Overhead power distribution equipment fault positioning and detecting system based on image recognition

Abstract

The invention belongs to the technical field of fault positioning detection, and discloses an overhead power distribution equipment fault positioning detection system based on image recognition. An equipment external data set is collected and preprocessed, and the equipment external data set comprises equipment damage data, equipment fracture data and equipment attachment data; processing the equipment external data set to obtain an equipment state reference value, and classifying the equipment state reference value to obtain an equipment state classification result; positioning the fault power distribution equipment to obtain fault position data; according to the method, equipment state classification results are analyzed, fault alarm short messages are sent in cooperation with fault position data, and generally, the method has the remarkable advantages of being good in equipment state early warning effect, high in auxiliary detection capacity and large in auxiliary decision making effect.

Description

Technical Field

[0001] The present invention relates to the technical field of fault location detection, and more specifically, to an overhead power distribution equipment fault location detection system based on image recognition. Background Art

[0002] Distribution equipment refers to electrical products with voltage levels of 3.6kV~550kV that play the role of switching, controlling or protecting in power generation, transmission, distribution, power conversion and consumption of power systems. They mainly include high-voltage circuit breakers, high-voltage disconnectors and grounding switches, high-voltage load switches, high-voltage automatic reclosing and sectionalizers, high-voltage operating mechanisms, high-voltage explosion-proof distribution devices and high-voltage switch cabinets. The high-voltage switch manufacturing industry is an important part of the power transmission and transformation equipment manufacturing industry and occupies a very important position in the entire power industry. With the rapid development of my country's economy in recent years, power supply has also developed rapidly as an important project to ensure people's livelihood. Overhead power distribution equipment is an extremely important part of power supply. How to ensure the smooth operation of overhead power distribution equipment has become a major problem that the power sector needs to solve. Thanks to the increasing development of science and technology, it has also ushered in a fast, low-cost and efficient detection method.

[0003] The patent application with the publication number CN217954608U discloses a ground fault detection device for overhead lines based on drones. The ground fault is detected by combining the drone detection device, the ground controller and the host, which greatly reduces the difficulty of detection, realizes the rapid troubleshooting of the fault point, effectively improves the detection efficiency of the ground fault, reduces the number of trips caused by the ground fault, and greatly improves the safety and stability of power transmission. The drone detection device combines the Hall element with the circular track, so that the Hall element can detect the ground fault directly above the line to be detected, effectively improving the flexibility of the detection equipment and the accuracy of the detection. At the same time, the utility model realizes the automatic access and recovery of the host by setting a host bearing device on the drone detection device, improves the intelligence of the detection equipment, and avoids the detection workers from directly contacting the high-voltage line, thereby improving the safety during the detection process.

[0004] Although the above-mentioned drone-based overhead line grounding fault detection device can achieve the safety and intelligence of overhead power distribution equipment fault detection to a certain extent through drone detection, this type of search device can only rely on drone inspections to discover existing problems, and it is difficult to predict faults of power distribution equipment. In addition, the detection cost of drone inspections themselves is relatively high, and it is difficult to achieve comprehensive real-time inspections.

[0005] In view of this, the present invention proposes an overhead power distribution equipment fault location detection system based on image recognition to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: comprising: The data collection module is used to collect and pre-process the external data set of the equipment, and the external data set of the equipment includes equipment damage data, equipment fracture data and equipment attachment data; Furthermore, the method of collecting the device external data set and the device internal data set includes: By installing optical screening equipment, the depth and surface area of ​​the damaged equipment shell are collected and substituted into the calculation formula: Get equipment damage data, where is the depth of shell damage, is the surface area of ​​the damaged shell, and are the corresponding weight factors respectively; By installing cameras, the data on whether the equipment is broken and the area of ​​the attached objects on the outside of the equipment are collected respectively, and the equipment breakage data and equipment attachment data are obtained; The preprocessing methods include data cleaning, data denoising and data normalization; The data processing module is used to process the external data set of the equipment, obtain the equipment status reference value, and classify it to obtain the equipment status classification result; Furthermore, the step of processing the device external data set includes: Q1: By substituting into the calculation formula: Get the equipment damage reference value, where Attach data to the device. For equipment fracture data, and are the weight factors corresponding to the equipment damage data and equipment attachment data respectively; Q2: Collect the damage reference values ​​of group P equipment as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P; Establish a damage classification model based on the sample set and randomly select The sample points are used as the initial cluster center points, and The initial cluster centers are marked as , ,... , and marked as ,in , ; Q3: Mark the data items outside the cluster center as data points, and mark the data points as , ,... , and marked as ,in ; By substituting into the calculation formula: Get the distance from the data point to the cluster center, where is the dimension of the data points, For data points No. The coordinates of the dimensions, The cluster center No. Coordinates of dimensions; Q4: According to The cluster centers are established clusters, of which ; Q5: Compare the data point with each cluster center point and assign the data point to the cluster corresponding to the cluster center point closest to the data point; Q6: , and jump to Q5; Q7: Repeat Q5 to Q6 until the preset number of iterations is reached, and the equipment damage classification model is output; Q8: Input the equipment damage reference value into the equipment damage classification model, and output the equipment status reference value; Further, the classification methods include: The equipment damage interval (D1, D2) is preset. When the equipment status reference value is less than D1, the equipment normal information is generated. When the equipment status value is greater than D1 and less than D2, the equipment damage information is generated. When the equipment status value is greater than D2, the equipment damage information is generated. The normal device information includes a group of fields indicating that the device is externally normal, the damaged device information includes a group of fields indicating that the device is externally damaged, and the destroyed device information includes a group of fields indicating that the device is externally broken; Pack the normal information of the equipment, the damaged information of the equipment and the destroyed information of the equipment to obtain the equipment status classification result; A fault location module is used to locate the faulty power distribution equipment and obtain the fault location data; Furthermore, the method for locating the faulty power distribution equipment includes: Obtain the images of the power distribution equipment taken by the camera and perform preprocessing, including denoising, contrast enhancement and sharpening; Compare the distribution equipment images showing equipment damage information and equipment destruction information to obtain the first distribution equipment feature, including the shape, color and equipment number of the distribution equipment; Based on the image registration system, the first power distribution equipment feature is calibrated, and the second power distribution equipment feature is output, and the second power distribution equipment feature is matched with the power distribution equipment feature in the equipment library, and the power distribution equipment location data is collected, and the fault location data is output; Fault alarm module, used to analyze the equipment status classification results and obtain fault alarm SMS in conjunction with fault location data; Furthermore, the method of analyzing the equipment status classification result includes: When the equipment status classification result is normal equipment information, the communication unit sends a normal equipment status SMS to the staff receiving end; when the equipment status classification result is damaged equipment information, the communication unit sends a damaged equipment status SMS to the staff receiving end; when the equipment status classification result is damaged equipment information, the communication unit sends a damaged equipment status SMS to the staff receiving end; The SMS message of "Equipment Status Normal" includes the following information: The external status of the power distribution equipment is normal, and reminds the staff to inspect, clean and maintain the external status of the power distribution equipment on schedule; The equipment status damage message includes a description of the damage to the external part of the power distribution equipment, requiring the staff to arrive at the damaged power distribution equipment as soon as possible based on the fault location data for on-site assessment, and replace, repair or reinforce the damaged parts of the power distribution equipment based on the assessment results; The equipment status damage message includes a description of the serious damage to the external part of the power distribution equipment, requiring the staff to immediately shut down the power supply of the damaged power distribution equipment according to the fault location data, immediately go to the damaged power distribution equipment to isolate the site, and notify the maintenance personnel to repair or replace the equipment on site; Pack the normal device status SMS, damaged device status SMS and destroyed device status SMS, and get the fault alarm SMS; Further, S1: collecting and preprocessing equipment external data sets, the equipment external data sets include equipment damage data, equipment fracture data and equipment attachment data; S2: Process the external data set of the equipment to obtain the equipment status reference value, and classify it to obtain the equipment status classification result; S3: locate the faulty power distribution equipment and obtain fault location data; S4: Analyze the equipment status classification results and send a fault alarm SMS according to the fault location data.

[0007] The technical effects and advantages of the overhead power distribution equipment fault location detection system based on image recognition of the present invention are as follows: The present invention obtains a reference value of the equipment status by processing an external data set of the equipment, and can perform calculations based on the external information of the power distribution equipment to obtain the influence of the equipment appearance status on the probability of equipment failure, so that the staff can intuitively know the operating status of the power distribution equipment, which greatly reduces the operating costs brought by traditional manual inspections or drone inspections. By locating the faulty power distribution equipment, the staff can know the specific location of the faulty power distribution equipment in a very short time, which greatly reduces the time cost required for positioning. By analyzing the equipment status classification results and cooperating with the fault alarm text messages obtained from the fault location data, the staff can be assisted in making the best decision in the shortest time, which greatly improves the accuracy and convenience of the staff's operation. Generally speaking, the present invention has the significant advantages of good equipment status early warning effect, strong auxiliary detection capability and large auxiliary decision-making function. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a schematic diagram of the overhead power distribution equipment fault location detection system based on image recognition of the present invention; Figure 2 It is a schematic diagram of the overhead power distribution equipment fault location detection method based on image recognition of the present invention. DETAILED DESCRIPTION

[0009] 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.

[0010] Example 1 See also Figure 1 As shown, the overhead power distribution equipment fault location detection system based on image recognition described in this embodiment includes: The data collection module is used to collect and pre-process the external data set of the equipment, and the external data set of the equipment includes equipment damage data, equipment fracture data and equipment attachment data; Furthermore, the methods of collecting the device external data set and the device internal data set include: By installing optical screening equipment, the depth and surface area of ​​the damaged equipment shell are collected and substituted into the calculation formula: Get equipment damage data, where is the depth of shell damage, is the surface area of ​​the damaged shell, and are the corresponding weight factors respectively; By installing cameras, the data on whether the equipment is broken and the area of ​​the attached objects on the outside of the equipment are collected respectively, and the equipment breakage data and equipment attachment data are obtained; It should be explained that when the device is broken, the value of the device breakage data is 0, and when the device is not broken, the value of the device breakage data is 1; The preprocessing methods include data cleaning, data denoising and data normalization; The data processing module is used to process the external data set of the equipment, obtain the equipment status reference value, and classify it to obtain the equipment status classification result; Furthermore, the step of processing the device external data set includes: Q1: By substituting into the calculation formula: Get the equipment damage reference value, where Attach data to the device. For equipment fracture data, and are the weight factors corresponding to the equipment damage data and equipment attachment data respectively; Q2: Collect the damage reference values ​​of group P equipment as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P; Establish a damage classification model based on the sample set and randomly select The sample points are used as the initial cluster center points, and The initial cluster centers are marked as , ,... , and marked as ,in , ; Q3: Mark the data items outside the cluster center as data points, and mark the data points as , ,... , and marked as ,in ; By substituting into the calculation formula: Get the distance from the data point to the cluster center, where is the dimension of the data points, For data points No. The coordinates of the dimensions, The cluster center No. Coordinates of dimensions; Q4: According to The cluster centers are established clusters, of which ; Q5: Compare the data point with each cluster center point and assign the data point to the cluster corresponding to the cluster center point closest to the data point; Q6: , and jump to Q5; Q7: Repeat Q5 to Q6 until the preset number of iterations is reached, and the equipment damage classification model is output; Q8: Input the equipment damage reference value into the equipment damage classification model, and output the equipment status reference value; Further classification methods include: The equipment damage interval (D1, D2) is preset. When the equipment status reference value is less than D1, the equipment normal information is generated. When the equipment status value is greater than D1 and less than D2, the equipment damage information is generated. When the equipment status value is greater than D2, the equipment damage information is generated. The normal device information includes a group of fields indicating that the device is externally normal, the damaged device information includes a group of fields indicating that the device is externally damaged, and the destroyed device information includes a group of fields indicating that the device is externally broken; Pack the normal information of the equipment, the damaged information of the equipment and the destroyed information of the equipment to obtain the equipment status classification result; A fault location module is used to locate the faulty power distribution equipment and obtain the fault location data; Furthermore, the method for locating the faulty power distribution equipment includes: Obtain the images of the power distribution equipment taken by the camera and perform preprocessing, including denoising, contrast enhancement and sharpening; Compare the distribution equipment images showing equipment damage information and equipment destruction information to obtain the first distribution equipment feature, including the shape, color and equipment number of the distribution equipment; Based on the image registration system, the first power distribution equipment feature is calibrated, and the second power distribution equipment feature is output, and the second power distribution equipment feature is matched with the power distribution equipment feature in the equipment library, and the power distribution equipment location data is collected, and the fault location data is output; Fault alarm module, used to analyze the equipment status classification results and obtain fault alarm SMS in conjunction with fault location data; Further, the method of analyzing the equipment status classification result includes: When the equipment status classification result is normal equipment information, the communication unit sends a normal equipment status SMS to the staff receiving end; when the equipment status classification result is damaged equipment information, the communication unit sends a damaged equipment status SMS to the staff receiving end; when the equipment status classification result is damaged equipment information, the communication unit sends a damaged equipment status SMS to the staff receiving end; The SMS message of "Equipment Status Normal" includes the following information: The external status of the power distribution equipment is normal, and reminds the staff to inspect, clean and maintain the external status of the power distribution equipment on schedule; The equipment status damage message includes a description of the damage to the external part of the power distribution equipment, requiring the staff to arrive at the damaged power distribution equipment as soon as possible based on the fault location data for on-site assessment, and replace, repair or reinforce the damaged parts of the power distribution equipment based on the assessment results; The equipment status damage message includes a description of the serious damage to the external part of the power distribution equipment, requiring the staff to immediately shut down the power supply of the damaged power distribution equipment according to the fault location data, immediately go to the damaged power distribution equipment to isolate the site, and notify the maintenance personnel to repair or replace the equipment on site; Pack the normal device status SMS, damaged device status SMS and destroyed device status SMS, and get the fault alarm SMS; The beneficial effects of this embodiment are as follows: by processing the external data set of the equipment, a reference value of the equipment status is obtained, and calculations can be performed based on the external information of the distribution equipment to obtain the influence of the equipment appearance status on the probability of equipment failure, so that the staff can intuitively know the operating status of the distribution equipment, which greatly reduces the operating costs brought by traditional manual inspections or drone inspections. By locating the faulty distribution equipment, the staff can know the specific location of the faulty distribution equipment in a very short time, which greatly reduces the time cost required for positioning. By analyzing the equipment status classification results and the fault alarm text messages obtained with the fault location data, the staff can be assisted in making the best decision in the shortest time, which greatly improves the accuracy and convenience of the staff's operations. In general, the present invention has the significant advantages of good equipment status early warning effect, strong auxiliary detection capability and large auxiliary decision-making function.

[0011] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in the description of embodiment 1, and a method for locating and detecting faults of overhead power distribution equipment based on image recognition is provided, comprising: S1: collecting and preprocessing a data set external to the equipment, the data set external to the equipment comprising equipment damage data, equipment fracture data and equipment attachment data; S2: Process the external data set of the equipment to obtain the equipment status reference value, and classify it to obtain the equipment status classification result; S3: locate the faulty power distribution equipment and obtain fault location data; S4: Analyze the equipment status classification results and send a fault alarm SMS according to the fault location data.

[0012] Example 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the overhead power distribution equipment fault location detection method based on image recognition provided above is implemented.

[0013] Since the electronic device introduced in this embodiment is an electronic device used to implement the overhead power distribution equipment fault location detection method based on image recognition in the embodiment of this application, based on the overhead power distribution equipment fault location detection method based on image recognition introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not introduced in detail here. As long as the technical personnel of this field implement the electronic device used by the overhead power distribution equipment fault location detection method based on image recognition in the embodiment of this application, it belongs to the scope of protection of this application.

[0014] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0015] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. Overhead power distribution equipment fault location detection system based on image recognition, characterized in that: include: The data collection module is used to collect and pre-process the external data set of the equipment, and the external data set of the equipment includes equipment damage data, equipment fracture data and equipment attachment data; The data processing module is used to process the external data set of the equipment, obtain the equipment status reference value, and classify it to obtain the equipment status classification result; A fault location module is used to locate the faulty power distribution equipment and obtain the fault location data; The fault alarm module is used to analyze the equipment status classification results and obtain fault alarm text messages in conjunction with the fault location data.

2. The overhead power distribution equipment fault location detection system based on image recognition according to claim 1, characterized in that: Methods for collecting device external data sets and device internal data sets include: By installing optical screening equipment, the depth and surface area of ​​the damaged equipment shell are collected and substituted into the calculation formula: Get equipment damage data, where is the depth of shell damage, is the surface area of ​​the damaged shell, and are the corresponding weight factors respectively; By installing cameras, the data on whether the equipment is broken and the area of ​​the attached objects on the outside of the equipment are collected respectively, and the equipment breakage data and equipment attachment data are obtained; The preprocessing methods include data cleaning, data denoising and data normalization.

3. The overhead power distribution equipment fault location detection system based on image recognition according to claim 2, characterized in that: The steps to process the external data set of the device include: 1: By substituting into the calculation formula: Get the equipment damage reference value, where Attach data to the device. For equipment fracture data, and are the weight factors corresponding to the equipment damage data and equipment attachment data respectively; Q2: Collect the damage reference values ​​of group P equipment as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P; Establish a damage classification model based on the sample set and randomly select The sample points are used as the initial cluster center points, and The initial cluster centers are marked as , ,... , and marked as ,in , ; Q3: Mark the data items outside the cluster center as data points, and mark the data points as , ,... , and marked as ,in ; By substituting into the calculation formula: Get the distance from the data point to the cluster center, where is the dimension of the data points, For data points No. The coordinates of the dimensions, The cluster center No. Coordinates of dimensions; Q4: According to The cluster centers are established clusters, of which ; Q5: Compare the data point with each cluster center point and assign the data point to the cluster corresponding to the cluster center point closest to the data point; Q6: , and jump to Q5; Q7: Repeat Q5 to Q6 until the preset number of iterations is reached, and the equipment damage classification model is output; Q8: Input the equipment damage reference value into the equipment damage classification model, and output the equipment status reference value.

4. The overhead power distribution equipment fault location detection system based on image recognition according to claim 3, characterized in that: The classification methods include: The equipment damage interval (D1, D2) is preset. When the equipment status reference value is less than D1, the equipment normal information is generated. When the equipment status value is greater than D1 and less than D2, the equipment damage information is generated. When the equipment status value is greater than D2, the equipment damage information is generated. The normal device information includes a group of fields indicating that the device is externally normal, the damaged device information includes a group of fields indicating that the device is externally damaged, and the destroyed device information includes a group of fields indicating that the device is externally broken; Pack the normal information of the equipment, the damaged information of the equipment and the destroyed information of the equipment to obtain the equipment status classification result.

5. The overhead power distribution equipment fault location detection system based on image recognition according to claim 4, characterized in that: The methods for locating faulty power distribution equipment include: Obtain the images of the power distribution equipment taken by the camera and perform preprocessing, including denoising, contrast enhancement and sharpening; Compare the distribution equipment images showing equipment damage information and equipment destruction information to obtain the first distribution equipment feature, including the shape, color and equipment number of the distribution equipment; Based on the image registration system, the first power distribution equipment feature is calibrated, and the second power distribution equipment feature is output. The second power distribution equipment feature is matched with the power distribution equipment feature in the equipment library, the power distribution equipment location data is collected, and the fault location data is output.

6. The overhead power distribution equipment fault location detection system based on image recognition according to claim 5, characterized in that: Methods for analyzing the equipment status classification results include: When the equipment status classification result is normal equipment information, the communication unit sends a normal equipment status SMS to the staff receiving end; when the equipment status classification result is damaged equipment information, the communication unit sends a damaged equipment status SMS to the staff receiving end; when the equipment status classification result is damaged equipment information, the communication unit sends a damaged equipment status SMS to the staff receiving end; The SMS message of "Equipment Status Normal" includes the following information: The external status of the power distribution equipment is normal, and reminds the staff to inspect, clean and maintain the external status of the power distribution equipment on schedule; The equipment status damage message includes a description of the damage to the external part of the power distribution equipment, requiring the staff to arrive at the damaged power distribution equipment as soon as possible based on the fault location data for on-site assessment, and replace, repair or reinforce the damaged parts of the power distribution equipment based on the assessment results; The equipment status damage message includes a description of the serious damage to the external part of the power distribution equipment, requiring the staff to immediately shut down the power supply of the damaged power distribution equipment according to the fault location data, immediately go to the damaged power distribution equipment to isolate the site, and notify the maintenance personnel to repair or replace the equipment on site; Pack the normal device status SMS, broken device status SMS and destroyed device status SMS, and get the fault alarm SMS.

7. An overhead power distribution equipment fault location detection method based on image recognition, implemented according to an overhead power distribution equipment fault location detection system based on image recognition according to any one of claims 1 to 6, characterized in that: S1: Collect and preprocess the external data set of the equipment. The external data set of the equipment includes equipment damage data, equipment fracture data and equipment attachment data; S2: Process the external data set of the equipment to obtain the equipment status reference value, and classify it to obtain the equipment status classification result; S3: locate the faulty power distribution equipment and obtain fault location data; S4: Analyze the equipment status classification results and send a fault alarm SMS according to the fault location data.

Images