Detection and identification system for primary equipment of intelligent substation
By designing data acquisition and analysis modules in smart substation equipment and building and training detection and identification models, the problem of equipment detection and identification delay is solved, real-time abnormal prediction and accurate identification of equipment are realized, and the reliability and response capabilities of the system are improved.
Patent Information
- Application Number
- CN202410965812.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-15
AI Technical Summary
The detection and identification system of existing smart substation equipment has a delay in data acquisition and processing, which leads to a certain delay in real-time detection and identification of equipment status, and may cause abnormal equipment detection and matching errors.
Design a system that includes a primary equipment historical data acquisition module, historical data analysis module, detection and identification model construction module, detection and identification model training module and real-time detection and identification module. By collecting the historical data of the equipment, data analysis and feature extraction, it constructs and train detection and recognition models to realize real-time abnormality prediction and recognition of the device.
Real-time status monitoring and abnormal prediction of smart substation equipment is realized, the risk of accidents is reduced, the accuracy and reliability of equipment detection is improved, and the equipment status changes are promptly responded to equipment status changes, providing accurate identification results.
Smart Images

Figure CN118965217A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of equipment identification, and in particular to a detection and identification system for primary equipment in a smart substation. Background Art
[0002] The detection and identification system of primary equipment in smart substations is an important part of ensuring the safe operation of power systems. It is used in the process of equipment matching and analysis. By analyzing and processing the data collected by sensors after detection and identification, it can realize real-time monitoring of equipment status, fault diagnosis and preventive maintenance, thereby improving the reliability and stability of the power system.
[0003] After searching, it was found that a document with publication number CN111817441B proposed a time-space operation data acquisition system and acquisition method for a substation. The subsystem and the main system information are matched through the main clock, so that the substation operation and maintenance personnel can monitor the substation voltage measurement data. When the voltage measurement data is in an abnormal state, the problem can be discovered and processed in time; and data is collected in real time. The subsystem and the main system are synchronized with the main clock through B code time synchronization, and the synchronization error between the subsystem and the subsystem, and the subsystem and the main system does not exceed 3us, which improves the monitoring accuracy of the substation, increases the sampling rate of the device, and reduces the measurement error; in addition, the subsystem and the main system interact with data, and the voltage measurement data of each substation can be monitored at the main station end, and the status of the substation voltage measurement data can be mastered, which is applied to equipment reliability evaluation, which is conducive to fault analysis.
[0004] Combining the search literature and existing technology for analysis, the current substation equipment analysis and processing steps still have delays in post-data collection processing, which leads to certain recognition delays in real-time detection and identification of equipment status, and may cause abnormal phenomena such as equipment detection matching errors.
[0005] In order to solve the above-mentioned problems, a detection and identification system for primary equipment in smart substations is proposed. Summary of the invention
[0006] The purpose of the present invention is to provide a detection and identification system for primary equipment of a smart substation to solve the shortcomings of the background technology.
[0007] In order to achieve the above-mentioned purpose, the detection and identification system for primary equipment of a smart substation comprises the following steps:
[0008] The detection and identification system for primary equipment of a smart substation includes:
[0009] Primary equipment historical data collection module: used to collect the historical data of primary equipment and send it to the historical data analysis module;
[0010] Historical data analysis module: used to analyze and process the historical data of a device, generate identification data, and send the identification data to the detection and identification model construction module;
[0011] Detection and recognition model building module; used to construct a detection and recognition model that can predict the abnormality of a primary device according to the input of the recognition data and the device number as the output;
[0012] Detection and recognition model training module: used to train the constructed detection and recognition model and set a prediction accuracy threshold. When the prediction accuracy of the detection and recognition model reaches the prediction accuracy threshold, the training is stopped.
[0013] Real-time detection and identification module: used to send the real-time detection device data to the trained detection and identification model for analysis, and output the matched primary device number as the final identification target.
[0014] In a preferred embodiment, the steps of collecting historical data of a device are as follows:
[0015] Step S1, marking the primary devices on the nth group of equipment layout lines as n1, n2, n3, ... nN, where N is the number of primary devices on the same equipment layout line, and obtaining historical data of different primary devices, the historical data including the power value of the equipment, the temperature value around the equipment, and the image data of the shape and volume of the primary equipment;
[0016] Step S2, writing a data acquisition program to collect data in real time through sensors or cameras and save the data to a designated storage device;
[0017] Step S3, designing a data storage and transmission mechanism, storing the collected data in a database or file, and ensuring the security and accessibility of the data, using real-time transmission or batch transmission, and selecting according to the data volume and real-time requirements;
[0018] Step S4, performing preprocessing steps such as data cleaning and filling missing values on the collected data, while monitoring the status and performance of the data collection equipment and recording any abnormal data collection conditions.
[0019] In a preferred embodiment, the steps of writing the data acquisition program are:
[0020] Configure the sensor or camera, connect it to the data acquisition device, ensure the normal operation of the sensor or camera, connect it to the data acquisition device through the appropriate interface, write the data acquisition program, collect data in real time through the sensor interface or camera interface, for sensor data, use the API or driver provided by the sensor to collect data; for camera data, use the corresponding camera driver to collect images, for the collected real-time data, it may be necessary to perform format conversion, unit conversion, and filtering, write the data storage interface program, save the collected data to the specified storage device, select the database or file system as the storage medium, and select the appropriate storage method according to actual needs; it is necessary to write the corresponding exception handling program to capture and handle exceptions in a timely manner, and record log information during the data collection process.
[0021] In a preferred embodiment, the data storage and transmission configuration mechanism is:
[0022] Select suitable data storage media according to data volume and real-time requirements; select suitable storage media according to actual needs and system architecture; write data storage interface program, save the collected data to the selected storage medium; use the corresponding database connection library or file operation interface according to the selected storage medium to implement data write operations; design data transmission mechanism, determine the mode and frequency of data transmission, select real-time transmission or batch transmission method, and make selections according to data volume and real-time requirements; import data into storage media in batches, take corresponding security measures and permission management strategies, encrypt storage and transmission of sensitive data, and limit data access rights.
[0023] In a preferred embodiment, the analysis steps of the historical data analysis module are:
[0024] The collected historical data are processed to remove outliers, fill missing values, perform data smoothing and image enhancement. For different types of data, corresponding feature extraction methods are designed. Based on numerical data, variance statistical features are extracted; based on image data, feature extraction is performed; for supervised learning tasks, historical data are annotated and marked, and equipment identification data is generated based on the analysis values of the analysis marks.
[0025] In a preferred embodiment, the steps of constructing the detection and recognition model are:
[0026] Determine the abnormal situation of the primary equipment based on historical data, and mark the abnormal data. Use the abnormal situation as the target label, collect the identification data of the primary equipment, extract features from the identification data, and extract features that help identify the abnormality. For the Nth primary equipment, preset the abnormal identification prediction situation, use the identification data as the input of the model, and use the primary equipment number predicted by the abnormal identification as the output to build a detection and identification model.
[0027] In a preferred embodiment, the steps of the detection and recognition model training are:
[0028] Step K1, select the adaptation model structure and algorithm according to the characteristics and annotations of the recognition data. For the detection and recognition task of a device, use deep learning models such as convolutional neural network (CNN), recurrent neural network (RNN), etc., and prepare training data sets and verification data sets according to the recognition data;
[0029] Step K2, use the prepared training data set to train the model, and perform parameter tuning and model optimization, appropriately optimize the algorithm and regularization strategy to prevent the model from overfitting or underfitting;
[0030] Step K3, use the validation data set to evaluate and verify the trained model, calculate the prediction accuracy G of the model, set the prediction accuracy threshold Gy, and stop training when the prediction accuracy G is close to the prediction accuracy threshold Gy. Adjust the model parameters and structure according to the training situation to improve the prediction and generalization capabilities of the model.
[0031] In a preferred embodiment, the step of finally identifying the target output is:
[0032] Receive the real-time collected device data, perform preprocessing and format conversion, input the preprocessed real-time data into the trained detection and recognition model for prediction and recognition, and determine the device number nN of the future matching error based on the model output results.
[0033] In the above technical solution, the technical effects and advantages provided by the present invention are:
[0034] The present invention covers the entire life cycle of primary equipment in a smart substation from data collection to model training to real-time detection, realizing comprehensive utilization and intelligent management of data. The system has the function of identifying abnormality prediction. Through the analysis of historical data and model construction, it can predict the abnormal conditions of primary equipment, so as to take measures in advance for maintenance and repair, and reduce the risk of accidents. At the same time, through real-time data collection and real-time detection modules, it can respond to changes in equipment status in a timely manner and provide accurate identification results, which is conducive to timely discovery and handling of problems. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0036] Figure 1 This is a module flow chart of a detection and identification system for primary equipment in a smart substation according to the present invention. DETAILED DESCRIPTION
[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0038] See also Figure 1 As shown, this embodiment proposes a detection and identification system for primary equipment of a smart substation, which includes a primary equipment historical data acquisition module, a historical data analysis module, a detection and identification model construction module, a detection and identification model training module, and a real-time detection and identification module:
[0039] Primary equipment historical data collection module: used to collect historical data of primary equipment;
[0040] Step S1, classifying data acquisition equipment; marking the primary equipment on the nth group of equipment layout lines as n1, n2, n3...nN, where N is the number of primary equipment on the same equipment layout line, and obtaining historical data of different primary equipment, the historical data including equipment power usage value, equipment surrounding temperature value and primary equipment shape volume image data;
[0041] It should be noted that different types of data require the selection of appropriate data acquisition equipment. For numerical data such as power usage and temperature around the equipment, sensors can be selected for real-time acquisition. For image data such as image monitoring of shape and volume, corresponding cameras or sensors are required.
[0042] Step S2, data acquisition program writing;
[0043] Write a data acquisition program to collect data in real time through sensors or cameras and save the data to a specified storage device;
[0044] The steps of writing the data acquisition program are:
[0045] Configure sensors or cameras, connect them to data acquisition devices, ensure the normal operation of sensors or cameras, connect them to data acquisition devices through appropriate interfaces, write data acquisition programs, collect data in real time through sensor interfaces or camera interfaces, use the API or driver provided by the sensor for sensor data collection; use the corresponding camera driver for image collection for camera data, and may need to perform format conversion, unit conversion, and filtering for collected real-time data. Write data storage interface programs, save collected data to specified storage devices, select databases or file systems as storage media, and select appropriate storage methods based on actual needs;
[0046] It is necessary to write corresponding exception handling programs to capture and handle exceptions in a timely manner and record log information during the data collection process.
[0047] Step S3, data storage and transmission
[0048] Design data storage and transmission mechanisms to store the collected data in databases or files, and ensure data security and accessibility. Use real-time or batch transmission methods, depending on the amount of data and real-time requirements;
[0049] The data storage and transmission settings are:
[0050] According to the data volume and real-time requirements, select suitable data storage media, including relational databases (such as MySQL, PostgreSQL), NoSQL databases (such as MongoDB, Red is), etc.; select suitable storage media according to actual needs and system architecture; write data storage interface programs, save the collected data to the selected storage media; according to the selected storage media, use the corresponding database connection library or file operation interface to implement data write operations; design data transmission mechanisms, determine the mode and frequency of data transmission, select real-time transmission or batch transmission, and make choices based on data volume and real-time requirements; import data into storage media in batches, take corresponding security measures and permission management strategies, encrypt storage and transmission of sensitive data, and restrict data access rights.
[0051] It should be noted that real-time transmission is achieved using technologies such as message queues and WebSocket.
[0052] Step S4, pre-processing steps such as data cleaning and filling missing values are performed on the collected data, while the status and performance of the data collection equipment are monitored and abnormal data collection situations are recorded.
[0053] The primary equipment historical data collection module sends the historical data to the historical data analysis module;
[0054] Historical data analysis module: used to analyze and process the historical data of a device and generate identification data;
[0055] The analysis steps of the historical data analysis module are:
[0056] The collected historical data are processed to remove outliers, fill missing values, perform data smoothing and image enhancement. For different types of data, corresponding feature extraction methods are designed. Based on numerical data, variance statistical features are extracted; based on image data, feature extraction is performed; for supervised learning tasks, historical data are annotated and marked, and equipment identification data is generated based on the analysis values of the analysis marks.
[0057] The historical data analysis module sends the recognition data to the detection and recognition model building module;
[0058] Detection and recognition model building module; used to construct a detection and recognition model that can predict the abnormality of a primary device according to the input of the recognition data and the device number as the output;
[0059] The steps of constructing the detection and recognition model are as follows:
[0060] Determine the abnormal situation of the primary equipment based on historical data, and annotate the abnormal data, use the abnormal situation as the target label, collect the identification data of the primary equipment, extract features from the identification data, extract features that are helpful for identifying abnormalities, preset the abnormal identification prediction situation for the Nth primary equipment, use the identification data as the input of the model, and use the primary equipment number predicted by the abnormal identification as the output to build a detection and identification model;
[0061] Detection and recognition model training module; used to train the constructed detection and recognition model and set the prediction accuracy threshold. When the prediction accuracy of the detection and recognition model reaches the prediction accuracy threshold, the training is stopped.
[0062] The steps of the detection and recognition model training are:
[0063] Step K1, select the adaptation model structure and algorithm according to the characteristics and annotations of the recognition data. For the detection and recognition task of a device, use deep learning models such as convolutional neural network (CNN), recurrent neural network (RNN), etc., and prepare training data sets and verification data sets according to the recognition data;
[0064] Step K2, use the prepared training data set to train the model, and perform parameter tuning and model optimization, appropriately optimize the algorithm and regularization strategy to prevent the model from overfitting or underfitting;
[0065] Step K3, use the validation data set to evaluate and verify the trained model, calculate the prediction accuracy G of the model, set the prediction accuracy threshold Gy, and stop training when the prediction accuracy G is close to the prediction accuracy threshold Gy. Adjust the model parameters and structure according to the training situation to improve the prediction and generalization capabilities of the model.
[0066] Real-time detection and identification module: used to send the real-time detection device data to the trained detection and identification model for analysis, and output the matched primary device number as the final identification target.
[0067] The steps of finally identifying the target output are:
[0068] Receive the real-time collected device data, perform preprocessing and format conversion, input the preprocessed real-time data into the trained detection and recognition model for prediction and recognition, and determine the device number nN of the future matching error based on the model output results.
[0069] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0070] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.
[0071] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.
[0072] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which 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 detection and identification system for primary equipment of a smart substation, characterized in that: The detection and identification system for primary equipment of smart substation includes a primary equipment historical data collection module, a historical data analysis module, a detection and identification model construction module, a detection and identification model training module, and a real-time detection and identification module: Primary equipment historical data collection module: used to collect the historical data of primary equipment and send it to the historical data analysis module; Historical data analysis module: used to analyze and process the historical data of a device, generate identification data, and send the identification data to the detection and identification model construction module; Detection and recognition model building module; used to construct a detection and recognition model that can predict the abnormality of a primary device according to the input of the recognition data and the device number as the output; Detection and recognition model training module; It is used to train the constructed detection and recognition model and set the prediction accuracy threshold. When the prediction accuracy of the detection and recognition model reaches the prediction accuracy threshold, the training is stopped. Real-time detection and recognition module; It is used to send the real-time detected device data to the trained detection and recognition model for analysis, and output the matched device number as the final recognition target.
2. A detection and identification system for primary equipment of a smart substation according to claim 1, characterized in that: The steps of collecting historical data of a device are as follows: Step S1, marking the primary devices on the nth group of equipment layout lines as n1, n2, n3, ... nN, where N is the number of primary devices on the same equipment layout line, and obtaining historical data of different primary devices, the historical data including the power value of the equipment, the temperature value around the equipment, and the image data of the shape and volume of the primary equipment; Step S2, writing a data acquisition program to collect data in real time through sensors or cameras and save the data to a designated storage device; Step S3, designing a data storage and transmission mechanism, storing the collected data in a database or file, and ensuring the security and accessibility of the data, using real-time transmission or batch transmission, and selecting according to the data volume and real-time requirements; Step S4, performing preprocessing steps such as data cleaning and filling missing values on the collected data, while monitoring the status and performance of the data collection equipment and recording any abnormal data collection conditions.
3. A detection and identification system for primary equipment of a smart substation according to claim 2, characterized in that: The steps of writing the data acquisition program are: Configure the sensor or camera, connect it to the data acquisition device, ensure the normal operation of the sensor or camera, connect it to the data acquisition device through the appropriate interface, write the data acquisition program, collect data in real time through the sensor interface or camera interface, for sensor data, use the API or driver provided by the sensor to collect data; for camera data, use the corresponding camera driver to collect images, for the collected real-time data, it may be necessary to perform format conversion, unit conversion, and filtering, write the data storage interface program, save the collected data to the specified storage device, select the database or file system as the storage medium, and select the appropriate storage method according to actual needs; it is necessary to write the corresponding exception handling program to capture and handle exceptions in a timely manner, and record log information during the data collection process.
4. A detection and identification system for primary equipment of a smart substation according to claim 3, characterized in that: The data storage and transmission settings are: Select suitable data storage media according to data volume and real-time requirements; select suitable storage media according to actual needs and system architecture; write data storage interface program, save the collected data to the selected storage medium; use the corresponding database connection library or file operation interface according to the selected storage medium to implement data write operations; design data transmission mechanism, determine the mode and frequency of data transmission, select real-time transmission or batch transmission method, and make selections according to data volume and real-time requirements; import data into storage media in batches, take corresponding security measures and permission management strategies, encrypt storage and transmission of sensitive data, and limit data access rights.
5. A detection and identification system for primary equipment of a smart substation according to claim 4, characterized in that: The analysis steps of the historical data analysis module are: Remove outliers, fill missing values, perform data smoothing and image enhancement on the collected historical data. Design corresponding feature extraction methods for different types of data. Extract variance statistical features based on numerical data; perform feature extraction based on image data. For supervised learning tasks, historical data is annotated and marked, and device identification data is generated based on the analysis values of the analysis marks.
6. A detection and identification system for primary equipment of a smart substation according to claim 5, characterized in that: The steps for constructing the detection and recognition model are: Determine the abnormal situation of the primary equipment based on historical data, and mark the abnormal data. Use the abnormal situation as the target label, collect the identification data of the primary equipment, extract features from the identification data, and extract features that help identify the abnormality. For the Nth primary equipment, preset the abnormal identification prediction situation, use the identification data as the input of the model, and use the primary equipment number predicted by the abnormal identification as the output to build a detection and identification model.
7. A detection and identification system for primary equipment of a smart substation according to claim 6, characterized in that: The steps of the detection and recognition model training are: Step K1, select the adaptation model structure and algorithm according to the characteristics and annotations of the recognition data. For the detection and recognition task of a device, use deep learning models such as convolutional neural network (CNN), recurrent neural network (RNN), etc., and prepare training data sets and verification data sets according to the recognition data; Step K2, use the prepared training data set to train the model, and perform parameter tuning and model optimization, appropriately optimize the algorithm and regularization strategy to prevent the model from overfitting or underfitting; Step K3, use the validation data set to evaluate and verify the trained model, calculate the prediction accuracy G of the model, set the prediction accuracy threshold Gy, and stop training when the prediction accuracy G is close to the prediction accuracy threshold Gy. Adjust the model parameters and structure according to the training situation to improve the prediction and generalization capabilities of the model.
8. A detection and identification system for primary equipment of a smart substation according to claim 7, characterized in that: The steps of finally identifying the target output are: Receive the real-time collected device data, perform preprocessing and format conversion, input the preprocessed real-time data into the trained detection and recognition model for prediction and recognition, and determine the device number nN of the future matching error based on the model output results.
