Intelligent electric energy meter communication fault early warning method and device

Abstract

The invention belongs to the technical field of communication, and discloses an intelligent electric energy meter communication fault early warning method and device. The method comprises the following steps: acquiring operation state data of the intelligent electric energy meter; performing fault detection on the intelligent electric energy meter according to the operation state data; after detecting that the intelligent electric energy meter has the communication fault, acquiring communication fault data of the intelligent electric energy meter; calculating a correlation coefficient between each fault feature in the communication fault data and a sample category, and selecting the fault feature with the maximum correlation coefficient as an important feature of the communication fault data; determining the attribute category distinction degree of the communication fault data according to the important features; and performing communication fault early warning based on the attribute category distinction degree. Through the above mode, the importance degree of the communication fault attribute of the intelligent electric meter is calculated to realize early warning of the communication fault area of the intelligent electric meter, the early warning accuracy is improved, and stable operation of the intelligent electric meter is ensured.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and device for early warning of communication failure of a smart electric energy meter. Background Art

[0002] Meter communication fault warning can ensure the communication security of smart meters and is conducive to the quality control of the whole process of smart energy meters. At present, data mining technology is used to provide real-time warning of smart meter faults, and the decision tree algorithm is applied to the construction of smart meter fault warning model. Through a large number of model training and using the test set of the model to warn of smart meter faults, a fault alarm system is established on the integrated development environment platform. Simulation experiments have proved that through early warning of power grid faults, abnormal power in power grid operation can be centrally inspected and repaired, thereby reducing the waste of manpower and resources, but the accuracy of communication fault warning of smart meters is low.

[0003] 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

[0004] The main purpose of the present invention is to provide a method and device for early warning of communication failure of a smart electric energy meter, aiming to solve the technical problem of low accuracy of early warning of communication failure.

[0005] To achieve the above object, the present invention provides a smart energy meter communication failure early warning method, the smart energy meter communication failure early warning method comprising the following steps:

[0006] Obtain the operating status data of the smart energy meter;

[0007] Performing fault detection on the smart electric energy meter according to the operating status data;

[0008] After detecting that the smart electric energy meter has a communication fault, acquiring communication fault data of the smart electric energy meter;

[0009] Calculating the correlation coefficient between each fault feature in the communication fault data and the sample category, and selecting the fault feature with the largest correlation coefficient as the important feature of the communication fault data;

[0010] Determining the attribute category distinction of the communication fault data according to the important features;

[0011] A communication failure warning is performed based on the attribute category distinction.

[0012] In some embodiments, the performing fault detection on the smart electric energy meter according to the operating status data includes:

[0013] Determine an observation vector corresponding to the operating state of the smart electric energy meter according to the operating state data;

[0014] Taking the observation vector as a key variable as a reference, calculating the average trajectory of the observation vector through the operating status data of the smart electric energy meter;

[0015] Determine the operation trajectory of the fault variable of the smart energy meter at different times based on the historical operation status data of the smart meter;

[0016] Determine key variable information based on the operation trajectory of the fault variable of the smart electric energy meter at different times;

[0017] Fault detection is performed on the smart electric energy meter according to the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart electric energy meter at different times, and the key variable information.

[0018] In some embodiments, the performing fault detection on the smart electric energy meter according to the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart electric energy meter at different times and the key variable information includes:

[0019] Counting the number of the key variables;

[0020] Extracting process data of the key variable information from the historical operation data;

[0021] Determine the fault similarity according to the dynamic characteristics corresponding to the key variables, the number of the key variables, the process data, the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart energy meter at different times and the key variable information;

[0022] When the fault similarity exceeds a preset similarity, it is determined that a communication fault exists in the smart electric energy meter.

[0023] In some embodiments, the method further comprises:

[0024] After acquiring the communication fault data, detecting data related to important features in the communication fault data;

[0025] If the data related to the important features meets the preset conditions, it is determined that the communication fault data meets the collection requirements, and the preset conditions at least include the data volume and feature category;

[0026] After the communication fault data meets the collection requirements, the step of calculating the correlation coefficient between each fault feature in the communication fault data and the sample category is performed.

[0027] In some embodiments, calculating the correlation coefficient between each fault feature in the communication fault data and the sample category includes:

[0028] Calculate the first mean of the numerical variable corresponding to any sample category and determine the corresponding sample category proportion;

[0029] Calculate the second mean of the numerical variable corresponding to another sample category;

[0030] Calculating a third mean value of the numerical variable corresponding to the communication fault data;

[0031] A correlation coefficient is determined according to the first mean, the sample category ratio, the second mean, and the third mean.

[0032] In some embodiments, determining the attribute category distinction of the communication fault data according to the important features includes:

[0033] Determining the intra-class aggregation degree of the communication fault data based on the important features;

[0034] Determining the inter-class aggregation degree of the communication fault data based on the important features;

[0035] determining the intra-class variance according to the intra-class aggregation degree;

[0036] Determining the inter-class dissimilarity according to the inter-class aggregation degree;

[0037] The attribute category discrimination is determined according to the intra-class variance and the inter-class dissimilarity.

[0038] In some embodiments, the performing communication failure warning based on the attribute category distinction includes:

[0039] Determining the discrimination range of the attribute category discrimination;

[0040] Determine the corresponding fault attribute category according to the discrimination range;

[0041] Locating the cause of the communication failure based on the failure attribute category;

[0042] An early warning is issued based on the cause of the communication failure.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also proposes a smart electric energy meter communication failure early warning device, the smart electric energy meter communication failure early warning device comprising:

[0044] An acquisition module, used to acquire the operating status data of the smart electric energy meter;

[0045] A detection module, used for performing fault detection on the smart electric energy meter according to the operating status data;

[0046] An extraction module, configured to obtain communication fault data of the smart electric energy meter after detecting that the smart electric energy meter has a communication fault;

[0047] A calculation module, used to calculate the correlation coefficient between each fault feature in the communication fault data and the sample category, and select the fault feature with the largest correlation coefficient as the important feature of the communication fault data;

[0048] The calculation module is used to determine the attribute category distinction of the communication fault data according to the important features;

[0049] The early warning module is used to provide early warning of communication failure based on the attribute category distinction.

[0050] In some embodiments, the detection module is used to determine the observation vector corresponding to the operating state of the smart energy meter according to the operating state data;

[0051] Taking the observation vector as a key variable as a reference, calculating the average trajectory of the observation vector through the operating status data of the smart electric energy meter;

[0052] Determine the operation trajectory of the fault variable of the smart energy meter at different times based on the historical operation status data of the smart meter;

[0053] Determine key variable information based on the operation trajectory of the fault variable of the smart electric energy meter at different times;

[0054] Fault detection is performed on the smart electric energy meter according to the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart electric energy meter at different times, and the key variable information.

[0055] In some embodiments, the detection module is used to count the number of the key variables;

[0056] Extracting process data of the key variable information from the historical operation data;

[0057] Determine the fault similarity according to the dynamic characteristics corresponding to the key variables, the number of the key variables, the process data, the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart energy meter at different times and the key variable information;

[0058] When the fault similarity exceeds a preset similarity, it is determined that a communication fault exists in the smart electric energy meter.

[0059] The present invention obtains the operation status data of the smart electric energy meter; performs fault detection on the smart electric energy meter according to the operation status data; obtains the communication fault data of the smart electric energy meter after detecting that the smart electric energy meter has a communication fault; calculates the correlation coefficient between each fault feature and the sample category in the communication fault data, and selects the fault feature with the largest correlation coefficient as the important feature of the communication fault data; determines the attribute category distinction of the communication fault data according to the important feature; performs communication fault warning based on the attribute category distinction, calculates the importance of the communication fault attribute of the smart electric energy meter, realizes the warning of the communication fault area of ​​the smart electric energy meter, improves the warning accuracy, and ensures the stable operation of the smart electric energy meter. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of the first embodiment of the method for early warning of communication failure of a smart electric energy meter according to the present invention;

[0061] Figure 2 This is a structural block diagram of the first embodiment of the communication fault warning device for a smart electric energy meter of the present invention.

[0062] 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

[0063] 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.

[0064] The embodiment of the present invention provides a method for early warning of communication failure of a smart energy meter, referring to Figure 1 , Figure 1 The present invention is a flowchart of a first embodiment of a method for early warning of communication failure of a smart electric energy meter.

[0065] In this embodiment, the smart energy meter communication failure early warning method includes the following steps:

[0066] Step S10: Acquire the operating status data of the smart electric energy meter.

[0067] In this embodiment, the executor of this embodiment is a smart power meter communication fault warning device, wherein the smart power meter communication fault warning device has functions such as data processing, data communication and program running. The smart power meter communication fault warning device 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.

[0068] It should be noted that meter communication fault warning can ensure the communication security of smart meters and is conducive to the whole process quality control of smart energy meters. At present, data mining technology is used to provide real-time warning of smart meter faults, and the decision tree algorithm is applied to the construction of smart meter fault warning model. Through a large number of model training and using the test set of the model to warn of smart meter faults, a fault alarm system was established on the integrated development environment platform. Simulation experiments have proved that through early warning of power grid faults, abnormal power in power grid operation can be centrally inspected and repaired, thereby reducing the waste of manpower and resources, but the accuracy of communication fault warning of smart meters is low.

[0069] In order to solve the above technical problems, this embodiment obtains the operating status data of the smart electric energy meter; performs fault detection on the smart electric energy meter according to the operating status data; obtains the communication fault data of the smart electric energy meter after detecting that the smart electric energy meter has a communication fault; calculates the correlation coefficient between each fault feature and the sample category in the communication fault data, and selects the fault feature with the largest correlation coefficient as the important feature of the communication fault data; determines the attribute category discrimination of the communication fault data according to the important feature; performs communication fault warning based on the attribute category discrimination, calculates the importance of the communication fault attribute of the smart electric energy meter, realizes the warning of the communication fault area of ​​the smart electric energy meter, improves the warning accuracy, and ensures the stable operation of the smart electric energy meter. Specifically, it can be implemented as follows.

[0070] In a specific implementation, in this embodiment, it is necessary to first collect the operating status data of the smart energy meter. Specifically, the operating status data can be collected through an electricity consumption collection terminal.

[0071] Step S20: performing fault detection on the smart electric energy meter according to the operating status data.

[0072] After the operation status data is collected, in this embodiment, fault detection can be performed on the smart energy meter based on the operation status data. It should be noted that the fault detection also needs to be combined with the historical operation status data.

[0073] The specific fault detection process is to determine the observation vector corresponding to the operating state of the smart energy meter according to the operating state data, for example Where S represents the observation vector, λ represents the threshold of the operating state of the smart energy meter, and s f represents the main metadata in the operating status data, Ce represents the historical operating data of the smart energy meter, and e i Represents the covariance matrix between the principal components. Then, in this embodiment, the observation vector is used as the key variable as a benchmark, and the average trajectory of the observation vector is calculated through the historical operation data of the smart energy meter, for example Among them, G r represents the average trajectory, s e Table key variable single element, s p Indicates the changing trend information of key variables during the operation time of the smart meter, s e With s p From the above S, we can get b p Represents the dynamic characteristics of the key variables, x t The variable value representing the communication fault detection sample of the smart energy meter, y i The trajectory vector representing the key variable. The operation trajectory of the fault variable of the smart energy meter at different times is determined based on the historical operation status data of the smart meter, for example Among them, e t represents the running trajectory, x p represents the weight of fault data in the trajectory operation space; v k Represents the trajectory judgment of fault data; ξ u represents the sampling interval of fault data; j p Indicates the similarity of fault data in the same period. Based on the above-obtained trajectory, we can obtain the trajectory trend graph of the fault data detection variable and the trajectory vector of the smart meter communication fault detection data sample, and combine the type set of smart meter communication fault samples and the score matrix of smart meter communication fault data in the principal element space to obtain key variable information, such as Among them, Z p Indicates key variable information, f p represents the type set of smart meter communication fault samples, f u Represents the trajectory trend diagram of the fault data detection variable, u 0 represents the score matrix of smart meter communication fault data in the principal element space, m l The trajectory vector represents the data sample of the communication fault detection of the smart meter. Finally, the fault detection of the smart meter can be performed by combining the average trajectory of the observation vector, the running trajectory of the fault variable of the smart meter at different times and the key variable information.

[0074] Furthermore, in this embodiment, it is necessary to count the number of key variables, extract process data of key variable information from historical operation data, and determine the fault similarity based on the dynamic characteristics corresponding to the key variables, the number of key variables, process data, average trajectory of observation vectors, operation trajectory of smart power meter fault variables at different times, and key variable information. The calculation formula is: Among them, J r represents the fault similarity, n is the number of key variables, τ eThe process data of the key variable information, the other parameters are as described above, and will not be repeated here. Finally, the fault similarity is compared with the preset similarity. If the fault similarity exceeds the preset similarity, it can be determined that there is a communication fault in the smart energy meter. It can be understood that since there are many types of faults, and this embodiment is aimed at the detection of communication faults, the preset similarity is associated with the communication fault.

[0075] Step S30: after detecting that the smart electric energy meter has a communication fault, obtaining communication fault data of the smart electric energy meter.

[0076] After detecting that a communication fault exists in the smart electric energy meter, in this embodiment, the communication fault needs to be further analyzed, and at this time, the communication fault data of the smart electric energy meter needs to be obtained.

[0077] It should be noted that in order to improve the accuracy of the early warning, it is necessary to detect the acquired communication fault data. Specifically, detect the data related to the important features in the communication fault data, and then determine whether the data volume and feature category corresponding to the data related to the important features meet the preset conditions. If so, it means that the acquired communication fault data meets the collection requirements, and subsequent fault early warning analysis can be performed. This detection can ensure that there is no missing key data in the communication fault data, thereby improving the accuracy of the early warning. The specific conditions corresponding to the preset conditions can be adjusted according to actual needs, and this is not limited in this embodiment.

[0078] Step S40: Calculate the correlation coefficient between each fault feature in the communication fault data and the sample category, and select the fault feature with the largest correlation coefficient as the important feature of the communication fault data.

[0079] The calculation process of the correlation coefficient specifically includes calculating the first mean of the numerical variable corresponding to any sample category and determining the corresponding sample category ratio, calculating the second mean of the numerical variable corresponding to another sample category, calculating the third mean of the numerical variable corresponding to the communication fault data, and determining the correlation coefficient according to the first mean, the sample category ratio, the second mean and the third mean, where the numerical variable is the specific data value, and the calculation formula of the correlation coefficient is specifically as follows: Among them, r pb is the correlation coefficient, M 1 With M 2 are the first mean and the second mean respectively, p is the sample category proportion, and σ is the third mean.

[0080] After the above correlation coefficients are calculated, in this embodiment, the correlation coefficients are sorted to determine the fault feature with the largest correlation coefficient, and then the fault feature is used as an important feature.

[0081] Step S50: determining the attribute category distinction of the communication fault data according to the important features.

[0082] In a specific implementation, the intra-class aggregation degree of the communication fault data is determined based on the determined important features, e.g. in is the intra-class aggregation degree, m represents the number of categories of communication fault data, It represents the degree of convergence between the fault features of type i and the important features. The intra-class variance is obtained by multiplying the intra-class convergence degree by the coefficient. The coefficient range is [0-1], and the specific value can be selected according to actual needs.

[0083] Furthermore, the calculation formula of inter-class aggregation degree is: in, represents the degree of aggregation between classes, n i represents the number of samples of smart meter fault data in the i-th category, represents the attribute vector of the smart meter fault data belonging to the i-th category, and w represents the attribute vector corresponding to the important feature. By adding the inter-class aggregation degrees corresponding to all categories, the inter-class dissimilarity can be obtained. Finally, the attribute category discrimination can be calculated based on the intra-class variance and inter-class dissimilarity. The calculation formula is: Where f(k) represents the attribute category discrimination, represents the intra-class variance, Represents the dissimilarity between classes.

[0084] Step S60: Providing communication failure warning based on the attribute category distinction.

[0085] After obtaining the attribute category discrimination, the discrimination range of the attribute category discrimination can be determined in this embodiment. Since different fault attribute categories correspond to different discrimination ranges, the fault attribute category in this embodiment can be determined through the above judgment, and then the cause of the communication fault can be located based on the fault attribute category. Fault attribute categories include weak communication signal, poor communication signal stability and no communication signal. Based on these fault attribute categories, the cause of the fault can be determined. For example, the cause of the no communication signal is a communication circuit board failure. Finally, early warnings can be issued for different communication fault causes.

[0086] This embodiment obtains the operation status data of the smart energy meter; performs fault detection on the smart energy meter according to the operation status data; obtains the communication fault data of the smart energy meter after detecting that the smart energy meter has a communication fault; calculates the correlation coefficient between each fault feature and the sample category in the communication fault data, and selects the fault feature with the largest correlation coefficient as the important feature of the communication fault data; determines the attribute category discrimination of the communication fault data according to the important feature; performs communication fault warning based on the attribute category discrimination, calculates the importance of the communication fault attribute of the smart energy meter, realizes the warning of the communication fault area of ​​the smart energy meter, improves the warning accuracy, and ensures the stable operation of the smart energy meter.

[0087] Reference Figure 2 , Figure 2 This is a structural block diagram of the first embodiment of the communication fault warning device for a smart electric energy meter of the present invention.

[0088] like Figure 2 As shown, the smart electric energy meter communication fault warning device proposed in the embodiment of the present invention includes:

[0089] The acquisition module 10 is used to acquire the operating status data of the smart electric energy meter.

[0090] The detection module 20 is used to perform fault detection on the smart electric energy meter according to the operating status data.

[0091] The extraction module 30 is used to obtain the communication fault data of the smart electric energy meter after detecting that the smart electric energy meter has a communication fault.

[0092] The calculation module 40 is used to calculate the correlation coefficient between each fault feature in the communication fault data and the sample category, and select the fault feature with the largest correlation coefficient as the important feature of the communication fault data.

[0093] The calculation module 40 is used to determine the attribute category distinction of the communication fault data according to the important features.

[0094] The early warning module 50 is used to issue a communication failure early warning based on the attribute category distinction.

[0095] This embodiment obtains the operation status data of the smart energy meter; performs fault detection on the smart energy meter according to the operation status data; obtains the communication fault data of the smart energy meter after detecting that the smart energy meter has a communication fault; calculates the correlation coefficient between each fault feature and the sample category in the communication fault data, and selects the fault feature with the largest correlation coefficient as the important feature of the communication fault data; determines the attribute category discrimination of the communication fault data according to the important feature; performs communication fault warning based on the attribute category discrimination, calculates the importance of the communication fault attribute of the smart energy meter, realizes the warning of the communication fault area of ​​the smart energy meter, improves the warning accuracy, and ensures the stable operation of the smart energy meter.

[0096] In some embodiments, the detection module 20 is used to determine the observation vector corresponding to the operating state of the smart power meter based on the operating state data; take the observation vector as the key variable as a reference, and calculate the average trajectory of the observation vector through the operating state data of the smart power meter; determine the operating trajectory of the fault variable of the smart power meter at different times based on the historical operating state data of the smart meter; determine the key variable information based on the operating trajectory of the fault variable of the smart power meter at different times; perform fault detection on the smart power meter based on the average trajectory of the observation vector, the operating trajectory of the fault variable of the smart power meter at different times and the key variable information.

[0097] In some embodiments, the detection module 20 is used to count the number of the key variables; extract the process data of the key variable information from the historical operation data; determine the fault similarity based on the dynamic characteristics corresponding to the key variables, the number of the key variables, the process data, the average trajectory of the observation vector, the operation trajectory of the smart power meter fault variable at different times and the key variable information; when the fault similarity exceeds the preset similarity, it is determined that the smart power meter has a communication fault.

[0098] In some embodiments, the detection module 20 is used to detect data related to important features in the communication fault data after the communication fault data is acquired; if the data related to the important features meets the preset conditions, it is determined that the communication fault data meets the collection requirements, and the preset conditions at least include the data volume and feature category; the calculation module 40 is used to calculate the correlation coefficient between each fault feature in the communication fault data and the sample category after the communication fault data meets the collection requirements.

[0099] In some embodiments, the calculation module 40 is used to calculate the first mean of the numerical variable corresponding to any sample category and determine the corresponding sample category ratio; calculate the second mean of the numerical variable corresponding to another sample category; calculate the third mean of the numerical variable corresponding to the communication fault data; and determine the correlation coefficient based on the first mean, the sample category ratio, the second mean and the third mean.

[0100] In some embodiments, the calculation module 40 is used to determine the intra-class aggregation degree of the communication fault data based on the important features; determine the inter-class aggregation degree of the communication fault data based on the important features; determine the intra-class variance according to the intra-class aggregation degree; determine the inter-class dissimilarity according to the inter-class aggregation degree; determine the attribute category distinction according to the intra-class variance and the inter-class dissimilarity.

[0101] In some embodiments, the warning module 50 is used to determine the discrimination range of the attribute category discrimination; determine the corresponding fault attribute category according to the discrimination range; locate the cause of the communication fault based on the fault attribute category; and issue a warning based on the cause of the communication fault.

[0102] An embodiment of the present application also provides a smart electric energy meter communication fault warning device, 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 the smart electric energy meter communication fault warning program; the processor is used to implement the above-mentioned smart electric energy meter communication fault warning method when executing the program stored in the memory.

[0103] The communication bus mentioned in the above-mentioned smart energy meter communication fault warning device 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 electric energy meter communication fault warning device 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 gates 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, computer, server or 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 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 may be made to the smart electric energy meter communication fault warning method 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, 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 smart electric energy meter communication failure early warning method, characterized in that: The smart electric energy meter communication failure early warning method comprises: Obtain the operating status data of the smart energy meter; Performing fault detection on the smart electric energy meter according to the operating status data; After detecting that the smart electric energy meter has a communication fault, acquiring communication fault data of the smart electric energy meter; Calculating the correlation coefficient between each fault feature in the communication fault data and the sample category, and selecting the fault feature with the largest correlation coefficient as the important feature of the communication fault data; Determining the attribute category distinction of the communication fault data according to the important features; A communication failure warning is performed based on the attribute category distinction.

2. The smart energy meter communication failure early warning method according to claim 1, characterized in that: The performing fault detection on the smart electric energy meter according to the operating status data comprises: Determine an observation vector corresponding to the operating state of the smart electric energy meter according to the operating state data; Taking the observation vector as a key variable as a reference, calculating the average trajectory of the observation vector through the operating status data of the smart electric energy meter; Determine the operation trajectory of the fault variable of the smart energy meter at different times based on the historical operation status data of the smart meter; Determine key variable information based on the operation trajectory of the fault variable of the smart electric energy meter at different times; Fault detection is performed on the smart electric energy meter according to the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart electric energy meter at different times, and the key variable information.

3. The smart energy meter communication failure early warning method according to claim 2, characterized in that: The performing fault detection on the smart electric energy meter according to the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart electric energy meter at different times and the key variable information includes: Counting the number of the key variables; Extracting process data of the key variable information from the historical operation data; Determine the fault similarity according to the dynamic characteristics corresponding to the key variables, the number of the key variables, the process data, the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart energy meter at different times and the key variable information; When the fault similarity exceeds a preset similarity, it is determined that a communication fault exists in the smart electric energy meter.

4. The smart energy meter communication failure early warning method according to claim 1, characterized in that: The method further comprises: After acquiring the communication fault data, detecting data related to important features in the communication fault data; If the data related to the important features meets the preset conditions, it is determined that the communication fault data meets the collection requirements, and the preset conditions at least include the data volume and feature category; After the communication fault data meets the collection requirements, the step of calculating the correlation coefficient between each fault feature in the communication fault data and the sample category is performed.

5. The smart energy meter communication failure early warning method according to claim 1, characterized in that: The calculating the correlation coefficient between each fault feature and the sample category in the communication fault data includes: Calculate the first mean of the numerical variable corresponding to any sample category and determine the corresponding sample category proportion; Calculate the second mean of the numerical variable corresponding to another sample category; Calculating a third mean value of the numerical variable corresponding to the communication fault data; A correlation coefficient is determined according to the first mean, the sample category ratio, the second mean, and the third mean.

6. The smart electric energy meter communication failure early warning method according to any one of claims 1 to 5, characterized in that: The determining the attribute category distinction of the communication fault data according to the important features includes: Determining the intra-class aggregation degree of the communication fault data based on the important features; Determining the inter-class aggregation degree of the communication fault data based on the important features; determining the intra-class variance according to the intra-class aggregation degree; Determining the inter-class dissimilarity according to the inter-class aggregation degree; The attribute category discrimination is determined according to the intra-class variance and the inter-class dissimilarity.

7. The smart energy meter communication failure early warning method according to claim 6, characterized in that: The performing of communication fault warning based on the attribute category distinction includes: Determining the discrimination range of the attribute category discrimination; Determine the corresponding fault attribute category according to the discrimination range; Locating the cause of the communication failure based on the failure attribute category; An early warning is issued based on the cause of the communication failure.

8. A smart electric energy meter communication failure warning device, characterized in that: The smart electric energy meter communication failure early warning device comprises: An acquisition module, used to acquire the operating status data of the smart electric energy meter; A detection module, used for performing fault detection on the smart electric energy meter according to the operating status data; An extraction module, configured to obtain communication fault data of the smart electric energy meter after detecting that the smart electric energy meter has a communication fault; A calculation module, used to calculate the correlation coefficient between each fault feature in the communication fault data and the sample category, and select the fault feature with the largest correlation coefficient as the important feature of the communication fault data; The calculation module is used to determine the attribute category distinction of the communication fault data according to the important features; The early warning module is used to provide early warning of communication failure based on the attribute category distinction.

9. The smart electric energy meter communication failure warning device according to claim 8, characterized in that: A detection module, used to determine an observation vector corresponding to the operating state of the smart electric energy meter according to the operating state data; Taking the observation vector as a key variable as a reference, calculating the average trajectory of the observation vector through the operating status data of the smart electric energy meter; Determine the operation trajectory of the fault variable of the smart energy meter at different times based on the historical operation status data of the smart meter; Determine key variable information based on the operation trajectory of the fault variable of the smart electric energy meter at different times; Fault detection is performed on the smart electric energy meter according to the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart electric energy meter at different times, and the key variable information.

10. The smart electric energy meter communication failure warning device according to claim 9, characterized in that: A detection module, used for counting the number of the key variables; Extracting process data of the key variable information from the historical operation data; Determine the fault similarity according to the dynamic characteristics corresponding to the key variables, the number of the key variables, the process data, the average trajectory of the observation vector, the operation trajectory of the fault variable of the smart energy meter at different times and the key variable information; When the fault similarity exceeds a preset similarity, it is determined that a communication fault exists in the smart electric energy meter.

Images