Abnormal alarm system applied to intelligent substation auxiliary system

Abstract

The invention discloses an abnormity alarm system applied to an intelligent substation auxiliary system, and belongs to the technical field of power systems. An abnormity alarm system applied to an intelligent substation auxiliary system comprises a data acquisition unit, a data analysis unit and an abnormity alarm unit. The problem that abnormal conditions cannot be accurately processed in the prior art is solved, the operation data of various devices in the transformer substation are collected in real time, the collected data are processed, analyzed and stored to achieve real-time monitoring of the operation states of the devices in the transformer substation, and according to a preset alarm rule, the abnormal conditions can be accurately processed. According to the invention, real-time alarm is carried out on monitored abnormal data, comprehensive monitoring of substation equipment, environmental parameters and operation states is realized, abnormal conditions are found and processed in time, and safety and stability of a power system are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and specifically to an abnormal alarm system applied to the auxiliary system of an intelligent substation. Background Art

[0002] A substation is an important guarantee for the safe operation of the power grid. Strengthening the intelligent construction of substations is crucial for the construction of the national power grid. The intelligent auxiliary control system of a substation is an important part of the intelligent construction of the substation. It can centrally monitor and uniformly manage multiple and scattered monitoring points, meet the diversified management needs of the current power operation and maintenance center for substations, effectively reduce the work pressure of inspection personnel, and improve work efficiency. However, there are numerous devices inside the substation and the operating environment is complex. Traditional manual monitoring methods often have difficulty in promptly and accurately discovering and handling various abnormal situations, which may lead to serious consequences such as equipment damage and power interruption; therefore, it does not meet the existing requirements, and for this reason, we propose an abnormal alarm system applied to the auxiliary system of an intelligent substation. Summary of the Invention

[0003] The purpose of the present invention is to provide an abnormal alarm system applied to the auxiliary system of an intelligent substation. By collecting the operation data of various devices in the substation in real time, processing, analyzing, and storing the collected data, real-time monitoring of the operation status of substation devices is achieved. According to the preset alarm rules, real-time alarms are issued for the detected abnormal data, the operation status of the substation is monitored in real time, abnormal situations are promptly discovered and handled, and the safety and stability of the power system are ensured, thus solving the problems raised in the above background art.

[0004] To achieve the above purpose, the present invention provides the following technical solution: An abnormal alarm system applied to the auxiliary system of an intelligent substation, the system includes a data acquisition unit, a data analysis unit, and an abnormal alarm unit; The data acquisition unit is configured to preprocess and store the data collected in real time by sensors and data acquisition devices, wherein the data collected in real time includes the operation data of various devices in the substation and the environmental data in the substation; The data analysis unit is configured to perform data analysis on the preprocessed operation data and environmental data respectively, determine whether there is abnormal data in the operation data and environmental data through analysis, and mark the detected abnormal data, wherein the data analysis includes: Based on a machine learning algorithm, training and optimizing a substation operation anomaly detection model, and using the substation operation anomaly detection model to analyze the operation data to determine whether there is abnormal data; Comparing the environmental data with a preset safety threshold, and once the environmental data exceeds the range of the safety threshold, the exceeded environmental data is determined as abnormal data; The abnormal alarm unit is configured to perform real-time alarm on the detected abnormal data according to the pre-set alarm rules.

[0005] Further, the data acquisition unit includes: A data collection module, configured to deploy sensors and data collection devices inside the substation to collect the operation data of various devices in the substation in real time, including data of voltage, current, temperature and pressure, and to collect the environmental data in the substation in real time, including temperature, humidity and smoke concentration; A data processing module, configured to preprocess the operation data and environmental data collected in real time before data storage, including data cleaning, data compression and data formatting; A data storage module, configured to store the preprocessed operation data and environmental data in a database, and the database provides functions of data query, data backup and data download.

[0006] Further, the execution steps of the data collection module further include: Extract the environmental data in the substation in real time; Obtain the temperature change rate and humidity change rate within each unit cycle according to the environmental data in the substation; Use the temperature change rate and humidity change rate within each unit cycle to obtain the average change rate of humidity corresponding to each unit change in temperature in the substation for all experienced unit cycles as the first change rate data; Extract the temperature and pressure in the operation data of various devices in the substation in real time; Obtain the temperature change rate and pressure change rate for each unit cycle according to the operation data of various devices in the substation; Obtain the average change rate of pressure corresponding to each unit change in temperature of various devices in the substation for all experienced unit cycles according to the temperature change rate and pressure change rate for each unit cycle as the second change rate data; Use the first change rate data and the second change rate data to adjust the data collection frequencies of voltage and current of various devices in the substation.

[0007] Further, using the first change rate data and the second change rate data to adjust the data collection frequencies of voltage and current of various devices in the substation includes: Retrieve the first change rate data and the second change rate data; Compare the first change rate data and the second change rate data; When the first change rate data is not lower than the second change rate data, adjust the data collection frequencies of voltage and current of various devices in the substation; Among them, the data acquisition frequency of the adjusted voltage corresponding to various devices in the substation is obtained through the following formula: ; Among them, F v represents the data acquisition frequency of the adjusted voltage; F v0 represents the data acquisition frequency of the voltage before adjustment; P 01 represents the average change rate of humidity corresponding to a unit change in temperature in the substation; P 02 represents the average change rate of pressure corresponding to a unit change in temperature of various devices in the substation; P 01max represents the maximum change rate of humidity corresponding to a unit change in temperature that appears in all unit cycles; P 02max represents the maximum change rate of pressure corresponding to a unit change in temperature that appears in all unit cycles of various devices in the substation; And, the data acquisition frequency of the adjusted current corresponding to various devices in the substation is obtained through the following formula: ; Among them, F I represents the data acquisition frequency of the adjusted current; F I0 represents the data acquisition frequency of the current before adjustment; F v represents the data acquisition frequency of the adjusted voltage; F v0 represents the data acquisition frequency of the voltage before adjustment.

[0008] Furthermore, using the first change rate data and the second change rate data to adjust the data acquisition frequencies of the voltage and current of various devices in the substation further includes: Retrieve the first change rate data and the second change rate data; Compare the first change rate data and the second change rate data; When the first change rate data is lower than the second change rate data, then retrieve the temperature change rate and humidity change rate in each unit cycle; Use the temperature change rate and humidity change rate in each unit cycle to adjust the data acquisition frequency of humidity; Among them, the adjusted data acquisition frequency of humidity is obtained through the following formula: ; Among them, F w represents the adjusted data acquisition frequency of humidity; F w0 represents the data acquisition frequency of humidity before adjustment; n represents the number of unit cycles; T i represents the temperature change rate corresponding to the i-th unit cycle; W iRepresents the humidity change rate corresponding to the i-th unit cycle; T x Represents a preset reference value for the temperature change rate; W x Represents a preset reference value for the humidity change rate.

[0009] Furthermore, the data processing module is specifically: Data cleaning: Identify and correct errors, anomalies, and inconsistencies in the operation data and environmental data, including missing value handling, outlier handling, data deduplication, and data consistency checking, where: Missing value handling is to check whether there are missing values in the operation data and environmental data, and adopt methods such as filling, deleting, or interpolation for processing; Outlier handling is to identify outliers using the 3σ principle and adopt methods such as correction or deletion according to the nature of the outliers for processing; Data deduplication is to check whether there are duplicate records in the operation data and environmental data, and delete the duplicates; Data consistency checking is to verify whether the logical relationships between the operation data and environmental data in different fields or tables are consistent, including the continuity of timestamps and the range limits of numerical values; Data compression: Use the PLAHUO SDC compression algorithm to compress the operation data and environmental data, reducing the storage space of the operation data and environmental data; Data formatting: Convert the operation data and environmental data into a unified data format.

[0010] Furthermore, the data analysis unit includes: Operation data analysis module, configured to build a substation operation anomaly detection model based on a machine learning algorithm, train and optimize it, deploy the trained substation operation anomaly detection model into actual use, analyze the preprocessed operation data, and determine whether there is abnormal data in the operation data through analysis; Environmental data analysis module, configured to compare the preprocessed environmental data with the preset safety thresholds. When the environmental data exceeds the range of the safety thresholds, the exceeded environmental data is determined as abnormal data, where the safety thresholds are specifically: The standard for the environmental temperature inside the substation is 5~30°C; The standard for the environmental humidity inside the substation is 40%~60%; The standard for the environmental smoke concentration inside the substation is 0.1 to 0.5 mg / m³; Data marking module, configured to mark the abnormal data detected in the operation data analysis module and the environmental data analysis module. The marked abnormal data is used for subsequent abnormal alarm.

[0011] Furthermore, the operation data analysis module includes: A feature extraction module, configured to collect a historical data set of a substation and perform feature extraction, extracting features from the historical data set, including statistical features, time-domain features, and frequency-domain features; A data partitioning module, configured to partition the historical data set after feature extraction into a training set and a test set, including using 70%-80% of the data as the training set and 20%-30% of the data as the test set; A model construction module, configured to construct an abnormal operation detection model of a substation based on a machine learning algorithm, and the machine learning algorithm uses a support vector machine, a random forest, or a neural network; A model training module, configured to train the abnormal operation detection model of the substation using the training set, including adjusting hyperparameters, and evaluating the trained abnormal operation detection model of the substation using the test set, and the evaluation metrics include accuracy, recall rate, and F1 value; A model deployment module, configured to use the trained abnormal operation detection model of the substation to perform abnormal detection on operation data, perform real-time analysis on the input operation data through the abnormal operation detection model of the substation, and output the abnormal detection result to determine the abnormal data in the operation data; A model optimization module, configured to regularly collect new historical data sets, realize regular retraining of the abnormal operation detection model of the substation, and update the parameters of the abnormal operation detection model of the substation.

[0012] Further, the data marking module is specifically: Distinguish normal data and abnormal data according to the analysis results of the operation data analysis module and the environmental data analysis module; Determine the data that meets the analysis conditions as normal data, and determine the data that does not meet the analysis conditions as abnormal data; Mark the determined normal data and abnormal data, and the marking method is to add labels; If it is normal data, add the label "normal"; If it is abnormal data, add the label "abnormal".

[0013] Further, the abnormal alarm unit includes: An alarm rule module, configured to set alarm rules according to the operation requirements and safety standards of the substation, including the type of abnormal data, the alarm method, and the alarm duration; A real-time alarm module, configured to perform real-time alarm on the detected abnormal data according to the set alarm rules; A human-computer interaction module, configured to provide a human-computer interaction interface to display the real-time alarm content, including displaying the detected abnormal data and the analysis results of the data analysis unit.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: Through the data acquisition unit, the present invention can collect the operation data and environmental data of various devices in the substation in real time, perform preprocessing and storage, providing an accurate and complete data basis for subsequent data analysis. The data analysis unit can automatically analyze the operation data based on machine learning algorithms, accurately identify abnormal situations in the data, improving the accuracy and efficiency of anomaly detection. At the same time, it can also compare the environmental data with preset safety thresholds, and the data exceeding the thresholds will be determined as abnormal, further enhancing the security of the system. Finally, the anomaly warning unit issues real-time warnings for the detected abnormal data according to preset warning rules, realizing comprehensive monitoring of the substation equipment, environmental parameters and operation status, promptly discovering and handling abnormal situations, and ensuring the safety and stability of the power system. Brief Description of the Drawings

[0015] Figure 1 It is a schematic diagram of the overall structure of the anomaly warning system of the present invention; Figure 2 It is a schematic diagram of the structure of the operation data analysis module of the present invention. Detailed Embodiments

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] To solve the technical problem that the existing manual monitoring method often fails to timely and accurately discover and handle various abnormal situations, which may lead to serious consequences such as equipment damage and power interruption, please refer to Figure 1 - Figure 2 , the present embodiment provides the following technical solutions: An anomaly warning system applied to the intelligent substation auxiliary system, the system includes a data acquisition unit, a data analysis unit and an anomaly warning unit; The data acquisition unit is configured to preprocess and store the data collected in real time by sensors and data acquisition devices, wherein the data collected in real time includes the operation data of various devices in the substation and the environmental data in the substation; The data analysis unit is configured to perform data analysis on the preprocessed operation data and environmental data respectively, determine whether there is abnormal data in the operation data and environmental data through analysis, and mark the detected abnormal data, wherein the data analysis includes: Based on machine learning algorithms, train and optimize the abnormal operation detection model of the substation. Use the abnormal operation detection model of the substation to analyze the operation data and determine whether there is abnormal data; Compare the environmental data with the preset safety threshold. Once the environmental data exceeds the range of the safety threshold, the exceeded environmental data is determined as abnormal data; The abnormal alarm unit is configured to perform real-time alarm on the detected abnormal data according to the preset alarm rules.

[0018] The technical effects of the above content are as follows: Through the data acquisition unit, it is possible to comprehensively and real-time collect the operation data (such as voltage, current, temperature, and pressure) of various devices in the substation and environmental data (such as temperature, humidity, and smoke concentration), providing a detailed data basis for subsequent data analysis and abnormal detection. The data analysis unit then uses machine learning algorithms to build and train and optimize the abnormal operation detection model of the substation, realizing intelligent analysis of the operation data, being able to accurately judge whether there is abnormality in the operation data. At the same time, by comparing the environmental data with the preset safety threshold, it is possible to automatically determine whether the environmental data is abnormal, improving the accuracy and efficiency of the analysis. Marking the abnormal data in the operation data and environmental data provides a clear basis for subsequent abnormal alarms. Finally, the abnormal alarm unit performs real-time alarm on the detected abnormal data according to the preset alarm rules, ensuring that the operation and maintenance personnel can obtain key information in a timely manner, take corresponding measures for processing, and avoid accidents. The above design realizes the comprehensive monitoring of the substation equipment, environmental parameters, and operation status through data collection, data analysis, and real-time alarm, discovers and processes abnormal situations in a timely manner, and ensures the safety and stability of the power system.

[0019] The data acquisition unit includes: The data collection module is configured to deploy sensors and data collection devices inside the substation to collect the operation data of various devices in the substation in real-time, including data on voltage, current, temperature, and pressure, and to collect the environmental data inside the substation in real-time, including temperature, humidity, and smoke concentration; The data processing module is configured to preprocess the operation data and environmental data collected in real-time before data storage, including data cleaning, data compression, and data formatting; The data storage module is configured to store the preprocessed operation data and environmental data in a database, and the database provides functions such as data query, data backup, and data download.

[0020] The technical effects of the above content are as follows: The data acquisition module can collect the operation data (voltage, current, temperature, pressure) of various devices and environmental data (temperature, humidity, smoke concentration) in the substation in real time and efficiently by deploying sensors and data acquisition devices inside the substation. This comprehensive data acquisition method ensures that the system can obtain key information on the operation of the substation, realizing comprehensive monitoring of the substation equipment, environmental parameters, and operation status, laying a solid foundation for subsequent data analysis and anomaly detection. The data processing module preprocesses the real-time collected data before data storage, including data cleaning, data compression, and data formatting. Data cleaning can identify and correct errors, anomalies, and inconsistencies in the data to ensure data accuracy. Data compression reduces the data storage space and improves the data processing efficiency. Data formatting converts the data into a unified format for subsequent data analysis and processing. The data storage module stores the preprocessed data in the database, and the database provides functions such as data query, data backup, and data download. The data storage module not only ensures the security and reliability of the data but also facilitates the operation and maintenance personnel to manage and use the data. For example, through the data query function, the operation and maintenance personnel can quickly obtain the required data. The data backup function ensures the data recovery ability in case of accidents, and the data download function supports the export and further analysis of the data.

[0021] Specifically, the execution steps of the data acquisition module further include: Real-time extraction of the environmental data inside the substation; Obtaining the temperature change rate and humidity change rate within each unit cycle according to the environmental data inside the substation; Using the temperature change rate and humidity change rate within each unit cycle to obtain the average change rate of humidity corresponding to each unit change in temperature inside the substation for all the experienced unit cycles as the first change rate data; Real-time extraction of the temperature and pressure in the operation data of various devices inside the substation; Obtaining the temperature change rate and pressure change rate for each unit cycle according to the operation data of various devices inside the substation; Obtaining the average change rate of pressure corresponding to each unit change in temperature of various devices inside the substation for all the experienced unit cycles according to the temperature change rate and pressure change rate for each unit cycle as the second change rate data; Adjusting the data acquisition frequency of the voltage and current of various devices inside the substation by using the first change rate data and the second change rate data.

[0022] The technical effects of the above technical solution are as follows: By extracting the environmental data (temperature, humidity) and equipment operation data (temperature, pressure) in the substation in real time and calculating the change rate within each unit cycle respectively, the dynamic changes in the environment and equipment status can be accurately captured. For example, by calculating the change rates of temperature and humidity, the fluctuations in environmental temperature and humidity can be clearly understood; by calculating the change rates of equipment temperature and pressure, the status changes during equipment operation can be accurately grasped. This provides an accurate data basis for subsequent in-depth analysis.

[0023] Obtain the average change rates of humidity and pressure corresponding to each unit change in temperature (the first change rate data and the second change rate data), and comprehensively analyze the associated changes between environmental factors and between equipment operation parameters from multiple dimensions. This comprehensive consideration makes the understanding of the complex situation in the substation more comprehensive, avoids the limitations of single data index analysis, and thus improves the accuracy and effectiveness of data collection. The first change rate data reflects the relationship between temperature and humidity in the environment, which helps to judge the potential impact of environmental conditions on equipment operation. For example, when the temperature rises and the humidity changes abnormally, it may affect the insulation performance of the equipment. By monitoring and analyzing such associated changes, potential risks in equipment operation can be detected in advance, enhancing the reliability of equipment operation status monitoring. At the same time, the second change rate data reflects the change relationship between temperature and pressure during equipment operation, providing an important basis for evaluating the health status of the equipment. For example, when the equipment temperature rises, if the pressure change does not conform to the normal change law, it indicates that there are potential faults in the equipment. By monitoring and analyzing the change relationships of these parameters, abnormal situations in the equipment can be detected in a timely manner, ensuring the reliable operation of the equipment.

[0024] Meanwhile, by adjusting the data acquisition frequency of the device voltage and current according to the first change rate data and the second change rate data, the dynamic optimization of the data acquisition frequency is achieved. When the environment or the device state changes drastically, increasing the acquisition frequency can obtain the device operation data more timely, so as to monitor the device state more accurately; when the change is relatively stable, reducing the acquisition frequency can reduce the amount of data acquisition, save resources, and improve the data processing efficiency. Reasonably adjusting the data acquisition frequency avoids unnecessary high-frequency data acquisition when the device state is stable, reduces the burden of data storage and processing, and saves system resources. At the same time, increasing the acquisition frequency during the critical period of device state change ensures that sufficient key data can be obtained, guarantees the effective monitoring of the device operation state, and realizes the rational utilization of resources. This technical solution can real-time sense the changes in the environment and device operation state in the substation, and adjust the data acquisition frequency and analysis strategy in a timely manner according to these changes. Whether it is the sudden change of the environmental temperature and humidity or the abnormal fluctuation of the device operation parameters, the system can make corresponding responses, improving the adaptability of the system to complex environments and device operation conditions. Through accurate data acquisition and reliable device state monitoring, problems in device operation can be discovered and processed in a timely manner, avoiding system downtime or accidents caused by device failures, guaranteeing the stable operation of the substation system, and improving the reliability and safety of the system.

[0025] Specifically, using the first change rate data and the second change rate data to adjust the data acquisition frequency of the voltage and current of various devices in the substation includes: Retrieve the first change rate data and the second change rate data; Compare the first change rate data and the second change rate data; When the first change rate data is not lower than the second change rate data, adjust the data acquisition frequency of the voltage and current of various devices in the substation; Among them, the adjusted data acquisition frequency of the voltage corresponding to various devices in the substation is obtained through the following formula: ; Among them, F v represents the adjusted data acquisition frequency of the voltage; F v0 represents the data acquisition frequency of the voltage before adjustment; P 01 represents the average change rate of humidity corresponding to each unit change in temperature in the substation; P 02 represents the average change rate of pressure corresponding to each unit change in temperature of various devices in the substation; P 01max represents the maximum change rate of humidity corresponding to each unit change in temperature that appears in all unit periods; P 02maxIt represents the maximum rate of change of pressure corresponding to each unit change in temperature that occurs in all kinds of equipment within the substation in each unit cycle. And, the data acquisition frequency of the adjusted current corresponding to various equipment within the substation is obtained through the following formula: ; Among them, F I represents the data acquisition frequency of the adjusted current; F I0 represents the data acquisition frequency of the current before adjustment; F v represents the data acquisition frequency of the adjusted voltage; F v0 represents the data acquisition frequency of the voltage before adjustment.

[0026] The technical effects of the above technical solution are as follows: Humidity changes are usually closely related to environmental factors. A large humidity change may mean that the environmental conditions where the substation is located have changed significantly. A large change in humidity affects the insulation performance of the equipment, and thus has a potential impact on the operating state of the equipment. The pressure change caused by the change in the equipment's own temperature is relatively small, indicating that the potential impact of environmental factors on the equipment is greater than the impact brought by the change in the equipment's own operating state at this time. In order to timely capture the impact of environmental factor changes on the electrical parameters (such as voltage and current) of the equipment, it is necessary to adjust the data acquisition frequency to more accurately monitor the operating condition of the equipment and discover possible problems in advance. At the same time, adjusting the acquisition frequency in this case can improve the acquisition accuracy and timeliness of the equipment voltage and current data when environmental factors change greatly. By collecting data more frequently, it can more accurately reflect the changes in the electrical performance of the equipment under complex environmental changes, which helps to timely discover possible abnormalities of the equipment, such as current changes and voltage fluctuations caused by insulation degradation. This is crucial for ensuring the safe and stable operation of the substation, and can take measures for maintenance and repair in advance to avoid serious consequences such as power outages caused by equipment failures.

[0027] There are correlations and influences between the environmental factors (temperature and humidity) and the equipment operation parameters (temperature and pressure) within a substation. Generally speaking, the changes in environmental temperature and humidity will affect the heat dissipation conditions, insulation performance, etc. of the equipment, and thus affect the operation state of the equipment; while the changes in the temperature and pressure of the equipment itself directly reflect the working conditions of the equipment. By comparing the average change rate of humidity corresponding to each unit change in temperature with the average change rate of pressure corresponding to each unit change in equipment temperature, the change trends of the environment and equipment operation state can be comprehensively evaluated. When the first change rate data is not lower than the second change rate data, it indicates that the influence of environmental factors on the operation of the substation is relatively large or comparable to the equipment's own factors. At this time, it is necessary to adjust the data acquisition frequencies of voltage and current in order to more comprehensively grasp the changes in electrical parameters of the substation under complex environmental and equipment operation conditions and timely detect possible abnormal situations. Specifically, humidity will affect the insulation performance of the equipment surface, and the change in humidity causes parameters such as the dielectric constant and resistivity of the insulating material to change. When the environmental temperature changes, the heat dissipation situation of the equipment will change, and the co-variation of humidity will further affect the heat dissipation efficiency and insulation performance of the equipment. For example, when the humidity is high, condensed water is likely to form on the equipment surface, reducing the insulation resistance and increasing the risk of electric leakage. At this time, it is necessary to more closely monitor the voltage and current of the equipment in order to timely detect electrical faults that may be caused by the decline in insulation performance. On the other hand, the temperature change inside the equipment will cause thermal expansion and contraction, thus resulting in a change in the internal pressure of the equipment. For example, during the operation of equipment such as transformers and capacitors, the increase in temperature will cause the volume of the internal insulating oil to expand and the pressure to increase. If the pressure change is abnormal, it indicates that there are faults inside the equipment, such as local overheating and insulation damage. Therefore, by monitoring the change rates of the equipment temperature and pressure, the operation state of the equipment can be indirectly judged. When the average change rate of pressure corresponding to each unit change in temperature is large, it indicates that the operation state of the equipment may be unstable, and it is necessary to increase the acquisition frequencies of voltage and current in order to more accurately capture the changes in the equipment's electrical parameters and timely detect potential faults.

[0028] By adjusting the data acquisition frequency of voltage and current according to the change rates of environmental data and equipment operation data, the matching degree between the data acquisition frequency and the actual operating environment state and equipment state can be effectively improved, as well as the sensitivity of the dynamic adjustment of the data acquisition frequency and its followability with the changes of environmental factors. When there is a specific relationship between the first change rate data (related to the environment) and the second change rate data (related to equipment operation), adjusting the acquisition frequency can ensure that when the environment or equipment state changes greatly, the acquisition frequency of relevant data is increased, so as to obtain key information more timely and accurately, which helps to more precisely monitor the operation state of the substation. Unnecessary high-frequency data acquisition is avoided when the environment and equipment state are relatively stable, reducing the resource consumption of the data acquisition system, including power, storage resources, etc., while also reducing the burden of data transmission and processing, and improving the operation efficiency and economy of the entire monitoring system. A more reasonable data acquisition frequency setting helps to timely discover potential problems in the operation of the substation, take measures in advance for prevention and treatment, thereby improving the reliability and stability of the substation operation and reducing risks such as power outages caused by equipment failures or environmental factors.

[0029] Specifically, using the first change rate data and the second change rate data to adjust the data acquisition frequency of the voltage and current of various equipment in the substation further includes: Retrieving the first change rate data and the second change rate data; Comparing the first change rate data and the second change rate data; When the first change rate data is lower than the second change rate data, the temperature change rate and humidity change rate within each unit cycle are retrieved; Using the temperature change rate and humidity change rate within each unit cycle to adjust the data acquisition frequency of humidity; Among them, the adjusted data acquisition frequency of humidity is obtained through the following formula: ; Among them, F w represents the adjusted data acquisition frequency of humidity; F w0 represents the data acquisition frequency of humidity before adjustment; n represents the number of unit cycles; T i represents the temperature change rate corresponding to the i-th unit cycle; W i represents the humidity change rate corresponding to the i-th unit cycle; T x represents the preset reference value of the temperature change rate; W x represents the preset reference value of the humidity change rate.

[0030] The technical effects of the above technical solution are as follows: By obtaining the temperature change rate, humidity change rate, and pressure change rate within each unit cycle, calculating the first change rate data and the second change rate data, and adjusting the data acquisition frequency of humidity based on this, the environmental data in the substation can be collected more accurately. This way of dynamically adjusting the acquisition frequency according to the actual environmental changes avoids the data deviation that may be caused by fixed-frequency acquisition, ensuring that the collected data can accurately reflect the real-time change of humidity in the substation. At the same time, when the first change rate data is lower than the second change rate data, the data acquisition frequency of humidity is adjusted using the temperature change rate and humidity change rate within each unit cycle, realizing the optimization of the data acquisition strategy. Considering the complexity and interrelationship of environmental factors in the substation, this targeted adjustment can flexibly adjust the acquisition frequency according to different environmental change characteristics, improving the efficiency and quality of data acquisition, making the collected data more representative and effective. The operating state of the equipment in the substation is closely related to environmental factors. By accurately collecting environmental data and adjusting the data acquisition frequency according to environmental changes, potential impacts of environmental factors on equipment operation can be detected in a timely manner. For example, changes in humidity may affect the insulation performance of the equipment. By collecting humidity data more accurately, corresponding measures can be taken in a timely manner to ensure the safe operation of the equipment, reduce the risk of equipment failure, and improve the overall operating reliability of the substation. Through the refined processing of environmental data and the intelligent adjustment of the acquisition frequency, this technical solution can effectively improve the adaptive dynamic adjustment sensitivity and accuracy of the data acquisition frequency adjustment of the substation monitoring system, thereby realizing more efficient management and maintenance of the substation and improving the stability and efficiency of the operation of the entire power system.

[0031] The data processing module is specifically as follows: Data cleaning: Identify and correct errors, anomalies, and inconsistencies in operation data and environmental data, including missing value processing, outlier processing, data deduplication, and data consistency checking, where: Missing value processing is to check whether there are missing values in the operation data and environmental data, and adopt methods such as filling, deleting, or interpolation for processing to ensure the integrity of the data; Outlier processing is to identify outliers using the 3σ principle and adopt methods such as correction or deletion according to the nature of the outliers, improving the accuracy and reliability of the data; Data deduplication is to check whether there are duplicate records in the operation data and environmental data, and delete the duplicates to avoid data redundancy and repeated analysis; Data consistency checking is to verify whether the logical relationships between operation data and environmental data in different fields or tables are consistent, including the continuity of timestamps and the range limits of numerical values, ensuring the consistency and accuracy of the data; Data Compression: The PLAHUO SDC compression algorithm is used to compress the operation data and environmental data, reducing the storage space of the operation data and environmental data, lowering the storage cost, and at the same time improving the efficiency of data processing; Data Formatting: The operation data and environmental data are converted into a unified data format, facilitating subsequent data analysis and processing, and improving the readability and usability of the data.

[0032] The technical effects of the above content are as follows: Through data cleaning, data compression, and data formatting, the quality, storage efficiency, and readability of the operation data and environmental data are improved. Through a series of data processing steps, the quality, storage efficiency, and readability of the data are effectively enhanced, providing a solid foundation for subsequent data analysis and anomaly detection, thereby improving the performance and reliability of the entire intelligent substation auxiliary system. Data Analysis Unit, including: Operation Data Analysis Module, configured to build, train, and optimize a substation operation anomaly detection model based on machine learning algorithms, deploy the trained substation operation anomaly detection model into actual use, analyze the preprocessed operation data, and determine whether there is abnormal data in the operation data through analysis; Environmental Data Analysis Module, configured to compare the preprocessed environmental data with the preset safety thresholds. When the environmental data exceeds the range of the safety thresholds, the exceeded environmental data is determined as abnormal data. Among them, the safety thresholds are specifically: The standard for the environmental temperature inside the substation is 5~30°C; The standard for the environmental humidity inside the substation is 40%~60%; The standard for the environmental smoke concentration inside the substation is 0.1 to 0.5 mg / m³; Data Marking Module, configured to mark the abnormal data detected in the Operation Data Analysis Module and the Environmental Data Analysis Module. The marked abnormal data is used for subsequent anomaly alerts.

[0033] The technical effects of the above content are as follows: The operation data analysis module uses machine learning algorithms to construct a substation operation anomaly detection model. Through training and optimization, it can accurately identify anomalies in operation data. Compared with traditional manual monitoring, the analysis method based on intelligent algorithms greatly improves the accuracy and efficiency of anomaly detection. Deploying the trained model to analyze the preprocessed operation data can determine in real time whether there are anomalies in the data, providing timely and reliable information support for operation and maintenance personnel. The environmental data analysis module compares the preprocessed environmental data with preset safety thresholds. When the data exceeds the threshold range, it is automatically determined as abnormal data. This method is simple and effective. By setting reasonable safety thresholds, it can quickly respond to environmental changes, providing important early warning information for operation and maintenance personnel to ensure the safe operation of the substation. The data marking module marks the abnormal data detected by the operation data analysis module and the environmental data analysis module. The marked abnormal data not only provides clear fault indications for operation and maintenance personnel but also provides important bases for subsequent data analysis and fault troubleshooting.

[0034] In summary, through intelligent operation data analysis, environmental data comparison, and abnormal data marking, comprehensive monitoring and anomaly detection of substation operation data and environmental data are achieved, significantly improving the operation and maintenance efficiency and safety of the substation.

[0035] The operation data analysis module includes: The feature extraction module is configured to collect the historical data set of the substation and perform feature extraction, extracting features from the historical data set, including statistical features, time-domain features, and frequency-domain features; The data division module is configured to divide the historical data set after feature extraction into a training set and a test set, including using 70%-80% of the data as the training set and 20%-30% of the data as the test set; The model construction module is configured to construct a substation operation anomaly detection model based on machine learning algorithms. The machine learning algorithms use support vector machines, random forests, or neural networks; The model training module is configured to use the training set to train the substation operation anomaly detection model, including adjusting hyperparameters, and using the test set to evaluate the trained substation operation anomaly detection model. The evaluation metrics include accuracy, recall rate, and F1 value; The model deployment module is configured to use the trained substation operation anomaly detection model to perform anomaly detection on operation data. Through real-time analysis of the input operation data by the substation operation anomaly detection model, the anomaly detection results are output to determine the abnormal data in the operation data; The model optimization module is configured to regularly collect new historical data sets, realize regular retraining of the substation operation anomaly detection model, and update the parameters of the substation operation anomaly detection model.

[0036] The technical effects of the above content are as follows: The feature extraction module can collect the historical data set of the substation and conduct in-depth feature extraction, including statistical features, time-domain features, and frequency-domain features. The extracted features can comprehensively reflect the operating state of the substation and provide a rich information basis for subsequent anomaly detection. The data partitioning module divides the historical data set after feature extraction into a training set of 70%-80% and a test set of 20%-30%. This partitioning method helps the model fully learn the data features during the training process and accurately evaluate the model performance during the test phase. The model construction module can construct a substation operation anomaly detection model based on machine learning algorithms. The machine learning algorithms are flexibly selected and diverse, including support vector machines, random forests, or neural networks, etc. These algorithms each have their own advantages and can provide efficient anomaly detection solutions according to different scenarios and requirements. The model training module uses the training set to fully train the model and optimizes the model performance by adjusting hyperparameters. Subsequently, the trained model is comprehensively evaluated using the test set. The evaluation metrics include accuracy, recall rate, and F1 value, etc., to ensure that the model has excellent anomaly detection capabilities in practical applications. The model deployment module deploys the trained model to conduct real-time anomaly detection on the operation data, can quickly analyze the input operation data, and accurately output the anomaly detection results, helping the operation and maintenance personnel to promptly discover and process abnormal data, ensuring the safe and stable operation of the substation. By regularly collecting new historical data sets through the model deployment module, the model can be periodically retrained and parameter updated. The continuous optimization mechanism helps the model adapt to the changing operating environment and maintain the accuracy and efficiency of the model's anomaly detection.

[0037] The data marking module, specifically: Based on the analysis results of the operation data analysis module and the environment data analysis module, distinguish normal data and abnormal data; Determine the data that meets the analysis conditions as normal data and the data that does not meet the analysis conditions as abnormal data; Mark the determined normal data and abnormal data, and the marking method is to add labels; If it is normal data, add the label "normal"; If it is abnormal data, add the label "abnormal".

[0038] The technical effects of the above content are as follows: By accurately distinguishing and marking normal data and abnormal data through the data marking module, abnormal data can be quickly located, improving the accuracy and efficiency of anomaly alarms, so that the subsequent anomaly alarm unit can promptly give alarms and take corresponding treatment measures, thereby ensuring the safe and stable operation of the substation.

[0039] The anomaly alarm unit includes: An alarm rule module, configured to set alarm rules according to the operation requirements and safety standards of the substation, including the types of abnormal data (such as current, voltage abnormalities, equipment failures, etc.), alarm methods (such as sound alarms, light prompts or SMS notifications), and alarm duration; A real-time alarm module, configured to perform real-time alarms on the detected abnormal data according to the set alarm rules; A human-machine interaction module, configured to provide a human-machine interaction interface to display the real-time alarm content, including displaying the detected abnormal data and the analysis results of the data analysis unit.

[0040] The technical effects of the above content are as follows: The alarm rule module sets alarm rules according to the operation requirements and safety standards of the substation, which can ensure that the operation and maintenance personnel can receive alarm information in a timely and continuous manner, providing clear standards and basis for subsequent real-time alarms. The real-time alarm module quickly responds to the detected abnormal data according to the set alarm rules. Once abnormal data appears, it will immediately trigger the alarm mechanism and send a warning to the operation and maintenance personnel through the preset alarm method. This real-time alarm ability enables the operation and maintenance personnel to quickly locate and handle abnormalities, effectively preventing potential safety hazards. The human-machine interaction module provides a human-machine interaction interface to clearly and intuitively display the real-time alarm content. The interface not only displays the detected abnormal data, but also presents the in-depth analysis results of the data by the data analysis unit. This display method enables the operation and maintenance personnel to clearly understand the specific situation and possible reasons of the abnormal data at a glance, so as to formulate more accurate countermeasures.

[0041] In summary, through the collaborative work of the alarm rule module, real-time alarm module and human-machine interaction module, the rapid identification, real-time alarm and intuitive display of abnormal data in the substation are realized, which not only improves the safety monitoring level of the substation, but also significantly improves the operation and maintenance efficiency, providing a strong guarantee for the safe and stable operation of the substation. Working principle: The data acquisition unit real-time collects operation data and environmental data and performs preprocessing and storage, providing an accurate and complete data basis for subsequent data analysis. The data analysis unit can automatically analyze the operation data based on machine learning algorithms, accurately identify abnormal situations in the data, improving the accuracy and efficiency of anomaly detection. At the same time, it can also compare the environmental data with the preset safety thresholds to further enhance the security of the system. Finally, the abnormal alarm unit performs real-time alarms on the detected abnormal data according to the preset alarm rules to ensure the safety and stability of the power system. Based on the above design, the comprehensive monitoring of substation equipment, environmental parameters and operation status is realized, so that abnormal situations can be detected and processed in a timely manner.

[0042] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0043] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

Claims

1. An abnormal alarm system applied to the auxiliary system of a smart substation, characterized in that, It includes a data acquisition unit, a data analysis unit, and an abnormal alarm unit; The data acquisition unit is configured to preprocess and store the data collected in real time by sensors and data acquisition devices. The data collected in real time includes the operation data of various devices in the substation and the environmental data in the substation; Among them, during data acquisition, the environmental data and device operation data in the substation are extracted in real time, and the change rate within each unit cycle is calculated respectively to capture the dynamic changes in the environment and device status; The data analysis unit is configured to perform data analysis on the preprocessed operation data and environmental data respectively, determine whether there is abnormal data in the operation data and environmental data through analysis, and mark the detected abnormal data. The data analysis includes: Based on machine learning algorithms, training and optimizing the substation operation abnormal detection model, and using the substation operation abnormal detection model to analyze the operation data to determine whether there is abnormal data; Comparing the environmental data with a preset safety threshold. If the environmental data exceeds the range of the safety threshold, the exceeded environmental data is determined as abnormal data; The abnormal alarm unit is configured to perform real-time alarm on the detected abnormal data according to the preset alarm rules.

2. The abnormal alarm system applied to the intelligent substation auxiliary system according to claim 1, characterized in that: The data acquisition unit includes: A data collection module, configured to deploy sensors and data acquisition devices inside the substation to collect the operation data of various devices in the substation in real time, including data on voltage, current, temperature, and pressure, and to collect the environmental data in the substation in real time, including temperature, humidity, and smoke concentration; A data processing module, configured to preprocess the operation data and environmental data collected in real time before data storage, including data cleaning, data compression, and data formatting; A data storage module, configured to store the preprocessed operation data and environmental data in a database, and the database provides functions such as data query, data backup, and data download.

3. The abnormal alarm system applied to the intelligent substation auxiliary system according to claim 2, wherein: The execution steps of the data collection module further include: Extracting the environmental data in the substation in real time; Obtaining the temperature change rate and humidity change rate within each unit cycle according to the environmental data in the substation; Using the temperature change rate and humidity change rate within each unit cycle to obtain the average change rate of humidity corresponding to each unit change in temperature in the substation for all experienced unit cycles as the first change rate data; Extracting the temperature and pressure in the operation data of various devices in the substation in real time; Obtaining the temperature change rate and pressure change rate for each unit cycle according to the operation data of various devices in the substation; Obtaining the average change rate of pressure corresponding to each unit change in temperature of various devices in the substation for all experienced unit cycles according to the temperature change rate and pressure change rate for each unit cycle as the second change rate data; Adjusting the data collection frequencies of voltage and current of various devices in the substation using the first change rate data and the second change rate data.

4. The abnormal alarm system applied to the intelligent substation auxiliary system according to claim 3, characterized in that: Adjusting the data collection frequencies of voltage and current of various devices in the substation using the first change rate data and the second change rate data includes: Retrieving the first change rate data and the second change rate data; Compare the first change rate data and the second change rate data; When the first change rate data is not lower than the second change rate data, adjust the data acquisition frequencies of the voltages and currents of various devices in the substation.

5. The abnormal alarm system applied to the intelligent substation auxiliary system according to claim 3, characterized in that: Adjusting the data acquisition frequencies of the voltages and currents of various devices in the substation by using the first change rate data and the second change rate data further includes: Retrieve the first change rate data and the second change rate data; Compare the first change rate data and the second change rate data; When the first change rate data is lower than the second change rate data, retrieve the temperature change rate and the humidity change rate in each unit cycle; Adjust the data acquisition frequency of humidity by using the temperature change rate and the humidity change rate in each unit cycle.

6. The abnormal alarm system applied to the intelligent substation auxiliary system according to claim 2, characterized in that: The data processing module is specifically: Data cleaning: Identify and correct errors, anomalies, and inconsistencies in operation data and environmental data, including missing value processing, outlier processing, data deduplication, and data consistency checking, where: Missing value processing is to check whether there are missing values in operation data and environmental data, and adopt methods such as filling, deleting, or interpolation for processing; Outlier processing is to identify outliers using the 3σ principle and adopt methods such as correction or deletion according to the nature of the outliers; Data deduplication is to check whether there are duplicate records in operation data and environmental data and delete the duplicates; Data consistency checking is to verify whether the logical relationships between operation data and environmental data in different fields or tables are consistent, including the continuity of timestamps and the range limits of numerical values; Data compression: Compress operation data and environmental data using the PLAHUO SDC compression algorithm to reduce the storage space of operation data and environmental data; Data formatting: Convert operation data and environmental data into a unified data format.

7. The abnormal alarm system applied to the intelligent substation auxiliary system according to claim 1, characterized in that: The data analysis unit includes: The operation data analysis module is configured to construct a substation operation anomaly detection model based on a machine learning algorithm, train and optimize it, deploy the trained substation operation anomaly detection model into actual use, analyze the preprocessed operation data, and determine whether there is abnormal data in the operation data through analysis; The environmental data analysis module is configured to compare the preprocessed environmental data with a preset safety threshold. When the environmental data exceeds the range of the safety threshold, the exceeded environmental data is determined as abnormal data, where the safety threshold is specifically: The standard for the ambient temperature in the substation is 5~30°C; The standard for the ambient humidity in the substation is 40%~60%; The standard for the ambient smoke concentration in the substation is 0.1 to 0.5 mg / m³; The data marking module is configured to mark the abnormal data detected in the operation data analysis module and the environmental data analysis module. The marked abnormal data is used for subsequent abnormal alarms.

8. An abnormal alarm system applied to an intelligent substation auxiliary system according to claim 7, characterized in that: The operation data analysis module includes: The feature extraction module is configured to collect the historical data set of the substation and perform feature extraction, and extract the features in the historical data set, including statistical features, time domain features, and frequency domain features; The data partitioning module is configured to partition the historical data set after feature extraction into a training set and a test set, including using 70%-80% of the data as the training set and 20%-30% of the data as the test set; The model construction module is configured to construct a substation operation anomaly detection model based on machine learning algorithms, and the machine learning algorithms use support vector machines, random forests or neural networks; The model training module is configured to train the substation operation anomaly detection model using the training set, including adjusting hyperparameters, and evaluate the trained substation operation anomaly detection model using the test set. The evaluation metrics include accuracy, recall rate and F1 value; The model deployment module is configured to use the trained substation operation anomaly detection model to perform anomaly detection on the operation data, perform real-time analysis on the input operation data through the substation operation anomaly detection model, and output the anomaly detection results to determine the abnormal data in the operation data; The model optimization module is configured to regularly collect new historical data sets, realize regular retraining of the substation operation anomaly detection model, and update the parameters of the substation operation anomaly detection model.

9. An abnormal alarm system applied to the auxiliary system of a smart substation according to claim 7, characterized in that: The data marking module is specifically: According to the analysis results of the operation data analysis module and the environmental data analysis module, distinguish normal data and abnormal data; Determine the data that meets the analysis conditions as normal data, and determine the data that does not meet the analysis conditions as abnormal data; Mark the determined normal data and abnormal data, and the marking method is to add labels; If it is normal data, add a normal label; If it is abnormal data, add an abnormal label.

10. The abnormal alarm system applied to the intelligent substation auxiliary system according to claim 1, characterized in that: The abnormal alarm unit includes: The alarm rule module is configured to set alarm rules according to the operation requirements and safety standards of the substation, including the type of abnormal data, the alarm method and the alarm duration; The real-time alarm module is configured to perform real-time alarm on the detected abnormal data according to the set alarm rules; The human-computer interaction module is configured to provide a human-computer interaction interface to display the real-time alarm content, including displaying the detected abnormal data and the analysis results of the data analysis unit.

Images