Real-time analysis method for power supply reliability of 10KV distribution network

Abstract

The invention relates to the technical field of distribution network power supply operation, and discloses a 10KV distribution network power supply reliability real-time analysis method, which comprises the following steps: carrying out data arrangement on a power supply map; splicing the main network model and the distribution network model; carrying out data matching on the sorted data and a main-distribution collaborative model; performing on-site investigation on the power supply map, separating on-site investigation data, and calculating a risk value; and according to the reference risk levels corresponding to the bus and the transformer substation, carrying out processing work on the on-site power failure. According to the real-time analysis method for the power supply reliability of the 10KV distribution network, image recognition is carried out on a line, a sensor collects power equipment, and data monitoring is carried out on a bus for power supply of the distribution network at the same time, so that the power supply reliability of the distribution network is analyzed and processed in real time, and power distribution faults can be analyzed and processed more quickly and effectively; therefore, the safety capability of distribution network power supply is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network power supply operation, and in particular to a real-time analysis method for 10KV distribution network power supply reliability. Background Art

[0002] The determination of power distribution faults is the basis for realizing various functions such as power distribution automation and fault self-healing. The power grid has many branches and complex operation. During normal operation, the system dispatch needs to collect and detect data from the entire network and receive and send a large amount of command information. When a fault occurs, it is necessary to diagnose and isolate the fault quickly and accurately in combination with the topological structure. Therefore, studying the method of determining power distribution faults is of great significance for formulating system dispatching strategies and improving system stability and reliability.

[0003] There are many power lines in mountainous areas, and ground faults occur frequently due to bamboo pressing on the lines. The existing technology cannot quickly and accurately locate the algorithms and devices supporting fault identification and section positioning of the fault interval, which is not conducive to better ensuring power supply reliability, resulting in greater uncertainty in power outage time. In view of this, we propose a real-time analysis method for 10KV distribution network power supply reliability. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time analysis method for 10KV distribution network power supply reliability to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a real-time analysis method for 10KV distribution network power supply reliability, the method comprising the following steps:

[0006] S1. Arrange data for the power supply map;

[0007] S2. Connect the main network model and the distribution network model to build a main and distribution coordination model;

[0008] S3. After the data is sorted, it is matched with the main distribution coordination model, and the historical operation data of the power equipment in various operating states and the real-time operation data in the real-time operating state are collected through a number of sensors;

[0009] S4. In case of power failure, conduct on-site inspection of the power supply map, separate the on-site inspection data, and calculate the risk value;

[0010] S5. Handle on-site power failures according to the corresponding benchmark risk levels of the busbar and substation.

[0011] Optionally, the process of collecting the historical operation data and the real-time operation data of the electric power equipment includes: setting a sensor for each electric power equipment and setting a number for each electric power equipment;

[0012] The sensor collects real-time status data of the power equipment at its location under real-time operating status; the data acquisition module integrates all received real-time status data to generate real-time operating data, and marks the number of the corresponding power equipment;

[0013] Optionally, the S3 further includes: collecting historical operation data of the power equipment in various operation states and marking corresponding numbers, wherein the operation states include normal operation states, abnormal operation states and involved operation states;

[0014] Medium voltage reliability analysis, using the transformer terminal voltage and current data;

[0015] Low voltage reliability analysis requires the use of low voltage meter voltage and current data.

[0016] Optionally, S5 further includes: evaluating the power supply safety capability of the main distribution network and the coordinated distribution network according to the benchmark risk level corresponding to the bus or substation; and analyzing the distribution network's power restoration capability in the first predetermined time period and the second predetermined time period after the bus or substation loses pressure.

[0017] Optionally, the S4 further includes:

[0018] S41, preparing a training sample set, and establishing positive and negative sample sets according to the types of defects that may occur in the distribution network power supply bus and their probability distribution; wherein the positive sample in the positive sample set is an image of the distribution network power supply bus, and the image of the distribution network power supply bus contains defective areas and non-defective areas; the negative sample in the negative sample set is a background image without the distribution network power supply bus in the picture;

[0019] S42, preprocessing the training sample set prepared in S41 by using an adaptive threshold segmentation algorithm to weaken the influence of unstable light on site, thereby better highlighting the texture features of the defects, and obtaining a preprocessed binary sample set;

[0020] S43, extracting LBP features from the positive samples in the binary sample set after preprocessing, establishing an LBP feature set, and assigning different label codes to each positive sample according to different types of defects and background LBP features;

[0021] S44, while using the LBP feature set to train the SVM classifier, the sparrow search algorithm is used to optimize the SVM penalty factor and kernel function parameters, and the classification error rate is used as the objective function for iterative calculation;

[0022] Stop training until the classification accuracy converges and obtain the LBP-SVM model file;

[0023] S45, loading the LBP-SVM model file, performing pyramid multi-scale sliding frame detection on the image to be detected, and then determining whether the current window contains the defect to be detected and what kind of defect exists, and finally obtaining the type and location of the defect.

[0024] Optionally, the S41 further includes:

[0025] S41, initialize the population, the number of iterations, and the ratio of initial predators and joiners;

[0026] S42, calculate fitness and sort:

[0027] S43, sparrows update predator positions;

[0028] S44, Sparrow updates the joiner position;

[0029] S45, Sparrow updates the position of the sentinel;

[0030] S46, calculating the fitness value and updating the sparrow position;

[0031] S47, using random walk to update the optimal sparrow;

[0032] S48, calculating the fitness value and updating the sparrow position;

[0033] S49: Check whether the stop condition is met. If so, exit and output the result. Otherwise, repeat steps S42 to S48.

[0034] Optionally, in S41, the ratio of the number of positive samples to that of negative samples in the positive sample set and the negative sample set is 1:3.

[0035] Compared with the prior art, the present invention provides a real-time analysis method for 10KV distribution network power supply reliability, which has the following beneficial effects:

[0036] The 10KV distribution network power supply reliability real-time analysis method realizes real-time analysis and processing of the distribution network power supply reliability by performing image recognition on the lines and using sensors to collect data from power equipment while monitoring the busbars that supply power to the distribution network. It can analyze and process distribution faults more quickly and effectively, thereby improving the safety capability of the distribution network power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] like Figure 1 As shown, the present invention provides a technical solution: a real-time analysis method for 10KV distribution network power supply reliability, the method comprising the following steps:

[0040] S1. Arrange data for the power supply map;

[0041] S2. Connect the main network model and the distribution network model to build a main and distribution coordination model;

[0042] S3. After the data is sorted, it is matched with the main distribution coordination model, and the historical operation data of the power equipment in various operation states and the real-time operation data in the real-time operation state are collected through a number of sensors; the historical operation data of the power equipment in various operation states are collected and marked with the corresponding numbers, where the operation state includes normal operation state, abnormal operation state and implicated operation state;

[0043] Medium voltage reliability analysis, using the transformer terminal voltage and current data;

[0044] Low voltage reliability analysis requires the use of low voltage meter voltage and current data.

[0045] S4. In case of power failure, conduct on-site inspection of the power supply map, separate the on-site inspection data, and calculate the risk value;

[0046] S41, preparing a training sample set, and establishing positive and negative sample sets according to the types of defects that may occur in the distribution network power supply bus and their probability distribution; wherein the positive sample in the positive sample set is an image of the distribution network power supply bus, and the image of the distribution network power supply bus contains defective areas and non-defective areas; the negative sample in the negative sample set is a background image without the distribution network power supply bus in the picture;

[0047] S41, initialize the population, the number of iterations, and the ratio of predators to joiners; the ratio of the number of positive and negative samples in the positive and negative sample sets is 1:3;

[0048] S42, calculate fitness and sort:

[0049] S43, sparrows update predator positions;

[0050] S44, Sparrow updates the joiner position;

[0051] S45, Sparrow updates the position of the sentinel;

[0052] S46, calculating the fitness value and updating the sparrow position;

[0053] S47, using random walk to update the optimal sparrow;

[0054] S48, calculating the fitness value and updating the sparrow position;

[0055] S49: Check whether the stop condition is met. If so, exit and output the result. Otherwise, repeat steps S42 to S48.

[0056] S42, preprocessing the training sample set prepared in S41 by using an adaptive threshold segmentation algorithm to weaken the influence of unstable light on site, thereby better highlighting the texture features of the defects, and obtaining a preprocessed binary sample set;

[0057] S43, extracting LBP features from the positive samples in the binary sample set after preprocessing, establishing an LBP feature set, and assigning different label codes to each positive sample according to different types of defects and background LBP features;

[0058] S44, while using the LBP feature set to train the SVM classifier, the sparrow search algorithm is used to optimize the SVM penalty factor and kernel function parameters, and the classification error rate is used as the objective function for iterative calculation;

[0059] Stop training until the classification accuracy converges and obtain the LBP-SVM model file;

[0060] S45, loading the LBP-SVM model file, performing pyramid multi-scale sliding frame detection on the image to be detected, and then determining whether the current window contains the defect to be detected and what kind of defect exists, and finally obtaining the type and location of the defect.

[0061] S5. Handle on-site power failures according to the corresponding benchmark risk levels of the busbar and substation. Evaluate the power supply safety capability of the main distribution and coordinated distribution network according to the corresponding benchmark risk levels of the busbar or substation; analyze the power restoration capability of the distribution network in the first predetermined time period and the second predetermined time period after the busbar or substation loses voltage.

[0062] The process of collecting historical operation data and real-time operation data of power equipment includes: setting sensors for each power equipment and setting numbers for each power equipment; the sensors collect real-time status data of the power equipment at their locations under real-time operation status; the data collection module integrates all received real-time status data to generate real-time operation data, and marks the number of the corresponding power equipment;

[0063] As an application of this embodiment:

[0064] The 10KV distribution network power supply reliability real-time analysis method realizes real-time analysis and processing of the distribution network power supply reliability by performing image recognition on the lines and using sensors to collect data from power equipment while monitoring the busbars that supply power to the distribution network. It can analyze and process distribution faults more quickly and effectively, thereby improving the safety capability of the distribution network power supply.

[0065] The above generally describes the present invention in detail, but it is obvious to a person skilled in the art that some modifications or improvements can be made to the present invention. Therefore, modifications or improvements that do not depart from the spirit of the present invention are within the scope of protection of the present invention.

Claims

1. A real-time analysis method for 10KV distribution network power supply reliability, characterized by: The method comprises the following steps: S1. Arrange data for the power supply map; S2. Connect the main network model and the distribution network model to build a main and distribution coordination model; S3. After the data is sorted, it is matched with the main distribution coordination model, and the historical operation data of the power equipment in various operating states and the real-time operation data in the real-time operating state are collected through a number of sensors; S4. In case of power failure, conduct on-site inspection of the power supply map, separate the on-site inspection data, and calculate the risk value; S5. Handle on-site power failures according to the corresponding benchmark risk levels of the busbar and substation.

2. A 10KV distribution network power supply reliability real-time analysis method according to claim 1, characterized in that: The process of collecting the historical operation data and real-time operation data of the power equipment includes: setting a sensor for each power equipment and setting a number for each power equipment; The sensor collects real-time status data of the power equipment at its location under real-time operating status; the data acquisition module integrates all received real-time status data to generate real-time operating data, and marks the number of the corresponding power equipment.

3. A 10KV distribution network power supply reliability real-time analysis method according to claim 2, characterized in that: The S3 further includes: collecting historical operation data of the power equipment in various operation states and marking corresponding numbers, wherein the operation states include normal operation state, abnormal operation state and involved operation state; Medium voltage reliability analysis, using the transformer terminal voltage and current data; Low voltage reliability analysis requires the use of low voltage meter voltage and current data.

4. A 10KV distribution network power supply reliability real-time analysis method according to claim 1, characterized in that: The S5 further includes: evaluating the power supply safety capability of the main distribution and coordinated distribution network according to the benchmark risk level corresponding to the bus or substation; and analyzing the power restoration capability of the distribution network in the first predetermined time period and the second predetermined time period after the bus or substation loses pressure.

5. A 10KV distribution network power supply reliability real-time analysis method according to claim 1, characterized in that: The S4 further comprises: S41, preparing a training sample set, and establishing positive and negative sample sets according to the types of defects that may occur in the distribution network power supply bus and their probability distribution; wherein the positive sample in the positive sample set is an image of the distribution network power supply bus, and the image of the distribution network power supply bus contains defective areas and non-defective areas; the negative sample in the negative sample set is a background image without the distribution network power supply bus in the picture; S42, preprocessing the training sample set prepared in S41 by using an adaptive threshold segmentation algorithm to weaken the influence of unstable light on site, thereby better highlighting the texture features of the defects, and obtaining a preprocessed binary sample set; S43, extracting LBP features from the positive samples in the binary sample set after preprocessing, establishing an LBP feature set, and assigning different label codes to each positive sample according to different types of defects and background LBP features; S44, while using the LBP feature set to train the SVM classifier, the sparrow search algorithm is used to optimize the SVM penalty factor and kernel function parameters, and the classification error rate is used as the objective function for iterative calculation; Stop training until the classification accuracy converges and obtain the LBP-SVM model file; S45, loading the LBP-SVM model file, performing pyramid multi-scale sliding frame detection on the image to be detected, and then determining whether the current window contains the defect to be detected and what kind of defect exists, and finally obtaining the type and location of the defect.

6. A 10KV distribution network power supply reliability real-time analysis method according to claim 5, characterized in that: The S41 further comprises: S41, initialize the population, the number of iterations, and the ratio of predators to joiners; S42, calculate fitness and sort: S43, sparrows update predator positions; S44, Sparrow updates the joiner position; S45, Sparrow updates the position of the sentinel; S46, calculating the fitness value and updating the sparrow position; S47, using random walk to update the optimal sparrow; S48, calculating the fitness value and updating the sparrow position; S49: Check whether the stop condition is met. If so, exit and output the result. Otherwise, repeat steps S42 to S48.

7. A 10KV distribution network power supply reliability real-time analysis method according to claim 6, characterized in that: In S41, the ratio of the number of positive samples to that of negative samples in the positive sample set and the negative sample set is 1:3.

Images