A transmission line risk prediction system based on cloud platform
Through the cloud-based transmission line risk prediction system, the mean drift algorithm and fault processing module are used to solve the problem of insufficient accuracy in transmission line fault handling in traditional technology, and the rapid and efficient prediction and processing of transmission line risks are achieved, which improves the The stability and user experience of the power system.
Patent Information
- Application Number
- CN202410098196.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-23
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-01-23
AI Technical Summary
The lack of prediction and analysis of transmission line risks in traditional technologies leads to inaccurate and efficient fault handling, and often requires power outages to maintain, affecting the convenience of life.
A transmission line risk prediction system based on cloud platform was designed, and the current, voltage, temperature and vibration parameters were measured in real time through the data acquisition unit, and the failure risk was predicted using the mean drift algorithm and risk assessment module, and timely positioning and processing were combined with the fault processing module. Fault.
It realizes rapid and efficient prediction and processing of transmission line risks, reduces the frequency of power outage maintenance, and improves the stability and user experience of the power system.
Smart Images

Figure CN118035675B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power transmission line risk prediction, and in particular to a power transmission line risk prediction system based on a cloud platform. Background Art
[0002] With the development of science and technology, people's quality of life has improved rapidly. In today's society, all mankind cannot do without electricity. Electricity permeates every aspect of our daily life. Among them, how to safely transmit and distribute electricity, how to use electricity safely, how to improve the quality of electricity and adhere to the concept of green environmental protection is a problem we are facing now.
[0003] In traditional technology, timely solutions are usually taken when encountering faults and problems, but there is no process of risk prediction and analysis of the transmission line under the current conditions. This leads to the inability to accurately and efficiently solve the faults due to insufficient preparation when encountering faults. In emergencies, the only way is to cut off power supply to maintain equipment and eliminate faults, causing inconvenience and trouble to people's lives. Summary of the invention
[0004] Purpose of the invention: In response to current problems, the present invention provides a transmission line risk prediction system based on a cloud platform, which can predict the current line risk level based on the current parameters of the transmission line, so that people can more efficiently deal with possible faults and risks in the transmission line.
[0005] Technical solution: The present invention discloses a transmission line risk prediction system based on a cloud platform, comprising:
[0006] The data acquisition unit includes a transmission line current sensor for measuring the current value of the transmission line at each hour; a transmission line voltage sensor for measuring the voltage value of the transmission line at each hour; a transmission line temperature sensor for measuring the temperature value of the transmission line at each hour; and a transmission line vibration parameter collector for measuring the vibration parameters of the transmission line at each hour.
[0007] The cloud platform receives data from the data acquisition unit and transmits it to the trunk control;
[0008] The main line control unit is used to monitor various parameters of the high-voltage transmission line and receive data feedback from the cloud platform;
[0009] The risk assessment and prediction module is set up at the trunk line control station. It uses the mean shift algorithm to assess and predict the failure risk of the transmission line through the various parameters of the transmission line acquired by the trunk line control station.
[0010] Furthermore, the trunk control department includes a trunk control room, a visualization display module and the risk assessment and prediction module. The trunk control room is used to monitor various parameters of the high-voltage transmission line and accept data feedback from the cloud platform; the visualization display module is used to summarize and display various transmission line parameters collected and transmitted via the cloud platform, and transmit them to the risk assessment and prediction module.
[0011] Furthermore, the specific process of the risk assessment prediction module is as follows:
[0012] 1) Establish the objective function:
[0013] Ripre(t)=max{a,b,c,d}[r amm (t)*k1+r vol (t)*k2+r tem (t)*k3+r vib (t)*k4]
[0014] Among them, Ripre(t) is the risk index of the transmission line at time t, max{a,b,c,d,e} is the clustering weight, r amm (t) is the current value of the transmission line at time t, measured by the transmission line current sensor; r vol (t) is the voltage value of the transmission line at time t, measured by the transmission line voltage sensor; r tem (t) is the conductor temperature of the transmission line at time t, measured by the transmission line temperature sensor; r vib (t) is the vibration parameter of the transmission line at time t, measured by the transmission line vibration parameter collector, k in1 , k in2 , k in3 , k in4 is the impact factor;
[0015] 2) Based on the collected transmission line data, the mean shift algorithm is used to calculate the clustering weight of the objective function as follows:
[0016] 2.1) Determine the kernel density estimation function, where the Gaussian kernel function is used:
[0017]
[0018] Where p is the bandwidth, which is a known quantity;
[0019] 2.2) Determine the initial seed point, that is, the original cluster center. Here, four initial seed points are randomly selected, labeled as a, b, c, and d. With the initial seed point as the center, calculate the weight of the sample data x under the kernel density estimation function. The sample data is the various parameters of the transmission line measured above, and the mean shift vector of the sample point is obtained. Suppose a series of sample data is x i, which is calculated as follows:
[0020]
[0021]
[0022] Among them, P i (x) is the drift mean vector of the sample points, For a radius of The set of high-dimensional ball regions, h, x i are all variables in the set, Δ is the expression of the region set, and n means that n sample points fall into area;
[0023] 2.3) Add the mean shift vector to the initial seed point, and then obtain a new seed point, that is, a new cluster center. If the distance between the new seed point and the original seed point is less than the preset range, it is considered that the mean shift converges, that is, no new cluster center appears, and the algorithm ends; otherwise, return to the above steps to continue calculating the mean shift vector, and update the seed point, and repeat the above process until the algorithm stops;
[0024] 2.4) According to the clustering results of the mean shift algorithm, compared with the number of samples in the four cluster centers, the cluster center weight of the cluster center with the largest number of samples is output, that is, a, b, c, d, and its size is artificially determined by the actual situation;
[0025] 2.5) Mining the historical data of the transmission line, analyzing the risk factors of the line, and establishing risk level assessment rules are as follows:
[0026]
[0027] Among them, Q R is the risk assessment level, Ripre(t) is the risk index of the transmission line at time t, N ris Ultra-low risk level, D ris Low risk level, Z ris Medium risk level, G ris For high risk level, T ris It is an ultra-high risk level; through the above risk level evaluation rules, the objective function can accurately locate its risk level.
[0028] Furthermore, the transmission line risk prediction system also includes a street control department, including a street control room and a step-down transformer. The current is transmitted to the street control department via the high-voltage transmission line through the step-up transformer set up at the trunk control department. The step-down transformer at the street control department reduces the voltage of the high-voltage transmission line current and transmits it to the user via the low-voltage transmission line; the street control room is used to monitor various parameters of the low-voltage transmission line, accept data feedback from the cloud platform, accept work arrangements from the trunk control department, and promptly feedback data information and problems to the trunk control department.
[0029] Furthermore, it also includes a fault handling module, which includes a fault locator, an overvoltage relay, an overcurrent relay, and an air knife switch; the fault locator promptly finds and locates the fault of the transmission line according to the risk level of the transmission line predicted by the risk assessment and prediction module; the overvoltage relay and the overcurrent relay immediately disconnect the line once the voltage and current values measured by the voltage sensor and the current sensor of the data acquisition module exceed the normal fluctuation range, and reclose the line after the line fault is eliminated and various parameters return to stability; the air knife switch is placed on the low-voltage transmission line, and according to the risk level output by the risk assessment and prediction module, once it is at a high level or above, the transmission line is immediately disconnected, and the switch is reclosed after the fault is eliminated and various parameters return to stability.
[0030] Beneficial effects:
[0031] The present invention provides a method capable of predicting the risk of a transmission line. In the design of the present invention, sensor technology is used to detect various index parameters of the transmission line in real time, so as to predict the risk level of the transmission line, and take corresponding risk measures according to the prediction results. The present invention uses a mean shift algorithm to evaluate and predict the failure risk of the transmission line based on the collected parameters of the transmission line, which is faster and more efficient than the original traditional evaluation and prediction methods. At the same time, the number of cluster centers can be modified artificially according to actual conditions, and the size of the cluster weight can also be determined according to actual conditions, which is more adaptable to actual problems and has universality, rather than indirectly obtaining the results of risk prediction through other means. In addition, the present invention includes Internet technologies such as manual inspection and user feedback, so that the entire system can respond to various emergencies and risks more efficiently and specifically. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 It is a structural schematic diagram of the present invention;
[0033] Figure 2 It is the operation logic diagram of the data acquisition module, fault processing module and visual display module of the present invention;
[0034] Figure 3 The flowchart of the algorithm of this method is shown in Figure 2. DETAILED DESCRIPTION
[0035] The present invention will be further described below in conjunction with the accompanying drawings.
[0036] The present invention discloses a transmission line risk prediction system based on a cloud platform, such as Figure 1 As shown, it includes: cloud platform, trunk control department, high-voltage transmission line, data acquisition module, street control department, fault handling module, low-voltage transmission line, user department and feedback module.
[0037] The data acquisition module includes a transmission line current sensor, which is used to measure the current value of the transmission line at every hour. The transmission line voltage sensor is used to measure the voltage value of the transmission line at every hour. The transmission line temperature sensor is used to measure the temperature value of the transmission line at every hour. The transmission line vibration parameter collector is used to measure the vibration parameters of the transmission line at every hour. The module then transmits the data to the cloud platform, and the data is transmitted to the trunk control room and the data aggregator in the visualization display module.
[0038] The main line control department includes a main line control room, a step-up transformer, a visualization display module, and a risk assessment and prediction module. The main line control room is used to monitor various parameters of the high-voltage transmission line and receive data feedback from the cloud platform. The current is transmitted to the street control department through the step-up transformer and then through the high-voltage transmission line. The visualization display module includes a data aggregator and a display screen. The data aggregator is used to summarize various transmission line parameters collected by the data acquisition module and transmitted via the cloud platform. The display screen is used to display the data summarized by the data aggregator and transmit it to the risk assessment and prediction module.
[0039] The visualization display module includes a data aggregator and a display screen. The data aggregator receives the parameters of various transmission lines measured by the data acquisition module, summarizes them, and displays the data on the display screen in a more intuitive way. The display screen transmits the summarized data to the risk assessment and prediction module, and at the same time, feeds back the data to the staff in the trunk control room, so that they can understand the current situation of the transmission line more intuitively and conveniently.
[0040] The risk assessment and prediction module uses the mean shift algorithm to assess and predict the failure risk of the transmission line based on the collected transmission line parameters. The specific steps are as follows:
[0041] 1. Establish the following objective function:
[0042] Ripre(t)=max{a,b,c,d}[r amm (t)*k1+r vol (t)*k2+r tem (t)*k3+r vib (t)*k4]
[0043] Among them, Ripre(t) is the risk index of the transmission line at time t, max{a,b,c,d,e} is the clustering weight, r amm (t) is the current value of the transmission line at time t, which is measured by the current sensor and is a known value; r vol (t) is the voltage value of the transmission line at time t, which is measured by the voltage sensor and is a known value; r tem (t) is the conductor temperature of the transmission line at time t, measured by the temperature sensor and is a known value; r vib (t) is the vibration parameter of the transmission line at time t, which is measured by the vibration parameter collector and is a known value. in1 , k in2 , k in3 , k in4 is the impact factor.
[0044] 2. Based on the collected transmission line data, the mean shift algorithm is used to calculate the clustering weight of the objective function.
[0045] 3. Determine the kernel density estimation function. Here we use the Gaussian kernel function:
[0046]
[0047] Where p is the bandwidth, which is a known quantity.
[0048] 4. Determine the initial seed point, that is, the original cluster center. Here, four initial seed points are randomly selected, labeled a, b, c, and d. With the initial seed point as the center, calculate the weight of the sample data x under the kernel density estimation function to obtain the mean shift vector of the sample point. Suppose a series of sample data is x i , which is calculated as follows:
[0049]
[0050]
[0051] Among them, P i (x) is the drift mean vector of the sample points, For a radius of The set of high-dimensional ball regions, h, x i are all variables in the set, Δ is the expression of the region set. n means that there are n sample points falling into area.
[0052] 5. Add the mean shift vector to the initial seed point, and a new seed point, i.e., a new cluster center, is obtained. If the distance between the new seed point and the original seed point is less than the preset range, the mean shift is considered to have converged, i.e., no new cluster center appears, and the algorithm ends. Otherwise, return to the above steps to continue calculating the mean shift vector, and update the seed point, and repeat the above process until the algorithm stops; the optimized objective function is used as the cluster center, and it is classified into the category of the cluster center that is closest to it.
[0053] 6. According to the clustering results of the mean shift algorithm, compared with the number of samples in the four cluster centers, the cluster center weights of the cluster center with the largest number of samples are output, namely a, b, c, d, and their sizes are artificially determined by actual conditions.
[0054] 7. Mining the historical data of the transmission lines, analyzing the risk factors of the lines, and establishing risk level assessment rules are as follows:
[0055]
[0056] Among them, Q R is the risk assessment level, Ripre(t) is the risk index of the transmission line at time t, N ris Ultra-low risk level, D ris Low risk level, Z ris Medium risk level, G ris For high risk level, T ris The risk level of the target function can be accurately determined through the above risk level evaluation rules.
[0057] The fault handling module includes a fault locator, patrol inspection work, overvoltage relay, overcurrent relay, and air knife switch. The fault locator promptly finds and locates the fault of the transmission line according to the risk level of the transmission line predicted by the risk assessment prediction module. The patrol inspection work is for the staff of the trunk control room and the street control room to regularly check the performance of the equipment, regularly patrol the transmission line and regularly clean the equipment, and promptly discover the risk problems of the transmission line, such as loose insulators and broken wires. Once the fault and equipment problems are found, they will be reported in time and the equipment will be maintained. Once the voltage and current values measured by the voltage sensor and current sensor of the data acquisition module exceed the normal fluctuation range, the overvoltage relay and the overcurrent relay will immediately disconnect the line, wait for the line fault to be eliminated, and the parameters will be restored to stability, and then the line will be closed again. The air knife switch is placed on the low-voltage transmission line. According to the risk level output by the risk assessment prediction module, once it is at a high level or above, the transmission line will be immediately disconnected, and the switch will be closed again after the fault is eliminated and the parameters are restored to stability.
[0058] The feedback module includes a feedback website, which is established by the main line control room. It is used for users to feedback the problems of power quality and power transmission safety of transmission lines to the street control room and the staff of the main line control room. It is also used for the main line control room and the street control room to send notifications, push news, and knowledge and common sense on safe use of electricity in a timely manner.
[0059] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent transformation or modification made according to the spirit of the present invention should be included in the protection scope of the present invention.
Claims
1. A transmission line risk prediction system based on a cloud platform, characterized in that: include: The data acquisition unit includes a transmission line current sensor for measuring the current value of the transmission line at each hour; A transmission line voltage sensor is used to measure the voltage value of the transmission line at every hour; The transmission line temperature sensor is used to measure the temperature value of the transmission line at every hour; the transmission line vibration parameter collector is used to measure the vibration parameters of the transmission line at every hour; The cloud platform receives data from the data acquisition unit and transmits it to the trunk control; The main line control unit is used to monitor various parameters of the high-voltage transmission line and receive data feedback from the cloud platform; The risk assessment and prediction module is set up at the main line control station. It uses the mean shift algorithm to assess and predict the fault risk of the transmission line through the various parameters of the transmission line acquired by the main line control station. The specific process of the risk assessment prediction module is as follows: 1) Establish the objective function: ; in, is the risk index of the transmission line at time t, is the clustering weight, is the current value of the transmission line at time t, measured by the transmission line current sensor; is the voltage value of the transmission line at time t, measured by the transmission line voltage sensor; is the conductor temperature of the transmission line at time t, measured by the transmission line temperature sensor; is the vibration parameter of the transmission line at time t, measured by the transmission line vibration parameter collector, is the impact factor; 2) Based on the collected transmission line data, the mean shift algorithm is used to calculate the clustering weight of the objective function as follows: 2.1) Determine the kernel density estimation function. Here, the Gaussian kernel function is used: ; in, p is the bandwidth, which is a known quantity; 2.2) Determine the initial seed point, that is, the original cluster center. Here, four initial seed points are randomly selected, labeled a, b, c, and d, and the sample data is calculated with the initial seed point as the center. The weights under the kernel density estimation function, the sample data are the parameters of the measured transmission line, and the mean shift vector of the sample points is obtained. Suppose a series of sample data is , which is calculated as follows: ; in, is the drift mean vector of the sample points, For a radius of The set of high-dimensional ball regions, h, are all variables in the set. is the expression of the region set, n Indicates that there is n The sample points fall into area; 2.3) Add the mean shift vector to the initial seed point, and then obtain a new seed point, that is, a new cluster center. If the distance between the new seed point and the original seed point is less than the preset range, it is considered that the mean shift converges, that is, no new cluster center appears, and the algorithm ends; otherwise, return to step 2.2) to continue calculating the mean shift vector and update the seed point, and repeat the above process until the algorithm stops; 2.4) According to the clustering results of the mean shift algorithm, compared with the number of samples in the four cluster centers, the cluster center weight of the cluster center with the largest number of samples is output; 2.5) Mining the historical data of the transmission lines, analyzing the risk factors of the lines, and establishing risk level assessment rules are as follows: ; in, For risk assessment level, is the risk index of the transmission line at time t, Ultra-low risk level, Low risk level, Medium risk level, For high risk level, It is an ultra-high risk level; through the above risk level evaluation rules, the objective function can accurately locate its risk level.
2. A cloud platform-based transmission line risk prediction system according to claim 1, characterized in that: The trunk control unit includes a trunk control room, a visualization display module, and the risk assessment and prediction module. The trunk control room is used to monitor various parameters of the high-voltage transmission line and receive data feedback from the cloud platform; The visualization display module is used to summarize and display the various transmission line parameters collected and transmitted via the cloud platform, and transmit them to the risk assessment and prediction module.
3. A cloud platform-based transmission line risk prediction system according to claim 1, characterized in that: The transmission line risk prediction system also includes a street control department, including a street control room and a step-down transformer. The current is transmitted to the street control department via the high-voltage transmission line through the step-up transformer set up at the trunk control department. The step-down transformer at the street control department reduces the voltage of the high-voltage transmission line current and transmits it to the user via the low-voltage transmission line; the street control room is used to monitor various parameters of the low-voltage transmission line, accept data feedback from the cloud platform, accept work arrangements of the trunk control department, and promptly feedback data information and problems to the trunk control department.
4. A cloud platform-based transmission line risk prediction system according to claim 3, characterized in that: It also includes a fault processing module, which includes a fault locator, an overvoltage relay, an overcurrent relay, and an air knife switch; the fault locator timely finds and locates the fault of the transmission line according to the risk level of the transmission line predicted by the risk assessment and prediction module; the overvoltage relay and the overcurrent relay immediately disconnect the line once the voltage and current values measured by the voltage sensor and the current sensor of the data acquisition module exceed the normal fluctuation range, and reclose the line after the line fault is eliminated and various parameters return to stability; The air knife switch is placed on the low-voltage transmission line. According to the risk level output by the risk assessment prediction module, once it is at a high level or above, the transmission line is immediately disconnected. After the fault is eliminated and all parameters return to stability, the switch is closed again.
Citation Information
Patent Citations
Fault examining system and method for power grid operation
CN103632311A
Power distribution network fault risk assessment method considering distributed power supply
CN116542426A
Power transmission line comprehensive risk assessment method under multiple meteorological disasters
CN116911606A
Lightning stroke risk assessment method and device based on machine learning, and storage medium
CN117056690A
Method for evaluating risk level of power system
KR1020120087300A
