Intelligent power distribution cabinet control method and power distribution cabinet

Abstract

The invention relates to the technical field of power distribution control, in particular to an intelligent power distribution cabinet control method and a power distribution cabinet, and the method comprises the steps: collecting operation parameters in real time, carrying out the hierarchical anomaly detection of each branch in the power distribution cabinet according to the obtained operation parameters, and setting the corresponding anomaly characteristics of each branch; identifying the composition of the abnormal feature corresponding to each branch, judging each composition of the abnormal feature, and setting an early warning parameter under the current abnormal power distribution; trend analysis is carried out according to the early warning parameters, the relative variation of the early warning parameters under the variation trend is identified, state deduction is carried out according to the relative variation, and a strategy control target under the variation trend is identified; the occurrence frequency of a target is controlled by using a strategy, the trigger condition of each branch is quantified, and a hierarchical control strategy is set based on the logic connection relationship of each branch under the trigger condition. The response speed and the control efficiency of power distribution cabinet control are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution control, and in particular to an intelligent power distribution cabinet control method and a power distribution cabinet. Background Art

[0002] A power distribution cabinet is a device used to connect to external power lines to centrally supply power. By collecting all energy data from the cabinet, real-time monitoring and operational management of the entire power distribution system are implemented. When analyzing energy data from the distribution cabinet, monitoring only single parameters such as voltage and current can lead to isolated parameter analysis and poor data adaptability, resulting in inadequate action or control.

[0003] For example, Chinese patent application publication number CN116760197A discloses a monitoring method, device and distribution cabinet for an intelligent distribution cabinet; the present invention simulates according to an existing wiring scheme to obtain an existing distribution model, and simulates according to a preset wiring scheme to obtain a preset distribution model, and performs data analysis on the preset distribution model to determine whether the preset wiring scheme is reasonable, thereby achieving the ability to determine whether the preset wiring scheme meets safety standards before implementing the preset wiring scheme, solving the problem in the prior art that it is difficult to predict the risks after changing the wiring scheme of the distribution cabinet.

[0004] For example, Chinese patent application publication number CN118983936A discloses a monitoring method, device and distribution cabinet for an intelligent distribution cabinet, which relates to the field of monitoring and analysis technology, including monitoring and collecting cabinet surface information and internal line information corresponding to the target distribution cabinet, analyzing the cabinet surface information and internal line information corresponding to the target distribution cabinet, and then confirming the equipment aging assessment coefficient corresponding to the target distribution cabinet; obtaining the operating status information and electrical safety information corresponding to the target distribution cabinet; analyzing the operating status information corresponding to the target distribution cabinet to confirm the operating status assessment coefficient corresponding to the target distribution cabinet, and analyzing the electrical safety information corresponding to the target distribution cabinet to confirm the electrical safety assessment coefficient corresponding to the target distribution cabinet; confirming the comprehensive assessment coefficient corresponding to the target distribution cabinet, and adjusting based on the comprehensive assessment coefficient corresponding to the target distribution cabinet.

[0005] The existing technology describes the processing methods for the wiring of the distribution cabinet and the processing methods for surface aging respectively, but ignores the actual operating status of the distribution cabinet connected to each branch, as well as the strategic control method. As a result, when the distribution cabinet identifies abnormal parameters such as current and voltage of the connected equipment, it cannot promptly perform early warning processing based on the situation of the connected equipment, resulting in risk identification delays and long processing responses when the distribution cabinet controls the equipment connection. Summary of the Invention

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: an intelligent distribution cabinet control method, including: S1, using multiple sensors deployed in the current distribution cabinet to collect operating parameters in real time, the operating parameters include but are not limited to the voltage and current of each branch, the status of each branch switch and the corresponding operating time of each branch switch.

[0007] S2: Based on the acquired operating parameters, perform layered anomaly detection on each branch in the power distribution cabinet and set the corresponding abnormal characteristics of each branch.

[0008] S3, identifying the combination components of the abnormal characteristics corresponding to each branch, determining each combination component of the abnormal characteristics, and setting warning parameters under the current abnormal power distribution.

[0009] S4, perform trend analysis based on the warning parameters, identify the relative changes of the warning parameters under the changing trend, and perform state deduction based on the relative changes to identify the strategic control targets under the changing trend.

[0010] S5, using the occurrence frequency of the strategy control target, quantify the triggering conditions of each branch, and set the hierarchical control strategy based on the logical connection relationship of each branch under the triggering conditions.

[0011] An intelligent power distribution cabinet comprises: a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute any of the above-described intelligent power distribution cabinet control methods.

[0012] The beneficial effects of the present invention are: 1. The present invention uses a layered anomaly detection method to detect abnormal features in the physical layer and logical layer corresponding to each operating parameter, so that the abnormal features can contain multi-dimensional data information, avoiding the reduction in the accuracy of current data analysis due to a single parameter and too small a dimension, and providing a data basis for subsequent data analysis.

[0013] 2. The present invention uses regular expressions to extract multi-parameter conditional dependencies through association rules and support differences, and quantifies the abnormality level based on the support difference. The combination of the abnormality levels of the current operating parameters is regarded as the output abnormal feature. The difference in the combination of abnormal features is used to regard the difference as the early warning parameter, so as to improve the response rate for the specificity of operating parameters in some scenarios and improve the response dimension for abnormal feature alarm processing.

[0014] 3. The present invention classifies the warning parameters according to trends and classifies them into multiple states after classification to simulate the parameter changes on each branch of the current distribution cabinet, and adopts a joint control strategy for the intersection of related elements under the same state classification, and adopts a difference strategy for the different parts to avoid the configuration of processing strategies for each branch and the occurrence of excessive control. Then, the threshold is dynamically adjusted according to the frequency of occurrence of the strategy control target, and after combining the trigger sequence, the priority control of each branch is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below with reference to the accompanying drawings and examples.

[0016] Figure 1 The present invention is a flow chart of a control method for an intelligent power distribution cabinet.

[0017] Figure 2 The present invention is a flow chart of step S2 of the intelligent power distribution cabinet control method.

[0018] Figure 3 The present invention is a flow chart of step S3 of the intelligent power distribution cabinet control method.

[0019] Figure 4 The present invention is a flow chart of step S4 of the intelligent power distribution cabinet control method.

[0020] Figure 5 The present invention is a flow chart of step S5 of the intelligent power distribution cabinet control method. DETAILED DESCRIPTION

[0021] The following embodiments of the present invention are described in detail. The embodiments described below are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention. Where specific techniques or conditions are not specified in the embodiments, the techniques or conditions described in the literature in the art or in the product specifications shall be followed.

[0022] See Figure 1 , a smart distribution cabinet control method, including: S1, using multiple sensors deployed in the current distribution cabinet to collect operating parameters in real time, the operating parameters include but are not limited to the voltage and current of each branch, the status of each branch switch and the corresponding operating time of each branch switch.

[0023] S2: Based on the acquired operating parameters, perform layered anomaly detection on each branch in the power distribution cabinet and set the corresponding abnormal characteristics of each branch.

[0024] S3, identifying the combination components of the abnormal characteristics corresponding to each branch, determining each combination component of the abnormal characteristics, and setting warning parameters under the current abnormal power distribution.

[0025] S4, perform trend analysis based on the warning parameters, identify the relative changes of the warning parameters under the changing trend, and perform state deduction based on the relative changes to identify the strategic control targets under the changing trend.

[0026] S5, using the occurrence frequency of the strategy control target, quantify the triggering conditions of each branch, and set the hierarchical control strategy based on the logical connection relationship of each branch under the triggering conditions.

[0027] At this time, the current and voltage conditions collected on each branch are obtained, and the opening and closing status of the circuit breaker and contactor, as well as the corresponding operating time of each branch switch, are used as the main operating parameters for identification. At this time, current sensors, voltage sensors, cameras, etc. are used to directly obtain operating parameters.

[0028] In step S1 , when the operating parameters are obtained, the current operating parameters need to be filled with the baseline data of the operating parameters.

[0029] That is, the implementation of step S1 also includes: S11, performing data perception on the operating parameters under multiple operating cycles, and obtaining the value range of each operating parameter under a continuous time window; in this case, the description of the operating cycle represents the data under the periodic inspection, control instruction execution, and periodic data archiving of the distribution cabinet. This data is divided into multiple combinations and viewed in the form of a continuous time window, and the value range of the operating parameters within these operating cycles is described. For example, the value range of current and voltage, whether each branch switch is normally opened and closed, and the operating time of each branch configured by the distribution cabinet in the corresponding operating cycle, etc., are processed separately to form data sets under various scenarios to facilitate subsequent classification control.

[0030] S12 , distributing the operating parameters into multiple data sets according to the operating scenarios based on the value ranges of the operating parameters, and outputting the operating parameters according to the time lengths of the multiple data sets.

[0031] The time length of the above data set represents the length of the time period represented by the difference between the maximum timestamp and the minimum timestamp of the data in the current data set, indicating the relative operating time of each data set in the corresponding operating scenario, to assist in judging the operating status of the equipment connected to the distribution cabinet.

[0032] Preferably, the above-mentioned hierarchical anomaly detection is carried out by deploying a three-phase power quality analyzer in the distribution cabinet, and adopting a wireless temperature measurement system in the terminal circuit to form a physical hierarchical architecture of high voltage-low voltage-terminal, and adopting different processing methods with different focuses for branches under different hierarchical architectures; for example, for branches connected to the distribution cabinet, such as high-voltage branches, the insulation resistance monitoring method is focused on to record their current and voltage, and low-voltage branches are focused on current overload. The physical layers are divided using the equipment type and the actual description of each branch on the distribution cabinet. The physical layer represents the different conditions of voltage and current configured on each branch when different devices are connected. These conditions are divided into multiple physical levels according to the high-voltage and low-voltage division standards, as well as the operating conditions after the corresponding branches are deployed; for example, labels describing the connected branches on the distribution cabinet, such as long-term operation, intermittent operation, suspended operation and waiting for inspection, are used as their operating conditions, and branches belonging to high voltage or low voltage are combined with their operating status labels for description to form physical layers under multiple mixed descriptions, so as to determine the relative operating status of each branch.

[0033] At the same time, logical layering can be used to achieve hierarchical anomaly detection for multiple branches of the distribution cabinet. For example, according to the current distribution cabinet usage scenario and the parts connected to the distribution cabinet, abnormal data can be classified based on clustering algorithms such as K-Means, and the risk level can be quantified in combination with the operating status of the distribution cabinet.

[0034] The hierarchical control strategy implemented at this point is divided into three levels. The first level provides local rapid response, implementing real-time control responses through real-time monitoring of branch switch status and immediate tripping of circuit breakers when current exceeds the limit. The second level emphasizes the logical relationships between multiple branches, adjusting the load and operation of each branch connected to the distribution cabinet. The third level uses long-term time series analysis in segmented time, using trend analysis as a representative indicator for peak-shifting control, to ensure that each branch's configured current output is stable.

[0035] like Figure 2 As shown, the implementation of step S2 includes: S21, using the numerical range of the operating parameter belonging to low pressure and high pressure, combined with the operating status of the operating parameter, to obtain the physical layer corresponding to the current operating parameter.

[0036] S22, using the operating parameters under the physical layer as the input features of the logical layer, clustering the branches in the distribution cabinet, and setting the logical layer of each operating parameter based on the deviation value of the operating parameters after clustering; and using the abnormality level represented by each layer in the logical layer as the output abnormality feature.

[0037] Preferably, when performing the above-mentioned logical stratification, the input voltage and current need to be normalized and then clustered; the state of each branch switch is used to indicate whether the switch is closed or open. The state of the branch switch is essentially to complete the clustering analysis of the voltage and current, and then combine the state and operating time of the switch with the clustered current and voltage to check whether the current switch performs corresponding disconnection processing after the branch current abnormal alarm, and whether the corresponding switch undergoes relevant state changes when the current and voltage are too large. These data are combined as the output abnormal characteristics.

[0038] That is, the implementation method of performing clustering processing in step S22 also includes: S221, using the current and voltage of each branch in the distribution cabinet as clustering parts, comparing the current and voltage with historical baseline data respectively, and obtaining multiple clusters.

[0039] S222: The standard deviation of each value in the cluster from the cluster center is regarded as the deviation value of the operating parameter, and an abnormal level is set for the current and voltage in the current operating parameters.

[0040] S223 , combining each abnormality level with the state and operation time of the branch switch, and treating the combined data as an output abnormality feature.

[0041] Preferably, when performing the above clustering processing, the current and voltage are clustered respectively according to the K-Means clustering method, and the standard deviation calculated for each cluster after clustering is compared with the standard deviation in the historical baseline data. At this time, the historical baseline data is the current and voltage values ​​of normal operation in the historical data; when the standard deviation calculated for the input current and voltage differs greatly from the historical baseline data, it indicates that abnormalities in the current and voltage are detected in the current distribution cabinet.

[0042] For example, if the current data standard deviation is less than the historical baseline data standard deviation, it is regarded as the first level abnormality level, which indicates the general operation condition; if the current data standard deviation is 1-2 times the historical baseline data standard deviation, it is regarded as the second level abnormality level, which is the data level that needs to be paid attention to; and if the current data standard deviation is greater than 2 times the historical baseline data standard deviation, it is regarded as the third level abnormality level, which represents the serious part that needs to be handled and needs to be handled with emphasis, so as to complete the abnormality level of current and voltage.

[0043] As for outputting abnormal characteristics, the abnormal levels of current and voltage are sequentially combined with the states and operating durations of the corresponding branch switches to obtain the output abnormal characteristics.

[0044] Preferably, the abnormal features combined in step S223 also include: taking the confidence of the state and operating time of the branch switch in the historical data as the basic condition, considering the product of the confidence of the state and operating time of the branch switch and the load rate of the current switch as the state quantity, clustering the state and operating time of the branch switch, and setting the abnormal level with the standard deviation of the state quantity relative to the standard deviation of the historical baseline data, and combining the abnormal levels contained in the current operating parameters and outputting them as abnormal features.

[0045] It should be noted that the confidence level of the branch switch state and operating time is calculated by the ratio of the number of item sets that combine the switch state and operating time to the number of item sets that contain the corresponding switch state through the relationship between switch state and operating time. This measures the probability that the branch switch contains the corresponding operating time when it is closed or open.

[0046] The above-mentioned load rate can be obtained by calculating the power of the real-time input voltage and current and dividing it by its rated power to obtain the state quantity corresponding to the current branch switch. When the branch switch is closed, the operating status of the current switch can be directly described. At this time, the confidence of the branch switch state and operating time is expressed in the form of instantaneous values ​​to describe its state quantity. When the switch is disconnected, the state quantity will be expressed as 0. At this time, its operating status can still be directly described. When the switch is disconnected, it will not be compared with the historical baseline data. Only when the state quantity is non-zero, the abnormal level is calculated with the historical baseline data. The abnormal level is handled in the same way as the voltage and current.

[0047] It should be noted that when using the K-Means clustering method for clustering, it is necessary to determine the number of clusters K to be selected. At this time, only when the sum of squared errors relative to the cluster center is minimized after statistics of multiple clusters and the silhouette coefficient is greater than 0.5, the corresponding number of clusters will be regarded as the cluster for the current clustering processing. At the same time, the historical baseline data can also be calculated based on the data in multiple time windows adjacent to the current input data to achieve real-time update of the historical baseline data.

[0048] Preferably, since the operating time represents the operating time of the equipment in a specific cycle, the confidence level is calculated based on the state of the branch switch and the operating time in order to quantify the state correlation of the equipment under continuous operation. It is necessary to combine multiple parameters such as the load rate to indicate the length of time of operation in a single operating cycle to determine whether the current distribution cabinet can operate stably.

[0049] Specifically, the current operation cycle for data collection and processing is based on days and hours. Each operation cycle is divided into time lengths of 1 day, 3 days, 7 days, and 15 days, and the data collected every hour is used as the content of the current analysis.

[0050] In one embodiment of the present invention, in step S3, it is necessary to combine and judge the parts of the operating parameters after dividing the abnormal levels, and check whether the corresponding abnormal features are interdependent parts, so as to obtain the partial feature combinations that are obviously abnormal under the feature combination, and output these feature combinations as early warning parameters, which represent the parts that need to be controlled and processed in the current distribution cabinet.

[0051] like Figure 3 As shown, the implementation of step S3 includes: S31, according to the feature combination of abnormal features, analyzing the conditional dependence of each combination component in the abnormal features, and collecting the combination judgment information of each abnormal feature.

[0052] S32, based on the conditional dependency associated with the combined judgment information, the combined data in the abnormal feature are sorted in the order of input of the operating parameters to obtain a processing record of the abnormal feature.

[0053] S33, using the abnormal feature processing record, compare the abnormal features, and regard the difference subsets of the components in the abnormal features as output warning parameters.

[0054] Preferably, the combination component is used to describe the values ​​of voltage, current, switch state, and operating time contained in each abnormal feature, and to describe the data set corresponding to the current abnormal feature; the conditional dependence of each combination component is used to describe the situation in which the voltage, current, the state of each branch switch, and the operating time corresponding to each branch switch trigger an early warning after the combination. At this time, it is necessary to calculate the similarity of the data under multiple abnormal levels contained in the abnormal feature with the data in the historical data that meets the early warning. For example, using the cosine similarity or Pearson correlation coefficient calculation method, the data after the combination of multiple abnormal levels is normalized, and then according to the abnormal level corresponding to the voltage, the abnormal level corresponding to the current, the state of each branch switch, and the abnormal level corresponding to the operating time of each branch switch, the three abnormal levels are combined in pairs and the Pearson correlation coefficient is calculated with the data in the historical data that meets the early warning. The similarity of the corresponding abnormal level combination is calculated, and these similarities are used as the identification method of the conditional dependence under its combination. If the cosine similarity is used to calculate its similarity, the data under the three abnormal level combinations are converted into vector form, and the similarity of these data is directly compared with the early warning part in the historical data. When the calculated similarity is greater than 0.6, the combination components of the corresponding abnormal features are considered to have conditional dependence, and the difference subset of the combination components in multiple abnormal features is regarded as the output warning parameter. The warning parameter is used to illustrate the different parts of multiple abnormal features in the data set of voltage, current, switching state and operating time combination, which may highlight potential abnormal situations.

[0055] The core purpose of combined judgment information is to identify conditional dependencies with statistical significance or potential risks by quantifying the similarity between the current abnormal feature combination and historical warning data, thereby providing a dynamic and explainable basis for warning decisions.

[0056] As for the processing process record, it is achieved by combining the conditional dependencies after the abnormal features of the sequential set of input parameters to form a set of association rule data such as voltage → current → switch state → operating time, and combining these data when using conditional dependencies to judge the combination judgment information to record multiple sets of data that meet data normalization → similarity calculation → early warning triggering.

[0057] When the features of the processing records are compared and the feature differences of the abnormal features are formed, the description of the abnormal features on the warning triggering in the processing records is further checked. At this time, the Apriori algorithm can be used for analysis to further describe the difference of the current parameters under the warning by the support of multiple conditionally dependent operating parameters contained in the processing records. At this time, the support will judge the support of multiple combinations of abnormal features under the data stored in the warning part in the historical data to illustrate the warning situation that the current operating parameter value can approach; the difference in support between the data of multiple groups of abnormal level combinations contained in the processing records is regarded as the feature difference of the abnormal features at this time, and the corresponding data is output as the warning parameter.

[0058] It should be noted that the current support is based on the ratio of the number of item sets of voltage, current, switch state and operating time in the constituent association rules under the corresponding values ​​to the number of item sets of all data combinations, which is used to illustrate the probability of occurrence of voltage, current, switch state and operating time under the corresponding values.

[0059] That is, the implementation method of step S33 also includes: using the processing process record of the current abnormal feature, checking the multiple combination components with conditional dependence under the current abnormal feature, and setting the association rules corresponding to each abnormal feature. The association rules represent the combination relationship between multiple data with conditional dependence. The association rules will be set based on regular expressions to explain the form of other parameters corresponding to when a certain value in the operating parameters changes, to explain the main associated parts existing in the current abnormal feature; for example, the association rules of voltage and current, the association rules of switch status and operating time, and the association rules of the combination of voltage, current and switch status, etc., the association rules are usually expressed in the form of X→Y, which explains the form in which the voltage, current, the status of each branch switch and the corresponding operating time of each branch switch in the abnormal feature can be combined.

[0060] Obtain the support of each abnormal feature under the corresponding association rule, generate a feature difference record of the abnormal feature by the difference between the support of each abnormal feature and the average support value, synchronize all feature difference records to the warning parameters, and make sure that each warning parameter corresponds to the abnormal level divided by the operating parameters.

[0061] The purpose of marking feature differences is to subsequently identify which data within the input operating parameters contain conditional associations, as well as data combinations with significantly higher differences than other combinations, to identify high-risk data. Support difference involves calculating the correlation of the association rules corresponding to the abnormal features, averaging the correlations of the multiple abnormal features currently being processed, comparing the support of each association rule with the average, and processing them sequentially based on the difference. Prioritizing processing of data with large support difference values ​​allows for rapid identification of abnormal features within the current distribution cabinet.

[0062] As for the purpose of adapting to the support when obtaining the difference subset, it is to further describe the probability of occurrence of the item set of voltage, current, switch state and operating time combination in the operating parameters in the historical data, and combine this occurrence probability with the subset of the current combination to obtain the difference, indicating the value set of the operating parameters that have differences during the early warning.

[0063] In one embodiment of the present invention, Figure 4 As shown, the implementation of step S4 includes: S41, converting the warning parameters into time series data, arranging the warning parameters according to timestamps, and calculating the relative change corresponding to each data in the warning parameters.

[0064] S42, identifying the state classification corresponding to the relative change amount based on the change trend of the relative change amount, and constructing a state transition diagram corresponding to the warning parameter based on the warning parameters associated with each state classification.

[0065] S43, using each warning parameter in the state transition diagram, performing strategy matching on each warning parameter, after strategy matching, for warning parameters belonging to the same state classification, determining the intersection of these warning parameters as the strategy control target.

[0066] S44, for warning parameters that do not belong to the same state classification, the difference between the warning parameters after strategy matching is regarded as the strategy control target.

[0067] It should be noted that the state transition diagram will divide the state categories according to the relative change amount of each warning parameter, connect and display multiple warning parameters according to the timestamp of the warning parameter, and mark the state category on each warning parameter to form a state transition diagram corresponding to each branch on the distribution cabinet.

[0068] The above relative changes will divide the warning parameters into three states: stable, deteriorating, and recovering. These three states represent the changing trends of the relative changes. For the relative changes of voltage and current, the stable state belongs to [-10%, 10%], the deteriorating state is greater than 30% and continues to rise, and the recovery state is less than -30% and returns to the normal range. The identification of the switch state and the operating time is based on the corresponding state quantity, and the state detection is performed on the non-zero part. The method used can use the same size interval range as that used for voltage and current to set the corresponding state. As for the numerical range not included between the three states of stability, deterioration, and recovery, it represents the relative fluctuation state. This part of the data is not used as the part for direct state classification. After setting its label with rising fluctuation and falling fluctuation, its label is used as the corresponding state classification to divide the state classification corresponding to stability, deterioration, recovery, rising fluctuation and falling fluctuation.

[0069] Then, multiple sets of warning parameters corresponding to stability, deterioration, recovery, rising fluctuations and falling fluctuations are used to connect the warning parameters on the corresponding branches with the timestamps of the warning parameters to form a state transition diagram; each type of state in the state transition diagram is configured with preset strategies such as current limiting, alarm, power supply restoration, etc. When matching strategies, the cosine similarity calculation is performed between the warning parameters under each state category and the parameters marked in the preset strategy, and the preset strategy corresponding to the maximum value after the cosine similarity calculation is used as the strategy corresponding to the warning parameter. When calculating the cosine similarity, the warning parameters need to be normalized and the similarity calculation is completed in the form of a vector; as for the selection of intersection and difference, it tends to dynamically identify the similarities and differences in the configuration strategies of the current branches after the warning parameters are identified, so as to determine the strategy methods that need to be adopted by different branches under strategy control, so as to prevent the limitations of a single strategy from causing misjudgment of the state of each branch. The output policy control target will further obtain the intersection and difference sets of the operating parameter parts contained in these preset policies, and use these data as the output data during policy matching analysis to emphasize the intersection part that is centrally reviewed during policy setting and the difference part that is auxiliary reviewed, to complete the selection of policy control targets under multiple state classifications. The output policy control target will include the specific values ​​of the operating parameters, abnormality levels, association rules, etc. The association between these data is output as a policy control target, so that when the policy control target sets the trigger conditions, the trigger conditions can directly correspond to the abnormality levels and association rules, so that when the policy is executed, the frequency of each operating parameter reaching the abnormality level under the warning can be used to indicate the policy control targets that currently need to be focused on, as well as some data that are not valid targets using differential processing.

[0070] Preferably, the association relationship described above represents the form of high voltage rising → switch disconnection, which means that the switch state and operating time are directly associated with the current and voltage. It can also be regarded as its association relationship based on the conditional dependency between the current multiple sets of warning parameters to illustrate the direct logical association between the multiple sets of warning parameters. This part can be directly extracted through the regular expression set in the database, that is, after filtering the warning parameters through association rules, its state classification and the corresponding parts of the association rules are regarded as multiple categories after combination. The intersection under the same category after the combination of association rules and state classification will be used as the current main policy target. If it cannot be in the same category after combination, the difference part will be emphasized to determine the difference during policy execution and adjust the strategy configured for each branch; for example, the intersection part is regarded as the core policy control target, and is processed by methods such as limiting voltage and current at the same time. The difference is regarded as the auxiliary policy control target, and is processed by methods such as adjusting only voltage without intervening in the switch.

[0071] In one embodiment of the present invention, Figure 5 As shown, the implementation method of step S5 also includes: S51, when the policy control target is a valid target, the occurrence frequency of the policy control target within a preset time period is used as the frequency threshold of the policy control target, and the valid target is the data that meets the trigger condition.

[0072] S52: When the policy control target is not a valid target, the data greater than the frequency threshold is regarded as the part that meets the frequency threshold, and the policy control target that meets the frequency threshold is used as the trigger condition of each branch.

[0073] S53, the order in which each branch is triggered when the trigger condition is met is regarded as a logical connection relationship, and strategies are set for each branch in the order of triggering. The set strategies are output one by one according to the abnormal level of the trigger condition to obtain a hierarchical control strategy.

[0074] In step S5, the strategy control targets that have been verified in the historical data to be able to accurately trigger early warnings or accurately handle early warnings are regarded as valid targets. These strategy control targets will represent the existence of effective processing means when controlling the distribution cabinet. For example, the strategy control target under the intersection is voltage + current dual limit. This target is triggered 5 times in unit time in the current data. At this time, it will represent that the voltage + current needs to be warned, and strategy control is set. At this time, the corresponding strategy control target is regarded as a valid target, and the relevant threshold is set; the part that is judged not to be a valid target is the difference part of the strategy control target when it is obtained. Under the currently set frequency threshold, these difference parts may represent potential warning events in the current scenario after the frequency of the corresponding data exceeds the frequency of obvious warnings. It is necessary to judge whether the corresponding strategy control target is a potential valid target.

[0075] As for setting the trigger conditions, it is to trigger the logic of whether the subsequent setting is a potential effective target. The triggering of each branch is processed in the triggering order, and the current strategy mode is set one by one according to the triggering order of the intersection and difference parts in the strategy control target. The intersection part is regarded as high priority and the difference part is regarded as low priority. After the strategy processing of the intersection part is completed, if there is still a problem, it is processed with the strategy corresponding to the difference part to complete the deployment of the current hierarchical control strategy, and the abnormal level of the original operating parameters after deployment is mapped to illustrate the overall execution process of the current strategy.

[0076] The present invention also provides an intelligent power distribution cabinet, comprising: a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes any of the intelligent power distribution cabinet control methods described above, and realizes the functions described below: using a variety of sensors deployed in the current power distribution cabinet to collect operating parameters in real time, the operating parameters including but not limited to the voltage, current, status of each branch switch and the corresponding operating time of each branch switch; based on the acquired operating parameters, performing hierarchical abnormality detection on each branch in the power distribution cabinet, and setting the abnormal characteristics corresponding to each branch; identifying the combination components of the abnormal characteristics corresponding to each branch, judging each combination component of the abnormal characteristics, and setting the early warning parameters under the current abnormal power distribution; performing trend analysis based on the early warning parameters, identifying the relative change of the early warning parameters under the change trend, and performing state deduction based on the relative change, and identifying the strategy control target under the change trend; using the frequency of occurrence of the strategy control target to quantify the triggering conditions of each branch, and setting a hierarchical control strategy based on the logical connection relationship of each branch under the triggering conditions; and finally completing the control processing of the power distribution cabinet.

[0077] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention, which are still covered by the scope of protection of the present invention.

Claims

1. A method for controlling an intelligent power distribution cabinet, characterized in that: include: S1 uses multiple sensors deployed in the current power distribution cabinet to collect operating parameters in real time. The operating parameters include but are not limited to the voltage and current of each branch, the status of each branch switch, and the corresponding operating time of each branch switch; S2, based on the acquired operating parameters, performs layered anomaly detection on each branch in the distribution cabinet and sets the corresponding abnormal characteristics of each branch; S3, identifying the combination components of the abnormal characteristics corresponding to each branch, determining each combination component of the abnormal characteristics, and setting the warning parameters under the current abnormal power distribution; S4, perform trend analysis based on the warning parameters, identify the relative changes of the warning parameters under the change trend, and perform state deduction based on the relative changes to identify the strategic control targets under the change trend; S5, using the occurrence frequency of the strategy control target, quantify the triggering conditions of each branch, and set the hierarchical control strategy based on the logical connection relationship of each branch under the triggering conditions.

2. The intelligent power distribution cabinet control method according to claim 1, characterized in that: The implementation of step S1 further includes: S11, performing data sensing on the operating parameters under multiple operating cycles to obtain the value range of each operating parameter under a continuous time window; S12 , distributing the operating parameters into multiple data sets according to the operating scenarios based on the value ranges of the operating parameters, and outputting the operating parameters according to the time lengths of the multiple data sets.

3. The intelligent power distribution cabinet control method according to claim 1, characterized in that: The implementation of step S2 includes: S21, using the numerical range of the operating parameter belonging to low pressure and high pressure, combined with the operating status of the operating parameter, to obtain the physical layer corresponding to the current operating parameter; S22, using the operating parameters under the physical layer as the input features of the logical layer, clustering the branches in the distribution cabinet, and setting the logical layer of each operating parameter based on the deviation value of the operating parameters after clustering; and using the abnormality level represented by each layer in the logical layer as the output abnormality feature.

4. The intelligent power distribution cabinet control method according to claim 3, characterized in that: The implementation of clustering processing in step S22 also includes: S221, using the current and voltage of each branch in the distribution cabinet as clustering parts, comparing the current and voltage with historical baseline data respectively to obtain multiple clusters; S222, the standard deviation of each value in the cluster from the cluster center is regarded as the deviation value of the operating parameter, and the abnormal level of the current and voltage in the current operating parameters is set; S223 , combining each abnormality level with the state and operation time of the branch switch, and treating the combined data as an output abnormality feature.

5. The intelligent power distribution cabinet control method according to claim 4, characterized in that: The abnormal features combined in step S223 also include: The confidence level of the branch switch status and operating time in historical data is used as the basic condition. The product of the confidence level of the branch switch status and operating time and the load rate of the current switch is regarded as the state quantity. The branch switch status and operating time are clustered, and the anomaly level is set according to the standard deviation of the state quantity relative to the standard deviation of the historical baseline data. The anomaly levels contained in the current operating parameters are combined and output as an anomaly feature.

6. The intelligent power distribution cabinet control method according to claim 1, characterized in that: The implementation of step S3 includes: S31, analyzing the conditional dependencies of the components of the abnormal features according to the feature combination of the abnormal features, and collecting the combination determination information of the abnormal features; S32, based on the conditional dependency associated with the combined judgment information, the combined data in the abnormal feature are processed in the order of the input operation parameters to obtain a processing record of the abnormal feature; S33, using the abnormal feature processing record, compare the abnormal features, and regard the difference subsets of the components in the abnormal features as output warning parameters.

7. The intelligent power distribution cabinet control method according to claim 6, characterized in that: The implementation of step S33 further includes: Based on the processing record of the current abnormal feature, check the multiple combination components with conditional dependencies under the current abnormal feature, and set the association rules corresponding to each abnormal feature; Obtain the support of each abnormal feature under the corresponding association rule, generate a feature difference record of the abnormal feature by the difference between the support of each abnormal feature and the average support value, synchronize all feature difference records to the warning parameters, and make sure that each warning parameter corresponds to the abnormal level divided by the operating parameters.

8. The intelligent power distribution cabinet control method according to claim 1, characterized in that: The implementation of step S4 includes: S41, converting the warning parameters into time series data, arranging the warning parameters according to timestamps, and calculating the relative change corresponding to each data in the warning parameters; S42, identifying the state category corresponding to the relative change amount based on the change trend of the relative change amount, and constructing a state transition diagram corresponding to the warning parameter based on the warning parameter associated with each state category; S43, using each warning parameter in the state transition diagram, performing strategy matching on each warning parameter. After strategy matching, for warning parameters belonging to the same state classification, the intersection of these warning parameters is determined as the strategy control target; S44, for warning parameters that do not belong to the same state classification, the difference between the warning parameters after strategy matching is regarded as the strategy control target.

9. The intelligent power distribution cabinet control method according to claim 1, characterized in that: The implementation of step S5 further includes: S51, when the policy control target is a valid target, the occurrence frequency of the policy control target within a preset time period is used as the frequency threshold of the policy control target, and the valid target is the data that meets the trigger condition; S52, when the policy control target is not a valid target, the data greater than the frequency threshold is regarded as the part that meets the frequency threshold, and the policy control target that meets the frequency threshold is used as the trigger condition of each branch; S53, the order in which each branch is triggered when the trigger condition is met is regarded as a logical connection relationship, and strategies are set for each branch in the order of triggering. The set strategies are output one by one according to the abnormal level of the trigger condition to obtain a hierarchical control strategy.

10. An intelligent power distribution cabinet, characterized in that: include: A computer-readable storage medium storing instructions, wherein when the instructions are executed on a computer, the computer executes the intelligent distribution cabinet control method according to any one of claims 1 to 9.

Images