A smart micro-break control device

Abstract

The present invention provides an intelligent micro-break control device, wherein the device includes: a circuit breaker state determination subsystem, for determining whether a target circuit is in a micro-break state based on current micro-break state data; a historical circuit data acquisition subsystem, for acquiring historical circuit data before the target circuit is in a micro-break state; a fault determination subsystem, for determining a fault based on historical circuit data; a judgment result determination subsystem, for acquiring a judgment result based on a fault and circuit parameters; and an intelligent micro-break control subsystem, for performing intelligent micro-break control based on different judgment results. An intelligent micro-break control device of the present invention determines whether a target circuit is in a micro-break state based on the current micro-break state data of the target circuit. If so, historical circuit data is introduced to determine the fault, and then whether the fault is resolved is determined based on circuit parameters. Intelligent micro-break control is performed based on the judgment result, and fault handling of the micro-break control circuit is more timely.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution equipment, and in particular to an intelligent micro-breaker control device. Background Art

[0002] Miniature circuit breakers (MCBs) are widely used. They primarily provide overload and short-circuit protection, ensuring circuit safety. In industrial settings, MCBs protect various equipment and machinery from damage caused by overloads and short circuits. In commercial buildings, they protect lighting, sockets, and small motors. In residential buildings, MCBs protect home electrical systems, ensuring safe use of electricity.

[0003] Smart micro-circuit breaker management and control refers to the use of intelligent technology to monitor and manage miniature circuit breakers. Through smart micro-circuit breaker management and control, the intelligence level of the power system can be effectively improved, electricity safety can be ensured, energy use can be optimized, and operation and maintenance efficiency and system stability can be improved.

[0004] The existing technology monitors the heartbeat signals of each fault recorder through a recording master station. Based on the monitoring results, the fault recorder to be restarted is determined, and the unit in the fault recorder to be restarted is determined. If the unit to be restarted is a recording unit, a soft restart command to control the recording unit is sent to the management unit. If the soft restart command is invalid, a hard restart command is directly sent to the recording unit. If the unit to be restarted is a management unit, a hard restart command is sent directly to the management unit. This combines soft and hard restarts and supports the independent restart of some functional modules. While enabling module-by-module restart, it reduces the number of hard restarts, avoids hardware damage caused by frequent restarts of the fault recorder, and extends the service life of the fault recorder.

[0005] However, the above-mentioned prior art determines the fault recorder to be restarted based on the monitoring result, but ignores the situation that the fault recorder itself needs to be repaired when it fails, and the repair efficiency of the fault recorder is not high.

[0006] In view of this, there is an urgent need for a smart micro-break control device to at least solve the above-mentioned shortcomings. Summary of the Invention

[0007] One of the purposes of the present invention is to provide an intelligent micro-break control device, which determines whether the target circuit is in a micro-break state based on the current micro-break status data of the target circuit. If so, historical circuit data is introduced to attribute the circuit fault. The fault is determined based on the fault attribution and the circuit parameters are obtained to determine whether the fault is resolved. Intelligent micro-break control is performed based on the judgment result, thereby improving the timeliness of micro-break control circuit fault processing.

[0008] An embodiment of the present invention provides a smart micro-break control device, comprising:

[0009] The circuit breaker status determination subsystem is used to obtain the current micro-break status data of the target circuit and determine whether the target circuit is in the micro-break state based on the current micro-break status data;

[0010] A historical circuit data acquisition subsystem is used to acquire historical circuit data before the target circuit is in the micro-break state if the target circuit is in the micro-break state;

[0011] The fault determination subsystem is used to attribute circuit faults and determine faults based on historical circuit data;

[0012] A judgment result determination subsystem is used to determine whether the fault is resolved and obtain the judgment result based on the fault and circuit parameters;

[0013] The smart micro-break control subsystem is used to perform smart micro-break control based on different judgment results.

[0014] Preferably, the circuit breaker status determination subsystem includes:

[0015] An access information acquisition module, used to acquire access information of a miniature circuit breaker of a target circuit;

[0016] The current micro-break status data determination module is used to parse the access information and obtain the current micro-break status data;

[0017] The circuit breaker status determination module is used to determine whether the target circuit is in a micro-break state based on the preset micro-break state determination template and the current micro-break state data.

[0018] Preferably, the historical circuit data acquisition subsystem includes:

[0019] The circuit breaking moment determination module is used to analyze the current micro-break status data and determine the circuit breaking moment;

[0020] The historical circuit data acquisition module is used to obtain historical circuit data based on the circuit breaking time and system log.

[0021] Preferably, the fault determination subsystem includes:

[0022] A historical fault case acquisition module is used to acquire historical fault cases;

[0023] Fault type library establishment module, used to establish a fault type library based on historical fault cases;

[0024] Circuit fault attribution model training module, used to train the circuit fault attribution model based on the fault type library;

[0025] Feature selection template construction module, used to construct feature selection templates based on the fault type library;

[0026] A historical circuit data information extraction module is used to determine a selection feature set and a fault type label based on a feature selection template and historical circuit data;

[0027] The fault determination output module is used to input the selected feature set into the model channel corresponding to the fault type label of the circuit fault attribution model, summarize the channel output of each model channel, and obtain the determined fault.

[0028] Preferably, the fault determination subsystem further includes:

[0029] A pre-attribution module, configured to perform circuit fault pre-attribution before performing circuit fault attribution based on historical circuit data;

[0030] Among them, the pre-attribution module includes:

[0031] The electric control scene data acquisition submodule is used to obtain the electric control scene data of the target period before the target circuit is in the micro-break state;

[0032] A multimodal information identification submodule is used to identify the multimodal information of the associated devices corresponding to the target circuit based on the electronic control scene data;

[0033] The associated device multimodal description matrix construction submodule is used to extract multimodal information features from multimodal information and construct the associated device multimodal description matrix based on the multimodal information features; the multimodal information features include: image features and associated semantic features;

[0034] The pre-attribution result acquisition submodule is used to pre-attribute circuit faults according to the multi-modal description matrix of associated devices and obtain pre-attribution results.

[0035] Preferably, the historical fault case acquisition module includes:

[0036] A circuit similarity index determination submodule is configured to determine a circuit similarity index between a target circuit and a preselected historical fault case circuit; wherein determining the circuit similarity index between the target circuit and the preselected historical fault case circuit comprises: obtaining a first circuit diagram of the target circuit and a second circuit diagram of the preselected historical fault case, and determining a circuit similarity index between the first circuit diagram and the second circuit diagram based on a preset circuit diagram comparison template;

[0037] The historical fault case determination submodule is used to take the corresponding pre-selected historical fault case as the historical fault case if the circuit similarity index is greater than or equal to a preset circuit similarity index threshold.

[0038] Preferably, the circuit similarity index determination submodule includes:

[0039] A circuit device similarity index determination unit is used to determine the circuit device similarity index based on the circuit diagram comparison template; the circuit device similarity index is determined by multiplying the similarity degree of each type of device and the device action weight and summing the results;

[0040] A circuit equivalent value determination unit, configured to determine a circuit equivalent value based on a circuit diagram comparison template;

[0041] The circuit similarity index calculation unit is used for accumulating and calculating the circuit device similarity index and the circuit equivalent value to obtain the circuit similarity index.

[0042] Preferably, the judgment result determination subsystem includes:

[0043] A fault handling measure acquisition module is used to obtain fault handling measures according to the fault determination;

[0044] The judgment result acquisition module is used to obtain the judgment result according to the fault handling measures.

[0045] Preferably, the fault handling measure acquisition module includes:

[0046] The first measure acquisition submodule is configured to determine a fault handling measure based on deep learning technology; wherein determining the fault handling measure based on deep learning technology includes: determining the fault handling measure based on the determined fault and the target circuit based on the deep learning technology;

[0047] and / or,

[0048] The second measure acquisition submodule is used to determine the fault handling measures based on the big database; wherein, determining the fault handling measures based on the big database includes: determining the pre-selected fault handling measures based on the determined fault and the big database, sending the pre-selected fault handling measures to the management node of the target circuit, and obtaining the fault handling measures replied by the management node.

[0049] Preferably, the intelligent micro-break control subsystem includes:

[0050] The first micro-circuit breaker control module is used to control the micro-circuit breaker to conduct if the fault is resolved;

[0051] The second micro-breaker control module is used to keep the micro-circuit breaker disconnected and perform corresponding fault processing if the judgment result is that the fault is not resolved.

[0052] Preferably, the second micro-break control module includes:

[0053] A first processing feature acquisition submodule is configured to extract processing features of the determined fault to obtain a first processing feature if the result of the determination is that the fault is not resolved;

[0054] A processing type acquisition submodule is used to acquire a processing type of the first processing feature according to a feature label of the first processing feature, where the processing type includes: automated processing and manual processing;

[0055] The fault handling submodule is used to handle faults according to the different types of processing;

[0056] Fault handling submodule, including:

[0057] a second processing feature determining unit, configured to use the first processing feature of the processing type being automated processing as the second processing feature;

[0058] a third processing feature acquiring unit, configured to acquire a third processing feature of the target circuit;

[0059] a matching result acquiring unit, configured to perform feature matching on the second processing feature and the third processing feature to acquire a matching result;

[0060] a startup strategy determining unit, configured to determine a startup strategy for the target circuit according to a third processing feature of the match if the matching result is a match;

[0061] a fourth processing feature determining unit configured to, if the matching result is a mismatch, determine the processing type as manual processing and use the first processing feature excluding the second processing feature in the first processing feature as the fourth processing feature;

[0062] a manual maintenance plan determining unit, configured to input the fourth processing feature into a manual maintenance plan determining model to determine a manual maintenance plan;

[0063] The target maintenance personnel determination unit is used to determine the target maintenance personnel based on the preset personnel selection template, according to the manual maintenance plan and the maintenance personnel information database, and dispatch the target maintenance personnel to perform corresponding fault processing.

[0064] The beneficial effects of the present invention are:

[0065] The present invention determines whether the target circuit is in a micro-break state based on the current micro-break state data of the target circuit. If so, historical circuit data is introduced to attribute the circuit fault. The fault is determined based on the fault attribution and the circuit parameters obtained to determine whether the fault is resolved. Intelligent micro-break management and control are performed based on the judgment result, thereby improving the timeliness of micro-break control circuit fault processing.

[0066] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0067] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0069] Figure 1 Schematic diagram of a smart micro-break control device in an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0071] The embodiment of the present invention provides a smart micro-break control device, such as Figure 1 As shown, including:

[0072] The circuit breaker status determination subsystem 1 is used to obtain the current micro-break status data of the target circuit and determine whether the target circuit is in a micro-break state based on the current micro-break status data. The target circuit is a circuit controlled by a miniature circuit breaker, such as the circuit corresponding to the air conditioner in a household distribution board. The current micro-break status data is real-time information about the current state of the target circuit, such as parameters such as current, voltage, power, and frequency. The micro-break status indicates that the circuit is disconnected.

[0073] The historical circuit data acquisition subsystem 2 is used to acquire historical circuit data before the target circuit is in the micro-break state if the target circuit is in the micro-break state; wherein the historical circuit data is: circuit operation data recorded by the system before the micro-break state occurs;

[0074] Fault determination subsystem 3 is used to attribute the circuit fault to the historical circuit data and determine the fault; wherein the circuit fault attribution is: determining the cause of the circuit fault based on the analysis of the historical circuit data; the fault is: the result of the circuit fault attribution, such as: overload, short circuit, etc.;

[0075] The judgment result determination subsystem 4 is used to determine whether the judgment fault is resolved based on the judgment fault and circuit parameters, and obtain the judgment result; wherein the circuit parameters are: various parameters during circuit operation; the judgment result is: circuit fault resolved or circuit fault not resolved;

[0076] The smart micro-circuit breaker control subsystem 5 is used to perform smart micro-circuit breaker control based on different judgment results. When performing smart micro-circuit breaker control, if the circuit fault is determined to be resolved, the system directly controls the micro-circuit breaker to close and conduct. Otherwise, the micro-circuit breaker remains open and a reminder is sent to the relevant personnel.

[0077] The working principle and beneficial effects of the above technical solution are:

[0078] This application determines whether the target circuit is in a micro-break state based on the current micro-break state data of the target circuit. If so, historical circuit data is introduced to attribute the circuit fault. The fault is determined based on the fault attribution and the circuit parameters obtained to determine whether the fault is resolved. Intelligent micro-break management and control are performed based on the judgment result, thereby improving the timeliness of micro-break control circuit fault handling.

[0079] In one embodiment, the circuit breaker status determination subsystem includes:

[0080] An access information acquisition module is used to obtain access information of the miniature circuit breaker of the target circuit; wherein the access information is information obtained by the system accessing the communication node of the miniature circuit breaker based on the Internet of Things technology;

[0081] The current micro-break status data determination module is used to parse the access information and obtain the current micro-break status data;

[0082] The circuit breaker status determination module is used to determine whether the target circuit is in a micro-break state based on the current micro-break state data and a preset micro-break state determination template. The micro-break state determination template is used to determine whether the target circuit is in a micro-break state based on the current micro-break state data. For example, if the current is zero, the target circuit is determined to be in a micro-break state.

[0083] The working principle and beneficial effects of the above technical solution are:

[0084] This application parses the access information of the miniature circuit breaker of the target circuit to determine the current micro-break status data, introduces a micro-break status determination template to determine whether the target circuit is in the micro-break state, and improves the standardization of the micro-break determination.

[0085] In one embodiment, the historical circuit data acquisition subsystem includes:

[0086] The circuit breaking moment determination module is used to analyze the current micro-break status data and determine the circuit breaking moment; wherein the circuit breaking moment is: the circuit breaking time point;

[0087] The historical circuit data acquisition module is used to acquire historical circuit data based on the circuit breaking time and system log. The system log records the circuit data at each time, and the circuit data from the start acquisition time to the circuit breaking time is acquired as the historical circuit data. The start acquisition time of the historical circuit data is manually preset.

[0088] The working principle and beneficial effects of the above technical solution are:

[0089] This application analyzes the current micro-break status data, determines the circuit breaking moment, and then intercepts historical circuit data based on the system log and the circuit breaking moment, so that the data acquisition is more accurate.

[0090] In one embodiment, determining a fault determination subsystem includes:

[0091] The historical fault case acquisition module is used to obtain historical fault cases; wherein, the historical fault cases are records of fault events that occurred in the past, such as historical fault records of air conditioning circuits;

[0092] A fault type library establishment module is used to establish a fault type library based on historical fault cases; wherein the fault type library is a database obtained by collating and merging historical fault cases and collating and storing fault data of the same fault type;

[0093] The circuit fault attribution model training module is used to train the circuit fault attribution model based on the fault type library. The circuit fault attribution model training based on the fault type library includes: performing model branch training based on the historical fault parameters corresponding to each fault type;

[0094] The feature selection template construction module is used to construct a feature selection template based on the fault type library. The feature selection template is a template that guides how to select features related to the fault type, such as which circuit parameters to extract for a short circuit fault or which circuit parameters to extract for an open circuit fault.

[0095] The historical circuit data information extraction module is used to determine the selection feature set and fault type label based on the feature selection template and the historical circuit data; wherein the selection feature set is a collection of analysis features of the historical circuit data extracted corresponding to the fault type; the fault type label is a unique identifier of the fault type;

[0096] The fault determination output module is used to input the selected feature set into the model channel corresponding to the fault type label of the circuit fault attribution model, summarize the channel output of each model channel, and obtain the determined fault.

[0097] In an embodiment of the present application, the fault type library establishment module can be specifically used to:

[0098] Obtain historical fault cases, which include multiple historical fault types.

[0099] Fault features of various historical fault types are extracted to obtain multiple fault feature sets.

[0100] For each fault feature set, a fault feature vector corresponding to each fault feature in the fault feature set is calculated.

[0101] The matching degree between each fault feature set and a standard database is calculated. The standard database includes multiple standard fault feature sets.

[0102] Specifically, the matching degree between each fault feature set and the standard database can be calculated using the first formula.

[0103] The first formula is as follows:

[0104]

[0105] Among them, P xy represents the similarity between the xth fault feature set and the yth standard fault feature set in the standard database, K xi represents the i-th fault feature vector in the x-th fault feature set, n represents the number of fault feature vectors in the fault feature set x, L ym represents the mth standard fault feature vector in the yth standard fault feature set, m represents the number of standard fault feature vectors in the standard fault feature set y, and w represents a positive number.

[0106] In P xy When the similarity is greater than a preset value, the matching degree between the fault feature set and the standard database is recorded as the first matching degree.

[0107] In P xy When the similarity is greater than or equal to the preset similarity, the matching degree between the fault feature set and the standard database is recorded as the second matching degree. The first matching degree is greater than the second matching degree.

[0108] For each fault feature set, the similarity between the fault feature set and each standard fault feature set in the standard database is counted to determine a plurality of first matching degrees and / or a plurality of second matching degrees.

[0109] A sum or average value of the plurality of first matching degrees and / or the plurality of second matching degrees is calculated as the matching degree between the fault feature set and the standard database.

[0110] For each fault feature set, when the matching degree between the fault feature set and the standard database is greater than a preset matching degree, a first number of standard fault features are selected from the standard database according to the first matching degree from largest to smallest to be added to the fault type library.

[0111] When the matching degree between the fault feature set and the standard database is less than or equal to the preset matching degree, the fault feature set is added to the fault type library.

[0112] The working principle and beneficial effects of the above technical solution are:

[0113] Neural network models are widely used in fault analysis tasks. However, there are many types of faults that occur in micro-break control circuits. Blindly extracting all circuit features and then analyzing them will result in low fault identification efficiency. Therefore, historical fault cases are introduced to establish a fault type library. The neural network branches are trained according to the historical fault parameters corresponding to each fault type. At the same time, a feature selection template is constructed and a selection feature set of historical circuit data is extracted. The selection feature set is input into the model channel corresponding to the fault type label of the circuit fault attribution model to obtain the judged fault, thereby improving the fault identification efficiency.

[0114] In one embodiment, the fault determination subsystem further includes:

[0115] A pre-attribution module, configured to perform circuit fault pre-attribution before performing circuit fault attribution based on historical circuit data;

[0116] Among them, the pre-attribution module includes:

[0117] The electric control scene data acquisition submodule is used to obtain electric control scene data for a target period of time before the target circuit is in a micro-break state. The target period of time is, for example, 10 minutes before the target circuit is in a micro-break state. The target period of time can also be set manually. The electric control scene data is the scene data of the space where the device controlled by the target circuit is located. The scene data includes scene images, scene voice, etc.

[0118] The multimodal information identification submodule is configured to identify multimodal information of associated devices corresponding to the target circuit based on the electronic control scenario data. The associated device is a control device of the target circuit. The multimodal information of the associated device is electronic control scenario data related to the associated device, such as a captured image containing the associated device or a voice message mentioning the associated device.

[0119] The associated device multimodal description matrix construction submodule is used to extract multimodal information features from multimodal information and construct an associated device multimodal description matrix based on the multimodal information features. The multimodal information features include image features and associated semantic features. When constructing the associated device multimodal description matrix, each associated device corresponds to an associated device multimodal description matrix, and the multimodal information features of each type of multimodal information correspond to a column of the associated device multimodal description matrix. The specific type of multimodal information multimodal information features corresponding to which column of the matrix is ​​manually preset.

[0120] The pre-attribution result acquisition submodule is used to pre-attribute circuit faults based on the associated device multimodal description matrix and obtain pre-attribution results. When pre-attributing circuit faults based on the associated device multimodal description matrix, a matrix matching is performed between the associated device multimodal description matrix and the pre-matched description matrix in the preset "to-be-matched description matrix - candidate pre-attribution result comparison template." If the matrix match is satisfactory, the corresponding candidate pre-attribution result is used as the pre-attribution result.

[0121] The working principle and beneficial effects of the above technical solution are:

[0122] Before performing circuit fault attribution based on historical circuit data, the present application performs circuit fault pre-attribution, performs circuit fault attribution based on the pre-attribution result and historical circuit data, determines the fault, and improves the efficiency of subsequent fault determination.

[0123] Specifically, the pre-attribution process is as follows: Electrical control scene data for the space containing the devices controlled by the target circuit during a target period before the target circuit enters a micro-break state is acquired. Based on this electrical control scene data, electrical control scene data related to the associated devices controlled by the target circuit is identified and used as multimodal information. Based on feature engineering corresponding to the multimodal information type and the multimodal information of different information types, multimodal information features are determined. A multimodal description matrix for the associated devices is constructed based on the multimodal information features. When constructing the multimodal description matrix for the associated devices, each associated device corresponds to an associated device multimodal description matrix, and the multimodal information features of each type of multimodal information correspond to a column of the associated device multimodal description matrix. The specific matrix columns corresponding to the multimodal information features of each type of multimodal information are manually pre-set. The associated device multimodal description matrix is ​​then matrix-matched with a preset description matrix to be matched - the candidate pre-attribution result, against the description matrix to be matched in the template. If the matrix matches, the corresponding candidate pre-attribution result is used as the pre-attribution result. This improves the accuracy of the pre-attribution results.

[0124] In one embodiment, the historical fault case acquisition module includes:

[0125] A circuit similarity index determination submodule is used to determine the circuit similarity index of the target circuit and the preselected historical fault case circuit; wherein, determining the circuit similarity index of the target circuit and the preselected historical fault case circuit includes: obtaining a first circuit diagram of the target circuit and a second circuit diagram of the preselected historical fault case, and based on a preset circuit diagram comparison template, determining the circuit similarity index of the first circuit diagram and the second circuit diagram according to the first circuit diagram and the second circuit diagram; wherein, the first circuit diagram is: the circuit diagram of the target circuit; the second circuit diagram is: the circuit diagram corresponding to the fault circuit in the preselected historical fault case obtained from big data; the circuit similarity index is: an index for measuring the degree of circuit similarity, such as: electrical parameter similarity, transfer function similarity, etc.;

[0126] The historical fault case determination submodule is configured to select the corresponding pre-selected historical fault case as the historical fault case if the circuit similarity index is greater than or equal to a preset circuit similarity index threshold, wherein the preset circuit similarity index threshold is manually preset.

[0127] The working principle and beneficial effects of the above technical solution are:

[0128] The present application determines the circuit similarity index of the target circuit and the pre-selected historical fault case circuit based on the first circuit diagram of the target circuit and the second circuit diagram of the pre-selected historical fault case introduced by big data. The index determination is more accurate, and the corresponding pre-selected historical fault cases whose circuit similarity index is greater than or equal to the preset circuit similarity index threshold are used as historical fault cases, thereby improving the suitability of subsequent model training.

[0129] In one embodiment, the circuit similarity index determination submodule includes:

[0130] A circuit device similarity index determination unit is configured to determine a circuit device similarity index based on a circuit diagram comparison template. The circuit device similarity index is determined by multiplying the similarity degree of each type of device and the device action weight and summing the results. The circuit diagram comparison template is a comparison template used to determine the circuit similarity index; the device similarity degree is the similarity degree of the device type; and the device action weight is determined based on the role of the device in the circuit. The larger the action weight, the more important the function of the corresponding device in the circuit.

[0131] A circuit equivalent value determination unit is used to determine a circuit equivalent value based on a circuit diagram comparison template; wherein the circuit equivalent value is: the similarity of the transfer function of the circuit equivalent;

[0132] The circuit similarity index calculation unit is used for accumulating and calculating the circuit device similarity index and the circuit equivalent value to obtain the circuit similarity index.

[0133] The working principle and beneficial effects of the above technical solution are:

[0134] This application introduces circuit device similarity index and circuit equivalent value calculation circuit similarity index, which improves the suitability of determining circuit similarity index.

[0135] In one embodiment, the judgment result determination subsystem includes:

[0136] A fault handling measure acquisition module is used to acquire a fault handling measure according to the determined fault; wherein the fault handling measure is: a circuit operation for handling the determined fault;

[0137] The judgment result acquisition module is used to obtain the judgment result based on the fault handling measures. When obtaining the judgment result based on the fault handling measures, the module simulates the simulated circuit parameters of the target circuit after the fault handling measures are implemented based on the historical fault handling measures implementation records. The module then determines whether the simulated circuit parameters are similar to the circuit parameters after the fault. If the similarity reaches a specified value (for example, 0.995), the judgment result is that the fault is resolved; otherwise, the fault is not resolved.

[0138] The working principle and beneficial effects of the above technical solution are:

[0139] The present application determines the fault handling measures for determining the fault, simulates the implementation of the fault handling measures to obtain analog circuit parameters, and determines whether the fault is resolved based on the similarity between the analog circuit parameters and the circuit parameters, which is more reasonable.

[0140] In one embodiment, the fault handling measure acquisition module includes:

[0141] The first measure acquisition submodule is configured to determine a fault handling measure based on deep learning technology; wherein determining the fault handling measure based on deep learning technology includes: determining the fault handling measure based on the determined fault and the target circuit based on the deep learning technology;

[0142] and / or,

[0143] The second action acquisition submodule is used to determine fault handling actions based on the large database. Determining fault handling actions based on the large database includes: determining pre-selected fault handling actions based on the determined fault and the large database, sending the pre-selected fault handling actions to the target circuit's management node, and obtaining the fault handling actions responded by the management node. The management node is the communication node of the HVAC electrical expert. The pre-selected fault handling actions are those in the large database that match the fault type of the determined fault. However, not all pre-selected fault handling actions are applicable and require adaptive adjustment based on the target circuit. Therefore, the pre-selected fault handling actions are sent to the management node, who then adaptively adjusts the pre-selected fault handling actions to obtain the fault handling actions.

[0144] The working principle and beneficial effects of the above technical solution are:

[0145] This application introduces a combination of deep learning technology, big data and expert discussion to obtain fault handling measures, thereby improving the suitability of fault handling measures.

[0146] In one embodiment, the smart micro-break control subsystem includes:

[0147] The first micro-circuit breaker control module is used to control the micro-circuit breaker to conduct if the fault is resolved;

[0148] The second micro-breaker control module is used to keep the micro-circuit breaker disconnected and perform corresponding fault processing if the judgment result is that the fault is not resolved.

[0149] The working principle and beneficial effects of the above technical solution are:

[0150] This application adaptively controls the state of the miniature circuit breaker according to different judgment results, without the need for manual operation, and is more intelligent.

[0151] In one embodiment, the second micro-break management and control module includes:

[0152] A first processing feature acquisition submodule is configured to extract processing features of the determined fault to obtain a first processing feature if the fault is determined to be unresolved. The first processing feature is a characteristic representation of a measure for resolving the determined fault, such as a script for automatically executing a reset script, a control instruction for automatically controlling a mechanical reset, or the maintenance skills of a maintenance personnel dispatched for maintenance.

[0153] a processing type acquisition submodule, configured to acquire a processing type of the first processing feature based on a feature label of the first processing feature, where the processing types include automated processing and manual processing; the feature label is a feature type label of the first processing feature, acquired based on feature engineering technology;

[0154] The fault handling submodule is used to handle faults according to the different types of processing;

[0155] Fault handling submodule, including:

[0156] a second processing feature determining unit, configured to use the first processing feature of the processing type being automated processing as the second processing feature;

[0157] a third processing feature acquisition unit, configured to acquire a third processing feature of the target circuit; wherein the third processing feature is an automated processing feature that can be executed by the target circuit, such as a program function of executing an automated program, an operation result of performing a control operation, etc.;

[0158] a matching result acquiring unit, configured to perform feature matching on the second processing feature and the third processing feature to acquire a matching result;

[0159] A startup strategy determining unit is configured to determine a startup strategy for the target circuit based on the third processing feature of the match if the matching result is a match; wherein the startup strategy is an automated processing startup plan for the target circuit;

[0160] a fourth processing feature determining unit configured to, if the matching result is a mismatch, determine the processing type as manual processing and use the first processing feature excluding the second processing feature in the first processing feature as the fourth processing feature;

[0161] a manual maintenance plan determination unit, configured to input the fourth processing feature into a manual maintenance plan determination model to determine a manual maintenance plan; wherein the manual maintenance plan determination model is an AI model that determines a manual maintenance plan for a circuit based on the maintenance skills of a maintenance worker dispatched to perform maintenance;

[0162] The target maintenance personnel determination unit is used to determine the target maintenance personnel based on a preset personnel selection template, the manual maintenance plan, and the maintenance personnel information database, and dispatch the target maintenance personnel to handle the corresponding fault. The preset personnel selection template is used to determine the personnel selection plan based on the manual maintenance plan and the maintenance personnel information database.

[0163] The working principle and beneficial effects of the above technical solution are:

[0164] When troubleshooting a micro-circuit breaker control circuit, not all repair personnel are required to be present. For example, in the case of overpower, the micro-circuit breaker can be directly turned on after the rated load is restored. However, in cases such as component "burnout", repair personnel are required to be present. Therefore, when the judgment result is that the fault is not resolved, this application extracts the processing feature and obtains the first processing feature.

[0165] When the second processing feature, indicating automated processing, is present, automated processing is prioritized. A third processing feature, indicating automated execution for the target circuit, is introduced, and the second and third processing features are matched. If the match is positive, the automated processing strategy for the target circuit is determined based on the third processing feature. Otherwise, the fourth processing feature, indicating manual processing, is input into the manual repair solution determination model to determine the manual repair solution. By introducing a personnel selection template and identifying target repair personnel based on the manual repair solution and the repair personnel database, these personnel are dispatched to perform the corresponding fault handling, improving the timeliness, rationality, and intelligence of fault handling.

[0166] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A smart micro-break control device, characterized in that: include: The circuit breaker status determination subsystem is used to obtain the current micro-break status data of the target circuit and determine whether the target circuit is in the micro-break state based on the current micro-break status data; The circuit breaker status determination subsystem includes: An access information acquisition module, used to acquire access information of a miniature circuit breaker of a target circuit; The current micro-break status data determination module is used to parse the access information and obtain the current micro-break status data; A circuit breaker status determination module is used to determine whether the target circuit is in a micro-break state based on a preset micro-break state determination template and the current micro-break state data; A historical circuit data acquisition subsystem is used to acquire historical circuit data before the target circuit is in the micro-break state if the target circuit is in the micro-break state; The fault determination subsystem is used to attribute circuit faults and determine faults based on historical circuit data; The fault determination subsystem includes: A historical fault case acquisition module is used to acquire historical fault cases; Fault type library establishment module, used to establish a fault type library based on historical fault cases; Circuit fault attribution model training module, used to train the circuit fault attribution model based on the fault type library; Feature selection template construction module, used to construct feature selection templates based on the fault type library; A historical circuit data information extraction module is used to determine a selection feature set and a fault type label based on a feature selection template and historical circuit data; A fault determination output module is used to input the selected feature set into the model channel corresponding to the fault type label of the circuit fault attribution model, summarize the channel output of each model channel, and obtain the determined fault; A judgment result determination subsystem is used to determine whether the fault is resolved and obtain the judgment result based on the fault and circuit parameters; The smart micro-break control subsystem is used to perform smart micro-break control based on different judgment results; The fault determination subsystem further includes: Pre-attribution module, including: The electric control scene data acquisition submodule is used to obtain the electric control scene data of the target period before the target circuit is in the micro-break state; A multimodal information identification submodule is used to identify the multimodal information of the associated devices corresponding to the target circuit based on the electronic control scene data; The associated device multimodal description matrix construction submodule is used to extract multimodal information features from multimodal information and construct the associated device multimodal description matrix based on the multimodal information features; the multimodal information features include: image features and associated semantic features; The pre-attribution result acquisition submodule is used to pre-attribute circuit faults according to the multi-modal description matrix of associated devices and obtain pre-attribution results.

2. The intelligent micro-break control device according to claim 1, characterized in that: Historical circuit data acquisition subsystem, including: The circuit breaking moment determination module is used to analyze the current micro-break status data and determine the circuit breaking moment; The historical circuit data acquisition module is used to obtain historical circuit data based on the circuit breaking time and system log.

3. The intelligent micro-break control device according to claim 1, characterized in that: The historical fault case acquisition module includes: A circuit similarity index determination submodule is configured to determine a circuit similarity index between a target circuit and a preselected historical fault case circuit; wherein determining the circuit similarity index between the target circuit and the preselected historical fault case circuit comprises: obtaining a first circuit diagram of the target circuit and a second circuit diagram of the preselected historical fault case, and determining a circuit similarity index between the first circuit diagram and the second circuit diagram based on a preset circuit diagram comparison template; The historical fault case determination submodule is used to take the corresponding pre-selected historical fault case as the historical fault case if the circuit similarity index is greater than or equal to a preset circuit similarity index threshold.

4. The intelligent micro-break control device according to claim 3, characterized in that: The circuit similarity index determination submodule includes: A circuit device similarity index determination unit is used to determine the circuit device similarity index based on the circuit diagram comparison template; the circuit device similarity index is determined by multiplying the similarity degree of each type of device and the device action weight and summing the results; A circuit equivalent value determination unit, configured to determine a circuit equivalent value based on a circuit diagram comparison template; The circuit similarity index calculation unit is used for accumulating and calculating the circuit device similarity index and the circuit equivalent value to obtain the circuit similarity index.

5. The intelligent micro-break control device according to claim 1, characterized in that: The judgment result determination subsystem includes: A fault handling measure acquisition module is used to obtain fault handling measures according to the fault determination; The judgment result acquisition module is used to obtain the judgment result according to the fault handling measures.

6. The intelligent micro-break control device according to claim 5, characterized in that: The fault handling measure acquisition module includes: The first measure acquisition submodule is configured to determine a fault handling measure based on deep learning technology; wherein determining the fault handling measure based on deep learning technology includes: determining the fault handling measure based on the determined fault and the target circuit based on the deep learning technology; and / or, The second measure acquisition submodule is used to determine the fault handling measures based on the big database; wherein, determining the fault handling measures based on the big database includes: determining the pre-selected fault handling measures based on the determined fault and the big database, sending the pre-selected fault handling measures to the management node of the target circuit, and obtaining the fault handling measures replied by the management node.

7. The intelligent micro-break control device according to claim 1, characterized in that: The intelligent micro-break control subsystem includes: The first micro-circuit breaker control module is used to control the micro-circuit breaker to conduct if the fault is resolved; The second micro-breaker control module is used to keep the micro-circuit breaker disconnected and perform corresponding fault processing if the judgment result is that the fault is not resolved.

8. The intelligent micro-break control device according to claim 7, characterized in that: The second micro-break control module includes: A first processing feature acquisition submodule is configured to extract processing features of the determined fault to obtain a first processing feature if the result of the determination is that the fault is not resolved; A processing type acquisition submodule is used to acquire a processing type of the first processing feature according to a feature label of the first processing feature, where the processing type includes: automated processing and manual processing; The fault handling submodule is used to perform corresponding fault handling according to different processing types.

Images