Power equipment field debugging system based on Internet of Things
The on-site debugging system for power equipment uses a sensor network and data analysis to generate intelligent debugging plans, enhancing efficiency and professionalism in power equipment maintenance.
Patent Information
- Application Number
- CN202411197207.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
On-site commissioning of power equipment requires significant professional knowledge, and uneven expertise among personnel can affect the effectiveness of the process.
An on-site debugging system for power equipment using a sensor network, remote control terminal, and local control module to collect and analyze data from sensors and smart devices, generating a debugging plan based on fault, environmental, and positioning information, and visually guiding personnel for efficient debugging.
The system enables efficient and professional debugging by less experienced personnel by organizing and analyzing large volumes of data, improving analysis efficiency and facilitating expert-like adjustments.
Smart Images

Figure CN119094561A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of Internet of Things analysis, and in particular relates to an on-site debugging system for electric power equipment based on the Internet of Things. Background Art
[0002] On-site commissioning of power equipment mainly includes comprehensive testing of equipment performance, parameter adjustment, troubleshooting, and system joint commissioning to ensure that the equipment meets the design requirements and reaches the best operating state. During the commissioning process, technicians will use professional testing instruments and tools to conduct comprehensive inspections and tests on the electrical performance, mechanical performance, and protection functions of the equipment. However, for on-site commissioning of power equipment, relevant personnel are required to have considerable professional knowledge, and the uneven professional knowledge and experience of relevant personnel may affect the effect of on-site regulation. Summary of the invention
[0003] In order to solve the above technical problems, the present invention proposes an on-site debugging system for power equipment based on the Internet of Things to solve the problems existing in the above-mentioned prior art.
[0004] To achieve the above object, the present invention provides an on-site debugging system for power equipment based on the Internet of Things, comprising:
[0005] A sensor network, a remote control terminal and a local control module, wherein the sensor network, the remote control terminal and the local control module are connected in sequence;
[0006] The remote control terminal receives the power equipment data, environmental data and positioning data collected by the sensor network, analyzes the power equipment data, environmental data and positioning data respectively, obtains fault location information, environmental and appearance defect information and key component movement information, and performs comprehensive analysis based on the fault location information, appearance defect information and key component movement information to obtain a debugging plan, and transmits the debugging plan to the local control module for visual display to guide relevant personnel to perform on-site debugging of power equipment.
[0007] Optionally, the sensor network includes different types of sensors and smart devices, wherein the sensors include temperature and humidity sensors, vibration sensors, and image sensors; the smart devices include smart meters and positioning devices; the power equipment data include current data, voltage data, and power data collected by smart meters and vibration data collected by vibration sensors; the environmental data include temperature and humidity data collected by temperature and humidity sensors and environmental image data collected by image sensors; and the positioning data include positioning data of power equipment and key components collected by positioning devices.
[0008] Optionally, the process of analyzing the power equipment data includes:
[0009] The power equipment data is sampled at fixed time intervals to obtain discrete data of the power equipment, the discrete data is constructed into a discrete matrix according to the numbering, and the discrete matrix is processed through a deep learning model to obtain predicted power equipment data and fault location information.
[0010] Optionally, the process of analyzing the environmental data includes:
[0011] The temperature and humidity thresholds are judged to obtain environmental defects, and the environmental image data is recognized through an image recognition model to obtain appearance defect information.
[0012] Optionally, the process of analyzing the positioning data includes:
[0013] Obtain the timestamp of installation time and location data of power equipment and key components;
[0014] In the timestamp after the installation time, the positioning data of the power equipment and the positioning data of the key components are differentially calculated to obtain the relative distance of the key components, and the relative distance is judged to obtain the movement information of the key components.
[0015] Optionally, the debugging solution generation process includes:
[0016] Comprehensive analysis of fault location information, appearance defects and key component movement information
[0017] When there is a fault location in the fault location information, the debugging solution outputs that the corresponding fault location fails;
[0018] When there is an environmental or appearance defect in the environmental and appearance defect information, the location of the appearance defect and the location of the fault location are judged, and the debugging solution outputs that the corresponding fault location has a fault, which may be caused by the environment or external damage;
[0019] If the relative distance of a key component in the key component movement information exceeds a threshold, the debugging solution outputs that a corresponding fault location has a fault, which may be caused by the movement of the key component.
[0020] Optionally, after analyzing the power equipment data, environmental data and positioning data respectively, the following further comprises:
[0021] The power equipment data, environmental data and positioning data are stored according to a tree storage architecture.
[0022] Optionally, the sensor network is connected to the remote control terminal via a gateway device.
[0023] Compared with the prior art, the present invention has the following advantages and technical effects:
[0024] Through the above technical solution, the present invention collects data of different aspects of power equipment through the sensor network, and transmits the data of different aspects to the remote control terminal for analysis. The remote control terminal processes and analyzes the data in different aspects to generate a corresponding on-site fault repair plan, and visualizes the above-mentioned on-site fault repair plan through the local control model until the on-site relevant personnel conduct on-site debugging. At the same time, the amount of data in the sensor network is large and disordered. The remote control terminal stores the collected data in an orderly manner through the relevant storage architecture, and can timely extract relevant data for analysis and processing, improve analysis efficiency, and facilitate tracing and viewing by relevant personnel. Through the generation of intelligent debugging solutions by the remote control terminal, less professional on-site debugging personnel can also make professional and efficient adjustments to power equipment, thereby effectively sinking debugging expertise. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0026] Figure 1 Schematic diagram of the system structure of an embodiment of the present invention. DETAILED DESCRIPTION
[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0028] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0029] like Figure 1 As shown, in this embodiment, a power equipment on-site debugging system based on the Internet of Things is provided, including:
[0030] Sensor network, remote control terminal and local control module;
[0031] Relevant sensor information of the power equipment is collected through the sensor network, and the sensor information is transmitted to the remote control terminal. The remote control terminal processes and analyzes the sensor information, and transmits the analysis results and debugging plan to the local control module. In the local control module, the debugging plan is visualized to guide relevant personnel to perform on-site debugging of the power equipment.
[0032] The sensor network contains different types of sensors and smart devices, including relevant temperature and humidity sensors, vibration sensors, current and voltage sensors, and image sensors. Smart devices include smart meters and positioning devices, such as positioning chips. The above-mentioned related sensors and smart devices are used to collect the operating status, power data, environmental data, and image information of the power equipment during the debugging process in real time. The relevant data collected by the sensor network include: environmental data such as temperature and humidity, debugging environment images, power equipment data such as current and voltage, power and related vibration data of power equipment, and positioning information of power equipment and key components.
[0033] In the above-mentioned sensor network, sensors for environmental data are set in the relevant environmental area to monitor the environmental data in real time. Sensors and intelligent devices corresponding to power equipment data are set at key detection positions of corresponding power equipment. The key detection positions are set according to the manual experience of relevant personnel, or by professionals explaining the key detection positions to relevant personnel for setting. Positioning equipment is set on power equipment or key components of power equipment to detect the positioning information of power equipment in real time. After the setting is completed, the sensors and intelligent devices are numbered, and when collecting relevant data, the relevant data and numbers are uploaded to the remote control terminal at the same time through data interception and transmission in a fixed time period.
[0034] The sensor network is connected to the remote control terminal through a gateway device, which acts as a data transmission relay to improve the real-time performance of data transmission and provide more ports to connect different sensors or smart devices in the sensor network to transmit data to the remote control terminal.
[0035] After the remote control terminal receives the information uploaded to the sensor network, it processes and analyzes the above-mentioned environmental data, power equipment data and power equipment positioning information through relevant processing and analysis methods, wherein relevant processing and analysis are performed based on the power equipment data to check whether the corresponding power equipment has a fault or a possible fault is detected. After the detection, a relevant fault repair plan, i.e., a debugging plan, is provided to realize remote debugging. Relevant processing and analysis are performed based on the environmental data to check whether there is a visual fault phenomenon in the power equipment. At the same time, relevant judgments are made on the environment where the power equipment is located to determine whether there are factors that cause the fault and whether the environment is safe. Relevant auxiliary information is provided based on the above results to assist in adjusting the above-mentioned fault repair plan. Relevant processing and analysis are performed on the positioning information of the power equipment and key components to analyze whether the power equipment or key components have moved. The positioning analysis results are also used as auxiliary information to assist in adjusting the above-mentioned fault repair plan.
[0036] Before the relevant processing and analysis, the remote control terminal first stores the above data to ensure the orderliness of its data, so as to facilitate the extraction and use of related data later. The data of the above sensor network is stored through a tree-shaped storage data architecture. During the storage process, its data architecture is first constructed. The root element in the data architecture is the corresponding debugging area, and sub-elements are constructed under the root element of the debugging area. The sub-elements are different power equipment numbers under the debugging area. The specific number values of different power equipment to be debugged are added to the sub-elements of the power equipment number. Corresponding sub-elements are constructed under the numbers of different power equipment. The sub-elements include data types, wherein the data types include power equipment data, environmental data and positioning information respectively, and corresponding sub-categories are constructed in the lower sub-elements of the power equipment data, including current data, voltage data, power data and vibration data, and the index of the corresponding storage position is constructed under its sub-category as a detailed description, and the corresponding sub-category is constructed in the lower sub-element of the environmental data, including temperature data, humidity data and image data, and the index of the corresponding storage position is constructed under its sub-category as a detailed description. The positioning information is directly described in detail, and the detailed description is the index of the storage position. When acquiring the data of the sensor network, the number of the data of the sensor network is extracted, and the corresponding debugging area, power equipment number, corresponding data type and data subtype are determined according to the number, and the data of the sensor network with a timestamp is stored in the corresponding storage location according to the index of the storage location in the above data architecture. When analyzing a certain power equipment, its number is checked, and the data is extracted according to the sub-elements under the number and the relevant detailed description content to obtain the relevant data corresponding to the power equipment. Through the above technical solution, only the relevant data of specific areas, specific power equipment numbers, and characteristic data subtypes are stored in different storage locations, and when extracting, all the data under the power equipment number are extracted separately and orderly, so that the above-mentioned relevant data can be effectively obtained to facilitate subsequent processing and analysis. At the same time, it is convenient for relevant personnel to trace and view data.
[0037] Specifically, the relevant processing and analysis of the power equipment data includes sampling the current, power, electricity data and vibration data in the power equipment data at fixed time periods, and after segmentation, analyzing the above-mentioned current, power and electricity data through a deep learning model, wherein the above-mentioned current, power, electricity data and vibration data set at different positions of the power equipment are sampled at fixed time intervals, and discretized to obtain a discrete matrix containing the current, power and electricity data, and the discrete matrix is predicted by the deep learning model to obtain the corresponding current, power, electricity data and vibration data for a period of time in the future, and at the same time, the relevant content of the corresponding fault location is output, and when there is no fault in the fault location, it is output that there is no fault. For the above discrete matrix, each row of the matrix represents a single sensor collecting data at different times, and the sensors are arranged in sequence according to the numbers. Each column from left to right represents the corresponding time before and after, wherein the sampling interval of the collected data can be set, such as 1h, 2h. The deep learning model adopts a fully connected neural network model, wherein the structure of the fully connected neural network model includes an input layer, a plurality of hidden layers, two fully connected layers and an output layer, the number of hidden layers is 5, and each hidden layer contains 200 neurons. The corresponding input data is identified by the above deep learning model to obtain the predicted data corresponding to the current power equipment data. The interval time between the predicted data and the input data, such as 6h, 12h or 24h, or the predicted data when, is determined according to the training data. The training data includes the historical data of the power equipment data collected by the above, and the data of the previous period of time in the historical data is used as the training data, and the collected data and the corresponding fault parts that need to be predicted in the subsequent period of time are used as labels. The training data includes relevant data of faults and related data of no faults in different parts of the power equipment. The deep learning model is trained by the training data, wherein one type of power equipment corresponds to one model, and the trained deep learning model is used to predict whether a possible fault will occur in the future. The output results of the deep learning model are used as a debugging plan to guide relevant personnel to make adjustments.
[0038] Specifically, the relevant contents of the relevant processing and analysis based on the environmental data include: the environmental data mainly includes temperature, humidity and environmental image data, wherein the temperature and humidity are judged by thresholds, and the thresholds are set according to relevant manual experience to judge whether the temperature and humidity meet the environmental conditions for the operation of the relevant power equipment. The environmental image data is identified by a relevant image recognition model to check whether there is any damage on the appearance, wherein the image recognition model can adopt the YOLOV5 model or other image recognition models, and the above image data is identified by the image recognition model to obtain the corresponding appearance defects and positions, and at the same time, a comprehensive judgment is made on the appearance defects and positions and the possible fault locations predicted by the power equipment data. When the distance between the appearance defects and positions and the possible fault locations predicted by the power equipment data is within a certain threshold, it may be a fault caused by external damage, and the above conclusions are added to the debugging plan for output, and the appearance defects and positions are output at the same time.
[0039] Specifically, the positioning information of the power equipment and key components is processed and analyzed to determine the timestamps of the power equipment and key components. After the installation is completed, the installation time is determined to the remote control terminal. In the timestamp after the installation time, the positioning data of the power equipment and key components are extracted. After the extraction, the difference between the positioning data of the power equipment and key components is calculated to determine the relative distance between the power equipment and the corresponding key component. When the relative distance changes, it is considered that the key component has moved, and the information of the moved key component may be faulty. At the same time, a threshold judgment is performed on the difference in the positioning information of the power equipment at different timestamps. When the positioning information of the power equipment moves significantly, the power equipment may not be installed firmly enough or there are other problems. At the same time, the above conclusions are supplemented to the debugging plan for output, and the positioning information of the power equipment and key components is output at the same time.
[0040] In the above data architecture, the index of the corresponding output data storage location is added to the detailed description of the data, and the above different analysis results and output contents are stored in the output data storage location to record the processing process and results of the remote control terminal.
[0041] In the local control module, the debugging scheme is displayed visually to guide relevant personnel to check and repair possible fault locations.
[0042] Through the above technical solution, the present invention collects data of different aspects of power equipment through the sensor network, and transmits the data of different aspects to the remote control terminal for analysis. The remote control terminal processes and analyzes the data in different aspects to generate a corresponding on-site fault repair plan, and visualizes the above-mentioned on-site fault repair plan through the local control model until the on-site relevant personnel conduct on-site debugging. At the same time, the amount of data in the sensor network is large and disordered. The remote control terminal stores the collected data in an orderly manner through the relevant storage architecture, and can timely extract relevant data for analysis and processing, improve analysis efficiency, and facilitate tracing and viewing by relevant personnel. Through the generation of intelligent debugging solutions by the remote control terminal, less professional on-site debugging personnel can also make professional and efficient adjustments to power equipment, thereby effectively sinking debugging expertise.
[0043] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A field debugging system for power equipment based on the Internet of Things, It is characterized in that include: A sensor network, a remote control terminal and a local control module, wherein the sensor network, the remote control terminal and the local control module are connected in sequence; The remote control terminal receives the power equipment data, environmental data and positioning data collected by the sensor network, analyzes the power equipment data, environmental data and positioning data respectively, obtains fault location information, environmental and appearance defect information and key component movement information, and performs comprehensive analysis based on the fault location information, appearance defect information and key component movement information to obtain a debugging plan, and transmits the debugging plan to the local control module for visual display to guide relevant personnel to perform on-site debugging of power equipment.
2. The system according to claim 1, It is characterized in that The sensor network includes different types of sensors and smart devices, wherein the sensors include temperature and humidity sensors, vibration sensors, and image sensors; the smart devices include smart meters and positioning devices; the power equipment data include current data, voltage data, and power data collected by smart meters and vibration data collected by vibration sensors; the environmental data include temperature and humidity data collected by temperature and humidity sensors and environmental image data collected by image sensors; and the positioning data include positioning data of power equipment and key components collected by positioning devices.
3. The system according to claim 1, It is characterized in that The process of analyzing the power equipment data includes: The power equipment data is sampled at fixed time intervals to obtain discrete data of the power equipment, the discrete data is constructed into a discrete matrix according to the numbering, and the discrete matrix is processed through a deep learning model to obtain predicted power equipment data and fault location information.
4. The system according to claim 2, It is characterized in that The process of analyzing the environmental data includes: The temperature and humidity thresholds are judged to obtain environmental defects, and the environmental image data is recognized through an image recognition model to obtain appearance defect information.
5. The system according to claim 1, It is characterized in that The process of analyzing the positioning data includes: Obtain the timestamp of installation time and location data of power equipment and key components; In the timestamp after the installation time, the positioning data of the power equipment and the positioning data of the key components are differentially calculated to obtain the relative distance of the key components, and the relative distance is judged to obtain the movement information of the key components.
6. The system according to claim 1, It is characterized in that The debugging solution generation process includes: Comprehensive analysis of fault location information, appearance defects and key component movement information When there is a fault location in the fault location information, the debugging solution outputs that the corresponding fault location fails; When there is an environmental or appearance defect in the environmental and appearance defect information, the location of the appearance defect and the location of the fault location are judged, and the debugging solution outputs that the corresponding fault location has a fault, which may be caused by the environment or external damage; If the relative distance of a key component in the key component movement information exceeds a threshold, the debugging solution outputs that a corresponding fault location has a fault, which may be caused by the movement of the key component.
7. The system according to claim 1, It is characterized in that After analyzing the power equipment data, environmental data and positioning data respectively, the method further includes: The power equipment data, environmental data and positioning data are stored according to a tree storage architecture.
8. The system according to claim 1, It is characterized in that The sensor network is connected to the remote control terminal via a gateway device.
Citation Information
Patent Citations
Data monitoring method and system based on electrical energy management system
CN117458722A
Remote diagnosis and debugging system and method for press line
CN118244744A
Electric power big data acquisition and processing method based on machine learning
CN118313812A
Unmanned inspection method and device for electric power facilities of power storage station
CN118554636A
Artificial intelligence system and method serving electric power robot
WO2022188379A1
