Mountainous area power distribution network line fault sensing system and method

Abstract

The invention provides a mountain area power distribution network line fault sensing system and method, and relates to the technical field of mountain area power distribution network line fault sensing, and the method comprises the steps: deploying various types of sensors at each line key node of a mountain area power distribution network, and collecting the electric quantity data, environment data and line physical state data of a line in real time; the collected data are transmitted to a data processing center through a wireless communication module; the data processing center preprocesses the received data, removes noise and abnormal values, and then constructs a fault prediction model by using a deep learning algorithm to improve the fault prediction accuracy: abundant data are collected through various types of sensors, and the fault prediction model is constructed by using the deep learning algorithm to improve the fault prediction accuracy; the method can comprehensively consider the electrical quantity, environment, physical state and other factors of the line, greatly improves the fault prediction accuracy compared with a traditional method, discovers the potential fault hidden danger in advance, and strives for more processing time for operation and maintenance personnel.

Description

Technical Field

[0001] The present invention belongs to the technical field of line fault sensing of a distribution network in mountainous areas, and more specifically, particularly relates to a system and method for sensing line faults of a distribution network in mountainous areas. Background Art

[0002] As a key infrastructure to ensure the living and production electricity consumption of mountain residents, mountain distribution network plays an important role in the power supply system. However, the special geographical environment and climatic conditions in mountainous areas have brought many severe challenges to the safe and stable operation of distribution network.

[0003] Mountainous areas have complex terrain, and distribution network lines usually need to cross mountains, deep valleys and rivers, and the lines are widely distributed and scattered. This not only increases the difficulty of line construction and maintenance, but also makes the lines more vulnerable to natural disasters such as lightning strikes, landslides, and mud-rock flows. For example, in the lightning-prone season, lightning strikes can easily cause line insulation breakdown and cause short-circuit faults; while landslides and mud-rock flows may damage the foundation of the tower, causing the line tower to tilt and collapse, and then cause line disconnection and other faults.

[0004] In addition, the climate in mountainous areas is changeable, with large temperature differences between day and night and high humidity. These factors will accelerate the aging and corrosion of line equipment. Long-term exposure to high humidity will cause the metal parts of the line to rust easily, reducing the mechanical strength and electrical performance of the equipment; and the large temperature difference between day and night will cause the line material to expand and contract, resulting in loose connection parts of the line, increasing contact resistance and causing overheating failures.

[0005] Traditional fault detection methods for distribution networks in mountainous areas mainly rely on manual inspections and simple electrical quantity monitoring. Manual inspections are limited by the complex terrain and poor traffic conditions in mountainous areas. The inspection cycle is long and the efficiency is low, making it difficult to detect potential fault hazards in real time. Moreover, manual inspections are easily affected by subjective factors, and some hidden faults may not be detected in time. Simple electrical quantity monitoring, such as monitoring only parameters such as voltage and current, is difficult to accurately determine the occurrence and type of faults in the early stages of a fault when the electrical quantity changes are not obvious.

[0006] With the continuous growth of electricity demand and the increasing requirements for power supply reliability, the existing fault detection methods can no longer meet the needs of safe and stable operation of mountain distribution networks. Therefore, it is of great practical significance to develop a system and method that can accurately and real-timely sense line faults in mountain distribution networks. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a system and method for sensing line faults in a mountain distribution network to solve the above problems.

[0008] The method for sensing line faults in mountainous distribution networks includes: Deploy various types of sensors at key nodes of each line of the mountain distribution network to collect real-time data on electrical quantities, environment, and physical status of the lines; The collected data is transmitted to the data processing center through the wireless communication module; The data processing center pre-processes the received data to remove noise and outliers, and then uses deep learning algorithms to build a fault prediction model to predict the probability of line faults based on real-time data; When the predicted failure probability exceeds the preset threshold, the data processing center determines the failure type based on the failure type identification algorithm and issues a failure warning message.

[0009] Preferably, the multiple types of sensors include but are not limited to current sensors, voltage sensors, temperature sensors, humidity sensors and image sensors, wherein the image sensor is used to collect the appearance image of the line to monitor whether the line is physically damaged. The wireless communication module adopts LoRa or 5G communication technology to ensure the stability and real-time performance of data transmission, and signal relay equipment is added in areas with weak signals. In the data preprocessing process, the 3σ principle based on statistics is adopted for the processing of outliers, and the wavelet denoising algorithm is used to remove noise. The deep learning algorithm adopts a model combining a convolutional neural network (CNN) and a long short-term memory network (LSTM), wherein CNN is used to extract the spatial features of the data, and LSTM is used to process the time series features of the data to improve the accuracy of fault prediction.

[0010] The mountain distribution network line fault sensing system includes: Sensor deployment module, used to deploy various types of sensors at key nodes of distribution network lines in mountainous areas; A data transmission module, which uses wireless communication technology to transmit the data collected by the sensor to the data processing center; The data processing module pre-processes the received data and uses deep learning algorithms to build fault prediction models and fault type identification algorithms; The early warning module issues a fault warning message when the fault prediction probability exceeds a preset threshold.

[0011] Preferably, the sensors in the sensor deployment module have self-calibration and self-diagnosis functions, and can regularly detect and calibrate their own status to ensure the accuracy of data collection. The data transmission module is equipped with a backup power supply, and can continue to work for a certain period of time when the city power is interrupted to ensure uninterrupted data transmission. The data processing module has the function of updating the fault prediction model in real time, and regularly trains and optimizes the model according to the newly collected data. The early warning module can send fault warning information to operation and maintenance personnel through various methods such as text messages, voice, and sound and light alarms, and record the warning information in the database for subsequent query and analysis.

[0012] Compared with the prior art, the present invention has the following beneficial effects: Improve the accuracy of fault prediction: By collecting rich data through various types of sensors and using deep learning algorithms to build a fault prediction model, it can comprehensively consider multiple factors such as the electrical quantity, environment, and physical state of the line. Compared with traditional methods, it greatly improves the accuracy of fault prediction, discovers potential fault hazards in advance, and buys more processing time for operation and maintenance personnel.

[0013] Quickly and accurately identify fault types: Combined with the fault type identification algorithm, the fault type can be quickly determined after the fault is predicted to occur, which helps operation and maintenance personnel to formulate targeted emergency repair plans, shorten fault handling time, and reduce power outage losses.

[0014] Real-time monitoring and early warning: wireless communication technology is used to realize real-time data transmission. The data processing center processes data in real time and issues early warning information, so that operation and maintenance personnel can grasp the line fault situation at the first time, take timely measures, and improve the emergency response capability of the distribution network.

[0015] Reduce operation and maintenance costs: Reduce the workload and frequency of manual inspections, and avoid unnecessary manual inspection costs. At the same time, by predicting faults in advance and handling them quickly, the degree of damage to equipment caused by faults is reduced, the cost of equipment maintenance and replacement is reduced, and the operating efficiency and economic benefits of the distribution network are improved.

[0016] Improve power supply reliability: Timely detection and handling of faults effectively reduces the duration and scope of power outages, ensures normal electricity supply for residents and enterprises in mountainous areas, improves power supply reliability, and plays an important role in promoting economic development and social stability in mountainous areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a topological diagram of the overall system for sensing line faults in a mountainous distribution network according to the present invention; Figure 2 It is a topological diagram of the system architecture of the present invention; Figure 3 It is a topological diagram of the system for realizing the functions of the present invention; Figure 4 It is the system topology diagram of the advantages of the system of the present invention; Figure 5 It is a system topology diagram of the application scenario of the present invention. DETAILED DESCRIPTION

[0018] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0019] See also Figure 1-Figure 5 The present invention provides a method for sensing line faults in a mountainous distribution network, comprising: Deploy various types of sensors at key nodes of each line of the mountain distribution network to collect real-time data on electrical quantities, environment, and physical status of the lines; The collected data is transmitted to the data processing center through the wireless communication module; The data processing center pre-processes the received data to remove noise and outliers, and then uses deep learning algorithms to build a fault prediction model to predict the probability of line faults based on real-time data; When the predicted failure probability exceeds the preset threshold, the data processing center determines the failure type based on the failure type identification algorithm and issues a failure warning message.

[0020] The multiple types of sensors include but are not limited to current sensors, voltage sensors, temperature sensors, humidity sensors and image sensors, wherein the image sensor is used to collect the appearance image of the line to monitor whether the line is physically damaged. The wireless communication module adopts LoRa or 5G communication technology to ensure the stability and real-time performance of data transmission, and signal relay equipment is added in areas with weak signals. In the data preprocessing process, the 3σ principle based on statistics is adopted for the processing of abnormal values, and the wavelet denoising algorithm is adopted for noise removal. The deep learning algorithm adopts a model combining a convolutional neural network (CNN) and a long short-term memory network (LSTM). CNN is used to extract the spatial features of the data, and LSTM is used to process the time series features of the data to improve the accuracy of fault prediction.

[0021] The mountain distribution network line fault sensing system includes: Sensor deployment module, used to deploy various types of sensors at key nodes of distribution network lines in mountainous areas; A data transmission module, which uses wireless communication technology to transmit the data collected by the sensor to the data processing center; The data processing module pre-processes the received data and uses deep learning algorithms to build fault prediction models and fault type identification algorithms; The early warning module issues a fault warning message when the fault prediction probability exceeds a preset threshold.

[0022] The sensors in the sensor deployment module have self-calibration and self-diagnosis functions, and can regularly detect and calibrate their own status to ensure the accuracy of data collection. The data transmission module is equipped with a backup power supply and can continue to work for a certain period of time when the city power is interrupted to ensure uninterrupted data transmission. The data processing module has the function of updating the fault prediction model in real time, and regularly trains and optimizes the model according to the newly collected data. The early warning module can send fault warning information to operation and maintenance personnel through various methods such as text messages, voice, and sound and light alarms, and record the warning information in the database for subsequent query and analysis. Example

[0023] Example 1: Basic configuration example: On a 10-kilometer-long line of a distribution network in a mountainous area, a key node is selected every 2 kilometers to deploy current sensors, voltage sensors, and temperature sensors. The wireless communication module uses LoRa technology, and the data processing center is equipped with a high-performance server. A simple linear regression algorithm is used to conduct a preliminary analysis of the collected data, and the fault probability threshold is set to 0.7. When the predicted fault probability exceeds the threshold, an early warning message is sent to the operation and maintenance personnel via SMS. Within one month of operation, two potential faults were successfully predicted and warned. After inspection by the operation and maintenance personnel, it was found that both were caused by loose connection parts of the line, resulting in a slight increase in temperature.

[0024] Embodiment 2: Multi-sensor expansion embodiment: In another similar mountain distribution network line, in addition to deploying current, voltage and temperature sensors, image sensors were installed on the towers to monitor the appearance of the line. The wireless communication module was upgraded to 5G technology to increase the data transmission speed. The data processing center uses a simple neural network model in the deep learning algorithm for fault prediction. The fault threshold is set to 0.65, and a voice alarm is added as the early warning method. After one month of operation, the system not only accurately predicted three potential faults, but also discovered a damaged line sheath through the image sensor, which was repaired in time to avoid the occurrence of faults.

[0025] Embodiment 3: Data processing optimization embodiment: The same sensors as those in Example 2 are deployed in the distribution network lines in a complex mountainous terrain. In the data preprocessing stage, advanced wavelet denoising algorithms and outlier processing methods based on cluster analysis are used. The data processing center uses convolutional neural networks (CNN) to build a fault prediction model. The fault threshold is set to 0.6, and the warning methods include SMS, voice, and sound and light alarms in the station. During the one-month operation period, the system successfully predicted 4 faults, and in a voltage sag fault caused by a lightning strike, the fault type was accurately identified, providing strong support for rapid repairs.

[0026] Embodiment 4: Model update embodiment: A variety of sensors are deployed and 5G communication is used on a mountain distribution network line that is greatly affected by severe weather. The data processing center uses a deep learning model that combines CNN and LSTM to predict faults. The model is updated and trained every week based on newly collected data. The fault threshold is set at 0.55, and warning information is sent through SMS, APP push and other methods. During the one-month monitoring process, the system predicted 5 faults in advance, including line anomalies caused by tower foundation settlement due to heavy rain. Due to timely discovery and processing, no power outages occurred.

[0027] Embodiment 5: Comprehensive functional embodiment: In a large-scale mountain distribution network area, various sensors are fully deployed, and the sensors have self-calibration and self-diagnosis functions. The data transmission module is equipped with a backup power supply to ensure uninterrupted data transmission. The data processing center uses advanced deep learning algorithms and combines big data analysis technology to mine historical data. The fault threshold is dynamically adjusted according to different seasons and line operation status. The early warning module can not only issue various forms of early warning information in a timely manner, but also automatically generate fault handling suggestions. In one month of operation, the system successfully predicted and handled 6 faults, effectively ensuring the stable operation of the distribution network in the area. Comparison of Examples

[0028]

[0029] The embodiments of the present invention are given for the purpose of illustration and description, and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. A method for sensing line faults in a mountainous distribution network, characterized in that: include: Deploy various types of sensors at key nodes of each line of the mountain distribution network to collect real-time data on electrical quantities, environment, and physical status of the lines; The collected data is transmitted to the data processing center through the wireless communication module; The data processing center pre-processes the received data to remove noise and outliers, and then uses deep learning algorithms to build a fault prediction model to predict the probability of line faults based on real-time data; When the predicted failure probability exceeds the preset threshold, the data processing center determines the failure type based on the failure type identification algorithm and issues a failure warning message.

2. The method for sensing line faults in a mountainous distribution network according to claim 1, characterized in that: The multiple types of sensors include but are not limited to current sensors, voltage sensors, temperature sensors, humidity sensors and image sensors, wherein the image sensors are used to capture appearance images of the line to monitor whether there is physical damage to the line.

3. The method for sensing line faults in a mountainous distribution network according to claim 1, characterized in that: The wireless communication module adopts LoRa or 5G communication technology to ensure the stability and real-time performance of data transmission, and adds signal relay equipment in areas with weak signals.

4. The method for sensing line faults in a mountainous distribution network according to claim 1, characterized in that: During the data preprocessing, the 3σ principle based on statistics is used to deal with outliers, and the wavelet denoising algorithm is used to remove noise.

5. The method for sensing line faults in a mountainous distribution network according to claim 1, characterized in that: The deep learning algorithm adopts a model that combines a convolutional neural network (CNN) with a long short-term memory network (LSTM). CNN is used to extract the spatial features of the data, and LSTM is used to process the time series features of the data to improve the accuracy of fault prediction.

6. Mountain distribution network line fault sensing system, characterized by: include: Sensor deployment module, used to deploy various types of sensors at key nodes of distribution network lines in mountainous areas; A data transmission module, which uses wireless communication technology to transmit the data collected by the sensor to the data processing center; The data processing module pre-processes the received data and uses deep learning algorithms to build fault prediction models and fault type identification algorithms; The early warning module issues a fault warning message when the fault prediction probability exceeds a preset threshold.

7. The mountain distribution network line fault sensing system according to claim 6, characterized in that: The sensors in the sensor deployment module have self-calibration and self-diagnosis functions, and can regularly detect and calibrate their own status to ensure the accuracy of data collection.

8. The mountain distribution network line fault sensing system according to claim 6, characterized in that: The data transmission module is equipped with a backup power supply, which can continue to work for a certain period of time when the mains power is interrupted, ensuring that data transmission is not interrupted.

9. The mountainous area power distribution network line fault sensing system according to claim 6, characterized in that: The data processing module has the function of updating the fault prediction model in real time and regularly training and optimizing the model according to newly collected data.

10. The mountainous area power distribution network line fault sensing system according to claim 6, characterized in that: The warning module can send fault warning information to operation and maintenance personnel through text messages, voice, sound and light alarms, and record the warning information in the database for subsequent query and analysis.

Images