A control method and system of an intelligent power circuit breaker

Abstract

The application discloses a control method and system of an intelligent power circuit breaker, and relates to the technical field of circuit breakers.The method comprises the following steps: collecting data group Xk(t) and substituting the data group into a load abnormality detection formula and a current harmonic abnormality detection formula to identify faults; obtaining load deviation ALk(t) and current harmonic deviation AHk(t); and integrating the deviations to form Ack(k) control action matrix to evaluate the execution linkage control of the circuit breaker, which not only ensures quick response in the event of a fault, but also avoids unnecessary system interference and improves the operation efficiency of the overall power grid.On this basis, the operation parameters and control actions of the distribution network are combined to further evaluate the stability of the power grid and obtain the overall stability score Sk(t) of the power grid, so that clear power grid optimization feedback is provided.The method can monitor the operation state of the power grid in real time, quickly respond to faults and make intelligent decisions, thereby significantly improving the stability and safety of the power grid.

Description

Technical Field

[0001] This invention relates to the field of circuit breaker technology, specifically to a control method and system for an intelligent power circuit breaker. Background Technology

[0002] As one of the core infrastructures of modern society, the power system involves multiple stages, including the generation, transmission, distribution, and consumption of electricity. Its reliability and security directly affect the normal operation of society. Within the power system, the distribution network, as a crucial bridge connecting power plants and end users, is responsible for efficiently and safely delivering electricity to various power-consuming units. With the development of smart grids and digital technologies, traditional distribution networks are gradually evolving towards intelligence and automation.

[0003] In traditional power distribution networks, circuit breakers typically operate according to pre-set, fixed logic, relying primarily on changes in local current and voltage parameters to determine whether to disconnect the circuit. While this design works effectively in simpler distribution networks, it often reveals numerous problems in complex, multi-tiered distribution networks. A significant drawback is that the action of a single circuit breaker is usually based solely on local fault information, lacking a global perspective and intelligent coordination. Consequently, a fault in one area of ​​the network may not be quickly isolated, leading to a substantial decrease in the reliability and stability of the entire power grid, and even triggering widespread power outages.

[0004] Furthermore, traditional power circuit breakers lack flexibility in their control methods. When a fault occurs, they cannot adjust the circuit breaker's operation in real time based on the specific fault type, location, and load status. Especially in cases of multiple faults or cascading effects, traditional circuit protection mechanisms often fail to provide a rapid and effective response. For example, when a localized overload occurs in a region, the power system may not disconnect the faulty load in time, leading to excessive load on the grid and damage to equipment, further exacerbating the burden on the power system. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a control method and system for intelligent power circuit breakers, solving the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a control method for an intelligent power circuit breaker, comprising the following steps:

[0007] S1. By connecting the operating data of multiple circuit breakers in the power system and preprocessing the operating data, a power system data acquisition group Xk(t) is formed.

[0008] S2. Substitute the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network, obtain the load deviation △Lk(t) and current harmonic deviation △Hk(t), and combine the load deviation △Lk(t) and current harmonic deviation △Hk(t) to form the feature vector Fk(t).

[0009] S3. Perform anomaly analysis based on the obtained feature vector Fk(t) to obtain the power protection strategy response action generated in the fault area;

[0010] S4. Evaluate the circuit breaker's linkage algorithm formula based on the power protection strategy response action, obtain the result of the circuit breaker linkage control, and mark it as the control action Ack(t).

[0011] S5. By fitting the control action Ack(t) with the operating parameters of the distribution network, the overall stability of the power grid is evaluated, the overall stability score Sk(t) of the power grid is obtained, and it is compared with the preset safe threshold Sthe for stable operation of the power grid to obtain feedback results for power grid operation optimization.

[0012] Preferably, S1 includes S11 and S12;

[0013] S11. By connecting multiple intelligent sensors integrated in the power system, the operation record information of each circuit breaker is collected in real time, including current information, voltage information, load information, frequency information, current harmonic component information and load change rate information. By marking the operation record information with time t and the unique identifier k of the circuit breaker, the current Ik(t), voltage Vk(t), load Zk(t), frequency Fk(t), current harmonic component Hk(t) and load change rate Pk(t) of circuit breaker k at time t are obtained, forming the operation data of circuit breaker k.

[0014] S12. The obtained operating data of circuit breaker k is preprocessed. The preprocessing includes noise reduction preprocessing, outlier detection preprocessing and missing value filling preprocessing. Then, the preprocessed operating data of circuit breaker k is standardized to eliminate the differences between different units and obtain the power system data set Xk(t) of circuit breaker k at time t.

[0015] The power system data collection group X is specifically X = (NIk(t), NVk(t), NZk(t), NFk(t), NHk(t), NPk(t)).

[0016] Preferably, S2 includes S21 and S22;

[0017] S21. Substitute the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network and obtain the load deviation ΔLk(t) and current harmonic deviation ΔHk(t) of circuit breaker k at time t.

[0018] S22. By integrating the power system data sets Xk(t), load deviation △Lk(t), and current harmonic deviation △Hk(t), an eigenvector F is formed.

[0019] Preferably, the load deviation ΔLk(t) is obtained by the following calculation formula:

[0020] ;

[0021] In the formula, NPk(t-1), NIk(t-1), and NVk(t-1) represent the load change rate, current, and voltage of circuit breaker k at time t-1, respectively, and p1 and p2 represent the influence coefficients on load deviation. Specifically, p1 represents the influence coefficient of current deviation on load deviation, and p2 represents the influence coefficient of voltage deviation on load deviation.

[0022] The current harmonic deviation ΔHk(t) is obtained by the following calculation formula:

[0023] ;

[0024] In the formula, NHk(t-1), NZk(t-1) and NFk(t-1) represent the current harmonic components, load and frequency of circuit breaker k at time t-1, respectively. h1 and h2 represent the influence coefficients on the current harmonic deviation. Specifically, h1 represents the influence coefficient of the load deviation on the current harmonic deviation, and h2 represents the influence coefficient of the frequency deviation on the current harmonic deviation.

[0025] Preferably, S3 includes S31 and S32;

[0026] S31. Perform vector correlation anomaly analysis based on multiple vectors in the feature vector Fk(t) to obtain the correlation coefficient Corr between adjacent vectors of circuit breaker k.

[0027] The correlation coefficient Corr is obtained using the following formula:

[0028] ;

[0029] In the formula, Corr(Fk1(t), Fk2(t)) represents the correlation coefficient between the first and second eigenvectors of the k-th circuit breaker, t represents time, n represents the size of the time window, specifically the time window used to calculate the mean and standard deviation, i represents the index of each data point in the time series, ranging from t-n+1 to t, Fk1(i) represents the eigenvector at index i in the time series, and UFk1 and UFk2 represent the mean of the first and second eigenvectors within the time window range t-n+1 to t, respectively.

[0030] Preferably, in step S32, the fault assessment mechanism is triggered based on the obtained correlation coefficients Corr (Fk1(t), Fk2(t)) to determine the fault area. The fault trend status of the kth circuit breaker is obtained by comparing it with the preset correlation threshold Cthe, and a power protection strategy response action is generated based on the obtained fault trend status.

[0031] The fault trend status is obtained through the following comparison method:

[0032] When the correlation coefficient Corr(Fk1(t), Fk2(t)) ≥ the correlation threshold Cthe, the fault trend status of the kth circuit breaker is obtained as no fault trend result, the circuit breaker k is marked as a non-fault area, and the power protection strategy response action of the circuit breaker k is cleared.

[0033] When the correlation coefficient Corr(Fk1(t), Fk2(t)) < the correlation threshold Cthe, the fault trend status of the k-th circuit breaker is obtained as a result of the existence of a fault trend. The k-th circuit breaker is marked as a fault area, and the power protection strategy response action of the circuit breaker k is generated to deal with short circuit protection, overload protection and frequency control strategies. The power protection strategy response action includes adjusting the load distribution through the control system, starting the harmonic filter to eliminate harmonic pollution in the power system, starting the frequency regulator and disconnecting the power supply corresponding to the circuit breaker k to reset and isolate it.

[0034] Preferably, S4 includes S41;

[0035] S41. Based on the evaluation of the linkage algorithm formula for the circuit breaker's response action according to the power protection strategy, obtain the result of the circuit breaker linkage control and mark it as the control action Ack(t). Update the linkage control of the circuit breaker by iteratively obtaining the control action Ack(t).

[0036] The control action Ack(t) is obtained through the following calculation formula:

[0037] ;

[0038] In the formula, M represents the number of power protection strategy response actions, V(j) represents the indicator function, specifically representing the activation state of the j-th control strategy, and Ac(t,j) represents the action of the j-th control strategy at time t, including adjusting load distribution, activating harmonic filters, and activating frequency regulators.

[0039] Preferably, S5 includes S51 and S52;

[0040] S51. By fitting the control action Ack(t) with the operating parameters of the distribution network, the overall stability of the power grid is evaluated, and the overall stability score Sk(t) of the power grid is obtained.

[0041] The overall power grid stability score Sk(t) is obtained using the following formula:

[0042] ;

[0043] In the formula, s1, s2, s3 and s4 represent the influence coefficients of the current difference, voltage difference, load difference and frequency difference at time t+1 and time t, respectively, and Ik(t+1), Vk(t+1), Zk(t+1) and Fk(t+1) represent the current, voltage, load and frequency at time t+1, respectively.

[0044] Preferably, in step S52, the obtained overall power grid stability score Sk(t) is compared with the preset power grid stable operation safety threshold Sthe to obtain feedback results for power grid operation optimization.

[0045] The feedback results of the power grid operation optimization were obtained through the following comparison method:

[0046] When the overall grid stability score Sk(t) ≥ the grid stable operation safety threshold Sthe, the feedback result is a safety result.

[0047] When the power grid stable operation safety threshold Sthe ≥ the overall power grid stability score Sk(t) ≥ (power grid stable operation safety threshold Sthe * 90%), the feedback result is qualified, and the current power grid is operating within the allowable fluctuation range;

[0048] When the overall stability score Sk(t) of the power grid is less than (the safe threshold for stable operation of the power grid * 90%), the feedback result is unqualified, and the current operation of the power grid exceeds the allowable fluctuation range. The operation of the power grid is iteratively optimized, including executing steps S3, S4 and S5 until the state of unqualified feedback result is exited.

[0049] A control system for an intelligent power circuit breaker includes a power operation data acquisition module, a feature extraction module, an anomaly analysis module, a linkage control module, and a decision-making and optimization module.

[0050] The power operation data acquisition module connects to the operation data of multiple circuit breakers in the power system and preprocesses the operation data to form a power system acquisition data group Xk(t).

[0051] The feature extraction module substitutes the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network, obtain the load deviation △Lk(t) and current harmonic deviation △Hk(t), and integrates the load deviation △Lk(t) and current harmonic deviation △Hk(t) to form the feature vector Fk(t).

[0052] The anomaly analysis module performs anomaly analysis based on the acquired feature vector Fk(t) to obtain the power protection strategy response action generated in the fault area;

[0053] The linkage control module evaluates the linkage algorithm formula of the circuit breaker based on the response action of the power protection strategy, obtains the result of the linkage control of the circuit breaker, and marks it as the control action Ack(t).

[0054] The decision-making and optimization module performs fitting processing between the control action Ack(t) and the operating parameters of the distribution network to evaluate the overall stability of the power grid operation, obtain the overall stability score Sk(t), and compare it with the preset power grid stable operation safety threshold Sthe to obtain feedback results for power grid operation optimization.

[0055] This invention provides a control method and system for an intelligent power circuit breaker, which has the following advantages:

[0056] (1) By substituting the collected data set Xk(t) into the load anomaly detection formula and the current harmonic anomaly detection formula for fault identification, load deviation ΔLk(t) and current harmonic deviation ΔHk(t) are obtained. Then, by integrating these deviations, an Ack(k) control action matrix is ​​formed to evaluate the execution linkage control of the circuit breaker. This not only ensures a rapid response when a fault occurs, but also avoids unnecessary system interference and improves the overall operating efficiency of the power grid. On this basis, combined with the operating parameters and control actions of the distribution network, the stability of the power grid is further evaluated to obtain the overall stability score Sk(t), thereby providing clear feedback for power grid optimization. It can monitor the operating status of the power grid in real time, respond quickly to faults, and make intelligent decisions, thereby significantly improving the stability and security of the power grid.

[0057] (2) By performing correlation analysis on the eigenvector Fk(t) of circuit breaker k in the time series, the correlation coefficient Corr(Fk1(t), Fk2(t)) between adjacent time points is calculated, effectively capturing abnormal fluctuations and trends that may occur during the operation of the power grid. This analysis, through the calculation of mean and standard deviation within the time window, can flexibly reflect the stability of the power system at different time scales. Especially when the system load fluctuates or current harmonic interference is large, it can identify fault risks in a timely manner. Once the fault assessment mechanism is triggered by the correlation coefficient, the system will judge whether there is a fault trend based on the preset correlation threshold Cthe. This reduces the impact on other parts of the power grid and automatically triggers protection measures based on real-time operating data, realizing timely identification and accurate response to power grid faults. Compared with the traditional static protection mechanism, this method not only improves the system's adaptability but also allows for flexible selection of response strategies for different types of power problems, ensuring the efficient and stable operation of the power grid.

[0058] (3) The control action Ack(t) is iteratively updated based on the response action of the power protection strategy. By evaluating the activation status of multiple control strategies, it can flexibly adjust load distribution, activate harmonic filters, and regulate frequencies, providing a precise feedback and response mechanism for real-time regulation of the power grid. Each updated control action Ack(t) will directly affect the operating parameters of the power grid, thereby ensuring the stability of the power system in a constantly changing environment. By fitting with the operating parameters of the power grid, the control action Ack(t) helps to evaluate the overall stability of the power grid in real time, generate a power grid stability score Sk(t), and compare it with the preset stable operation safety threshold Sthe. Iteratively execute the power protection strategy to ensure the continuous stability of the power grid operation, forming an adaptive power grid regulation mechanism that can quickly respond to changes in the power system, ensure the long-term stable and reliable operation of the power grid, and ensure timely optimization and adjustment when the system exceeds the allowable fluctuation range. Attached Figure Description

[0059] Figure 1 This is a schematic diagram of the control method steps for an intelligent power circuit breaker according to the present invention;

[0060] Figure 2 This is a schematic block diagram of the control system of an intelligent power circuit breaker according to the present invention. Detailed Implementation

[0061] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0062] Example 1

[0063] This invention provides a control method for an intelligent power circuit breaker. Please refer to [link / reference]. Figure 1 This includes the following steps:

[0064] S1. By connecting the operating data of multiple circuit breakers in the power system and preprocessing the operating data, a power system data acquisition group Xk(t) is formed.

[0065] S2. Substitute the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network, obtain the load deviation △Lk(t) and current harmonic deviation △Hk(t), and combine the load deviation △Lk(t) and current harmonic deviation △Hk(t) to form the feature vector Fk(t).

[0066] S3. Perform anomaly analysis based on the obtained feature vector Fk(t) to obtain the power protection strategy response action generated in the fault area;

[0067] S4. Evaluate the circuit breaker's linkage algorithm formula based on the power protection strategy response action, obtain the result of the circuit breaker linkage control, and mark it as the control action Ack(t).

[0068] S5. By fitting the control action Ack(t) with the operating parameters of the distribution network, the overall stability of the power grid is evaluated, the overall stability score Sk(t) of the power grid is obtained, and it is compared with the preset safe threshold Sthe for stable operation of the power grid to obtain feedback results for power grid operation optimization.

[0069] In this embodiment, the operating data of multiple circuit breakers are preprocessed to form a power system data set Xk(t). This data is then substituted into the load anomaly detection formula and the current harmonic anomaly detection formula for fault identification, obtaining the load deviation ΔLk(t) and the current harmonic deviation ΔHk(t). These deviations are then integrated to form a feature vector Fk(t), laying the foundation for subsequent anomaly analysis and fault location. Next, in-depth analysis of the feature vector accurately identifies fault areas in the power grid, generating power protection strategy response actions based on this. The execution of the circuit breaker's linkage control is evaluated using the Ack(k) control action matrix, ensuring rapid response during fault occurrence and avoiding unnecessary system interference, thus improving the overall power grid operating efficiency. Based on this, combined with the distribution network's operating parameters and control actions, a power grid stability assessment is further performed, obtaining the overall power grid stability score Sk(t), which is compared with a preset power grid stable operation safety threshold Sthe, providing clear power grid optimization feedback. Through this series of steps, the method can monitor the power grid's operating status in real time, respond quickly to faults, and make intelligent decisions, thereby significantly improving the stability and security of the power grid. It solves problems such as insufficient fault response and difficulty in assessing system stability in traditional power systems, and achieves more intelligent, accurate, and efficient power management.

[0070] Example 2

[0071] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically: S1 includes S11 and S12;

[0072] S11. By connecting multiple intelligent sensors integrated in the power system, the operation record information of each circuit breaker is collected in real time, including current information, voltage information, load information, frequency information, current harmonic component information and load change rate information. By marking the operation record information with time t and the unique identifier k of the circuit breaker, the current Ik(t), voltage Vk(t), load Zk(t), frequency Fk(t), current harmonic component Hk(t) and load change rate Pk(t) of circuit breaker k at time t are obtained, forming the operation data of circuit breaker k.

[0073] S12. The obtained operating data of circuit breaker k is preprocessed. The preprocessing includes noise reduction preprocessing, outlier detection preprocessing and missing value filling preprocessing. Then, the preprocessed operating data of circuit breaker k is standardized to eliminate the differences between different units and obtain the power system data set Xk(t) of circuit breaker k at time t.

[0074] The power system data collection group X is specifically X = (NIk(t), NVk(t), NZk(t), NFk(t), NHk(t), NPk(t)).

[0075] S2 includes S21 and S22;

[0076] S21. Substitute the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network and obtain the load deviation ΔLk(t) and current harmonic deviation ΔHk(t) of circuit breaker k at time t.

[0077] S22. By integrating the power system data sets Xk(t), load deviation △Lk(t), and current harmonic deviation △Hk(t), an eigenvector F is formed.

[0078] The load deviation ΔLk(t) is obtained by the following calculation formula:

[0079] ;

[0080] In the formula, NPk(t-1), NIk(t-1), and NVk(t-1) represent the load change rate, current, and voltage of circuit breaker k at time t-1, respectively, and p1 and p2 represent the influence coefficients on load deviation. Specifically, p1 represents the influence coefficient of current deviation on load deviation, and p2 represents the influence coefficient of voltage deviation on load deviation.

[0081] Among them, p1 and p2 are determined based on the historical operating data of the same type of circuit breaker. Specifically, historical normal operating periods and historical abnormal operating periods are selected. The current change ratio, voltage change ratio and load change rate change ratio at the same time point are matched, and p1 and p2 are adjusted so that the load deviation ΔLk(t) calculated during the historical normal operating period is within the historical normal deviation range, and the load deviation ΔLk(t) corresponding to the period when the current change ratio, voltage change ratio or load change rate change ratio exceeds the historical normal range exceeds the historical normal deviation range. Thus, p1 and p2 are determined.

[0082] The current harmonic deviation ΔHk(t) is obtained by the following calculation formula:

[0083] ;

[0084] In the formula, NHk(t-1), NZk(t-1) and NFk(t-1) represent the current harmonic components, load and frequency of circuit breaker k at time t-1, respectively. h1 and h2 represent the influence coefficients on the current harmonic deviation. Specifically, h1 represents the influence coefficient of the load deviation on the current harmonic deviation, and h2 represents the influence coefficient of the frequency deviation on the current harmonic deviation.

[0085] In this embodiment, multiple integrated intelligent sensors collect key operational data of the circuit breaker in real time, providing comprehensive data information for subsequent fault detection. Through preprocessing of this data—removing noise, detecting outliers, and filling missing values—further standardization is performed to form a power system data set Xk(t), providing a high-quality data foundation for further analysis. Based on this, by substituting the Xk(t) data into the load anomaly detection formula and the current harmonic anomaly detection formula, the load deviation ΔLk(t) and current harmonic deviation ΔHk(t) can be accurately calculated. These deviations are then integrated to form a feature vector Fk(t), providing a reliable basis for subsequent fault diagnosis and protection decisions. Particularly in the calculation of load deviation ΔLk(t) and current harmonic deviation ΔHk(t), the actual operating state and abnormal fluctuations of the power grid can be more accurately reflected, thereby effectively improving the accuracy and real-time performance of fault identification. Furthermore, through precise analysis of the power system data set Xk(t), potential fault areas in the power grid can be quickly identified, providing strong data support for intelligent protection of the power system and significantly improving the operational safety and fault response efficiency of the power grid. This approach not only enables comprehensive monitoring of the power grid's operational status but also enhances the power system's adaptability and response speed in dynamic environments through meticulous fault detection and precise feature analysis. This multi-dimensional data fusion and efficient analysis method effectively overcomes the problems of lagging fault diagnosis and insufficient data processing in traditional methods, providing a more reliable guarantee for the safety and stability of the power grid.

[0086] Example 3

[0087] This embodiment is an explanation based on Embodiment 2. Please refer to it. Figure 1 Specifically: S3 includes S31 and S32;

[0088] S31. Perform vector correlation anomaly analysis based on multiple vectors in the feature vector Fk(t) to obtain the correlation coefficient Corr between adjacent vectors of circuit breaker k.

[0089] The correlation coefficient Corr is obtained using the following formula:

[0090] ;

[0091] In the formula, Corr(Fk1(t), Fk2(t)) represents the correlation coefficient between the first and second eigenvectors of the k-th circuit breaker, t represents time, n represents the size of the time window used to calculate the mean and standard deviation, and also indicates how many past time points need to be considered when calculating the current time t, i represents the index of each data point in the time series, ranging from t-n+1 to t, Fk1(i) represents the eigenvector at index i in the time series, specifically the eigenvector of circuit breaker k at time point i, and UFk1 and UFk2 represent the mean of the first and second eigenvectors within the time window range t-n+1 to t, respectively. This represents the covariance between the first and second eigenvectors, specifically used to capture the linear relationship between them. The standard deviation between the first and second eigenvectors is used to limit the correlation coefficient Corr(Fk1(t), Fk2(t)) to the range of -1 to 1.

[0092] UFk1 and UFk2 are obtained directly based on the feature vector data already acquired within the time window. Specifically, each Fk1(i) within the time window from t-n+1 to t is added together and divided by the number of data n within the time window to obtain UFk1. Each Fk2(i) within the same time window is added together and divided by the number of data n to obtain UFk2.

[0093] S32. Based on the obtained correlation coefficients Corr (Fk1(t), Fk2(t)), trigger the fault assessment mechanism to determine the fault area. By comparing with the preset correlation threshold Cthe, obtain the fault trend status of the kth circuit breaker, and generate power protection strategy response actions based on the obtained fault trend status.

[0094] The fault trend status is obtained through the following comparison method:

[0095] When the correlation coefficient Corr(Fk1(t), Fk2(t)) ≥ the correlation threshold Cthe, the fault trend status of the kth circuit breaker is obtained as no fault trend result, the circuit breaker k is marked as a non-fault area, and the power protection strategy response action of the circuit breaker k is cleared.

[0096] When the correlation coefficient Corr(Fk1(t), Fk2(t)) < correlation threshold Cthe, the fault trend status of the kth circuit breaker is obtained as a result of the existence of a fault trend, the kth circuit breaker is marked as a fault area, and the power protection strategy response action of the circuit breaker k is generated to deal with short circuit protection, overload protection and frequency control strategies. The power protection strategy response action includes adjusting the load distribution through the control system, starting the harmonic filter to eliminate harmonic pollution in the power system, starting the frequency regulator and disconnecting the power supply corresponding to the circuit breaker k to reset and isolate it.

[0097] Among them, adjusting the load distribution through the control system is used to ensure that the load on circuit breaker k does not exceed the maximum load, specifically including starting the backup power supply and adjusting the load of the distribution network.

[0098] Activating a harmonic filter eliminates harmonic pollution in the power system. This is used to adjust for harmonic pollution in the power system that causes current waveform distortion. Specifically, it is done by cutting off equipment and circuits that exceed harmonic limits to prevent further impact on system stability.

[0099] The frequency regulator is activated and the power supply corresponding to circuit breaker k is reset and isolated to deal with faults related to a sharp increase in current. Specifically, the automatic circuit breaker reset mechanism is activated to quickly isolate the fault area, and the disconnecting switch is remotely activated to quickly isolate the fault area and protect the rest of the power grid.

[0100] In this embodiment, correlation analysis is performed on the feature vector Fk(t) of circuit breaker k over time to calculate the correlation coefficient Corr(Fk1(t), Fk2(t)) between adjacent time points, effectively capturing abnormal fluctuations and trends that may occur during power grid operation. This analysis, calculated using the mean and standard deviation within a time window, can flexibly reflect the stability of the power system at different time scales. Especially under conditions of significant system load fluctuations or current harmonic interference, it can promptly identify fault risks. Once the fault assessment mechanism is triggered by the correlation coefficient, the system will determine whether a fault trend exists based on a preset correlation threshold Cthe. When the correlation coefficient is below the threshold, circuit breaker k is marked as a fault area, and corresponding power protection strategy response actions are generated. Through this mechanism, the system can intelligently activate multiple emergency measures such as short-circuit protection, overload protection, and frequency control, reducing the impact on other parts of the power grid. It can also automatically trigger protection measures based on real-time operating data, achieving timely identification and accurate response to power grid faults. Compared to traditional static protection mechanisms, this method not only improves the system's adaptability but also allows for flexible selection of response strategies for different types of power problems, ensuring the efficient and stable operation of the power grid.

[0101] Example 4

[0102] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically: S4 includes S41;

[0103] S41. Based on the evaluation of the linkage algorithm formula for the circuit breaker's response action according to the power protection strategy, obtain the result of the circuit breaker linkage control and mark it as the control action Ack(t). Update the linkage control of the circuit breaker by iteratively obtaining the control action Ack(t).

[0104] The control action Ack(t) is obtained through the following calculation formula:

[0105] ;

[0106] In the formula, M represents the number of response actions of the power protection strategy, V(j) represents the indicator function, specifically the activation state of the j-th control strategy. Specifically, the indicator function V(j) = 1 indicates the activation state, meaning the j-th control strategy needs to be executed, and the indicator function V(j) = 0 indicates the deactivation state, meaning the j-th control strategy does not need to be executed. Ac(t,j) represents the action of the j-th control strategy at time t, including adjusting load distribution, starting the harmonic filter, and starting the frequency regulator.

[0107] The control strategy includes adjusting load allocation, activating a harmonic filter, and activating a frequency regulator. When the fault assessment mechanism generates a power protection strategy response action corresponding to the j-th control strategy, V(j) takes the value of 1; when no corresponding power protection strategy response action is generated, V(j) takes the value of 0. Ac(t,j) represents the action parameter value adopted by the j-th control strategy at time t. The action parameter value corresponding to adjusting load allocation is determined based on the difference between the current load and the maximum load. The action parameter value corresponding to activating the harmonic filter is determined based on the difference between the current current harmonic component and the upper limit of the allowable range. The action parameter value corresponding to activating the frequency regulator is determined based on the difference between the current frequency and the rated frequency.

[0108] S5 includes S51 and S52;

[0109] S51. By fitting the control action Ack(t) with the operating parameters of the distribution network, the overall stability of the power grid is evaluated, and the overall stability score Sk(t) of the power grid is obtained.

[0110] The overall power grid stability score Sk(t) is obtained using the following formula:

[0111] ;

[0112] In the formula, s1, s2, s3 and s4 represent the influence coefficients of the current difference, voltage difference, load difference and frequency difference at time t+1 and time t, respectively, and Ik(t+1), Vk(t+1), Zk(t+1) and Fk(t+1) represent the current, voltage, load and frequency at time t+1, respectively.

[0113] S52. Compare the obtained overall power grid stability score Sk(t) with the preset power grid stable operation safety threshold Sthe to obtain feedback results for power grid operation optimization.

[0114] The feedback results of the power grid operation optimization were obtained through the following comparison method:

[0115] When the overall grid stability score Sk(t) ≥ the grid stable operation safety threshold Sthe, the feedback result is a safety result.

[0116] When the power grid stable operation safety threshold Sthe ≥ the overall power grid stability score Sk(t) ≥ (power grid stable operation safety threshold Sthe * 90%), the feedback result is qualified, and the current power grid is operating within the allowable fluctuation range;

[0117] When the overall stability score Sk(t) of the power grid is less than (the safe threshold for stable operation of the power grid * 90%), the feedback result is unqualified, and the current operation of the power grid exceeds the allowable fluctuation range. The operation of the power grid is iteratively optimized, including executing steps S3, S4 and S5 until the state of unqualified feedback result is exited.

[0118] In this embodiment, the control action Ack(t) is iteratively updated based on the response actions of the power protection strategy. By evaluating the activation states of multiple control strategies, load allocation, harmonic filter activation, and frequency adjustment can be flexibly implemented, providing a precise feedback and response mechanism for real-time power grid regulation. Each updated control action Ack(t) directly affects the operating parameters of the power grid, thereby ensuring the stability of the power system in a constantly changing environment. By fitting the control action Ack(t) to the power grid operating parameters, the control action Ack(t) helps to assess the overall stability of the power grid in real time, generating a power grid stability score Sk(t), which is then compared with a preset stable operation safety threshold Sthe. The power protection strategy is iteratively executed to ensure the continuous stability of the power grid operation. The power grid operating state can be dynamically adjusted according to the control action Ack(t), thereby accurately responding to instantaneous fluctuations and potential faults in the system and avoiding safety accidents caused by excessive power grid fluctuations. By combining the power protection strategy with the power grid operation stability score, an adaptive power grid regulation mechanism is formed, which can quickly respond to changes in the power system, ensure the long-term stable and reliable operation of the power grid, and ensure timely optimization and adjustment when the system exceeds the allowable fluctuation range. This precise dynamic optimization and feedback mechanism effectively improves the power grid's ability to cope with complex power problems, providing strong support for the efficient operation and safety of the power system.

[0119] Example 5

[0120] A control system for an intelligent power circuit breaker, please refer to Figure 2 Specifically, it includes a power operation data acquisition module, a feature extraction module, an anomaly analysis module, a linkage control module, and a decision-making and optimization module;

[0121] The power operation data acquisition module connects to the operation data of multiple circuit breakers in the power system and preprocesses the operation data to form a power system acquisition data group Xk(t).

[0122] The feature extraction module substitutes the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network, obtain the load deviation △Lk(t) and current harmonic deviation △Hk(t), and integrates the load deviation △Lk(t) and current harmonic deviation △Hk(t) to form the feature vector Fk(t).

[0123] The anomaly analysis module performs anomaly analysis based on the acquired feature vector Fk(t) to obtain the power protection strategy response action generated in the fault area;

[0124] The linkage control module evaluates the linkage algorithm formula of the circuit breaker based on the response action of the power protection strategy, obtains the result of the linkage control of the circuit breaker, and marks it as the control action Ack(t).

[0125] The decision-making and optimization module performs fitting processing between the control action Ack(t) and the operating parameters of the distribution network to evaluate the overall stability of the power grid operation, obtain the overall stability score Sk(t), and compare it with the preset power grid stable operation safety threshold Sthe to obtain feedback results for power grid operation optimization.

[0126] Although embodiments of the invention have been shown and described, it will be understood by those skilled 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 invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A control method for an intelligent power circuit breaker, characterized in that: Includes the following steps: S1. By connecting the operating data of multiple circuit breakers in the power system and preprocessing the operating data, a power system data acquisition group Xk(t) is formed. S2. Substitute the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network, obtain the load deviation △Lk(t) and current harmonic deviation △Hk(t), and combine the load deviation △Lk(t) and current harmonic deviation △Hk(t) to form the feature vector Fk(t). S3. Perform anomaly analysis based on the obtained feature vector Fk(t) to obtain the power protection strategy response action generated in the fault area; S4. Evaluate the circuit breaker's linkage algorithm formula based on the power protection strategy response action, obtain the result of the circuit breaker linkage control, and mark it as the control action Ack(t). S5. By fitting the control action Ack(t) with the operating parameters of the distribution network, the overall stability of the power grid is evaluated, the overall stability score Sk(t) of the power grid is obtained, and it is compared with the preset safe threshold Sthe for stable operation of the power grid to obtain feedback results for power grid operation optimization.

2. The control method for an intelligent power circuit breaker according to claim 1, characterized in that: S1 includes S11 and S12; S11. By connecting multiple intelligent sensors integrated in the power system, the operation record information of each circuit breaker is collected in real time, including current information, voltage information, load information, frequency information, current harmonic component information and load change rate information. By marking the operation record information with time t and the unique identifier k of the circuit breaker, the current Ik(t), voltage Vk(t), load Zk(t), frequency Fk(t), current harmonic component Hk(t) and load change rate Pk(t) of circuit breaker k at time t are obtained, forming the operation data of circuit breaker k. S12. The obtained operating data of circuit breaker k is preprocessed. The preprocessing includes noise reduction preprocessing, outlier detection preprocessing and missing value filling preprocessing. Then, the preprocessed operating data of circuit breaker k is standardized to eliminate the differences between different units and obtain the power system data set Xk(t) of circuit breaker k at time t. The power system data collection group X is specifically X = (NIk(t), NVk(t), NZk(t), NFk(t), NHk(t), NPk(t)).

3. The control method for an intelligent power circuit breaker according to claim 2, characterized in that: S2 includes S21 and S22; S21. Substitute the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network and obtain the load deviation ΔLk(t) and current harmonic deviation ΔHk(t) of circuit breaker k at time t. S22. By integrating the power system data sets Xk(t), load deviation △Lk(t), and current harmonic deviation △Hk(t), an eigenvector F is formed.

4. The control method for an intelligent power circuit breaker according to claim 3, characterized in that: The load deviation ΔLk(t) is obtained by the following calculation formula: ； In the formula, NPk(t-1), NIk(t-1), and NVk(t-1) represent the load change rate, current, and voltage of circuit breaker k at time t-1, respectively, and p1 and p2 represent the influence coefficients on load deviation. Specifically, p1 represents the influence coefficient of current deviation on load deviation, and p2 represents the influence coefficient of voltage deviation on load deviation. The current harmonic deviation ΔHk(t) is obtained by the following calculation formula: ； In the formula, NHk(t-1), NZk(t-1) and NFk(t-1) represent the current harmonic components, load and frequency of circuit breaker k at time t-1, respectively. h1 and h2 represent the influence coefficients on the current harmonic deviation. Specifically, h1 represents the influence coefficient of the load deviation on the current harmonic deviation, and h2 represents the influence coefficient of the frequency deviation on the current harmonic deviation.

5. The control method for an intelligent power circuit breaker according to claim 3, characterized in that: S3 includes S31 and S32; S31. Perform vector correlation anomaly analysis based on multiple vectors in the feature vector Fk(t) to obtain the correlation coefficient Corr between adjacent vectors of circuit breaker k. The correlation coefficient Corr is obtained using the following formula: ； In the formula, Corr(Fk1(t), Fk2(t)) represents the correlation coefficient between the first and second eigenvectors of the k-th circuit breaker, t represents time, n represents the size of the time window, specifically the size of the time window used to calculate the mean and standard deviation, i represents the index of each data point in the time series, ranging from t-n+1 to t, Fk1(i) represents the eigenvector at index i in the time series, and UFk1 and UFk2 represent the mean of the first and second eigenvectors within the time window range t-n+1 to t, respectively.

6. The control method for an intelligent power circuit breaker according to claim 5, characterized in that: S32. Based on the obtained correlation coefficients Corr (Fk1(t), Fk2(t)), trigger the fault assessment mechanism to determine the fault area. By comparing with the preset correlation threshold Cthe, obtain the fault trend status of the kth circuit breaker, and generate power protection strategy response actions based on the obtained fault trend status. The fault trend status is obtained through the following comparison method: When the correlation coefficient Corr(Fk1(t), Fk2(t)) ≥ the correlation threshold Cthe, the fault trend status of the kth circuit breaker is obtained as no fault trend result, the circuit breaker k is marked as a non-fault area, and the power protection strategy response action of the circuit breaker k is cleared. When the correlation coefficient Corr(Fk1(t), Fk2(t)) < the correlation threshold Cthe, the fault trend status of the k-th circuit breaker is obtained as a result of the existence of a fault trend. The k-th circuit breaker is marked as a fault area, and the power protection strategy response action of the circuit breaker k is generated to deal with short circuit protection, overload protection and frequency control strategies. The power protection strategy response action includes adjusting the load distribution through the control system, starting the harmonic filter to eliminate harmonic pollution in the power system, starting the frequency regulator and disconnecting the power supply corresponding to the circuit breaker k to reset and isolate it.

7. The control method for an intelligent power circuit breaker according to claim 6, characterized in that: S4 includes S41; S41. Based on the evaluation of the linkage algorithm formula for the circuit breaker's response action according to the power protection strategy, obtain the result of the circuit breaker linkage control and mark it as the control action Ack(t). Update the linkage control of the circuit breaker by iteratively obtaining the control action Ack(t). The control action Ack(t) is obtained through the following calculation formula: ； In the formula, M represents the number of power protection strategy response actions, V(j) represents the indicator function, specifically representing the activation state of the j-th control strategy, and Ac(t,j) represents the action of the j-th control strategy at time t, including adjusting load distribution, activating harmonic filters, and activating frequency regulators.

8. The control method for an intelligent power circuit breaker according to claim 7, characterized in that: S5 includes S51 and S52; S51. By fitting the control action Ack(t) with the operating parameters of the distribution network, the overall stability of the power grid is evaluated, and the overall stability score Sk(t) of the power grid is obtained. The overall power grid stability score Sk(t) is obtained using the following formula: ； In the formula, s1, s2, s3 and s4 represent the influence coefficients of the current difference, voltage difference, load difference and frequency difference at time t+1 and time t, respectively, and Ik(t+1), Vk(t+1), Zk(t+1) and Fk(t+1) represent the current, voltage, load and frequency at time t+1, respectively.

9. The control method for an intelligent power circuit breaker according to claim 8, characterized in that: S52. Compare the obtained overall power grid stability score Sk(t) with the preset power grid stable operation safety threshold Sthe to obtain feedback results for power grid operation optimization. The feedback results of the power grid operation optimization were obtained through the following comparison method: When the overall grid stability score Sk(t) ≥ the grid stable operation safety threshold Sthe, the feedback result is a safety result. When the power grid stable operation safety threshold Sthe ≥ the overall power grid stability score Sk(t) ≥ (power grid stable operation safety threshold Sthe * 90%), the feedback result is qualified, and the current power grid is operating within the allowable fluctuation range; When the overall stability score Sk(t) of the power grid is less than (the safe threshold for stable operation of the power grid * 90%), the feedback result is unqualified, and the current operation of the power grid exceeds the allowable fluctuation range. The operation of the power grid is iteratively optimized, including executing steps S3, S4 and S5 until the state of unqualified feedback result is exited.

10. A control system for an intelligent power circuit breaker, applied to the control method for an intelligent power circuit breaker according to any one of claims 1 to 9, characterized in that: It includes a power operation data acquisition module, a feature extraction module, an anomaly analysis module, a linkage control module, and a decision-making and optimization module; The power operation data acquisition module connects to the operation data of multiple circuit breakers in the power system and preprocesses the operation data to form a power system acquisition data group Xk(t). The feature extraction module substitutes the power system data set Xk(t) into the established load anomaly detection formula and current harmonic anomaly detection formula to identify potential faults in the distribution network, obtain the load deviation △Lk(t) and current harmonic deviation △Hk(t), and integrates the load deviation △Lk(t) and current harmonic deviation △Hk(t) to form the feature vector Fk(t). The anomaly analysis module performs anomaly analysis based on the acquired feature vector Fk(t) to obtain the power protection strategy response action generated in the fault area; The linkage control module evaluates the linkage algorithm formula of the circuit breaker based on the response action of the power protection strategy, obtains the result of the linkage control of the circuit breaker, and marks it as the control action Ack(t). The decision-making and optimization module performs fitting processing between the control action Ack(t) and the operating parameters of the distribution network to evaluate the overall stability of the power grid operation, obtain the overall stability score Sk(t), and compare it with the preset power grid stable operation safety threshold Sthe to obtain feedback results for power grid operation optimization.

Images