Power centralized control system transformer state acquisition system and method based on edge analysis

Abstract

The invention discloses an electric power centralized control system transformer state acquisition system and method based on edge analysis, and belongs to the field of enterprise substation operation and maintenance technology management.The system comprises an intelligent gateway machine, an edge analysis device, a camera and a transformer winding temperature measuring device; the edge analysis device is connected with the intelligent gateway machine, the camera and the transformer winding temperature measurement device, and the camera and the transformer winding temperature measurement device are arranged on a transformer site and used for collecting transformer oil liquid level video information and transformer winding temperature information respectively and transmitting the information to the edge analysis device. The intelligent gateway machine is deployed in a substation secondary room and is used for acquiring power load information of a transformer and transmitting the power load information to the edge analysis device; and the edge analysis device is deployed in a transformer substation secondary room, analyzes the transformer oil liquid level video information, the transformer winding temperature information and the transformer power load information through an edge analysis algorithm to obtain a transformer health state value, and transmits the transformer health state value to the electric power centralized control system after conversion.

Description

Technical Field

[0001] The present invention relates to the field of enterprise substation operation and maintenance technology management, and more specifically to a transformer status acquisition system and method for a power centralized control system based on edge analysis. Background Art

[0002] Chinese enterprises usually build power centralized control systems to achieve centralized monitoring of multiple substations under their jurisdiction, aiming to achieve unmanned (less manned) operation mode of substations through remote centralized monitoring, comprehensive data analysis and diagnosis, and unified operation and maintenance management. As the main equipment of electric substations, it is very necessary to timely and effectively connect the health status of transformers to the enterprise power centralized control system. The health status of transformers includes two important parameters: transformer oil level and transformer winding temperature. These two parameters need to be collected and combined with the transformer load status for comprehensive analysis to determine the health status of the transformer. Therefore, the power centralized control system cannot collect this important information through the usual data collection method.

[0003] At present, there are two methods for the power centralized control system to collect the health status of transformers. Method 1: Through traditional manual inspection, the inspectors go to the site to observe and judge, and manually enter the results into the power centralized control system. Method 2: By deploying an intelligent video patrol system, the intelligent patrol system comprehensively judges the health status of the transformer through video observation and video analysis, and transmits the judgment results to the power centralized control system through data interaction through the intelligent patrol server in the centralized control center. Method 1 requires the inspectors to observe on-site and manually enter the observation results, which has the problem of untimely discovery of problems. At the same time, due to the technical level and working status of the inspectors, there is a problem of inaccurate observation results. Method 2 requires the deployment of a video analysis server and the uploading of video information to the centralized control center. There are problems such as complex construction of the transmission network (the distance between substations is far and is limited by optical fiber resources), excessive investment in the video analysis server (including analysis algorithms), and complex docking between the intelligent video patrol system and the power centralized control system (involving network security partitioning and forward and reverse isolation). Therefore, there is an urgent need for an accurate, reliable, low-investment, and flexible deployment method to realize the collection of transformer health status by the power centralized control system.

[0004] Prior art document CN114264981A discloses a regional power grid power transformer health status assessment system based on cloud-edge fusion, characterized in that it includes a data acquisition and processing component, a communication module, and a central cloud server. The data acquisition and processing component includes multiple cloud-edge acquisition processors for acquiring, storing and processing the evaluation data of the power transformer; the data acquisition and processing component interacts with the central cloud server through the communication module; the central cloud server acquires the regional standard index based on the evaluation index of the power transformer in the area to be evaluated, acquires the power transformer whose evaluation index exceeds or is lower than the preset threshold of the regional standard index as the transformer to be adjusted, and adjusts the load of the transformer to be adjusted. Its disadvantage is that the prior art discloses a health status assessment method based on "cloud" technology and arithmetic average regional standard index of data fusion of multiple transformers, and the acquisition of fusion data of multiple transformers requires the deployment of high-frequency acquisition modules, current collectors, and voltage collectors on the transformer side, which is complicated to operate, and the transformation of the transformer body and the addition of sensors may also cause adverse effects on operational safety. Summary of the invention

[0005] The present invention is a method and system for realizing centralized power control and collecting transformer health status based on edge analysis technology, which is implemented through the following technical solutions.

[0006] A first aspect of the present invention provides a transformer state acquisition system for a power centralized control system based on edge analysis, the system comprising:

[0007] Intelligent gateway, edge analysis device, camera and transformer winding temperature measuring device. The edge analysis device is connected to the intelligent gateway, camera and transformer winding temperature measuring device respectively. The camera and transformer winding temperature measuring device are deployed at the transformer site to collect transformer oil level video information and transformer winding temperature information respectively and transmit them to the edge analysis device. The intelligent gateway is deployed in the secondary room of the substation to collect transformer power load information and transmit it to the edge analysis device.

[0008] The edge analysis device is deployed in the secondary room of the substation. It analyzes the transformer oil level video information, transformer winding temperature information and transformer power load information through the edge analysis algorithm to obtain the transformer health status value, which is then transmitted to the power centralized control system after protocol conversion.

[0009] Optionally, the edge analysis device includes an Internet of Things agent control unit.

[0010] Optionally, the power centralized control system includes a front-end server, a centralized control server and a centralized control center workstation. The intelligent gateway converts the transformer health status value and transmits it to the front-end server, and the front-end server transmits the transformer health status value to the centralized control server and the centralized control center workstation.

[0011] The second aspect of the present invention provides a method for collecting transformer status of a power centralized control system based on edge analysis, and the method is based on the power centralized control system transformer status collection system based on edge analysis described in the first aspect of the present invention, comprising the following steps:

[0012] The edge analysis device collects information about the transformer through the intelligent gateway, camera and transformer winding temperature measuring device, including transformer power load information, transformer oil level video information and transformer winding temperature information; the edge analysis device executes the edge analysis algorithm at the set time interval to analyze the collected information separately, and converts the analysis results into structured data; the structured data is comprehensively processed to obtain the transformer health status value, and the transformer health status value is converted into a protocol and transmitted to the power centralized control system through the optical fiber network.

[0013] Optionally, the edge analysis device identifies the transformer oil level video information through an image intelligent analysis algorithm and outputs the image information analysis result to obtain the transformer oil level information; during the identification process, if the analysis times out, an image analysis timeout fault code will be output, and the transformer oil level video information will be collected again.

[0014] Optionally, in the method, the edge analysis device uses a multi-source transformer abnormality identification algorithm to comprehensively process and analyze three different source parameters of transformer oil level, transformer winding temperature, and transformer power load to obtain the health status of the transformer.

[0015] Optionally, the determination process of the multi-source transformer abnormality determination algorithm includes:

[0016] First, determine the oil level of the transformer. If the oil level is less than the first set threshold, output the first fault code; if the oil level is not less than the first set threshold, determine the temperature rise of the transformer winding. If the temperature rise is greater than the second set threshold, output the second fault code, otherwise determine whether the temperature rise is greater than the third set threshold; if the temperature rise is not greater than the third set threshold, output the first normal code, if the temperature rise is greater than the third set threshold, determine whether the transformer power load is greater than the rated value; if the transformer power load is not greater than the rated value, output the third fault code, otherwise determine whether the temperature rise is greater than the fourth set threshold; if the temperature rise is greater than the fourth set threshold, output the second normal code, otherwise output the fourth fault code.

[0017] Optionally, in the discrimination process of the multi-source transformer abnormality discrimination algorithm, when a fault code or a normal code is output, the discrimination process ends; outputting a fault code indicates that the health state of the transformer is abnormal, and outputting a normal code indicates that the health state of the transformer is normal; according to the different output fault codes, the abnormal conditions of the transformer oil level, transformer winding temperature or transformer power load can be judged, and corresponding processing measures can be taken.

[0018] Optionally, the edge analysis device converts the transformer health status value into a protocol and transmits the result to the power centralized control system through the optical fiber network, including:

[0019] The edge analysis device converts the transformer health status value according to the IEC61850 protocol and transmits it to the intelligent gateway machine, and the intelligent gateway machine then converts the transformer health status value according to the IEC104 protocol and transmits it to the power centralized control system.

[0020] Optionally, the edge analysis device collects transformer winding temperature information through RS485 protocol; and obtains intelligent gateway transformer power load information through IEC61850 protocol.

[0021] Compared with the prior art, the beneficial effects of the present invention include:

[0022] The present invention configures IoT proxy control units and high-definition network cameras in substations. The edge analysis technology and distributed AI analysis technology are combined to realize the collection of transformer health status by power centralized control. Compared with the prior art, the problem of untimely information collection and inaccurate transformer health status judgment in method 1 mentioned in the background technology is solved; the problem of complex transmission network construction, heavy investment in video analysis servers and analysis algorithms, and complex docking between intelligent video patrol systems and power centralized control systems in method 2 is solved. The present method has accurate data, low cost, and flexible deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the arrangement of field equipment in an embodiment of the present invention;

[0024] Figure 2 A schematic diagram of a data collection process in an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of information transmission and system network structure in an embodiment of the present invention;

[0026] Figure 4 Schematic diagram of the determination process of the multi-source transformer abnormality determination algorithm in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0028] The present invention provides a transformer status acquisition system for a power centralized control system based on edge analysis in embodiment 1, such as Figure 1 As shown, the system includes:

[0029] Intelligent gateway, edge analysis device, camera and transformer winding temperature measuring device. The edge analysis device is connected to the intelligent gateway, camera and transformer winding temperature measuring device respectively. The camera and transformer winding temperature measuring device are deployed at the transformer site to collect transformer oil level video information and transformer winding temperature information respectively and transmit them to the edge analysis device. The intelligent gateway is deployed in the secondary room of the substation to collect transformer power load information and transmit it to the edge analysis device.

[0030] The edge analysis device is deployed in the secondary room of the substation. It analyzes the transformer oil level video information, transformer winding temperature information and transformer power load information through the edge analysis algorithm to obtain the transformer health status value, which is then transmitted to the power centralized control system after protocol conversion.

[0031] In a further preferred but non-limiting embodiment, the edge analysis device includes an Internet of Things agent control unit.

[0032] In a further preferred but non-limiting embodiment, the camera includes: a high-definition network camera is deployed at an outdoor transformer site, the high-definition network camera monitors the transformer oil level, the transformer manufacturer and model are different, the transformer oil level indicator device is also different, and the high-definition network camera is required to collect transformer oil level video information;

[0033] Specifically, different analysis algorithms are customized for different types of transformer oil level indicating devices, and the analysis algorithms are installed in the IoT agent control unit. The IoT agent control unit identifies the transformer oil level value through the analysis algorithms.

[0034] In actual projects, IoT agent control units loaded with different analysis algorithms are deployed for tube-type oil level gauges, pointer-type oil level gauges, float-type oil level gauges, etc. according to different transformer manufacturers and models;

[0035] Specifically, the IoT proxy control unit CSC-1361D has local data acquisition and processing (including switch quantity, analog quantity, audio and video), protocol conversion, IoT access and transfer, audio and video intelligent recognition, AI intelligent analysis, intelligent device control, and video linkage functions. It can realize information collection, IoT proxy and edge computing.

[0036] The present invention provides a method for collecting transformer status of a power centralized control system based on edge analysis in Example 2. Based on the method for collecting transformer status of a power centralized control system based on edge analysis described in Example 1 of the present invention, Figure 2As shown, the method comprises the following steps:

[0037] The edge analysis device collects information through the intelligent gateway, camera and transformer winding temperature measuring device, including transformer power load information, transformer oil level video information and transformer winding temperature information; the edge analysis device executes the edge analysis algorithm at the set time interval to analyze the collected information separately, and converts the analysis results into structured data; the structured data is comprehensively processed to obtain the transformer health status value, and the transformer health status value is converted into a protocol and transmitted to the power centralized control system through the optical fiber network.

[0038] In a further preferred but non-limiting embodiment, in the method, the edge analysis device further includes:

[0039] The edge analysis device collects the video of the transformer oil level from the video camera through the video signal;

[0040] In a further preferred but non-limiting embodiment, Figure 2 As shown, the edge analysis device uses an image intelligent analysis algorithm to identify the transformer oil level on the video acquisition information and outputs the image information analysis result. If the analysis times out, an image analysis timeout fault code will be output;

[0041] In a further preferred but non-limiting embodiment, the edge analysis device acquires transformer winding temperature information further comprising:

[0042] The edge analysis device collects transformer winding temperature through RS485 protocol;

[0043] In a further preferred but non-limiting embodiment, the edge analysis device acquires transformer load information further comprising:

[0044] The edge analysis device obtains the transformer load of the smart gateway through the IEC61850 protocol;

[0045] In a further preferred but non-limiting embodiment, the edge analysis device comprehensively processes the transformer oil level, transformer winding temperature, and transformer load to analyze whether the above information is abnormal and whether the logical relationship between the load information and the oil level and winding temperature matches. If the comprehensive information processing is abnormal, a transformer status fault code will be output; otherwise, a transformer status normal code will be output and the next timing interval will be waited for.

[0046] In a further preferred but non-limiting embodiment, Figure 3 As shown, the edge analysis device converts the transformer health status value into a protocol and transmits it to the power centralized control system through the optical fiber network, including:

[0047] The edge analysis device converts the transformer health status value according to the IEC61850 protocol and transmits it to the intelligent gateway machine, and the intelligent gateway machine converts the transformer health status value according to the IEC104 protocol and transmits it to the power centralized control system;

[0048] In a further preferred but non-limiting embodiment, the power centralized control system includes a front-end server, a centralized control server and a centralized control center workstation. The intelligent gateway converts the transformer health status value according to the IEC104 protocol and transmits it to the front-end server. The front-end server can transmit the transformer health status value to the centralized control server and the centralized control center workstation.

[0049] In a further preferred but non-limiting embodiment, the edge analysis device confidently comprehensively processes three different source parameters of transformer oil level, transformer winding temperature, and transformer power load to analyze and obtain the transformer health status. This method is a multi-source transformer abnormality discrimination algorithm;

[0050] Specifically, the judgment process of the multi-source transformer abnormality judgment algorithm is as shown in the attached figure. Figure 4 As shown, the transformer winding temperature rise refers to the difference between the transformer winding temperature and the ambient air temperature. Excessive temperature rise will cause the transformer to overheat and increase the risk of fire. First, the transformer oil level is judged. If the level is less than the set threshold 1, it is necessary to add insulating oil and output fault code 1; secondly, the transformer temperature rise is judged. If the difference exceeds the set threshold 2, fault code 2 is output; if the temperature rise is less than or equal to the set threshold 3, the transformer is considered normal and normal code 1 is output; if the temperature rise is greater than the set threshold 3, the transformer load should be comprehensively judged at this time. The transformer power load change will affect the winding temperature rise. When the overload or load fluctuation is large, the winding temperature rise increases. The transformer winding temperature rise under different transformer power loads corresponds to a specific numerical range. If the transformer load is less than or equal to the rated load, fault code 3 is output; if the transformer load is greater than the rated load, its temperature rise is considered. If the temperature rise is greater than the set threshold 4, fault code 4 is output, otherwise the transformer is considered normal and normal code 2 is output.

[0051] Specifically, in the discrimination process of the multi-source transformer abnormality discrimination algorithm, when a fault code or a normal code is output, the discrimination process ends; outputting a fault code indicates that the health state of the transformer is abnormal, and outputting a normal code indicates that the health state of the transformer is normal; according to the different output fault codes, the abnormal conditions of the transformer oil level, transformer winding temperature or transformer power load can be judged, and corresponding processing measures can be taken.

[0052] Specifically, the threshold value 1 is generally set to 45%, the threshold value 2 is generally set to 95°C, the threshold value 3 is generally set to 65°C, and the threshold value 4 is generally set to 80°C.

[0053] After the edge analysis device analyzes the health status value of the transformer, it converts the protocol and sends the information to the power centralized control system through the intelligent gateway deployed in the substation. This completes the collection of the health status of the transformer by the power centralized control system and displays the health status of the transformer through the power centralized control system. The whole process includes data acquisition, data analysis, and information comprehensive processing. The edge analysis algorithm plays a core role in image recognition and information comprehensive processing. The results of information comprehensive processing are converted through the protocol and transmitted to the power centralized control system through the optical fiber network. The information transmission steps and analysis logic are shown in the attached figure. Figure 3 The information transmission and system network structure diagram is shown in the figure. At the same time, the edge analysis device can also transmit the information to other production management systems. This method can also identify the comprehensive information of other equipment and expand the scope of application.

[0054] The present invention provides a transformer status acquisition system and method for a power centralized control system based on edge analysis. Compared with the prior art, the present invention does not require additional sensors to the existing transformer, is not limited by cloud technology, and is not limited by complex intelligent video patrol systems. It adopts a decentralized, safe, highly reliable, and easily expandable IoT proxy control unit CSC-1361D as a carrier for analog quantity and audio and video data access and AI intelligent analysis. Based on this significant difference, the technical effects actually achieved by the present invention include at least the following: the IoT proxy control unit CSC-1361D realizes the acquisition and processing of data required for intelligent analysis, integrates multi-source data from different sensors, audio and video, and more comprehensively reflects the actual operating status of the transformer, avoiding It eliminates the diagnostic limitations caused by a single data type; as an intelligent analysis device, the IoT proxy control unit CSC-1361D uses advanced algorithms and models to conduct in-depth analysis of multi-source fusion data, and can accurately identify various fault types inside the transformer, conduct early fault warning and self-diagnosis, accurately identify the health status of the transformer, and conduct a comprehensive assessment of the transformer operation status; the main data collected by the IoT proxy control unit CSC-1361D are the transformer winding temperature and transformer oil level. The transformer winding temperature is a preset sensor for the transformer, and the transformer oil level uses a transformer external camera for liquid level image recognition. The above data collection does not involve the transformation of the transformer body or the addition of sensors, avoiding adverse effects on the transformer's operating safety.

[0055] Finally, 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A transformer status acquisition system for a power centralized control system based on edge analysis, characterized in that: The system includes: Intelligent gateway, edge analysis device, camera and transformer winding temperature measuring device. The edge analysis device is connected to the intelligent gateway, camera and transformer winding temperature measuring device respectively. The camera and transformer winding temperature measuring device are deployed at the transformer site to collect transformer oil level video information and transformer winding temperature information respectively and transmit them to the edge analysis device. The intelligent gateway is deployed in the secondary room of the substation to collect transformer power load information and transmit it to the edge analysis device. The edge analysis device is deployed in the secondary room of the substation. It analyzes the transformer oil level video information, transformer winding temperature information and transformer power load information through the edge analysis algorithm to obtain the transformer health status value, which is then transmitted to the power centralized control system after protocol conversion.

2. According to the edge analysis-based transformer status acquisition system of the power centralized control system of claim 1, it is characterized by: The edge analysis device includes an Internet of Things agent control unit.

3. According to the edge analysis-based transformer status acquisition system of the power centralized control system of claim 1, it is characterized by: The electric power centralized control system includes a front-end server, a centralized control server and a centralized control center workstation. The intelligent gateway converts the transformer health status value and transmits it to the front-end server, and the front-end server transmits the transformer health status value to the centralized control server and the centralized control center workstation.

4. A method for collecting transformer status of a power centralized control system based on edge analysis, based on a system for collecting transformer status of a power centralized control system based on edge analysis according to claims 1-3, characterized in that: The steps include: The edge analysis device collects information about the transformer through the intelligent gateway, camera and transformer winding temperature measuring device, including transformer power load information, transformer oil level video information and transformer winding temperature information; the edge analysis device executes the edge analysis algorithm at the set time interval to analyze the collected information respectively, and converts the analysis results into structured data; The structured data is comprehensively processed to obtain the transformer health status value, which is then converted into a protocol and transmitted to the power centralized control system through the optical fiber network.

5. The method for collecting transformer status of a power centralized control system based on edge analysis according to claim 4 is characterized in that: The edge analysis device identifies the transformer oil level video information through an image intelligent analysis algorithm and outputs the image information analysis result to obtain the transformer oil level information; during the identification process, if the analysis times out, an image analysis timeout fault code will be output, and the transformer oil level video information will be collected again.

6. The method for collecting transformer status of a power centralized control system based on edge analysis according to claim 4 is characterized in that: In the method, the edge analysis device uses a multi-source transformer abnormality identification algorithm to comprehensively process and analyze three different source parameters of transformer oil level, transformer winding temperature, and transformer power load to obtain the health status of the transformer.

7. The method for collecting transformer status of a power centralized control system based on edge analysis according to claim 6 is characterized in that: The determination process of the multi-source transformer abnormality determination algorithm includes: First, determine the oil level of the transformer. If the oil level is less than the first set threshold, output the first fault code; if the oil level is not less than the first set threshold, determine the temperature rise of the transformer winding. If the temperature rise is greater than the second set threshold, output the second fault code, otherwise determine whether the temperature rise is greater than the third set threshold; if the temperature rise is not greater than the third set threshold, output the first normal code, if the temperature rise is greater than the third set threshold, determine whether the transformer power load is greater than the rated value; if the transformer power load is not greater than the rated value, output the third fault code, otherwise determine whether the temperature rise is greater than the fourth set threshold; if the temperature rise is greater than the fourth set threshold, output the second normal code, otherwise output the fourth fault code.

8. The method for collecting transformer status of a power centralized control system based on edge analysis according to claim 7 is characterized in that: In the discrimination process of the multi-source transformer abnormality discrimination algorithm, when a fault code or a normal code is output, the discrimination process ends; outputting a fault code indicates that the health state of the transformer is abnormal, and outputting a normal code indicates that the health state of the transformer is normal; according to the different output fault codes, the abnormal conditions of the transformer oil level, transformer winding temperature or transformer power load can be judged, and corresponding processing measures can be taken.

9. The method for collecting transformer status of a power centralized control system based on edge analysis according to claim 4 is characterized in that: The edge analysis device converts the transformer health status value into a protocol and transmits it to the power centralized control system through the optical fiber network, including: The edge analysis device converts the transformer health status value according to the IEC61850 protocol and transmits it to the intelligent gateway machine, and the intelligent gateway machine then converts the transformer health status value according to the IEC104 protocol and transmits it to the power centralized control system.

10. The method for collecting transformer status of a power centralized control system based on edge analysis according to claim 4 is characterized in that: The edge analysis device collects transformer winding temperature information through the RS485 protocol; and obtains the intelligent gateway machine transformer power load information through the IEC61850 protocol.

Images