Intelligent electric energy meter state detection method and device based on power consumption collection terminal

Abstract

The present invention belongs to the technical field of intelligent power meter detection, and discloses a method and device for detecting the state of an intelligent power meter based on an electricity consumption collection terminal. The method comprises: the electricity consumption collection terminal collects the original operation data of the intelligent power meter, and processes the original operation data to obtain the processed operation data; performs data abnormal value judgment on the processed operation data; constructs a fault data set based on the judgment result; determines the correlation between the fault type and the fault characteristic attribute according to the fault data set, and screens out a fault characteristic subset from the processed operation data based on the correlation; and performs state detection on the intelligent power meter based on the fault characteristic subset. In the above manner, the operation data is first cleaned, and then the intelligent power meter is detected in combination with the correlation between different fault types and fault attributes, thereby improving the accuracy of detection.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent electric energy meter detection, and in particular to an intelligent electric energy meter state detection method and device based on an electricity consumption collection terminal. Background Art

[0002] Economic development and technological progress have further promoted the construction of smart grids. As an important part of the electricity consumption information collection system, the reliability and collection accuracy of smart electricity meters have become the most concerned objects of power departments and users. How to accurately detect the status of smart electricity meters based on the status data displayed by them is a problem to be solved in the field of smart electricity meter health management.

[0003] Currently, detection is performed based on fault data through machine learning algorithms. However, due to the complex structure of smart electricity meter fault data, the amount of sample data under different fault types is extremely uneven, and different machine learning algorithms have different advantages and disadvantages, and their recognition capabilities for different types of faults are also different. However, the current status detection of smart electricity meters does not take into account the correlation between different fault characteristics and fault types, resulting in low detection accuracy.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide a method and device for detecting the state of an intelligent electric energy meter based on an electricity collection terminal, aiming to solve the technical problem that the current state detection of the intelligent electric energy meter does not take into account the correlation between different fault characteristics and fault types, resulting in low detection accuracy.

[0006] To achieve the above object, the present invention provides a method for detecting the state of an intelligent electric energy meter based on an electric energy collection terminal, and the method for detecting the state of an intelligent electric energy meter based on an electric energy collection terminal comprises the following steps:

[0007] The power consumption collection terminal collects the original operation data of the smart power meter, and processes the original operation data to obtain processed operation data;

[0008] Performing data outlier judgment on the processed operating data;

[0009] Construct a fault data set based on the judgment results;

[0010] Determining the degree of association between the fault type and the fault characteristic attribute according to the fault data set, and filtering out a fault characteristic subset from the processed operation data based on the degree of association;

[0011] The state of the smart electric energy meter is detected based on the fault feature subset.

[0012] In some embodiments, the processing the original operation data to obtain processed operation data includes:

[0013] identifying missing data in the raw operational data;

[0014] Obtaining the mean and variance corresponding to the original running data;

[0015] constructing supplementary data according to the mean and the variance, wherein the supplementary data is normally distributed data;

[0016] The missing data is completed based on the supplementary data to obtain processed operating data.

[0017] In some embodiments, the completing the missing data based on the supplementary data to obtain processed operating data includes:

[0018] Determine the data type of the missing data;

[0019] Screening data of the same type as the missing data from the supplementary data;

[0020] The data of the same type are completed based on the missing data corresponding to the missing data.

[0021] In some embodiments, the step of determining data outliers on the processed operating data includes:

[0022] determining a number of quartiles based on the processed operating data;

[0023] Select the first quartile and the third quartile from a number of quartiles;

[0024] Calculate the difference between the first quartile and the third quartile;

[0025] A data outlier judgment range is constructed using the difference, the first quartile, and the third quartile, wherein the lower limit of the data outlier judgment range is determined by the first quartile and the difference, and the upper limit of the data outlier judgment range is determined by the difference and the third quartile.

[0026] In some embodiments, determining the correlation between the fault type and the fault characteristic attribute according to the fault data set includes:

[0027] Get any fault feature attribute λ in the fault data set k And any fault type y i;

[0028] Calculate the correlation degree ρ according to the arbitrary fault characteristic attribute and the arbitrary fault type y k ,Place

[0029] The calculation formula of the correlation is: .

[0030] In some embodiments, the performing status detection on the smart electric energy meter based on the fault feature subset includes:

[0031] Initialize various parameters of GWO and WOA algorithms;

[0032] Update the individual position information of the wolf pack in GWO and the individual position information of the whale in WOA, wherein the individual position information of the wolf pack or the individual position information of the whale corresponds to the parameter combination of the decomposition scale K and the penalty factor α of VMD;

[0033] The combination of K and α parameters is used to perform VMD decomposition, and the Ec value of each IMF obtained after VMD decomposition is calculated;

[0034] Determine whether the iteration stop conditions of the GWO and WOA algorithms are met. If so, output the target K and α parameter combination;

[0035] Perform VMD decomposition on the fault feature subset using the target K and α parameter combination to obtain K IMF components, and calculate dimensionless indicators corresponding to the IMF components to obtain a fault feature vector;

[0036] The fault feature vector is input into a pre-created fault detector for fault detection.

[0037] In some embodiments, the method further comprises:

[0038] Initializing algorithm parameters and randomly generating an initial antibody population, wherein the algorithm parameters at least include antibody population size, crossover probability, mutation probability, and termination condition;

[0039] Calculating the affinity between each antigen and antibody in the initial antibody group, and sorting them from large to small according to affinity, and taking the top N antibodies as memory cells based on the affinity ranking results;

[0040] Antibodies with affinity greater than a threshold are selected for clone selection, where affinity is positively correlated with clone size;

[0041] Perform cross-mutation operations on the antibodies produced after cloning;

[0042] Calculate the affinity between the cross-mutated antibody and antigen, and rank them with the affinity between the parental memory cells and antigen;

[0043] Determine whether the evolution termination condition is met, and if not, return to the step of selecting antibodies with affinity greater than the threshold for clonal selection to update the antibody population, and use the first M antibodies as the initial antibody population of the next generation based on the affinity ranking result until the termination condition is met;

[0044] When the termination condition is met, the generated cross-mutated antibodies are used as fault diagnosis detectors.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a smart electric energy meter state detection device based on an electric energy collection terminal, and the smart electric energy meter state detection device based on an electric energy collection terminal comprises:

[0046] The collection module is used for collecting the original operation data of the smart energy meter through the power collection terminal, and processing the original operation data to obtain the processed operation data;

[0047] A judgment module, used for judging data abnormal values ​​on the processed operation data;

[0048] A construction module, used for constructing a fault data set based on the judgment result;

[0049] A screening module, configured to determine the degree of association between the fault type and the fault characteristic attribute according to the fault data set, and to screen out a fault characteristic subset from the processed operation data based on the degree of association;

[0050] A detection module is used to perform status detection on the smart electric energy meter based on the fault feature subset.

[0051] In some embodiments, the acquisition module is used to identify missing data in the original operation data;

[0052] Obtaining the mean and variance corresponding to the original running data;

[0053] constructing supplementary data according to the mean and the variance, wherein the supplementary data is normally distributed data;

[0054] The missing data is completed based on the supplementary data to obtain processed operating data.

[0055] In some embodiments, the acquisition module is used to determine the data type of the missing data;

[0056] Screening data of the same type as the missing data from the supplementary data;

[0057] The data of the same type are completed based on the missing data corresponding to the missing data.

[0058] The present invention collects the original operation data of the smart energy meter through the power collection terminal, and processes the original operation data to obtain the processed operation data; performs data abnormal value judgment on the processed operation data; constructs a fault data set based on the judgment result; determines the correlation between the fault type and the fault characteristic attribute according to the fault data set, and screens out a fault characteristic subset from the processed operation data based on the correlation; and performs status detection on the smart energy meter based on the fault characteristic subset. In the above manner, the operation data is first cleaned, and then the smart energy meter is detected in combination with the correlation between different fault types and fault attributes, thereby improving the accuracy of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of a first embodiment of a method for detecting a state of an intelligent electric energy meter based on an electric power collection terminal according to the present invention;

[0060] Figure 2 It is a structural block diagram of the first embodiment of the intelligent electric energy meter state detection device based on the electricity consumption collection terminal of the present invention.

[0061] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0062] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0063] The embodiment of the present invention provides a method for detecting the state of an intelligent electric energy meter based on an electric power collection terminal. Figure 1 , Figure 1 The present invention is a flowchart of a first embodiment of a method for detecting the state of an intelligent electric energy meter based on an electric power collection terminal.

[0064] In this embodiment, the smart energy meter state detection method based on the power consumption collection terminal includes the following steps:

[0065] Step S10: The electricity consumption collection terminal collects original operation data of the smart energy meter, and processes the original operation data to obtain processed operation data.

[0066] In this embodiment, the executor of this embodiment is a smart power meter status detection device based on a power consumption collection terminal, wherein the smart power meter status detection device based on a power consumption collection terminal has functions such as data processing, data communication and program running. The smart power meter status detection device based on a power consumption collection terminal can be a computer terminal device or other network device, and of course it can also be other devices with similar functions, and this embodiment does not limit this.

[0067] It should be noted that currently, detection is performed based on fault data through machine learning algorithms. However, due to the complex structure of smart electricity meter fault data, the amount of sample data under different fault types is extremely uneven, and different machine learning algorithms have different advantages and disadvantages, and their recognition capabilities for different types of faults are also different. However, the current status detection of smart electricity meters does not take into account the correlation between different fault characteristics and fault types, resulting in low detection accuracy.

[0068] In order to solve the above technical problems, in this embodiment, the original operation data of the smart energy meter is collected through the power collection terminal, and the original operation data is processed to obtain the processed operation data; the data abnormal value judgment is performed on the processed operation data; a fault data set is constructed based on the judgment result; the correlation between the fault type and the fault characteristic attribute is determined according to the fault data set, and a fault characteristic subset is screened out from the processed operation data based on the correlation; the state of the smart energy meter is detected based on the fault characteristic subset. In the above manner, the operation data is first cleaned, and then the smart energy meter is detected in combination with the correlation between different fault types and fault attributes, which improves the accuracy of the detection, which can be specifically implemented in the following manner.

[0069] In the specific implementation, in this embodiment, the operating data of the smart power meter is first collected through the electricity consumption collection terminal. The collected operating data is the original operating data. In order to improve the accuracy of subsequent detection, in this embodiment, it is necessary to further process the original operating data through the electricity consumption collection terminal to obtain the processed operating data.

[0070] The process of processing the original operation data specifically includes identifying missing data in the original operation data, obtaining the mean and variance corresponding to the original operation data, and constructing supplementary data according to the mean and the variance. The supplementary data is normally distributed data. For example, the mean and the variance can be calculated by means of mean calculation and variance calculation. For example, the mean and the variance of parameter values ​​such as current values ​​or voltage values ​​in the original operation data are calculated. After obtaining the mean and the variance, it is assumed that the mean is μ.

[0071] The variance is σ, and the constructed supplementary data is N (μ, σ) = , where X represents

[0072] The missing data is shown, and the supplementary data is the normal distribution corresponding to the missing data. Different missing data X can find corresponding supplementary data based on the normal data. Finally, the missing data is completed based on the supplementary data to obtain the processed operation data. It should be noted that the normal distribution of the above supplementary data can obtain the specific missing value corresponding to the missing data. In order to make the completion more accurate, the data type of the missing data needs to be determined in this embodiment, and then the data of the same type is searched from the supplementary data based on the data type. After the data type and data value are determined, the corresponding completion can be performed.

[0073] Step S20: performing data outlier determination on the processed operating data.

[0074] Step S30: constructing a fault data set based on the judgment result.

[0075] It is easy to understand that state detection and fault detection need to be based on abnormal data in the operating data. In this embodiment, it is necessary to first determine several quartiles contained in the processed operating data, such as the first quartile, the second quartile and the third quartile, where the first quartile indicates that 25% of the data points in the data set are less than or equal to this value, and 75% of the data points are greater than this value, the second quartile indicates that the data set is divided into two halves, 50% of the data points are less than or equal to this value, and the other 50% are greater than or equal to this value, and the third quartile indicates that 75% of the data points in the data set are less than or equal to this value, and 25% of the data points are greater than this value. In this embodiment, the first quartile and the third quartile are selected, that is, the first quartile and the third quartile mentioned above, and then the difference between them is calculated. The data outlier judgment range can be determined by combining the difference and the first quartile and the third quartile mentioned above. Specifically, the lower limit of the data outlier judgment range is determined by the first quartile and the difference, and the upper limit of the data outlier judgment range is determined by the difference and the third quartile. For example, assuming that the first quartile is Q1, the third quartile is Q3, the difference is Q3-Q1, and the data outlier judgment range is [Q1-1.25(Q3-Q1), Q3+1.25(Q3-Q1)]. The coefficient 1.25 in the data outlier judgment range can be adjusted accordingly according to actual needs, and this is not limited in this embodiment.

[0076] Based on the judgment results, outliers in the processed operating data can be determined. These outliers represent corresponding fault data, and a fault data set can be further constructed.

[0077] Step S40: determining the correlation between the fault type and the fault characteristic attribute according to the fault data set, and filtering out a fault characteristic subset from the processed operation data based on the correlation.

[0078] The fault data set constructed above is D={(x1,y1),(x2,y2),...,(x n ,y n )}, where xi represents the characteristic attribute information of the i-th sample, its dimension is N, n represents the number of samples in the fault data set, and y i represents the fault type of the i-th sample, and the dimension of any fault sample is N + 1. In the i-th sample, the relationship between each feature attribute and the fault type is ri = [ρ1, ρ2…ρ k …ρ N ], where ρ k represents the correlation between the kth fault feature attribute and the fault type, ρ k The calculation formula is as follows:

[0079]

[0080] in, It represents the kth fault feature attribute.

[0081] Step S50: performing status detection on the smart electric energy meter based on the fault feature subset.

[0082] After obtaining the fault feature subset, the Grey Wolf Optimizer (GWO) and the Whale Optimization Algorithm (WOA) are used in this embodiment to construct the feature vector. Specifically, various parameters of the GWO and WOA algorithms are initialized, and then the individual position information of the wolf group in the GWO and the individual position information of the whale in the WOA are updated. At this time, the individual position information of the wolf group or the individual position information of the whale corresponds to the decomposition scale K and the penalty factor α parameter combination of the variational mode decomposition (VMD). The K and α parameter combination is used to perform VMD decomposition, and the Ec value of each IMF obtained after VMD decomposition is calculated. IMF is also the intrinsic mode function. The Ec value is used to evaluate the IMF convergence and decomposition quality during the VMD decomposition process. Ec=|| ||, is the value of the kth IMF at the nth iteration.

[0083] Then, it is further determined whether the iteration stop conditions of the GWO and WOA algorithms are met. If so, the target K and α parameter combination is output. Finally, the fault feature subset is subjected to VMD decomposition using the target K and α parameter combination to obtain K IMF components. The IMF components are dimensionlessly processed, i.e., standardized, to obtain the fault feature vector. Finally, the fault feature vector is input into the pre-created fault detector for fault detection.

[0084] In some embodiments, the fault diagnosis detector creation process is specifically to initialize algorithm parameters and randomly generate an initial antibody group, wherein the algorithm parameters include at least antibody population size, crossover probability, mutation probability and termination condition; calculate the affinity of each antigen and antibody in the initial antibody group, the calculation method may be binary coding, real number coding and attribute matching, etc., which is not limited in this embodiment, and sort them from large to small according to affinity, and take the top N antibodies as memory cells based on the affinity sorting result, that is, the top N antibodies with higher affinity as memory cells; select antibodies with affinity greater than a threshold for cloning selection operation, such as replicating the antibodies multiple times, wherein affinity is positively correlated with cloning scale; perform crossover mutation operation on the antibodies generated after cloning, the crossover operation is to randomly select two antibodies from the selected antibodies for crossover, and the mutation operation may include randomly changing certain parts of the antibody, such as certain genes or attribute values ​​in the antibody encoding, and new variants may be introduced through mutation to increase the diversity of the antibody population; Calculate the affinity of the antibody and antigen after cross-mutation, and sort them with the affinity of the parent memory cell and antigen; determine whether the evolution termination condition is met, and if not, return to the step of selecting antibodies with affinity greater than the threshold for clonal selection to update the antibody population, and use the top M antibodies (i.e., the top M antibodies with higher affinity) as the initial antibody population of the next generation based on the affinity ranking result until the termination condition is met;

[0085] When the termination condition is met, the generated cross-mutated antibodies are used as fault diagnosis detectors. The antibodies here are excellent antibodies. For example, assuming that the first M antibodies meet the termination condition as the initial antibody group of the next generation, then L antibodies with affinity greater than the threshold are selected from the M antibodies, and the antibodies generated after cloning are subjected to cross-mutation operations. The cross-mutated antibodies finally generated are excellent antibodies.

[0086] This embodiment collects the original operation data of the smart energy meter through the power collection terminal, and processes the original operation data to obtain processed operation data; performs data abnormal value judgment on the processed operation data; constructs a fault data set based on the judgment result; determines the correlation between the fault type and the fault characteristic attribute according to the fault data set, and screens out a fault characteristic subset from the processed operation data based on the correlation; and performs status detection on the smart energy meter based on the fault characteristic subset. In the above manner, the operation data is first cleaned, and then the smart energy meter is detected in combination with the correlation between different fault types and fault attributes, thereby improving the accuracy of detection.

[0087] Reference Figure 2 , Figure 2 It is a structural block diagram of the first embodiment of the intelligent electric energy meter state detection device based on the electricity consumption collection terminal of the present invention.

[0088] like Figure 2 As shown, the smart electric energy meter state detection device based on the power consumption collection terminal proposed in the embodiment of the present invention includes:

[0089] The collection module 10 is used for the electricity collection terminal to collect the original operation data of the smart energy meter and process the original operation data to obtain processed operation data.

[0090] The judgment module 20 is used to judge whether there are abnormal values ​​in the processed operation data.

[0091] The construction module 30 is used to construct a fault data set based on the judgment result.

[0092] The screening module 40 is used to determine the correlation between the fault type and the fault characteristic attribute according to the fault data set, and screen out the fault characteristic subset from the processed operation data based on the correlation.

[0093] The detection module 50 is used to perform status detection on the smart electric energy meter based on the fault feature subset.

[0094] This embodiment collects the original operation data of the smart energy meter through the power collection terminal, and processes the original operation data to obtain processed operation data; performs data abnormal value judgment on the processed operation data; constructs a fault data set based on the judgment result; determines the correlation between the fault type and the fault characteristic attribute according to the fault data set, and screens out a fault characteristic subset from the processed operation data based on the correlation; and performs status detection on the smart energy meter based on the fault characteristic subset. In the above manner, the operation data is first cleaned, and then the smart energy meter is detected in combination with the correlation between different fault types and fault attributes, thereby improving the accuracy of detection.

[0095] In some embodiments, the acquisition module 10 is used to identify missing data in the original operating data; obtain the mean and variance corresponding to the original operating data; construct supplementary data based on the mean and the variance, and the supplementary data is normally distributed data; and complete the missing data based on the supplementary data to obtain processed operating data.

[0096] In some embodiments, the acquisition module 10 is used to determine the data type of the missing data; filter data of the same type as the missing data from the supplementary data; and complete the data of the same type based on the missing corresponding to the missing data.

[0097] In some embodiments, the judgment module 20 is used to determine a number of quartiles based on the processed operating data; select a first quartile and a third quartile from the number of quartiles; calculate the difference between the first quartile and the third quartile; construct a data outlier judgment range with the difference, the first quartile and the third quartile, the lower limit of the data outlier judgment range is determined by the first quartile and the difference, and the upper limit of the data outlier judgment range is determined by the difference and the third quartile.

[0098] In some embodiments, the screening module 40 is used to obtain any fault characteristic attribute λ in the fault data set. k And any fault type y i According to the arbitrary fault characteristic attribute and the arbitrary

[0099] Calculate the correlation degree ρ of the fault type y k , the correlation calculation formula is: .

[0100] In some embodiments, the detection module 50 is used to initialize various parameters of the GWO and WOA algorithms; update the individual position information of the wolf pack in GWO and the individual position information of the whale in WOA, the individual position information of the wolf pack or the individual position information of the whale corresponding to the decomposition scale K and penalty factor α parameter combination of VMD; use the K and α parameter combination to perform VMD decomposition, and calculate the Ec value of each IMF obtained after VMD decomposition; determine whether the iteration stop condition of the GWO and WOA algorithms is met, and if so, output the target K and α parameter combination; use the target K and α parameter combination to perform VMD decomposition on the fault feature subset, decompose to obtain K IMF components, and calculate the dimensionless index corresponding to the IMF component to obtain a fault feature vector; input the fault feature vector into a pre-created fault detector for fault detection.

[0101] In some embodiments, the detection module 50 is used to initialize algorithm parameters and randomly generate an initial antibody population, wherein the algorithm parameters include at least the size of the antibody population, the crossover probability, the mutation probability, and the termination condition; calculate the affinity between each antigen and antibody in the initial antibody population, and sort them from large to small according to the affinity, and use the first N antibodies as memory cells based on the affinity sorting result; select antibodies with an affinity greater than a threshold for cloning selection operation, wherein the affinity is positively correlated with the cloning size; perform a crossover mutation operation on the antibodies generated after cloning; calculate the affinity of the crossover-mutated antibodies and antigens, and sort them with the affinity of the parent memory cells and antigens; determine whether the evolution termination condition is met, and if not, return to the step of selecting antibodies with an affinity greater than the threshold for cloning selection operation to update the antibody population, and use the first M antibodies as the initial antibody population of the next generation based on the affinity sorting result until the termination condition is met; when the termination condition is met, the generated crossover-mutated antibodies are used as fault diagnosis detectors.

[0102] The embodiment of the present application also provides a smart energy meter status detection device based on an electricity consumption collection terminal, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, and the memory is used to store computer programs; the processor is used to implement the above-mentioned smart energy meter status detection method based on the electricity consumption collection terminal when executing the program stored in the memory.

[0103] The communication bus mentioned in the above-mentioned smart energy meter status detection device based on the electricity consumption collection terminal can be a peripheral component interconnect standard (English: Peripheral Component Interconnect, referred to as: PCI) bus or an extended industry standard architecture (English: Extended Industry Standard Architecture, referred to as: EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0104] The communication interface is used for communication between the above-mentioned smart energy meter status detection device based on the electricity consumption collection terminal and other devices.

[0105] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0106] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0107] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0108] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0109] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0110] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0111] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0112] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0113] In addition, for technical details not fully described in this embodiment, reference can be made to the smart energy meter state detection method based on the electricity consumption collection terminal provided in any embodiment of the present invention, and will not be repeated here.

[0114] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0115] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0116] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0117] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0118] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

Claims

1. A method for detecting the state of an intelligent electric energy meter based on an electric power collection terminal, characterized in that: The smart energy meter state detection method based on the power consumption collection terminal includes: The power consumption collection terminal collects the original operation data of the smart power meter, and processes the original operation data to obtain processed operation data; Performing data outlier judgment on the processed operating data; Construct a fault data set based on the judgment results; Determining the degree of association between the fault type and the fault characteristic attribute according to the fault data set, and filtering out a fault characteristic subset from the processed operation data based on the degree of association; Wherein, determining the correlation between the fault type and the fault characteristic attribute according to the fault data set includes: Get any fault feature attribute λ in the fault data set k And any fault type y i ; According to the arbitrary fault characteristic attribute and the arbitrary fault type y i Calculate the correlation ρ k , the correlation calculation formula is: ; Performing status detection on the smart electric energy meter based on the fault feature subset; Wherein, the state detection of the smart electric energy meter based on the fault feature subset further includes: initializing various parameters of GWO and WOA algorithms; Update the individual position information of the wolf pack in GWO and the individual position information of the whale in WOA, wherein the individual position information of the wolf pack or the individual position information of the whale corresponds to the parameter combination of the decomposition scale K and the penalty factor α of VMD; The combination of K and α parameters is used for VMD decomposition, and the Ec value of each IMF obtained after VMD decomposition is calculated, where VMD decomposition is variational mode decomposition. The Ec value is used to evaluate the IMF convergence and decomposition quality during VMD decomposition. Ec=|| ||, is the value of the kth IMF at the nth iteration, where the IMF is the intrinsic mode function; Determine whether the iteration stop conditions of the GWO and WOA algorithms are met. If so, output the target decomposition scale K and penalty factor α parameter combination; Perform VMD decomposition on the fault feature subset using the target decomposition scale K and the penalty factor α parameter combination to obtain K IMF components, and calculate the dimensionless index corresponding to the IMF components to obtain a fault feature vector; The fault feature vector is input into a pre-created fault detector for fault detection.

2. The method for detecting the state of an intelligent electric energy meter based on an electric power collection terminal according to claim 1, characterized in that: The processing of the original operation data to obtain processed operation data includes: identifying missing data in the raw operational data; Obtaining the mean and variance corresponding to the original running data; constructing supplementary data according to the mean and the variance, wherein the supplementary data is normally distributed data; The missing data is completed based on the supplementary data to obtain processed operating data.

3. The method for detecting the state of an intelligent electric energy meter based on an electric power collection terminal according to claim 2, characterized in that: The step of completing the missing data based on the supplementary data to obtain processed operating data includes: Determine the data type of the missing data; Screening data of the same type as the missing data from the supplementary data; The data of the same type are completed based on the missing data corresponding to the missing data.

4. The method for detecting the state of an intelligent electric energy meter based on an electric power collection terminal according to claim 1, characterized in that: The step of judging data abnormality on the processed operation data includes: determining a number of quartiles based on the processed operating data; Select the first quartile and the third quartile from a number of quartiles; Calculate the difference between the first quartile and the third quartile; A data outlier judgment range is constructed using the difference, the first quartile, and the third quartile, wherein the lower limit of the data outlier judgment range is determined by the first quartile and the difference, and the upper limit of the data outlier judgment range is determined by the difference and the third quartile.

5. The method for detecting the state of an intelligent electric energy meter based on an electric power collection terminal according to claim 1, characterized in that: The method further comprises: Initializing algorithm parameters and randomly generating an initial antibody population, wherein the algorithm parameters at least include antibody population size, crossover probability, mutation probability, and termination condition; Calculating the affinity between each antigen and antibody in the initial antibody group, and sorting them from large to small according to affinity, and taking the top N antibodies as memory cells based on the affinity ranking results; Antibodies with affinity greater than a threshold are selected for clone selection, where affinity is positively correlated with clone size; Perform cross-mutation operations on the antibodies produced after cloning; Calculate the affinity between the cross-mutated antibody and antigen, and rank them with the affinity between the parental memory cells and antigen; Determine whether the evolution termination condition is met, and if not, return to the step of selecting antibodies with affinity greater than the threshold for clonal selection to update the antibody population, and use the first M antibodies as the initial antibody population of the next generation based on the affinity ranking result until the termination condition is met; When the termination condition is met, the generated cross-mutated antibodies are used as fault diagnosis detectors.

6. A smart electric energy meter state detection device based on an electric power collection terminal, characterized in that: The smart electric energy meter state detection device based on the electricity consumption collection terminal includes: The collection module is used for collecting the original operation data of the smart energy meter through the power collection terminal, and processing the original operation data to obtain the processed operation data; A judgment module, used for judging data abnormal values ​​on the processed operation data; A construction module, used for constructing a fault data set based on the judgment result; a screening module, configured to determine the correlation between the fault type and the fault characteristic attribute according to the fault data set, and to screen out a fault characteristic subset from the processed operation data based on the correlation, wherein the screening module is further configured to obtain any fault characteristic attribute λ in the fault data set; k And any fault type y i ; According to the arbitrary fault characteristic attribute and the arbitrary fault type y i Calculate the correlation ρ k , the correlation calculation formula is: ; A detection module, configured to perform status detection on the smart electric energy meter based on the fault feature subset; The detection module is further used to update the individual position information of the wolf pack in GWO and the individual position information of the whale in WOA, wherein the individual position information of the wolf pack or the individual position information of the whale corresponds to the decomposition scale K and penalty factor α parameter combination of VMD; The combination of K and α parameters is used for VMD decomposition, and the Ec value of each IMF obtained after VMD decomposition is calculated, where VMD decomposition is variational mode decomposition. The Ec value is used to evaluate the IMF convergence and decomposition quality during VMD decomposition. Ec=|| ||, is the value of the kth IMF at the nth iteration, where the IMF is the intrinsic mode function; Determine whether the iteration stop conditions of the GWO and WOA algorithms are met. If so, output the target decomposition scale K and penalty factor α parameter combination; Perform VMD decomposition on the fault feature subset using the target decomposition scale K and the penalty factor α parameter combination to obtain K IMF components, and calculate the dimensionless index corresponding to the IMF components to obtain a fault feature vector; The fault feature vector is input into a pre-created fault detector for fault detection.

7. The intelligent electric energy meter state detection device based on the electric energy collection terminal according to claim 6 is characterized in that: The acquisition module is used to identify missing data in the original operation data; Obtaining the mean and variance corresponding to the original running data; constructing supplementary data according to the mean and the variance, wherein the supplementary data is normally distributed data; The missing data is completed based on the supplementary data to obtain processed operating data.

8. The intelligent electric energy meter state detection device based on the electric energy collection terminal according to claim 7 is characterized in that: The acquisition module is used to determine the data type of the missing data; Screening data of the same type as the missing data from the supplementary data; The data of the same type are completed based on the missing data corresponding to the missing data.

9. The intelligent electric energy meter state detection device based on the electric energy collection terminal according to claim 6, characterized in that: The judgment module is used to determine a number of quartiles according to the processed operating data; Select the first quartile and the third quartile from a number of quartiles; Calculate the difference between the first quartile and the third quartile; A data outlier judgment range is constructed using the difference, the first quartile, and the third quartile, wherein the lower limit of the data outlier judgment range is determined by the first quartile and the difference, and the upper limit of the data outlier judgment range is determined by the difference and the third quartile.

Images