end traveling wave sensor module and the environmental monitoring module. The double-end traveling wave sensor module uses Fourier transform technology to capture the traveling wave signals in the line and detect faults and abnormal conditions in the power system. At the same time, the environmental monitoring module monitors the status of the power system and equipment through voltage sensors, current sensors, temperature sensors and humidity sensors, and comprehensively collects the operating data of the environment and electrical system. Then the signal processing unit pre-processes the collected data, and the wavelet transform module extracts key feature information from the complex signal, making the data more concise and meaningful, improving the data quality. At the same time, the GPS synchronization clock module ensures that all collected All the data in the data set have accurate timestamps to ensure the time accuracy of data analysis, which provides a reliable time reference for subsequent fault location and pattern analysis. Next, the data analysis unit conducts in-depth analysis on the processed data. The feature extraction module uses the linear discriminant analysis algorithm to extract the key features of the signal such as amplitude, frequency, and phase, while the pattern recognition module automatically identifies abnormal patterns in the data through the neural network algorithm to discover potential problems in a timely manner. The further analysis module conducts detailed analysis on the identified anomalies, including comparing with historical data to find out the trend of changes, applying the anomaly detection algorithm to identify abnormal points in the data, and repairing the damaged or missing data through the data repair submodule to ensure the integrity of the data. In addition, the predictive maintenance module is based on historical data. The fault construction submodule constructs a fault model based on data analysis to provide a basis for subsequent fault diagnosis and location. At the same time, the positioning and warning unit uses the double-end traveling wave positioning technology to accurately determine the fault location through the least squares algorithm. The positioning result drives the warning decision module to make a response decision. Once the fault location is determined, the warning decision module immediately makes the predetermined response measures. Finally, the notification module is responsible for issuing an alarm in time to inform relevant personnel of the fault situation and provide specific response measures to ensure that the operation and maintenance personnel can respond quickly and handle it. Secondly, the data learning unit continuously optimizes and adjusts the system performance under the input of new data. The optimization module is based on the new The data automatically adjusts the algorithm parameters to improve the prediction accuracy of the entire system. The multi-source data fusion module fuses data from different sensors through Kalman filtering and particle filtering algorithms to form a unified data set for subsequent analysis. The time-frequency analysis submodule performs a comprehensive analysis of the data in the time domain and frequency domain. The feature selection submodule selects the most representative and discriminative features to further improve the accuracy and efficiency of the model. Finally, the big data unit provides historical data support by storing and managing fault traveling wave data, which facilitates subsequent fault analysis and location. The fault traveling wave database uses the NoSQL database management system for storage to ensure efficient data management and query. The pattern matching submodule finds the most similar fault mode by comparing it with the known mode.Provide input for the classification submodule to quickly identify the fault type. The decision submodule combines the data analysis results to provide a fault response plan, and continuously optimizes and adjusts the decision plan through the solution optimization submodule to ensure its feasibility.

[0053] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. The collector line is equipped with an integrated device for potential safety hazards, which is characterized by: It includes data acquisition unit, signal processing unit, data analysis unit, positioning warning unit, data learning module and big data unit; The data acquisition unit includes a double-end traveling wave sensor module for real-time acquisition of traveling wave signals at both ends of the power line, and an environmental monitoring module for real-time monitoring of the operating status of the power system; The signal processing unit includes a wavelet transform module for preprocessing the received data and extracting key feature information, and a GPS synchronous clock module for ensuring the time accuracy of all operations and providing an accurate time reference for data analysis; The data analysis unit includes a feature extraction module for extracting key information from the processed data, a pattern recognition module for analyzing the information to identify potential problems, and an analysis module for further in-depth analysis of the identified problems.

2. The integrated device for removing potential safety hazards installed on the collector line according to claim 1, characterized in that: The environmental monitoring module includes a voltage sensor for measuring the voltage value in the electrical system, a current sensor for monitoring the current flow in the electrical system, a temperature sensor for monitoring the ambient temperature and the operating temperature of the equipment, and a humidity sensor for monitoring the ambient humidity level.

3. The integrated device for removing potential safety hazards installed on the collector line according to claim 1, characterized in that: The analysis module includes a data comparison submodule for comparing current data with historical data to find out changing trends and abnormal points, an abnormality detection submodule for detecting abnormal conditions in data through algorithms, a data repair submodule for repairing and filling damaged or missing data, a predictive maintenance submodule for predicting possible problems in the future based on historical data and current data and performing maintenance in advance, and a fault construction submodule for constructing a fault model based on the data analysis results to provide a basis for subsequent fault diagnosis and location.

4. The integrated device for removing potential safety hazards installed on the collector line according to claim 1, characterized in that: The positioning and warning unit includes a double-end traveling wave positioning module for quickly and accurately determining the fault location using double-end traveling wave positioning technology, a warning decision module for making corresponding response measures according to the positioning result, and a notification module for issuing an alarm to inform the fault situation and response measures.

5. The integrated device for removing potential safety hazards installed on the collector line according to claim 4 is characterized in that: The data learning unit includes an optimization module for continuously adjusting optimization algorithm parameters according to new data, and a multi-source data fusion module for integrating data from different sensors.

6. The integrated device for removing potential safety hazards installed on the collector line according to claim 1, characterized in that: The optimization module includes a time-frequency analysis submodule for analyzing data in the time domain and frequency domain to extract more useful feature information, a feature selection submodule for selecting the most representative and discriminative features from a large number of features to improve the accuracy and efficiency of the model, a model training submodule for training data using a machine learning algorithm to establish a prediction model, a model optimization submodule for optimizing the trained model, and an incremental learning submodule for dynamically updating and optimizing the model as new data is continuously added.

7. The integrated device for removing potential safety hazards installed on the collector line according to claim 1, characterized in that: The large number unit includes a fault traveling wave database for storing traveling wave data related to faults, so as to facilitate fault analysis and positioning.

8. The integrated device for removing potential safety hazards installed on the collector line according to claim 7, characterized in that: The guidance module includes a pattern matching submodule for matching current data with known patterns to find the most similar pattern, a classification submodule for classifying data, a decision submodule for making decision suggestions based on data analysis results, and a solution optimization submodule for optimizing and adjusting decision solutions.

Images