Method and system for acquiring operation data of edge equipment of transformer substation

Abstract

The invention discloses a substation edge equipment operation data acquisition method and system, and relates to the field of electric power system intelligent monitoring, and the method comprises the steps: arranging an infrared thermal imager and embedded edge equipment, collecting substation equipment operation data, outputting image data with qualified definition, receiving the image data with qualified definition, and transmitting the image data to a server; carrying out preprocessing and equipment identification analysis, calculating equipment hot spot temperature and relative temperature difference, outputting equipment operation state information, receiving the equipment operation state information, carrying out compression and encryption, sending the information to a receiving terminal through a low-power-consumption wireless transmission technology, uploading the information to a cloud platform, receiving data information uploaded to the cloud platform, and carrying out further analysis; and storing the data in a corresponding table of the MySQL database. According to the invention, efficient, real-time and energy-saving data acquisition and processing are realized through three key points of a self-adaptive dynamic data acquisition strategy, real-time data processing based on edge calculation and a low-power-consumption wireless transmission technology.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring of power systems, and in particular to a method and system for collecting operating data of substation edge equipment. Background Art

[0002] With the continuous improvement of the automation level of power systems, substations, as the core components of power systems, have become particularly important for real-time monitoring of their operating status. In recent years, with the rapid development of Internet of Things technology, the concept of smart substations has emerged. Among them, edge computing technology has attracted much attention due to its ability to process data near the data source. In addition, infrared thermal imaging technology, as a non-contact detection method, has shown great potential in monitoring the health status of power equipment.

[0003] The existing system lacks effective security measures during data transmission and is vulnerable to data tampering or theft, which poses a threat to the safe and stable operation of the power system. Therefore, how to improve the quality of data acquisition, realize automated analysis, and ensure the security of data transmission has become a key issue that needs to be solved urgently. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a substation edge device operation data collection method and system to solve the problems in the prior art of low data collection quality, manual intervention required in the analysis process, and poor data transmission security.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for collecting operation data of a substation edge device, which comprises:

[0008] The infrared image signal of the substation equipment is collected by the infrared thermal imager, and the embedded edge device outputs the image data with qualified clarity;

[0009] Receive infrared image data with qualified clarity, perform pre-processing and equipment identification analysis, calculate the equipment hotspot temperature and relative temperature difference, and output equipment operation status information;

[0010] Receive the device operation status information, compress and encrypt it, send the compressed and encrypted device operation status information to the receiving terminal through low-power wireless transmission technology, and upload it to the cloud platform;

[0011] The compressed and encrypted device operation status information is analyzed and stored in the corresponding table of the MySQL database.

[0012] As a preferred solution of the substation edge device operation data collection method of the present invention, wherein: the embedded edge device includes an intelligent device installed inside the substation that converts infrared image signals into image data;

[0013] The qualified clarity includes that the image data meets the requirements of resolution and signal-to-noise ratio;

[0014] The equipment operation status information includes abnormal status and normal status;

[0015] The corresponding table of the MySQL database includes device ID, acquisition time, hot spot temperature, and relative temperature difference.

[0016] As a preferred solution of the substation edge device operation data collection method of the present invention, wherein: the infrared image signal of the substation equipment is collected by an infrared thermal imager, and the embedded edge device outputs image data with qualified clarity. The specific steps are as follows:

[0017] Based on the substation equipment layout, the infrared thermal imager is set up by calculating the distance and angle between the substation equipment and the infrared thermal imager;

[0018] The infrared thermal imager is started by controlling the embedded edge device, and the infrared image data of the substation equipment is automatically collected based on the sampling frequency;

[0019] Connect the infrared thermal imager to the embedded edge device using a USB cable, configure a data stream pipeline on the embedded edge device, and transmit the infrared image data to the embedded edge device in real time through the TCP protocol;

[0020] Image clarity detection is performed based on the gradient information of the infrared image data, images that do not meet the requirements of 640×480 pixels and signal-to-noise ratio SNR≥20dB are cleaned, and infrared image data with qualified clarity is output.

[0021] As a preferred solution of the substation edge device operation data collection method of the present invention, wherein: the infrared image data with qualified clarity is received, pre-processed and equipment identification analysis is performed, and the hot spot temperature and relative temperature difference of the equipment are calculated, and the equipment operation status information is output. The specific steps are as follows:

[0022] The embedded edge device receives the image data output by the infrared thermal imager with qualified clarity and smoothes the image through a Gaussian filter;

[0023] Through deep learning algorithm, the preprocessed image I g Perform device identification and output device category labels;

[0024] By detecting the temperature of each pixel in the smoothed image, the temperature of the pixel with the highest temperature is determined as the device hotspot temperature T max , calculate the relative temperature difference ΔT between the hot spot temperature of the equipment and the ambient temperature;

[0025] The operating state of the device is judged according to the relative temperature difference. If the relative temperature difference ΔT is less than or equal to the relative temperature difference threshold ΔT0, the device is judged to be in an abnormal state. Otherwise, the device is operating normally.

[0026] As a preferred solution of the substation edge device operation data collection method of the present invention, wherein: the pre-processed image I is processed by the deep learning algorithm g Perform device identification and output device category labels. The specific steps are as follows:

[0027] Using convolutional neural networks, the input layer receives the preprocessed image Gaussian filtering results, and the convolution layer extracts local features from the input image Gaussian filtering results. Each convolution layer contains a set of filters that slide on the input image and perform convolution operations with the local area;

[0028] In the pooling layer, sampling is performed by selecting the maximum value in each pooling window;

[0029] After a series of convolution and pooling layers, the feature map is flattened into a one-dimensional vector and passed to the fully connected layer, which maps the extracted features to the substation classification set and outputs the final recognition result.

[0030] As a preferred solution of the substation edge device operation data collection method of the present invention, the device operation status information is received, compressed and encrypted, and the compressed and encrypted device operation status information is sent to the receiving terminal through low-power wireless transmission technology, and uploaded to the cloud platform. The specific steps are as follows:

[0031] The embedded edge device receives the image data and temperature difference data of the device operation status, compresses the image data using discrete cosine transform, fuses the compressed image data and temperature difference data, and encrypts the fused data using an encryption algorithm based on elliptic curve cryptography;

[0032] Adopt OFDM modulation algorithm, dynamically adjust the transmission rate according to the prediction model of channel state information, adjust the data transmission intensity on each subcarrier according to the current channel state information, and obtain the information filtering function G(C,H);

[0033] The receiving terminal receives the fused data via low-power wireless transmission and uploads it to the cloud platform for storage and further analysis.

[0034] As a preferred solution of the substation edge device operation data collection method of the present invention, wherein: the compressed and encrypted device operation status information is analyzed and stored in the corresponding table of the MySQL database, the specific steps are as follows:

[0035] The cloud platform receives data uploaded from the receiving terminal through the API Gateway, the interface layer between the front-end and back-end, and performs integrity checks on the data;

[0036] The data is decrypted using the elliptic curve cryptography decryption algorithm, and the original data is restored using the inverse discrete cosine transform;

[0037] Remove noise and invalid information from the data, convert the data into JSON format, identify abnormalities in the equipment operation status information based on the box plot, use the machine learning model to conduct in-depth analysis of the equipment operation status, and predict the possibility of equipment failure;

[0038] The cleaned and formatted data is stored in batches into the MySQL database.

[0039] In a second aspect, the present invention provides a substation edge device operation data acquisition system, including a data acquisition module, a data preprocessing and analysis module, a data transmission module, and a cloud data analysis and storage module;

[0040] The data acquisition module is responsible for collecting the operation data of the substation equipment through the infrared thermal imager and the embedded edge device, and generating high-quality image data;

[0041] The data preprocessing and analysis module is used to receive the image data from the data acquisition module, perform preprocessing and equipment identification analysis on it, calculate the equipment hot spot temperature and relative temperature difference, and generate equipment operation status information;

[0042] The data transmission module is used to compress and encrypt the device operation status information, and send it to the receiving terminal using low-power wireless technology, and upload it to the cloud platform at the same time;

[0043] The cloud data analysis and storage module is used to receive the data uploaded from the data transmission module, perform in-depth analysis on the cloud platform, and store the processed data in the corresponding table of the MySQL database.

[0044] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the substation edge device operation data collection method as described in the first aspect of the present invention is implemented.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the substation edge device operation data collection method as described in the first aspect of the present invention is implemented.

[0046] The beneficial effects of the present invention are as follows: by placing an infrared thermal imager and an embedded edge device, the present invention collects substation equipment operation data based on the accurately calculated equipment layout and installation position, and outputs image data with qualified clarity, thereby realizing non-contact monitoring of the substation equipment operation status and improving the accuracy and efficiency of data collection. Preprocessing and equipment identification analysis are performed on image data with qualified clarity, thereby improving the speed and accuracy of image processing and making equipment identification more accurate. Through compression and encryption technology, low-power wireless transmission technology is used to send the data to a receiving terminal and then upload it to a cloud platform, thereby reducing the risk of data being tampered with during transmission. In addition, the application of low-power technology extends the working life of the equipment, realizes long-term preservation of data, and facilitates statistical analysis of the data at a later stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0048] Figure 1 This is a flow chart of the substation edge device operation data collection method in Example 1.

[0049] Figure 2 This is a module diagram of the substation edge device operation data acquisition system in Example 1. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0051] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for collecting substation edge device operation data, comprising the following steps:

[0052] S1. Collect infrared image signals of substation equipment through infrared thermal imager, and output image data with qualified clarity through embedded edge device.

[0053] Furthermore, based on the substation equipment layout, determine the best installation location for the infrared thermal imager to ensure coverage of all key equipment areas while avoiding interference from direct sunlight or heat sources. Set up the infrared thermal imager by calculating the distance and angle between the substation equipment and the infrared thermal imager to ensure that the infrared thermal imager can capture clear thermal images.

[0054] The infrared thermal imager is started by controlling the embedded edge device, and the sampling frequency is set to collect data once every 30 seconds. The infrared image data of the substation equipment is automatically collected and transmitted in JPEG format.

[0055] Furthermore, the infrared thermal imager is connected to the embedded edge device using a USB cable to ensure a stable communication connection between the two, a data stream pipeline is configured on the embedded edge device to ensure that the data collected by the infrared thermal imager can be transmitted to the edge device in real time, and the infrared image data is transmitted to the embedded edge device in real time through the TCP protocol;

[0056] Perform image clarity detection based on the gradient information of the infrared image data, clean the image that does not meet the requirements of 640×480 pixels and signal-to-noise ratio SNR ≥ 20dB, use histogram equalization to improve the image quality, use bilateral filtering to remove noise in the image, and output infrared image data with qualified clarity;

[0057] It should be noted that by optimizing the installation position and parameter settings of the infrared thermal imager and combining the automated control and image processing technology of embedded edge devices, the monitoring efficiency and accuracy are improved while ensuring the quality of the image data.

[0058] S2. Receive image data with qualified clarity, perform preprocessing and equipment identification analysis, calculate the equipment hot spot temperature and relative temperature difference, and output equipment operation status information.

[0059] Furthermore, the embedded edge device receives the image data with qualified clarity output by the infrared thermal imager with qualified clarity, and smoothes the image by using a Gaussian filter to reduce the influence of noise and enhance the image contrast, and defines the new value of the pixel point in the image after Gaussian filtering as I g (x,y), the expression is as follows:

[0060]

[0061] Among them, (x, y) is the calculated central pixel, (u, v) is the pixel within ±3σ around the central pixel, I(u, v) is the value of the pixel (u, v) in the original pixel, π is the circumference, σ is the standard deviation of the Gaussian kernel, which determines the width and smoothness of the filter, and 2πσ 2is the normalization coefficient of the Gaussian function, ensuring that the integral value of the entire Gaussian function is 1;

[0062] Calculate each pixel in the image to get the Gaussian filter result I of the entire image g ;

[0063] Furthermore, through deep learning algorithms, the pre-processed image Gaussian filtering results are used to perform device identification and output device category labels;

[0064] Preferably, a convolutional neural network (CNN) is used to identify substation equipment, the network comprising a plurality of convolutional layers, pooling layers and fully connected layers;

[0065] The input layer receives the preprocessed image Gaussian filtering result, and the convolution layer extracts local features from the input Gaussian filtering result. Each convolution layer contains a set of filters that slide on the input image and perform convolution operations with the local area;

[0066] In the pooling layer, sampling is performed by selecting the maximum value in each pooling window;

[0067] After a series of convolution and pooling layers, the feature map is flattened into a one-dimensional vector and passed to the fully connected layer, which maps the extracted features to the separated set of substation equipment and outputs the final recognition result;

[0068] By detecting the temperature of each pixel in the preprocessed image, the temperature of the pixel with the highest temperature is determined as the device hotspot temperature T max , calculate the relative temperature difference ΔT between the hot spot temperature of the equipment and the ambient temperature, the expression is as follows:

[0069]

[0070] Among them, T is the ambient temperature, and the influence of the ambient temperature is taken into account, making the calculated temperature difference more valuable for reference;

[0071] The operating state of the equipment is determined according to the relative temperature difference. When the relative temperature difference ΔT is less than or equal to the relative temperature difference threshold ΔT0, the equipment is determined to be in an abnormal state. Otherwise, the equipment is operating normally.

[0072] Establish a fault mode database containing typical features of different fault types, match the extracted features with the fault features in the fault mode database, and use the Euclidean distance to measure the similarity to find the most similar fault mode. Define the pattern matching function, the expression is as follows:

[0073]

[0074] Where M(f,m) is the result of pattern matching, the Euclidean distance between two feature vectors, f is the feature vector extracted from the image, and fi is the i-th feature vector extracted from the image, m is the feature vector in the fault mode library, and m i is the i-th feature vector in the fault mode library, and n is the dimension of the feature vector;

[0075] According to the matching results of the fault mode, combined with the hot spot temperature and relative temperature difference of the equipment, the fault level of the equipment is evaluated, and a fault level evaluation function of the substation edge equipment is defined. The expression is as follows:

[0076]

[0077] Among them, θ1, θ2 are thresholds for distinguishing the matching degree of fault modes set according to historical data, and θ3, θ4 are thresholds for judging whether the hot spot temperature and relative temperature difference of the equipment are within the normal range, set according to historical data;

[0078] According to the fault level diagnosis results of the substation edge equipment, when the fault level reaches medium or above, an early warning notification is generated;

[0079] The notification content includes the device identifier, the fault type based on the diagnosis results, and the fault severity;

[0080] Through the integrated communication module, the SMTP server sends the warning information in the form of email, automatically sending it to the designated recipient, reducing the need for manual intervention and improving the response speed.

[0081] It should be noted that effective noise reduction and accurate equipment identification of infrared thermal imagers are achieved through Gaussian filter preprocessing and deep learning algorithms, and the equipment operating status can be reliably evaluated by calculating the hotspot temperature and relative temperature difference, thereby improving the accuracy and efficiency of fault detection.

[0082] S3: Receive the device operation status information, compress and encrypt it, send it to the receiving terminal through low-power wireless transmission technology, and upload it to the cloud platform.

[0083] Furthermore, the embedded edge device receives the image data and temperature difference data of the device operation status, compresses the image data using discrete cosine transform (DCT), and fuses the compressed image data and temperature difference data.

[0084] Preferably, in order to ensure the security of the data, an encryption algorithm based on elliptic curve cryptography (ECC) is used to encrypt the fused data;

[0085] Furthermore, OFDM modulation algorithm is adopted, which is a modulation technology based on orthogonal frequency division multiplexing, to realize low-power wireless transmission of the fused data. The transmission rate is dynamically adjusted based on the prediction model of channel state information (CSI) to optimize the transmission efficiency. An information filtering function G(C,H) is obtained to adjust the data transmission intensity on each subcarrier according to the current channel state information. The expression is as follows:

[0086]

[0087] Among them, C is the encrypted data vector, C i is the encrypted data on the i-th subcarrier, H is the channel state information vector, H i is the channel state information of the i-th subcarrier, i is the index variable, μ H is the mean of the channel state information of all subcarriers, α is the parameter for adjusting the exponential decay speed, ranging from (0.1, 1), which is used to adjust the steepness of the exponential function, thereby affecting the adjustment of data transmission intensity, and N is the number of subcarriers, which determines the bandwidth and complexity of OFDM modulation technology;

[0088] The receiving terminal receives the fused data via low-power wireless transmission and uploads it to the cloud platform for storage and further analysis;

[0089] It should be noted that by integrating low-power wireless transmission technology with compression, secure encryption and intelligent speed regulation, the equipment operation status information can be efficiently, securely and stably transmitted to the cloud for analysis and processing.

[0090] S4. Analyze the compressed and encrypted device operation status information and store it in the corresponding table of the MySQL database.

[0091] Furthermore, the cloud platform receives data uploaded from the receiving terminal through the API Gateway, the interface layer between the front-end and back-end, and performs integrity checks on the data;

[0092] Preferably, the data is decrypted using an elliptic curve cryptography (ECC) decryption algorithm, and the original data is restored using an inverse discrete cosine transform (IDCT);

[0093] Preferably, IQR (interquartile range) is used to identify data points far from the mean, thresholds are set to identify variant data and duplicate data, and the query function of the database is used to find and delete duplicate records. For malformed data, regular expressions are used to correct the data format to meet the format requirements;

[0094] Convert the data into JSON format, which is suitable for further analysis. Based on the box plot, identify abnormalities in the equipment operation status information. Use machine learning models to conduct in-depth analysis of the equipment operation status and predict the possibility of equipment failure.

[0095] The cleaned and formatted data is stored in batches into the MySQL database.

[0096] This embodiment also provides a substation edge device operation data acquisition system, including: a data acquisition module, a data preprocessing and analysis module, a data transmission module, and a cloud data analysis and storage module.

[0097] The data acquisition module is responsible for collecting the operating data of substation equipment through infrared thermal imagers and embedded edge devices, and generating high-quality image data;

[0098] The data preprocessing and analysis module is used to receive the image data from the data acquisition module, perform preprocessing and equipment identification analysis on it, calculate the equipment hot spot temperature and relative temperature difference, and generate equipment operation status information;

[0099] The data transmission module is used to compress and encrypt the equipment operation status information, and send it to the receiving terminal using low-power wireless technology, and upload it to the cloud platform at the same time;

[0100] The cloud data analysis and storage module is used to receive the data uploaded from the data transmission module, perform in-depth analysis on the cloud platform, and store the cleaned and formatted data in the corresponding table of the MySQL database.

[0101] This embodiment also provides a computer device, which is suitable for the case of a substation edge device operation data collection method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the substation edge device operation data collection method proposed in the above embodiment.

[0102] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0103] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for collecting operating data of substation edge equipment proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0104] In summary, the present invention achieves non-contact monitoring of the operating status of substation equipment and improves the accuracy and efficiency of data collection by placing an infrared thermal imager and an embedded edge device, collecting substation equipment operating data based on accurately calculated equipment layout and installation position, and outputting image data with qualified clarity, thereby improving the speed and accuracy of image processing and making device identification more accurate. Through compression and encryption technology, the data is sent to a receiving terminal using low-power wireless transmission technology and then uploaded to a cloud platform, thereby reducing the risk of data being tampered with during transmission. In addition, the application of low-power technology extends the working life of the equipment, achieves long-term data preservation, and facilitates statistical analysis of the data at a later stage.

[0105] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the substation edge device operation data collection method are provided.

[0106] Set up a simulated substation environment, including various power equipment in actual operation, such as transformers and circuit breakers, select the HT-3000 high-precision infrared thermal imager with a resolution of 640×480 pixels, and configure an ED-1000 embedded edge device with a built-in high-performance processor and sufficient memory space.

[0107] In the simulated substation, the infrared thermal imager is installed in a position that can cover all key equipment and connected to the embedded edge device via a USB cable. The TCP protocol data stream pipeline is configured on the embedded edge device.

[0108] Start the infrared thermal imager and set the sampling frequency to one frame every 30 seconds. The embedded edge device receives the image data, smoothes it through a Gaussian filter, and uses a deep learning algorithm - convolutional neural network (CNN) to identify the device type, calculate the hot spot temperature and relative temperature difference of the device, classify the device operation status, and output status information.

[0109] The compressed and encrypted data is sent to the receiving terminal using low-power wireless technology and uploaded to the cloud platform simultaneously. The cloud platform decrypts, recovers, cleans and converts the received data into JSON format and stores it in the MySQL database.

[0110] The details are shown in Table 1 below:

[0111] Table 1 Performance comparison of substation edge equipment operation data collection methods

[0112] Experimental subjects Resolution Signal-to-Noise Ratio Transmission efficiency Analytical accuracy Technical solution of the present invention 640×480 23.5 94.2％ 96.8％ Prior art A 480×360 18.2 78.5％ 89.3％ Prior Art B 640×480 21.8 82.1％ 92.5％

[0113] In terms of transmission efficiency, the new method achieved 94.2%, far exceeding the 78.5% of the existing technology A and the 82.1% of the existing technology B. This is due to the use of advanced compression encryption technology and low-power wireless transmission technology, which makes data transmission more efficient.

[0114] In terms of analysis accuracy, the accuracy of the new method is 96.8%, which is also better than 89.3% of the existing technology A and 92.5% of the existing technology B. This shows that the new method not only improves the quality of data acquisition, but also achieves higher accuracy in equipment status analysis.

[0115] By comparing the data in Table 1, it can be seen that the present invention has demonstrated significant advantages in terms of image resolution, signal-to-noise ratio, transmission efficiency, and analysis accuracy, and provides a more reliable technical guarantee for substation equipment operation status monitoring.

[0116] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for collecting operation data of substation edge equipment, characterized in that: include, The infrared image signal of the substation equipment is collected by the infrared thermal imager, and the embedded edge device outputs the image data with qualified clarity; Receive infrared image data with qualified clarity, perform pre-processing and equipment identification analysis, calculate the equipment hotspot temperature and relative temperature difference, and output equipment operation status information; Receive the device operation status information, compress and encrypt it, send the compressed and encrypted device operation status information to the receiving terminal through low-power wireless transmission technology, and upload it to the cloud platform; The compressed and encrypted device operation status information is deeply analyzed and stored in the corresponding table of the MySQL database.

2. The substation edge device operation data collection method according to claim 1, characterized in that: The embedded edge device includes an intelligent device installed inside the substation that converts infrared image signals into image data; The qualified clarity includes that the image data meets the requirements of resolution and signal-to-noise ratio; The equipment operation status information includes abnormal status and normal status; The corresponding table of the MySQL database includes device ID, acquisition time, hot spot temperature, and relative temperature difference.

3. The substation edge device operation data collection method according to claim 2, characterized in that: The infrared image signal of the substation equipment is collected by the infrared thermal imager, and the embedded edge device outputs the image data with qualified clarity. The specific steps are as follows: Based on the substation equipment layout, the infrared thermal imager is set up by calculating the distance and angle between the substation equipment and the infrared thermal imager; The infrared thermal imager is started by controlling the embedded edge device, and the infrared image data of the substation equipment is automatically collected based on the sampling frequency; Connect the infrared thermal imager to the embedded edge device using a USB cable, configure a data stream pipeline on the embedded edge device, and transmit the infrared image data to the embedded edge device in real time through the TCP protocol; Image clarity detection is performed based on the gradient information of the infrared image data, images that do not meet the requirements of 640×480 pixels and signal-to-noise ratio SNR≥20dB are cleaned, and infrared image data with qualified clarity is output.

4. The substation edge device operation data collection method according to claim 3, characterized in that: The infrared image data with qualified clarity is received, pre-processed and the equipment is identified and analyzed, and the hot spot temperature and relative temperature difference of the equipment are calculated, and the equipment operation status information is output. The specific steps are as follows: The embedded edge device receives the image data with qualified clarity output by the infrared thermal imager and smoothes the image through a Gaussian filter; Calculate each pixel in the image to get the Gaussian filter result I of the entire image g ; Through deep learning algorithms, the Gaussian filtering results are used to identify devices and output device category labels; By detecting the temperature of each pixel in the smoothed image, the temperature of the pixel with the highest temperature is determined as the device hotspot temperature T max , calculate the relative temperature difference ΔT between the hot spot temperature of the equipment and the ambient temperature; The operating state of the device is judged according to the relative temperature difference. If the relative temperature difference ΔT is less than or equal to the relative temperature difference threshold ΔT0, the device is judged to be in an abnormal state. Otherwise, the device is operating normally.

5. The substation edge device operation data collection method according to claim 4, characterized in that: The deep learning algorithm is used to process the preprocessed image I g Perform device identification and output device category labels. The specific steps are as follows: Using convolutional neural networks, the input layer receives the preprocessed image Gaussian filtering results, and the convolution layer extracts local features from the image Gaussian filtering results. Each convolution layer contains a set of filters that slide on the input image and perform convolution operations with the local area; In the pooling layer, sampling is performed by selecting the maximum value in each pooling window; After a series of convolution and pooling layers, the feature map is flattened into a one-dimensional vector and passed to the fully connected layer, which maps the extracted features to the substation equipment classification set and outputs the final recognition result.

6. The substation edge device operation data collection method according to claim 5, characterized in that: The receiving device operation status information is compressed and encrypted, the compressed and encrypted device operation status information is sent to the receiving terminal through low-power wireless transmission technology, and uploaded to the cloud platform. The specific steps are as follows: The embedded edge device receives the image data and temperature difference data of the device operation status, compresses the image data using discrete cosine transform, fuses the compressed image data and temperature difference data, and encrypts the fused data using an encryption algorithm based on elliptic curve cryptography; Adopt OFDM modulation algorithm, dynamically adjust the transmission rate according to the prediction model of channel state information, adjust the data transmission intensity on each subcarrier according to the current channel state information, and obtain the information filtering function G(C,H); The receiving terminal receives the fused data via low-power wireless transmission and uploads it to the cloud platform for storage and further analysis.

7. The substation edge device operation data collection method according to claim 6, characterized in that: The compressed and encrypted device operation status information is analyzed and stored in the corresponding table of the MySQL database. The specific steps are as follows: The cloud platform receives data uploaded from the receiving terminal through the API Gateway, the interface layer between the front-end and back-end, and performs integrity checks on the data; The data is decrypted using the elliptic curve cryptography decryption algorithm, and the original data is restored using the inverse discrete cosine transform; Remove noise and invalid information from the data and convert the data into JSON format. Based on the box plot, identify abnormalities in the equipment operation status information. Use machine learning models to conduct in-depth analysis of the equipment operation status and predict the possibility of equipment failure. The cleaned and formatted data is stored in batches into the MySQL database.

8. A substation edge device operation data collection system, based on the substation edge device operation data collection method according to any one of claims 1 to 7, characterized in that: Including data acquisition module, data preprocessing and analysis module, data transmission module, cloud data analysis and storage module; The data acquisition module is responsible for collecting the operation data of the substation equipment through the infrared thermal imager and the embedded edge device, and generating high-quality image data; The data preprocessing and analysis module is used to receive the image data from the data acquisition module, perform preprocessing and equipment identification analysis on it, calculate the equipment hot spot temperature and relative temperature difference, and generate equipment operation status information; The data transmission module is used to compress and encrypt the device operation status information, and send it to the receiving terminal using low-power wireless technology, and upload it to the cloud platform at the same time; The cloud data analysis and storage module is used to receive the data uploaded from the data transmission module, perform in-depth analysis on the cloud platform, and store the processed data in the corresponding table of the MySQL database.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the substation edge device operation data collection method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the substation edge device operation data collection method according to any one of claims 1 to 7 are implemented.

Images