Power grid fault detection system and method based on intelligent sensor

Abstract

The invention relates to the technical field of power grid fault detection, in particular to a power grid fault detection system and method based on an intelligent sensor, and the system comprises a data collection module which collects historical data, extracts fault data, builds a fault database, and collects the change data of power grid operation; the adaptive adjustment module adaptively adjusts the sensitivity and the detection frequency of fault detection according to the change data by establishing a fault detection model; when the system is used, the system is helped to recognize potential fault risks of a power grid more accurately, find abnormal fluctuation in time, make adjustment in advance, avoid major faults, improve the stability of a fault detection model working in different operation states, and improve the fault detection efficiency by adjusting the detection frequency in a self-adaptive mode. Therefore, unnecessary frequent detection is reduced, resource utilization of fault detection is optimized, calculation and communication loads are reduced, and the efficiency of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid fault detection, and in particular to a power grid fault detection system and method based on intelligent sensors. Background Art

[0002] Grid fault detection is one of the key technologies to ensure the safe and stable operation of the power system. By timely and accurately detecting and locating faults, measures can be taken quickly to restore power supply, reduce power outage losses, and improve system reliability.

[0003] The patent application number is CN202110711926.1, which states in the specification that "a distribution network fault detection system includes a fault indicator, a master station and a mobile terminal; multiple groups of fault indicators are equidistantly arranged along the power grid line, and a fault detection module, an alarm module and a first communication module are arranged in the fault indicator; the master station includes a second communication module, a detection area division module, a fault indicator numbering module, a fault type judgment module, a display module and a fault recording module; each time a new fault occurs, the fault recording module searches and compares the fault records in the previously set time period A to find out whether there have been faults in the same area. If there have been faults in the previous time period A in the same area, A warning message is displayed on the display module. In the present invention, the fault area of ​​the power grid can be quickly located, and the positioning time of the fault detection point can be gradually reduced, so as to continuously improve the efficiency of fault detection. The above technology frequently adds new fault indicators in high fault rate areas, which will make the redundant management of fault indicators complicated. Over time, too many redundant fault indicators may affect the management efficiency of the system and increase maintenance costs. Although the above technology supports multiple fault types such as high-resistance faults and short-circuit faults, in complex power grid environments such as weather changes, equipment aging and load fluctuations, they will have a certain impact on the stability and accuracy of the fault detection system, resulting in false alarms or missed alarms.

[0004] In summary, developing a power grid fault detection system and method based on intelligent sensors is still a key issue that needs to be urgently addressed in the field of power grid fault detection technology. Summary of the invention

[0005] The purpose of the present invention is to solve the problem in the prior art that the above-mentioned technology frequently adds new fault indicators in high fault rate areas, which makes the redundant management of fault indicators complicated. Over time, too many redundant fault indicators may affect the management efficiency of the system and increase maintenance costs. Although the above-mentioned technology supports multiple fault types such as high-resistance faults and short-circuit faults, in complex power grid environments such as weather changes, equipment aging and load fluctuations, factors will have a certain impact on the stability and accuracy of the fault detection system, resulting in false alarms or missed alarms. The present invention provides a power grid fault detection system and method based on intelligent sensors.

[0006] To achieve the above object, the present invention provides the following technical solutions: The present invention provides a power grid fault detection system based on intelligent sensors, comprising: a data acquisition module, which acquires historical data, extracts fault data, establishes a fault database, and simultaneously acquires change data of power grid operation; An adaptive adjustment module, which adaptively adjusts the sensitivity and detection frequency of fault detection according to the change data by establishing a fault detection model; A self-check optimization module, which optimizes the distribution of fault indicators according to the changes in sensitivity and detection frequency; The anti-false alarm module cross-validates the same change data through an independent detection method, combines meteorological data and power grid load, and automatically adjusts the sensitivity of fault detection.

[0007] Furthermore, the data acquisition module includes: Obtain historical fault data through maintenance records and repair logs, store them in a fault database, deploy multiple sensors to monitor the operation status of the power grid in real time, obtain operation data, and simultaneously collect environmental data related to the operation status of the power grid to obtain environmental data, and then extract change data from the operation data and environmental data; The adaptive adjustment module includes: A fault detection model for the power grid is established based on the operating data and environmental data, and is trained according to the fault data in the fault database so that the fault detection model can identify different types of faults and respond. At the same time, an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the fault detection model according to the changing data.

[0008] Furthermore, the self-check optimization module includes: Based on the changes in the detection sensitivity and detection frequency, the fault occurrence frequency, load conditions and grid topology of each area are analyzed through an optimization algorithm, the number and position of the fault indicators are intelligently adjusted, and the fault indicators are equipped with a self-checking function so that the fault indicators can perform a self-check of the working status every three minutes; The anti-false alarm module includes: A variety of independent fault detection methods are used to cross-validate the occurrence of faults. A data fusion algorithm is a technology that combines information from multiple data sources to provide more accurate, complete, and reliable decision support or analysis results. The operating data and environmental data from different sensors are processed to obtain a fused data set, and the sensitivity of fault detection is dynamically adjusted according to the fused data set.

[0009] Furthermore, the workflow of the data acquisition module is: By reading maintenance records and repair logs, we can obtain past fault data, including fault occurrence time, fault type, fault cause and fault impact area. The fault data is stored in the fault database. We deploy a variety of sensors to monitor the grid operation status in real time and simultaneously collect environmental data related to the grid operation status. Based on the operation data and environmental data, we can extract the change trend of the grid operation status. The storage formula for historical fault data is as follows: ,in is a data set, Indicates the time when the fault occurs. Indicates the type of fault. Indicates the area affected by the fault, Indicates the cause of the fault, real-time data collection model formula: ,in Indicates at time Collect operation data and environmental data at all times. Indicates at time The current value at the moment, Indicates at time The voltage value at the moment, is the temperature data, is the frequency data, is the vibration data, is the ambient temperature data, is the ambient humidity data, is the ambient wind speed data, and the change trend formula is: ,in Indicates at a point in time With time point The amount of change in a particular data between Indicates at a point in time A data at a certain moment, Indicates at a point in time The same data at the moment.

[0010] Furthermore, the workflow of the adaptive adjustment module is: A power grid fault detection model is established based on the operation data and environmental data using a machine learning algorithm, and the operation data and environmental data are input into the power grid fault detection model for training, and then a fault prediction is output according to the subsequent change data, and an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the power grid fault detection model according to the change data. The fault prediction formula is: ,in It's in time The current value in the power grid at It's in time The voltage value in the power grid at It's in time The temperature of power grid related equipment such as transformers and conductors, is the indicator function of the fault type in the power grid, Is the power grid at time The load state at the time reflects the load change of the power grid. It's in time The temperature value of the power grid surrounding environment is It's in time The humidity value of the power grid surrounding environment at that time, It's in time The wind speed value of the power grid surrounding environment at that time, and the detection sensitivity adjusted adaptively based on the data: ,in It's in time The sensitivity of the power grid fault detection model is It's in time The change in current compared to the reference value when It's in time The voltage change compared to the reference value when It's in time The temperature change of other parameters in the power grid at this time, is the current value, is the current voltage value, is the current temperature value, The weight factor determines the influence of current, voltage and temperature on the sensitivity adjustment, and the detection frequency is adaptively adjusted based on the data: ,in It's in time Adjust the detection frequency according to the changes in system data. is the dynamic adjustment factor, represents the number of areas in the grid for monitoring, It is The amount of change in a region over time.

[0011] Furthermore, the workflow of the self-check optimization module is: Based on the changes in detection sensitivity and detection frequency, an optimization algorithm is used to analyze the fault frequency, load conditions and grid topology of the power grid area. The optimization algorithm refers to a type of mathematical method and algorithm used to find the best solution. Its purpose is to maximize or minimize a certain objective function under given constraints, dynamically adjust the location and number of fault indicators, and optimize the objective function formula: ,in is the minimization objective value, is the number of monitored areas in the grid, It corresponds to The impact weight of the fault frequency in each area, It corresponds to The impact weight of the regional load, It corresponds to The impact weight of the regional power grid topology cost, It is The frequency of failures in each area, It is The grid load in the region, It is The cost of the regional power grid topology structure, each fault indicator self-check cycle is 3 minutes, if a problem is detected, a self-check report is sent, the self-check formula is: ,in It is at the moment The self-test status, It is at the moment Current data, It is at the moment Voltage data, It is at the moment Temperature data, Is a self-checking function.

[0012] Furthermore, the workflow of the anti-false alarm module is: Multiple independent fault detection methods are used to cross-validate the same event. Multiple independent fault detection methods refer to the use of different technologies, algorithms and methods to detect faults in systems, equipment and processes. Changes in current and temperature can be used as independent detection signals. When both signals indicate a fault, the alarm level is increased, otherwise the alarm level is reduced. The cross-validation result formula is: ,in It is at the moment The fault status determined, It is Independent detection methods at time The test results, It is the intersection symbol in set operation. Through the data fusion algorithm, the input data of different sensors are synthesized into a fusion data set to obtain the comprehensive fault status. The data fusion formula is: ,in It is at the moment The result after data fusion is is the summation symbol indicating that to All the data from the sensors are weighted summed. It is The weight coefficient of each sensor, It is The sensor at the time The output detection data dynamically adjusts the detection sensitivity and false alarm threshold according to the fused data set. The dynamic threshold adjustment formula is: ,in It is at the moment The fault detection threshold after dynamic adjustment, is the baseline threshold, It is at the moment The adjustment factor, It is the fault detection value after multi-sensor data fusion processing.

[0013] On the other hand, the present invention also provides a power grid fault detection method based on an intelligent sensor, which comprises the following steps: S1. Collect historical data, extract fault data, establish a fault database, and collect change data of power grid operation; S2. By establishing a fault detection model, adaptively adjusting the sensitivity and detection frequency of fault detection according to the change data; S3. Optimizing the distribution of fault indicators according to the changes in sensitivity and detection frequency; S4. Cross-validate the same change data through an independent detection method, combine meteorological data and power grid load, and automatically adjust the sensitivity of fault detection.

[0014] Furthermore, in step S1, the method of collecting historical data, extracting fault data, establishing a fault database, and collecting change data of power grid operation at the same time is: Obtain historical fault data through maintenance records and repair logs, store them in a fault database, deploy multiple sensors to monitor the operation status of the power grid in real time, obtain operation data, and simultaneously collect environmental data related to the operation status of the power grid to obtain environmental data, and then extract change data from the operation data and environmental data; In step S2, by establishing a fault detection model, the method of adaptively adjusting the sensitivity and detection frequency of fault detection according to the change data is as follows: A fault detection model for the power grid is established based on the operating data and environmental data, and is trained according to the fault data in the fault database so that the fault detection model can identify different types of faults and respond. At the same time, an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the fault detection model according to the changing data.

[0015] Furthermore, in step S3, according to the changes in the sensitivity and the detection frequency, the method for optimizing the distribution of the fault indicators is: Based on the changes in the detection sensitivity and detection frequency, the fault occurrence frequency, load conditions and power grid topology of each area are analyzed through an optimization algorithm, the number and position of the fault indicators are intelligently adjusted, and the fault indicators are equipped with a self-checking function so that the fault indicators can perform a self-check of the working status every three minutes; In step S4, the same change data is cross-validated by an independent detection method, and the method of automatically adjusting the sensitivity of fault detection by combining meteorological data and power grid load is as follows: A variety of independent fault detection methods are used to cross-validate the occurrence of faults. A data fusion algorithm is a technology that combines information from multiple data sources to provide more accurate, complete, and reliable decision support or analysis results. The operating data and environmental data from different sensors are processed to obtain a fused data set, and the sensitivity of fault detection is dynamically adjusted according to the fused data set.

[0016] Beneficial Effects Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects: When used, the present invention is helpful in helping the system to more accurately identify potential fault risks of the power grid, discover abnormal fluctuations in a timely manner, make adjustments in advance, and avoid the occurrence of major faults. It is also helpful to improve the stability of the fault detection model when working under different operating conditions. By adaptively adjusting the detection frequency, it is convenient to reduce unnecessary frequent detection, optimize resource utilization for fault detection, reduce computing and communication loads, and help improve the efficiency of the system.

[0017] When used, the present invention is conducive to ensuring that key areas are properly monitored, avoiding excessive redundancy or insufficient deployment, reducing installation and maintenance costs, and improving the efficiency of monitoring resource utilization, which is conducive to ensuring that detection results are more reliable. At the same time, it adapts to environmental factors such as power grid load fluctuations and changeable weather, improves the system's response to actual faults, avoids false alarms in fault-free situations caused by excessive sensitivity, and reduces maintenance and processing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1A system diagram of a power grid fault detection system based on an intelligent sensor according to the present invention; Figure 2 The present invention is a flow chart of a power grid fault detection method based on intelligent sensors. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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 should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but includes other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] The present invention is further described in detail below in conjunction with the accompanying drawings: Embodiment 1: like Figure 1 As shown, the present invention provides a power grid fault detection system based on intelligent sensors, including: a data acquisition module, which collects historical data, extracts fault data, establishes a fault database, and collects change data of power grid operation; The data acquisition module includes: Obtain historical fault data through maintenance records and repair logs, store them in a fault database, deploy multiple sensors to monitor the operation status of the power grid in real time, obtain operation data, and simultaneously collect environmental data related to the operation status of the power grid to obtain environmental data, and then extract change data from the operation data and environmental data; The workflow of the data acquisition module is: By reading maintenance records and repair logs, we can obtain past fault data, including fault occurrence time, fault type, fault cause and fault impact area. The fault data is stored in the fault database. We deploy a variety of sensors to monitor the grid operation status in real time and simultaneously collect environmental data related to the grid operation status. Based on the operation data and environmental data, we can extract the change trend of the grid operation status. The storage formula for historical fault data is as follows: ,in is a data set, Indicates the time when the fault occurs. Indicates the type of fault. Indicates the area affected by the fault, Indicates the cause of the fault, real-time data collection model formula: ,in Indicates at time Collect operation data and environmental data at all times. Indicates at time The current value at the moment, Indicates at time The voltage value at the moment, is the temperature data, is the frequency data, is the vibration data, is the ambient temperature data, is the ambient humidity data, is the ambient wind speed data, and the change trend formula is: ,in Indicates at a point in time With time point The amount of change in a particular data between Indicates at a point in time A data at a certain moment, Indicates at a point in time The same data at the moment; Specifically, by reading maintenance records and repair logs, we can obtain data on past faults, including the time, type, cause and affected area of ​​the fault. These data are stored in a fault database for subsequent analysis and modeling. By deploying a variety of sensors such as current sensors, voltage sensors, temperature sensors, frequency sensors and vibration sensors, we can monitor the operating status of the power grid in real time. At the same time, we can collect environmental data related to the power grid, such as temperature, humidity and wind speed. We can extract the changing trend of the power grid operating status from the operating data and environmental data, and perform trend analysis by calculating the change in data between different time points. This will help the system identify potential fault risks of the power grid more accurately, detect abnormal fluctuations in a timely manner, make adjustments in advance, and avoid major faults.

[0022] An adaptive adjustment module, which adaptively adjusts the sensitivity and detection frequency of fault detection according to the change data by establishing a fault detection model; The adaptive adjustment module includes: Establishing a fault detection model of the power grid based on the operation data and the environmental data, and training it according to the fault data in the fault database, so that the fault detection model can identify different types of faults and respond to them, and automatically adjusting the detection sensitivity and detection frequency of the fault detection model according to the change data using an adaptive algorithm; The workflow of the adaptive adjustment module is: A power grid fault detection model is established based on the operation data and environmental data using a machine learning algorithm, and the operation data and environmental data are input into the power grid fault detection model for training, and then a fault prediction is output according to the subsequent change data, and an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the power grid fault detection model according to the change data. The fault prediction formula is: ,in It's in time The current value in the power grid at It's in time The voltage value in the power grid at It's in time The temperature of power grid related equipment such as transformers and conductors, is the indicator function of the fault type in the power grid, Is the power grid at time The load state at the time reflects the load change of the power grid. It's in time The temperature value of the power grid surrounding environment is It's in time The humidity value of the power grid surrounding environment at that time, It's in time The wind speed value of the power grid surrounding environment at that time, and the detection sensitivity adjusted adaptively based on the data: ,in It's in time The sensitivity of the power grid fault detection model is It's in time The change in current compared to the reference value when It's in time The voltage change compared to the reference value when It's in time The temperature change of other parameters in the power grid at this time, is the current value, is the current voltage value, is the current temperature value, The weight factor determines the influence of current, voltage and temperature on the sensitivity adjustment, and the detection frequency is adaptively adjusted based on the data: ,in It's in time Adjust the detection frequency according to the changes in system data. is the dynamic adjustment factor, represents the number of areas in the grid for monitoring, It is The amount of change in a region over time; Specifically, the main purpose of the adaptive adjustment module is to establish an intelligent fault detection model based on power grid operation data and environmental data, and automatically adjust the sensitivity and detection frequency of fault detection according to the changing data, so as to improve the accuracy of fault detection and reduce false alarms and missed alarms. Through automatic adjustment based on changing data, it is convenient to dynamically optimize the detection parameters of the fault detection model under the conditions of power grid load fluctuations and environmental changes such as temperature and humidity changes, which is beneficial to improve the stability of the fault detection model when working under different operating conditions. By adaptively adjusting the detection frequency, it is convenient to reduce unnecessary frequent detection, optimize the resource utilization of fault detection, reduce computing and communication loads, and help improve the efficiency of the system.

[0023] A self-check optimization module, which optimizes the distribution of fault indicators according to the changes in sensitivity and detection frequency; The self-check optimization module includes: Based on the changes in the detection sensitivity and detection frequency, the fault occurrence frequency, load conditions and power grid topology of each area are analyzed through an optimization algorithm, the number and position of the fault indicators are intelligently adjusted, and the fault indicators are equipped with a self-checking function so that the fault indicators can perform a self-check of the working status every three minutes; The workflow of the self-check optimization module is as follows: Based on the changes in detection sensitivity and detection frequency, an optimization algorithm is used to analyze the fault frequency, load conditions and grid topology of the power grid area. The optimization algorithm refers to a type of mathematical method and algorithm used to find the best solution. Its purpose is to maximize or minimize a certain objective function under given constraints, dynamically adjust the location and number of fault indicators, and optimize the objective function formula: ,in is the minimization objective value, is the number of monitored areas in the grid, It corresponds to The impact weight of the fault frequency in each area, It corresponds to The impact weight of the regional load, It corresponds to The impact weight of the regional power grid topology cost, It is The frequency of failures in each area, It is The grid load in the region, It is The cost of the regional power grid topology structure, each fault indicator self-check cycle is 3 minutes, if a problem is detected, a self-check report is sent, the self-check formula is: ,in It is at the moment The self-test status, It is at the moment Current data, It is at the moment Voltage data, It is at the moment Temperature data, It is a self-checking function; Specifically, the self-check optimization module dynamically analyzes the fault frequency, load and grid topology of the power grid area according to the changes in fault detection sensitivity and frequency, intelligently optimizes the location and number of fault indicators, and ensures that the fault indicators have self-checking functions. It performs self-checks every three minutes and checks their working status in real time to improve their reliability during operation, ensure that key areas are properly monitored, avoid excessive redundancy or insufficient deployment, reduce installation and maintenance costs, and improve the efficiency of monitoring resource utilization.

[0024] The anti-false alarm module cross-validates the same change data through independent detection methods, combines meteorological data and power grid load, and automatically adjusts the sensitivity of fault detection; The anti-false alarm module includes: A plurality of independent fault detection methods are used to cross-validate the occurrence of faults, and the operating data and environmental data from different sensors are processed to obtain a fused data set through a data fusion algorithm, which is a technology that combines information from multiple data sources to provide more accurate, complete and reliable decision support or analysis results, and the sensitivity of fault detection is dynamically adjusted according to the fused data set; The workflow of the anti-false alarm module is: Multiple independent fault detection methods are used to cross-validate the same event. Multiple independent fault detection methods refer to the use of different technologies, algorithms and methods to detect faults in systems, equipment and processes. Changes in current and temperature can be used as independent detection signals. When both signals indicate a fault, the alarm level is increased, otherwise the alarm level is reduced. The cross-validation result formula is: ,in It is at the moment The fault status determined, It is Independent detection methods at time The test results, It is the intersection symbol in set operation. Through the data fusion algorithm, the input data of different sensors are synthesized into a fusion data set to obtain the comprehensive fault status. The data fusion formula is: ,in It is at the moment The result after data fusion is is the summation symbol indicating that to All the data from the sensors are weighted summed. It is The weight coefficient of each sensor, It is The sensor at the time The output detection data dynamically adjusts the detection sensitivity and false alarm threshold according to the fused data set. The dynamic threshold adjustment formula is: ,in It is at the moment The fault detection threshold after dynamic adjustment, is the baseline threshold, It is at the moment The adjustment factor, It is the fault detection value after multi-sensor data fusion processing; Specifically, multiple independent fault detection methods are used for cross-validation to reduce false alarms caused by a single detection signal. The fault status is further judged more comprehensively and accurately based on the fused data set. At the same time, the sensitivity and false alarm threshold of fault detection are dynamically adjusted to accurately judge whether there is a fault under different environmental and load conditions. When the detection results of multiple sensors are consistent, the alarm level is increased, which is conducive to ensuring that the detection results are more reliable. At the same time, it adapts to environmental factors such as grid load fluctuations and changeable meteorological factors, improves the system's response ability to actual faults, avoids false alarms in fault-free situations caused by excessive sensitivity, and reduces maintenance and processing costs.

[0025] Embodiment 2: like Figure 2 As shown, embodiment 2 provides a power grid fault detection method based on smart sensors, which includes the following steps: S1. Collect historical data, extract fault data, establish a fault database, and collect change data of power grid operation; S2. By establishing a fault detection model, adaptively adjusting the sensitivity and detection frequency of fault detection according to the change data; S3. Optimizing the distribution of fault indicators according to the changes in sensitivity and detection frequency; S4. Cross-validate the same change data through an independent detection method, combine meteorological data and power grid load, and automatically adjust the sensitivity of fault detection.

[0026] Furthermore, in step S1, the method of collecting historical data, extracting fault data, establishing a fault database, and collecting change data of power grid operation at the same time is: Obtain historical fault data through maintenance records and repair logs, store them in a fault database, deploy multiple sensors to monitor the operation status of the power grid in real time, obtain operation data, and simultaneously collect environmental data related to the operation status of the power grid to obtain environmental data, and then extract change data from the operation data and environmental data; In step S2, by establishing a fault detection model, the method of adaptively adjusting the sensitivity and detection frequency of fault detection according to the change data is as follows: A fault detection model for the power grid is established based on the operating data and environmental data, and is trained according to the fault data in the fault database so that the fault detection model can identify different types of faults and respond. At the same time, an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the fault detection model according to the changing data.

[0027] Furthermore, in step S3, according to the changes in the sensitivity and the detection frequency, the method for optimizing the distribution of the fault indicators is: Based on the changes in the detection sensitivity and detection frequency, the fault occurrence frequency, load conditions and power grid topology of each area are analyzed through an optimization algorithm, the number and position of the fault indicators are intelligently adjusted, and the fault indicators are equipped with a self-checking function so that the fault indicators can perform a self-check of the working status every three minutes; In step S4, the same change data is cross-validated by an independent detection method, and the method of automatically adjusting the sensitivity of fault detection by combining meteorological data and power grid load is as follows: A variety of independent fault detection methods are used to cross-validate the occurrence of faults. A data fusion algorithm is a technology that combines information from multiple data sources to provide more accurate, complete, and reliable decision support or analysis results. The operating data and environmental data from different sensors are processed to obtain a fused data set, and the sensitivity of fault detection is dynamically adjusted according to the fused data set.

[0028] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power grid fault detection system based on intelligent sensors, characterized in that: include: Data acquisition module, which collects historical data, extracts fault data, establishes a fault database, and collects change data of power grid operation; An adaptive adjustment module, which adaptively adjusts the sensitivity and detection frequency of fault detection according to the change data by establishing a fault detection model; A self-check optimization module, which optimizes the distribution of fault indicators according to the changes in sensitivity and detection frequency; The anti-false alarm module cross-validates the same change data through an independent detection method, combines meteorological data and power grid load, and automatically adjusts the sensitivity of fault detection.

2. A power grid fault detection system based on intelligent sensors according to claim 1, characterized in that: The data acquisition module includes: Obtain historical fault data through maintenance records and repair logs, store them in a fault database, deploy multiple sensors to monitor the operation status of the power grid in real time, obtain operation data, and simultaneously collect environmental data related to the operation status of the power grid to obtain environmental data, and then extract change data from the operation data and environmental data; The adaptive adjustment module includes: A fault detection model for the power grid is established based on the operating data and environmental data, and is trained according to the fault data in the fault database so that the fault detection model can identify different types of faults and respond. At the same time, an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the fault detection model according to the changing data.

3. A power grid fault detection system based on intelligent sensors according to claim 2, characterized in that: The self-check optimization module includes: Based on the changes in the detection sensitivity and detection frequency, the fault occurrence frequency, load conditions and grid topology of each area are analyzed through an optimization algorithm, the number and position of the fault indicators are intelligently adjusted, and the fault indicators are equipped with a self-checking function so that the fault indicators can perform a self-check of the working status every three minutes; The anti-false alarm module includes: A variety of independent fault detection methods are used to cross-validate the occurrence of faults. A data fusion algorithm is a technology that combines information from multiple data sources to provide more accurate, complete, and reliable decision support or analysis results. The operating data and environmental data from different sensors are processed to obtain a fused data set, and the sensitivity of fault detection is dynamically adjusted according to the fused data set.

4. The power grid fault detection system based on intelligent sensors according to claim 3 is characterized in that: The workflow of the data acquisition module is: By reading maintenance records and repair logs, we can obtain past fault data, including fault occurrence time, fault type, fault cause and fault impact area. The fault data is stored in the fault database. We deploy a variety of sensors to monitor the grid operation status in real time and simultaneously collect environmental data related to the grid operation status. Based on the operation data and environmental data, we can extract the change trend of the grid operation status. The storage formula for historical fault data is as follows: ,in is a data set, Indicates the time when the fault occurs. Indicates the type of fault. Indicates the area affected by the fault, Indicates the cause of the fault, real-time data collection model formula: ,in Indicates at time Collect operation data and environmental data at all times. Indicates at time The current value at the moment, Indicates at time The voltage value at the moment, is the temperature data, is the frequency data, is the vibration data, is the ambient temperature data, is the ambient humidity data, is the ambient wind speed data, and the change trend formula is: ,in Indicates at a point in time With time point The amount of change in a particular data between Indicates at a point in time A data at a certain moment, Indicates at a point in time The same data at the moment.

5. The power grid fault detection system based on intelligent sensors according to claim 4 is characterized in that: The workflow of the adaptive adjustment module is: A power grid fault detection model is established based on the operation data and environmental data using a machine learning algorithm, and the operation data and environmental data are input into the power grid fault detection model for training, and then a fault prediction is output according to the subsequent change data, and an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the power grid fault detection model according to the change data. The fault prediction formula is: ,in It's in time The current value in the power grid at It's in time The voltage value in the power grid at It's in time The temperature of power grid related equipment such as transformers and conductors, is the indicator function of the fault type in the power grid, The grid is at time The load state at the time reflects the load change of the power grid. It's in time The temperature value of the power grid surrounding environment is It's in time The humidity value of the power grid surrounding environment at that time, It's in time The wind speed value of the power grid surrounding environment at that time, and the detection sensitivity adjusted adaptively based on the data: ,in It's in time The sensitivity of the power grid fault detection model is It's in time The change in current compared to the reference value when It's in time The voltage change compared to the reference value when It's in time The temperature change of other parameters in the power grid at this time, is the current value, is the current voltage value, is the current temperature value, The weight factor determines the influence of current, voltage and temperature on the sensitivity adjustment, and the detection frequency is adaptively adjusted based on the data: ,in It's in time Adjust the detection frequency according to the changes in system data. is the dynamic adjustment factor, represents the number of areas in the grid for monitoring, It is The amount of change in a region over time.

6. A power grid fault detection system based on intelligent sensors according to claim 5, characterized in that: The workflow of the self-check optimization module is as follows: Based on the changes in detection sensitivity and detection frequency, an optimization algorithm is used to analyze the fault frequency, load conditions and grid topology of the power grid area. The optimization algorithm refers to a type of mathematical method and algorithm used to find the best solution. Its purpose is to maximize or minimize a certain objective function under given constraints, dynamically adjust the location and number of fault indicators, and optimize the objective function formula: ,in is the minimization objective value, is the number of monitored areas in the grid, It corresponds to The impact weight of the fault frequency in each area, It corresponds to The impact weight of the regional load, It corresponds to The impact weight of the regional power grid topology cost, It is The frequency of failures in each area, It is The grid load in the region, It is The cost of the regional power grid topology structure, each fault indicator self-check cycle is 3 minutes, if a problem is detected, a self-check report is sent, the self-check formula is: ,in It is at the moment The self-test status, It is at the moment Current data, It is at the moment Voltage data, It is at the moment Temperature data, Is a self-checking function.

7. A power grid fault detection system based on intelligent sensors according to claim 6, characterized in that: The workflow of the anti-false alarm module is: Multiple independent fault detection methods are used to cross-validate the same event. Multiple independent fault detection methods refer to the use of different technologies, algorithms and methods to detect faults in systems, equipment and processes. Changes in current and temperature can be used as independent detection signals. When both signals indicate a fault, the alarm level is increased, otherwise the alarm level is reduced. The cross-validation result formula is: ,in It is at the moment The fault status determined, It is Independent detection methods at time The test results, It is the intersection symbol in set operation. Through the data fusion algorithm, the input data of different sensors are synthesized into a fusion data set to obtain the comprehensive fault status. The data fusion formula is: ,in It is at the moment The result after data fusion is is the summation symbol indicating that to All the data from the sensors are weighted summed. It is The weight coefficient of each sensor, It is The sensor at the time The output detection data dynamically adjusts the detection sensitivity and false alarm threshold according to the fused data set. The dynamic threshold adjustment formula is: ,in It is at the moment The fault detection threshold after dynamic adjustment, is the baseline threshold, It is at the moment The adjustment factor, It is the fault detection value after multi-sensor data fusion processing.

8. A method for detecting power grid faults based on smart sensors, based on a power grid fault detection system based on smart sensors according to any one of claims 1 to 7, characterized in that: The following steps are involved: S1. Collect historical data, extract fault data, establish a fault database, and collect change data of power grid operation; S2. By establishing a fault detection model, adaptively adjusting the sensitivity and detection frequency of fault detection according to the change data; S3. Optimizing the distribution of fault indicators according to the changes in sensitivity and detection frequency; S4. Cross-validate the same change data through an independent detection method, combine meteorological data and power grid load, and automatically adjust the sensitivity of fault detection.

9. A method for detecting power grid faults based on intelligent sensors according to claim 8, characterized in that: In step S1, the method of collecting historical data, extracting fault data, establishing a fault database, and collecting change data of power grid operation is as follows: Obtain historical fault data through maintenance records and repair logs, store them in a fault database, deploy multiple sensors to monitor the operation status of the power grid in real time, obtain operation data, and simultaneously collect environmental data related to the operation status of the power grid to obtain environmental data, and then extract change data from the operation data and environmental data; In step S2, by establishing a fault detection model, the method of adaptively adjusting the sensitivity and detection frequency of fault detection according to the change data is as follows: A fault detection model for the power grid is established based on the operating data and environmental data, and is trained according to the fault data in the fault database so that the fault detection model can identify different types of faults and respond. At the same time, an adaptive algorithm is used to automatically adjust the detection sensitivity and detection frequency of the fault detection model according to the changing data.

10. A method for detecting power grid faults based on intelligent sensors according to claim 9, characterized in that: In step S3, according to the changes in sensitivity and detection frequency, the method for optimizing the distribution of fault indicators is: Based on the changes in the detection sensitivity and detection frequency, the fault occurrence frequency, load conditions and grid topology of each area are analyzed through an optimization algorithm, the number and position of the fault indicators are intelligently adjusted, and the fault indicators are equipped with a self-checking function so that the fault indicators can perform a self-check of the working status every three minutes; In step S4, the same change data is cross-validated by an independent detection method, and the method of automatically adjusting the sensitivity of fault detection by combining meteorological data and power grid load is as follows: A variety of independent fault detection methods are used to cross-validate the occurrence of faults. A data fusion algorithm is a technology that combines information from multiple data sources to provide more accurate, complete, and reliable decision support or analysis results. The operating data and environmental data from different sensors are processed to obtain a fused data set, and the sensitivity of fault detection is dynamically adjusted according to the fused data set.

Images