Circuit data detection methods, devices, electronic equipment and storage media

Abstract

This disclosure provides a circuit data detection method, apparatus, electronic device, and storage medium, relating to the field of data processing technology, and particularly to the field of industrial big data. The specific implementation scheme is as follows: based on multiple historical detection indicators of the circuit detection target, a detection tool for the circuit detection target is determined; using the detection tool, each current detection indicator of the circuit detection target is detected to obtain a first indicator set of the circuit detection target; using objective constraints based on circuit principles, each normal indicator in the first indicator set is detected to obtain a second indicator set of the circuit detection target. Using the embodiments of this disclosure, it is possible to avoid missing abnormal circuit indicators.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more particularly to the field of industrial big data, specifically to a circuit data detection method, apparatus, electronic device, and storage medium. Background Technology

[0002] In actual circuits or power grids, it is common to collect indicator values ​​at different times from one or more monitoring points, such as voltage, current, or active power, to measure the operating status of the circuit or power grid. However, due to various reasons, these indicator values ​​may be abnormal. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for detecting circuit data.

[0004] According to one aspect of this disclosure, a method for detecting circuit data is provided, comprising:

[0005] Based on multiple historical detection indicators of the circuit detection target, the detection tool for the circuit detection target is determined;

[0006] Using the aforementioned detection tool, each current detection index of the circuit detection target is detected to obtain a first set of indicators for the circuit detection target;

[0007] By employing objective constraints based on circuit principles, each normal indicator in the first indicator set is detected to obtain the second indicator set of the circuit detection target.

[0008] According to another aspect of this disclosure, a circuit data detection device is provided, comprising:

[0009] The detection tool determination module is used to determine the detection tool for the circuit detection target based on multiple historical detection indicators of the circuit detection target.

[0010] The first detection module is used to use the detection tool to detect each current detection index of the circuit detection target, and obtain a first index set of the circuit detection target;

[0011] The second detection module is used to detect each normal indicator in the first indicator set using objective constraints set based on circuit principles, so as to obtain the second indicator set of the circuit detection target.

[0012] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0013] At least one processor; and

[0014] The memory is communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods in any embodiment of this disclosure.

[0016] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods of any embodiment of this disclosure.

[0017] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods of any embodiment of this disclosure.

[0018] According to the technology disclosed herein, it is possible to avoid missing abnormal circuit indicators and improve the accuracy of circuit indicator detection.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0020] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0021] Figure 1 This is a flowchart of a circuit data detection method according to an embodiment of the present disclosure;

[0022] Figure 2 This is a schematic diagram of a circuit data detection method according to another embodiment of the present disclosure;

[0023] Figure 3 This is a structural block diagram of a circuit data detection device according to an embodiment of the present disclosure;

[0024] Figure 4 This is a structural block diagram of a circuit data detection device according to another embodiment of the present disclosure;

[0025] Figure 5 This is a block diagram of an electronic device that implements the data detection method of the embodiments of this disclosure. Detailed Implementation

[0026] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0027] In practical power supply circuits, the electrical power supplied to the load includes two types: active power and reactive power. Active power is the electrical power required to maintain the normal operation of electrical equipment; that is, the electrical power that converts electrical energy into other forms of energy, such as mechanical energy, light energy, and heat energy. For example, a motor with an active power of 5.5 kilowatts can convert 5.5 kilowatts of electrical energy into corresponding mechanical energy to drive a water pump or a threshing machine; various lighting devices convert electrical energy into light energy to provide illumination for people's lives and work.

[0028] Therefore, the active power of electrical equipment is a very important indicator that power grid companies pay close attention to, and it plays a vital role in people's daily lives. Active power can be divided into high-voltage side, medium-voltage side, and low-voltage side, with the value on the high-voltage side being the most important indicator.

[0029] In actual power grid operation, due to various reasons, the active power data collected on the high-voltage side may be abnormal, mainly including the following three situations:

[0030] First, data jumps. The value at a certain moment changes significantly compared to the value at the previous moment;

[0031] Secondly, data is missing. Values ​​at a certain point in time were not collected.

[0032] Third, the value remains unchanged. Theoretically, the value at a certain monitoring point in the power grid changes dynamically at every moment. If the value collected remains unchanged over a period of time, this is also an anomaly.

[0033] The latter two types of anomalies are relatively easy to identify. However, the first type of anomaly is difficult to identify because the evaluation criteria for data jumps are not uniform or constant. If multiple detection indicators are used to detect data jump anomalies, and too few anomalies are detected, it indicates that there are missed anomalies among these indicators. Moreover, the detection methods used to determine whether an indicator is a jump anomaly are manually set or based on simple rules, which is also one of the reasons for missed detections.

[0034] Therefore, this disclosure provides a circuit data detection method to avoid missed detections.

[0035] Figure 1 This is a flowchart of a circuit data detection method according to an embodiment of the present disclosure.

[0036] like Figure 1 As shown, the circuit data detection method may include:

[0037] S110 is a testing tool that determines the circuit testing target based on multiple historical testing indicators of the circuit testing target.

[0038] S120, using a testing tool, detect each current testing index of the circuit testing target to obtain the first index set of the circuit testing target;

[0039] S130: Using objective constraints set based on circuit principles, each normal indicator in the first indicator set is detected to obtain the second indicator set of the circuit detection target.

[0040] For example, the target of circuit testing may include a testing point in a circuit or power grid, or a device or equipment. The testing point may include a current output terminal, a current input terminal, etc.

[0041] For example, the detection indicators may include voltage, current, active power, and reactive power.

[0042] For example, historical monitoring metrics may include monitoring metrics for each moment within a set time period such as the past week, month, or quarter, or for each specified data collection moment. For instance, the active power of a user equipment at each moment within the past week.

[0043] For example, historical detection indicators may include indicators that have been detected and determined to be normal in the past. For example, historical detection indicators determined based on steps S110 and S120 as described above, or historical detection indicators determined based on steps S110 to S130 as described above.

[0044] For example, historical and current detection indicators belong to the same category. The difference lies in the data collection time of the historical and current indicators. Detection tools determined based on historical detection indicators can detect any other indicator within the same category as the historical indicators.

[0045] For example, a detection tool is a basis for screening or determining anomalies in detection indicators. Detection tools may include detection models, detection standards, detection conditions, or detection strategies.

[0046] For example, the first set of indicators may include the detection result of each detection indicator currently being detected, the detection result including whether the detection indicator is a normal indicator or an abnormal indicator. The second set of indicators may include the detection result of each detection indicator currently being detected.

[0047] For example, the circuit principle may include the law of conservation of energy, Kirchhoff's voltage or current law, etc., and the objective constraints may include voltage constraints for voltage detection, current constraints for current detection, active power constraints for active power detection, and reactive power constraints for reactive power detection, etc.

[0048] In this embodiment, a detection tool is determined based on multiple historical detection indicators of the circuit detection target. This tool is then used to determine whether each current detection indicator is abnormal. For indicators determined to be normal, objective constraints based on circuit principles are further used to verify whether the indicator is an abnormal indicator, thereby accurately avoiding missed detections of anomalies.

[0049] For example, the above-mentioned testing tools may include testing standards. Therefore, in step S110, the testing tool for determining the testing target based on multiple historical testing indicators of the circuit testing target may include:

[0050] Based on the time characteristics of each historical detection index among multiple historical detection indices of the circuit detection target, at least one standard detection index is determined among the multiple historical detection indices.

[0051] Based on at least one standard testing index, determine the testing standard for the circuit testing target.

[0052] In this example, one or more standard detection indicators are selected from multiple historical detection indicators based on time characteristics. Using such standard detection indicators to determine the detection standard is beneficial to improving the accuracy of anomaly detection.

[0053] In some embodiments, indicators with first-time characteristics can be selected from historical detection indicators as standard detection indicators. For example, indicators from different dates but at the same time point can be selected as standard detection indicators, or indicators from different dates but within the same time range can be selected as standard detection indicators.

[0054] For example, each of the at least one standard detection indicator has the same time characteristic. For example, detection indicators whose data collection time is between 9:00 AM and 10:00 AM, or detection indicators whose data collection time is at 12:00 PM.

[0055] In some embodiments, since the detection standard is time-dependent, using this detection standard to detect indicators with the same characteristics can further improve the accuracy of anomaly detection.

[0056] For example, in step S120 above, using a detection tool to detect each current detection index of the circuit detection target to obtain a first index set of the circuit detection target may include:

[0057] Based on the time characteristics of at least one standard detection index, at least one target detection index is determined from multiple current detection indexes of the circuit detection target.

[0058] Based on the detection standard, each of the at least one target detection index is detected to obtain the first index set of the circuit detection target.

[0059] In this example, target detection indicators are selected based on the time characteristics corresponding to the benchmark, making the detection using the benchmark more targeted and improving the accuracy of anomaly detection.

[0060] For example, assuming the standard detection indicator has a time characteristic of collection time between 9:00 and 10:00 on the same day, the collection date of the target detection indicator can be different from that of the standard detection indicator, but the collection time is between 9:00 and 10:00 on the same day.

[0061] During testing, if a target detection indicator does not meet the detection standard, it is marked as an abnormal indicator in the first indicator set. If the target detection indicator meets the detection standard, it is marked as a normal indicator in the first indicator set.

[0062] In some embodiments, the detection tool may include a detection model, which is used to detect current detection indicators.

[0063] For example, the detection tool includes a detection model. In step S110 above, the detection tool for determining the circuit detection target based on multiple historical detection indicators of the circuit detection target may include:

[0064] Based on multiple historical detection indicators of the circuit detection target and the labeled value corresponding to each of the multiple historical detection indicators, the established detection model is trained to obtain the detection model of the circuit detection target; wherein, the labeled value indicates whether the historical detection indicator is an abnormal indicator or a normal indicator.

[0065] In this example, training the detection model using multiple historical detection metrics yields a model with satisfactory accuracy. Therefore, using such a model to detect current metrics helps improve the accuracy of anomaly detection.

[0066] During training, historical detection metrics are output to the detection model to obtain predicted values. These predicted values ​​indicate whether the input historical detection metrics are abnormal or normal. The predicted values ​​are compared with the labeled values ​​corresponding to the input historical detection metrics. If the difference between them meets the set conditions, the training of the detection model can be stopped. If the difference between them does not meet the set conditions, the training step is returned to continue training the detection model.

[0067] After obtaining the trained detection model, in step S120 above, the current detection index is input into the detection model to obtain a predicted value indicating whether the current detection index is an abnormal or normal index. This predicted value can be a binary classification value or a probability value.

[0068] After obtaining the first set of indicators for the circuit detection target according to the method provided in the above embodiments, the normal indicators in the first set of indicators can be further verified based on the objective constraints set by the circuit principle.

[0069] In some embodiments, the circuit principle can be the law of conservation of energy, and the active power constraint conditions of the target to be detected by the circuit can be determined based on the law of conservation of energy.

[0070] For example, the objective constraints include the sum of the active power on both sides of the circuit detection target being a value within a set range;

[0071] In step S130 above, objective constraints based on circuit principles are used to detect normal indicators in the first indicator set, resulting in a second indicator set for the circuit detection target, including:

[0072] If the first set of indicators includes the active power on the first side and the active power on the first side is a normal indicator, determine the active power on the second side of the circuit detection target.

[0073] If the sum of the active power on the first side and the active power on the second side is not a value within a set range, the active power on the first side in the second set of indicators for circuit detection targets is determined to be abnormal.

[0074] In this example, by utilizing the objective constraint that the sum of the active power on both sides of the target detected by the circuit is a value within a set range, the normal indicators in the first set of indicators are re-verified, which can effectively avoid missed detections.

[0075] Ideally, the sum of the active power on both sides of the target detected by the circuit is zero. In practical applications, however, active power is subject to losses when it is converted into a specific form of energy. Therefore, the sum of the active power on both sides of the target detected by the circuit is a range or interval close to zero.

[0076] For example, the active power on the first side can be the active power on the input side of the target detected by the circuit, and the active power on the second side can be the active power on the output side of the target detected by the circuit. Alternatively, the two can be reversed.

[0077] Figure 2 This is a schematic diagram of a circuit data detection method according to another embodiment of this disclosure. Figure 2 As shown, the method includes the following steps:

[0078] The first step is information acquisition. Sensors or detection devices are used to collect the indicators of the target in the circuit, obtaining the indicators of the target at each moment.

[0079] The second step involves performing anomaly detection on each of the following four detection strategies to obtain a set of anomaly indicators corresponding to each detection strategy.

[0080] The first detection strategy: a strategy based on strong rules.

[0081] The current detection index is compared with the detection index at the previous moment. Based on the comparison results and the set detection standards, it is determined whether the current detection index is an abnormal index.

[0082] The testing standards include:

[0083] If the current detection index is greater than or less than the detection index at the previous moment by a set ratio, the current detection index will be identified as an abnormal index.

[0084] If the absolute value of the difference between the current detection index and the previous detection index is greater than the set threshold, the current detection index will be identified as an abnormal index.

[0085] The detection indicators from the previous moment cannot be abnormal.

[0086] The second detection strategy: a statistical strategy.

[0087] Based on the 3-sigma principle and box plot principles, each detection indicator is checked to determine whether it is an abnormal indicator. It's important to note that in the power grid scenario, the upper and lower limits of these two principles need to be determined, and these values ​​are based on data within a defined time range. Arbitrary data cannot be used directly. This is because the values ​​of power grid detection indicators are strongly correlated with time. For example, the active power of the same electrical equipment may differ significantly between 9 AM and 9 PM on the same day. Therefore, when using the second detection strategy to detect anomalies, the upper and lower limits of the 3-sigma principle and box plot need to be determined based on data with similar time characteristics. For example, the detection indicators between 9 AM and 10 AM each day are grouped into a set, and the normal value range for the indicators between 9 AM and 10 AM is calculated based on this set. Then, each detection indicator collected between 9 AM and 10 AM is evaluated based on this normal value range to determine whether it is an abnormal indicator. If the indicator is outside this normal value range, it is identified as an abnormal indicator. Similarly, this method can be used to detect data from other points in time.

[0088] The third detection strategy: a strategy based on power grid constraints.

[0089] During the operation of the power grid, there are some objective constraints. For example, when the active power of the target being monitored includes the high-voltage side, the medium-voltage side, and the low-voltage side, the sum of their active power is a value close to zero.

[0090] For a given high-voltage side active power at a specific moment, the corresponding medium-voltage side active power and low-voltage side active power are obtained. If the difference between the sum of the high-voltage side active power, medium-voltage side active power, and low-voltage side active power and zero is within a set range, the high-voltage side active power is determined as a normal indicator; otherwise, it is determined as an abnormal indicator. For example, a large difference is very likely an anomaly.

[0091] The fourth detection strategy: model-based strategy.

[0092] An unsupervised model is used to learn from multiple unlabeled historical detection metrics to obtain the corresponding model. Then, the model is used to detect the input metrics to obtain the detection result of whether the metric is an anomaly.

[0093] Unsupervised models can include isolated forests, principal component analysis (PCA) models, and local outlier factor (LOF) algorithms.

[0094] The third step involves obtaining four sets of abnormal indicators based on the four detection strategies mentioned above. Based on the intersection, union, and difference of the four sets of abnormal indicators, the final list of abnormal points of the detection target is determined.

[0095] In this example, various strategies can be used to detect anomalies in the power grid's monitoring indicators, reducing the chance of missed detections.

[0096] Figure 3 This is a structural block diagram of a circuit data detection device according to an embodiment of the present disclosure.

[0097] like Figure 3 As shown, the circuit data detection device may include:

[0098] The detection tool determination module 310 is used to determine the detection tool for the circuit detection target based on multiple historical detection indicators of the circuit detection target;

[0099] The first detection module 320 is used to use the detection tool to detect each current detection index of the circuit detection target, and obtain a first index set of the circuit detection target.

[0100] The second detection module 330 is used to detect each normal indicator in the first indicator set using objective constraints set based on circuit principles, so as to obtain the second indicator set of the circuit detection target.

[0101] Figure 4 This is a structural block diagram of a circuit data detection device according to another embodiment of this disclosure. Figure 4 As shown, the detection tool determination module 410, the first detection module 420 and the second detection module 430 included in the circuit data detection device have the same functions as the detection tool determination module 310, the first detection module 320 and the second detection module 330 in the above embodiment, and will not be described in detail here.

[0102] For example, such as Figure 4 As shown, the detection tool includes a detection standard, and the detection tool determination module 410 includes:

[0103] The standard index determination unit 411 is used to determine at least one standard index among a plurality of historical detection indices based on the time characteristics of each historical detection index among a plurality of historical detection indices of the circuit detection target.

[0104] The detection standard determination unit 412 is used to determine the detection standard of the detection target based on the at least one standard detection index.

[0105] For example, each of the at least one standard detection index has the same time characteristics.

[0106] For example, such as Figure 4 As shown, the first detection module 420 includes:

[0107] The target indicator determination unit 421 is used to determine at least one target detection indicator from multiple current detection indicators of the circuit detection target based on the time characteristics of the at least one standard detection indicator.

[0108] The first anomaly detection unit 422 is used to detect each of the at least one target detection indicators based on the detection standard, so as to obtain a first indicator set of the circuit detection target.

[0109] For example, such as Figure 4 As shown, the detection tool includes a detection model, and the detection tool determination module 410 includes:

[0110] The detection model determination unit 413 is used to train a set detection model based on multiple historical detection indicators of the circuit detection target and the label value corresponding to each of the multiple historical detection indicators to obtain the detection model of the circuit detection target; wherein, the label value indicates whether the historical detection indicator is an abnormal indicator or a normal indicator.

[0111] For example, the objective constraint condition includes the sum of the active power on both sides of the target detected by the circuit being a value within a set range;

[0112] The second detection module 430 includes:

[0113] The power acquisition unit 431 is used to determine the second-side active power of the circuit detection target when the first indicator set includes the first-side active power and the first-side active power is a normal indicator.

[0114] The second anomaly detection unit 432 is used to determine that the first-side active power in the second index set of the circuit detection target is abnormal when the sum of the first-side active power and the second-side active power is not a value in the set range.

[0115] The functions of each unit, module, or sub-module in the various devices of this disclosure embodiment can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here.

[0116] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0117] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0118] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0119] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0120] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the circuit data detection method. For example, in some embodiments, the circuit data detection method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via ROM 102 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the circuit data detection method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the circuit data detection method by any other suitable means (e.g., by means of firmware).

[0121] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to the processor or controller of a general-purpose computer, special-purpose computer, or other programmable circuit data detection device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0124] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0125] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0126] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0127] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0128] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for detecting circuit data, comprising: Based on multiple historical detection indicators of the circuit detection target, the detection tool for the circuit detection target is determined; Using the aforementioned detection tool, each current detection index of the circuit detection target is detected to obtain a first index set of the circuit detection target; the first index set includes the detection result of each detection index, and the detection result includes whether the detection index is a normal index or an abnormal index; Using objective constraints based on circuit principles, each normal indicator in the first indicator set is detected to verify whether the normal indicator is an abnormal indicator, thereby obtaining the second indicator set of the circuit detection target. The objective constraint condition includes that the sum of the active power on both sides of the target detected by the circuit is a value within a set range. The method employs objective constraints based on circuit principles to detect normal indicators in the first indicator set, thereby obtaining a second indicator set for the circuit detection target, including: If the first set of indicators includes the first-side active power and the first-side active power is a normal indicator, then the second-side active power of the circuit detection target is determined; wherein, the first-side active power is the active power on the input side of the circuit detection target, and the second-side active power is the active power on the output side of the circuit detection target, or, the first-side active power is the active power on the output side of the circuit detection target, and the second-side active power is the active power on the input side of the circuit detection target; If the sum of the active power on the first side and the active power on the second side is not a value within the set range, the active power on the first side in the second set of indicators of the circuit detection target is determined to be abnormal.

2. The method according to claim 1, wherein, The detection tool includes detection standards. The detection tool, which determines the detection target based on multiple historical detection indicators of the circuit detection target, includes: Based on the time characteristics of each of the multiple historical detection indicators of the circuit detection target, at least one standard detection indicator is determined among the multiple historical detection indicators. Based on the at least one standard detection index, the detection standard for the circuit detection target is determined.

3. The method according to claim 2, wherein, Each of the at least one standard detection index has the same time characteristics.

4. The method according to claim 2 or 3, wherein, The method involves using the detection tool to detect each current detection index of the circuit detection target, thereby obtaining a first set of indicators for the circuit detection target, including: Based on the time characteristics of the at least one standard detection index, at least one target detection index is determined from the multiple current detection indexes of the circuit detection target. Based on the detection standard, each of the at least one target detection index is detected to obtain a first set of indicators for the circuit detection target.

5. The method according to claim 1, wherein, The detection tool includes a detection model. The detection tool, which determines the circuit detection target based on multiple historical detection indicators, includes: Based on multiple historical detection indicators of the circuit detection target and the labeled value corresponding to each of the multiple historical detection indicators, the set detection model is trained to obtain the detection model of the circuit detection target; wherein, the labeled value indicates whether the historical detection indicator is an abnormal indicator or a normal indicator.

6. A circuit data detection device, comprising: The detection tool determination module is used to determine the detection tool for the circuit detection target based on multiple historical detection indicators of the circuit detection target. The first detection module is used to use the detection tool to detect each current detection index of the circuit detection target, and obtain a first index set of the circuit detection target; the first index set includes the detection result of each detection index, and the detection result includes whether the detection index is a normal index or an abnormal index; The second detection module is used to detect each normal indicator in the first indicator set using objective constraints set based on circuit principles, verify whether the normal indicator is an abnormal indicator, and obtain the second indicator set of the circuit detection target. The objective constraint condition includes that the sum of the active power on both sides of the target detected by the circuit is a value within a set range. The second detection module includes: A power acquisition unit is configured to determine the second-side active power of the circuit detection target when the first indicator set includes the first-side active power and the first-side active power is a normal indicator; wherein the first-side active power is the active power on the input side of the circuit detection target and the second-side active power is the active power on the output side of the circuit detection target, or the first-side active power is the active power on the output side of the circuit detection target and the second-side active power is the active power on the input side of the circuit detection target; The second anomaly detection unit is used to determine that the first-side active power in the second index set of the circuit detection target is abnormal when the sum of the first-side active power and the second-side active power is not a value in the set range.

7. The apparatus according to claim 6, wherein, The detection tool includes a detection standard, and the detection tool determination module includes: A standard indicator determination unit is used to determine at least one standard detection indicator among a plurality of historical detection indicators of a circuit detection target based on the time characteristics of each historical detection indicator. The detection standard determination unit is used to determine the detection standard of the circuit detection target based on the at least one standard detection index.

8. The apparatus according to claim 7, wherein, Each of the at least one standard detection index has the same time characteristics.

9. The apparatus according to claim 7 or 8, wherein, The first detection module includes: A target indicator determination unit is used to determine at least one target detection indicator from multiple current detection indicators of the circuit detection target based on the time characteristics of the at least one standard detection indicator. The first anomaly detection unit is used to detect each of the at least one target detection index based on the detection standard, so as to obtain a first index set of the circuit detection target.

10. The apparatus according to claim 6, wherein, The detection tool includes a detection model, and the detection tool determination module includes: The detection model determination unit is used to train a set detection model based on multiple historical detection indicators of the circuit detection target and the label value corresponding to each of the multiple historical detection indicators to obtain the detection model of the circuit detection target; wherein, the label value indicates whether the historical detection indicator is an abnormal indicator or a normal indicator.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

12. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images