A method and system for automatic analysis and processing of electric energy metering structured data

Abstract

The present invention discloses an automatic analysis and processing method and system for electric energy metering structured data, the method comprising real-time collection of metering data of electric energy meters. The present invention first collects a variety of data, and fills missing values ​​in the collected multiple data, so that the data is complete, separates the multiple data according to the type based on the concentration trend and discrete degree of the metering data, and merges the same data, which, on the one hand, reduces the data memory, and on the other hand, speeds up the subsequent data processing, and also improves the accuracy of electric energy metering data analysis. By adopting a neural network model, the historical metering data of the electric energy meter before the alarm state is analyzed and studied, and an electric energy analysis model is constructed. By inputting the real-time metering data analysis set into the electric energy analysis model, it is judged whether an alarm occurs, and the staff intervenes in advance, preventing electrical failures and meeting the needs of the staff.

Description

Technical Field

[0001] The present invention generally relates to the technical field of data analysis, and in particular to a method and system for automatic analysis and processing of electric energy metering structured data. Background Art

[0002] The DC energy meter is designed for applications such as DC panels and solar power supply. The DC energy meter can measure the voltage, current, power, forward and reverse electric energy and other metering data in the DC system, so as to realize the deployment of subsequent measurement and control systems and solve the data measurement in different application scenarios.

[0003] Since the electric energy meter can monitor a large amount of power data, most of the existing systems directly input the metering data into the model for analysis, lacking data classification and fusion, resulting in inaccurate analysis results of the metering data; and the existing system also lacks learning of the metering data of the electric energy meter before the alarm state, so it is impossible to intervene in power failures in advance based on real-time metering data, and it is difficult to meet the needs of staff. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for automatic analysis and processing of structured data of electric energy metering is provided. The technical solution solves the problem that most of the existing systems proposed in the above background technology directly input the metering data into the model for analysis, lack of data classification and fusion, resulting in inaccurate analysis results of the metering data; and the existing system also lacks learning of the metering data of the electric energy meter before the alarm state, and thus cannot intervene in power failures in advance based on real-time metering data.

[0005] In a first aspect of the present invention, a method for automatic analysis and processing of electric energy metering structured data is provided. The method comprises:

[0006] Collect metering data of the electric energy meter in real time, and preprocess the metering data to obtain preprocessed metering data, wherein the preprocessing is missing value filling;

[0007] Calculate the central tendency and dispersion of pre-processed measurement data, divide the pre-processed measurement data into several groups, and merge the same measurement data;

[0008] Form a quantitative data analysis set from multiple fused data;

[0009] Retrieve all historical measurement data before the alarm state occurs from the database, record them as the alarm data set, and annotate and divide the historical measurement data to obtain a training set, a validation set, and a test set;

[0010] Based on feedforward neural network, construct power analysis model;

[0011] The metering data analysis set is input into the electric energy analysis model to determine whether to issue an alarm.

[0012] Preferably, the missing value filling includes:

[0013] Mark the metering data of all electric energy meters with coordinates (x, y);

[0014] Arrange the measurement data coordinates (x, y) of all electric energy meters into one column;

[0015] Retrieve all data coordinates (x, y). If there is a gap in x or y, fill in the data at that position. The data collected is the mean of the adjacent data at the same position.

[0016] Preferably, the calculation of the central tendency and dispersion degree of the measurement data includes:

[0017] Calculate the mean value of measurement data and calculate the variance of data according to the variance formula;

[0018] Setting the variance as the central tendency of the complete measurement data and assigning a trend identification code to the central tendency;

[0019] Pair each data in the measurement data with the remaining data in the measurement data to obtain at least one paired group;

[0020] Calculate the absolute value of the difference between two data in each paired group of measurement data, and accumulate the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value;

[0021] The discrete value is set as the discrete degree of the data, and a discrete identification code is assigned to the discrete degree.

[0022] Preferably, the variance is:

[0023]

[0024] Among them, D is the variance, n is the number of data, x i is the value of the data, and a is the average value of the data.

[0025] Preferably, the method of dividing the pre-processed metering data into several groups includes:

[0026] Retrieve data normalization standard 1 from the database, and obtain the range interval of the central tendency ratio and the range interval of the dispersion ratio in the data normalization standard 1;

[0027] Calculate the ratio of the central tendency of the data to the mean of the central tendency of the sample data;

[0028] Calculate the ratio of the degree of dispersion of the data to the mean of the degree of dispersion of the sample data;

[0029] Ratio 1 is compared with the first preset threshold and ratio 2 is compared with the second preset threshold to determine whether the central trend of the data belongs to the range interval of the central tendency ratio and the range interval of the dispersion ratio in normalization standard 1, and based on the judgment result, the measurement data is fused.

[0030] Preferably, the fusing of the measurement data based on the judgment result includes:

[0031] If the ratio value 1 is greater than or equal to the first preset threshold, it belongs to the range interval of the central tendency ratio in the normalization standard 1;

[0032] If the ratio value 1 is less than the first preset threshold, it does not belong to the range interval of the central tendency ratio value in the normalization standard 1;

[0033] If the second ratio is greater than or equal to the second preset threshold, it belongs to the range interval of the discrete degree ratio in the normalization standard one;

[0034] If the second ratio is less than the second preset threshold, it does not belong to the range interval of the discrete degree ratio in the normalization standard one;

[0035] The data belonging to the range interval of the central tendency ratio and the range interval of the dispersion ratio in the normalization standard 1 are attributed to the first data;

[0036] The data that does not belong to the range interval of the central tendency ratio and the range interval of the dispersion ratio in the first normalization standard are classified as the second data;

[0037] The first data and the second data are fused respectively to obtain first fused data and second fused data.

[0038] Preferably, the constructing of the electric energy analysis model based on the feedforward neural network includes:

[0039] Based on feedforward neural network, construct power analysis model;

[0040] Based on machine learning, the multiple historical measurement data are labeled and divided to obtain a training set, a validation set, and a test set;

[0041] The training set, validation set and test set are used to perform supervised training, validation and testing on the electric energy analysis model to obtain the electric energy analysis model whose accuracy meets the preset accuracy requirements.

[0042] Preferably, the electric energy analysis model is:

[0043]

[0044] Where C is the degree of fit between the characteristic parameters of the input measurement data analysis set and the characteristic parameters of the alarm data set in the system, S i is the i-th characteristic parameter, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

[0045] In a second aspect of the present invention, a pipeline fault early warning system based on artificial intelligence is provided. The system comprises:

[0046] A preprocessing module is used to collect metering data of the electric energy meter in real time, and preprocess the metering data to obtain preprocessed metering data, wherein the preprocessing is missing value filling;

[0047] The classification and fusion module is used to calculate the central tendency and dispersion degree of the pre-processed measurement data, and to divide the pre-processed measurement data into several groups and fuse the same measurement data;

[0048] A formation module is used to form a measurement data analysis set from multiple fused data;

[0049] The retrieval module is used to retrieve all historical measurement data before the alarm state occurs from the database, record them as the alarm data set, and mark and divide the historical measurement data to obtain the training set, verification set and test set;

[0050] A building block for building an electric energy analysis model based on a feedforward neural network;

[0051] The processing module is used to input the metering data analysis set into the electric energy analysis model to determine whether to issue an alarm.

[0052] In a third aspect of the present invention, an electronic device is provided. The electronic device has at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method of the first aspect of the present invention.

[0053] Compared with the prior art, the present invention provides a method and system for automatic analysis and processing of electric energy metering structured data, which has the following beneficial effects:

[0054] The present invention first collects a variety of data, and fills missing values ​​for the collected data to make the data complete. Based on the concentration trend and discreteness of the metering data, the various data are separated according to types, and the same data are merged. On the one hand, the data memory is reduced, and on the other hand, the speed of subsequent data processing is accelerated, and the accuracy of electric energy metering data analysis is also improved. By adopting a neural network model, the historical metering data of the electric energy meter before the alarm state is analyzed and studied, and an electric energy analysis model is constructed. By inputting the real-time metering data analysis set into the electric energy analysis model, it is determined whether an alarm occurs, and the staff intervenes in advance to prevent power failures and meet the needs of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0056] Figure 1 It is a schematic diagram of the automatic analysis and processing method of electric energy metering structured data in the present invention;

[0057] Figure 2 A schematic diagram of a method for calculating the central tendency and dispersion degree of preprocessed measurement data in the present invention;

[0058] Figure 3 A schematic diagram of a method for dividing pre-processed metering data into several groups of categories in the present invention;

[0059] Figure 4 It is a schematic diagram of a method for fusing measurement data based on the judgment result in the present invention;

[0060] Figure 5 A schematic diagram of a method for constructing an electric energy analysis model based on a feedforward neural network in the present invention;

[0061] Figure 6 A block diagram of an automatic analysis and processing system for electric energy metering structured data according to the present invention is shown;

[0062] Figure 7 A block diagram of an exemplary electronic device capable of implementing embodiments of the present invention is shown;

[0063] Among them, 800 is an electronic device, 801 is a computing unit, 802 is a ROM, 803 is a RAM, 804 is a bus, 805 is an I / O interface, 806 is an input unit, 807 is an output unit, 808 is a storage unit, and 809 is a communication unit. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0066] Example 1

[0067] Please refer to Figure 1-Figure 5 As shown, a method for automatic analysis and processing of electric energy metering structured data includes:

[0068] S100, collecting metering data of the electric energy meter in real time, and preprocessing the metering data to obtain preprocessed metering data, wherein the preprocessing is to fill missing values;

[0069] S200, calculating the central tendency and dispersion degree of the preprocessed measurement data;

[0070] S300, dividing the pre-processed measurement data into several groups;

[0071] S400, fusing the same type of measurement data, and forming a measurement data analysis set with multiple types of fused data;

[0072] S500, retrieve all historical measurement data before the alarm state occurs from the database, record them as the alarm data set, and mark and divide the historical measurement data to obtain a training set, a validation set, and a test set;

[0073] S600, build an electric energy analysis model based on feedforward neural network;

[0074] S700: Input the metering data analysis set into the electric energy analysis model to determine whether to issue an alarm.

[0075] Those skilled in the art can understand that, when actually used, the electric energy meter can measure a variety of data, such as voltage data, current data, and power data. The present invention first collects a variety of data, and fills missing values ​​for the collected data to make the data complete. Based on the concentration trend and discreteness of the metering data, the various data are separated by type, and the same data is merged, which, on the one hand, reduces the data memory, and on the other hand, speeds up the subsequent data processing, and also improves the accuracy of the electric energy metering data analysis. By adopting a neural network model, the historical metering data of the electric energy meter before the alarm state is analyzed and studied, and an electric energy analysis model is constructed. By inputting the real-time metering data analysis set into the electric energy analysis model, it is determined whether an alarm occurs, and the staff intervenes in advance to prevent power failures, thereby meeting the needs of the staff;

[0076] It is worth mentioning here that the historical metering data of the electric energy meter before the alarm state is the data 1s-1min before the electric energy meter alarm, rather than the data with a long interval, because the data with a long interval has no reference significance.

[0077] Missing value filling includes:

[0078] S101, marking the metering data of all electric energy meters with coordinates (x, y);

[0079] S102, arranging the measurement data coordinates (x, y) of all electric energy meters into one column;

[0080] S103, retrieve all data coordinates (x, y), if x or y is missing, fill in the data at that position, and collect the data as the average of the adjacent data at the same position.

[0081] It can be understood by those skilled in the art that the metering data of the electric energy meter is organized into a list or database form, and a coordinate (x, y) is assigned to each data point, where x is time or other appropriate dimensions, and y is the corresponding metering data, ensuring that each data point has a unique coordinate label; and by creating a new list or array to store the metering data coordinates of all electric energy meters, traverse the metering data coordinate list of each electric energy meter, and add it to the new list in turn, ensuring that the coordinates in the new list are arranged in order, such as in time order; and traverse the integrated data coordinate list again, check whether the x and y values ​​of each coordinate are missing, if it is found that the x or y value is missing, then find the adjacent coordinates of the coordinate (the previous and the next one), for the missing x value, linear interpolation or other appropriate interpolation methods can be performed according to the x values ​​of the adjacent coordinates to fill it. However, in this step, since x usually represents an ordered variable such as time and is usually not missing, the filling of the y value is mainly concerned. For the missing y value, the mean of the y values ​​of the adjacent coordinates is calculated, and the mean is used as the filling value, the data coordinate list is updated, and the filled coordinates replace the original missing coordinates.

[0082] Calculating the central tendency and dispersion of preprocessed measurement data includes:

[0083] S201, calculating the average value of the measurement data, and calculating the variance of the data according to the variance formula;

[0084] S202, setting the variance as the central tendency of the complete measurement data, and assigning a trend identification code to the central tendency;

[0085] S203, pairing each data in the measurement data with the remaining data in the measurement data to obtain at least one pairing group;

[0086] S204, calculating the absolute value of the difference between two data in each paired group of measurement data, and accumulating the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value;

[0087] S205. Set the discrete value as the discrete degree of the data, and assign a discrete identification code to the discrete degree.

[0088] The variance is:

[0089]

[0090] Among them, D is the variance, n is the number of data, x i is the value of the data, and a is the average value of the data.

[0091] The measurement data is divided into several groups, including:

[0092] S301, retrieve data normalization standard 1 from the database, and obtain the range interval of the central tendency ratio and the range interval of the dispersion ratio in the data normalization standard 1;

[0093] S302, calculating the ratio of the central tendency of the data to the central tendency mean of the sample data;

[0094] S303, calculating the ratio of the degree of dispersion of the data to the mean value of the degree of dispersion of the sample data;

[0095] S304, comparing ratio 1 with the first preset threshold and comparing ratio 2 with the second preset threshold, determining whether the central tendency of the data belongs to the range interval of the central tendency ratio and the range interval of the dispersion ratio in normalization standard 1, and fusing the measurement data based on the determination result.

[0096] Those skilled in the art can understand that the basis for judgment is that the categories covered by the sample data group include all categories, and the fused data group must belong to one of the categories. When the data group to be fused belongs to one of the categories, the ratio of the central tendency of the data group to be fused to the mean of the central tendency of the sample data group must belong to the range of the central tendency ratio of the given category, and the ratio of the degree of dispersion of the fused data group to the mean of the degree of dispersion of the sample data group must belong to the range of the degree of dispersion ratio of the given category. Therefore, the type of the data group can be judged based on this.

[0097] Based on the judgment results, the fusion of measurement data includes:

[0098] S401: If the ratio value 1 is greater than or equal to the first preset threshold, it belongs to the range interval of the central tendency ratio in the normalization standard 1;

[0099] S402: If the ratio value 1 is less than the first preset threshold, it does not belong to the range interval of the central tendency ratio value in the normalization standard 1;

[0100] S403: If the second ratio is greater than or equal to the second preset threshold, it belongs to the range interval of the discrete degree ratio in the normalization standard 1;

[0101] S404: If the second ratio is less than the second preset threshold, it does not belong to the range interval of the discrete degree ratio in the normalization standard 1;

[0102] S405, classifying the data belonging to the range interval of the central tendency ratio and the range interval of the dispersion ratio in the normalization standard 1 as the first data;

[0103] S406, classifying the data that does not belong to the range interval of the central tendency ratio and the range interval of the dispersion ratio in the first normalization standard as the second data;

[0104] S407 , fuse the first data and the second data respectively to obtain first fused data and second fused data.

[0105] Those skilled in the art can understand that, during fusion, the original data position remains unchanged, but the position of the data group to be fused is not determined, therefore, the smallest judgment sum is calculated and selected, and the target data group one corresponding to the smallest judgment sum is associated with the data group to be fused, because the two must be the data with the strongest correlation, therefore, during fusion, the two are set adjacent to each other, and since the position of the target data group one is determined, the fusion position of the data group to be fused is determined.

[0106] Based on the feedforward neural network, the power analysis model is constructed including:

[0107] S601. Constructing an electric energy analysis model based on a feedforward neural network;

[0108] S602. Based on machine learning, label and divide multiple historical measurement data to obtain a training set, a validation set, and a test set;

[0109] S603: Use the training set, validation set and test set to perform supervised training, validation and testing on the electric energy analysis model to obtain an electric energy analysis model whose accuracy meets the preset accuracy requirements.

[0110] Those skilled in the art can understand that a feedforward neural network is a type of artificial neural network, which adopts a unidirectional multi-layer structure, in which the 0th layer is called the input layer, the last layer is called the output layer, and the other intermediate layers are called hidden layers. The hidden layer can be one layer or multiple layers. Each hidden layer contains a number of neurons, each neuron can receive signals from neurons in the previous layer and generate outputs to the next layer. There is no feedback in the entire network, and the signal propagates unidirectionally from the input layer to the output layer. Multiple historical measurement data are marked with features as construction data, and the construction data is randomly divided into training sets, validation sets, and test sets according to a certain ratio, and the divided training sets, validation sets, and test sets are labeled;

[0111] Exemplarily, the preferred ratio of the present application is 8:1:1, wherein the training set is used to train the model, i.e., to determine the model's weights and biases and other learning parameters; the validation set is used to validate each model using validation set data after multiple models are trained in the training set, and to record the model accuracy, and then select the best model and its corresponding parameters; the test set is used only once, i.e., when evaluating the final model after the training is completed, and does not participate in the process of learning parameters or the process of selecting hyperparameters, but is only used for the evaluation of the model. Based on machine learning, the model is supervised and trained through the training set, the obtained model is verified through the validation set, and the trained model is evaluated through the test set, and the hyperparameters are continuously adjusted until the accuracy meets the preset requirements, and the electric energy analysis model is output.

[0112] The power analysis model is:

[0113]

[0114] Where C is the degree of fit between the characteristic parameters of the input measurement data analysis set and the characteristic parameters of the alarm data set in the system, S i is the i-th characteristic parameter, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

[0115] Those skilled in the art can understand that by inputting the metering data analysis set into the electric energy analysis model, the degree of adaptation is obtained. If the degree of adaptation is high, it means that the metering data analysis set and the alarm data set have a high similarity, then an alarm is issued; otherwise, an alarm is issued.

[0116] The above is an introduction to a method embodiment. The following is a further explanation of the scheme of the present invention through a device embodiment having the same inventive concept as the method in the aforementioned embodiment.

[0117] like Figure 6 As shown, an artificial intelligence-based pipeline fault early warning system 700 includes:

[0118] The preprocessing module 710 is used to collect metering data of the electric energy meter in real time, and preprocess the metering data to obtain preprocessed metering data, wherein the preprocessing is missing value filling;

[0119] The classification and fusion module 720 is used to calculate the central tendency and dispersion degree of the pre-processed measurement data, and to classify the pre-processed measurement data into several groups and to fuse the measurement data of the same type;

[0120] A forming module 730 is used to form a measurement data analysis set from a plurality of fused data;

[0121] The retrieval module 740 is used to retrieve all historical measurement data before the alarm state occurs from the database, record them as the alarm data set, and mark and divide the historical measurement data to obtain a training set, a validation set and a test set;

[0122] A construction module 750 is used to construct an electric energy analysis model based on a feedforward neural network;

[0123] Processing module 760, used to input the metering data analysis set into the power analysis model to determine whether to issue an alarm

[0124] In summary, the present invention first collects multiple data, and fills missing values ​​for the collected multiple data to make the data complete. Based on the concentration trend and discreteness of the metering data, the multiple data are separated by type, and the same data are merged. On the one hand, the data memory is reduced, and on the other hand, the speed of subsequent data processing is accelerated, and the accuracy of electric energy metering data analysis is also improved. By adopting a neural network model, the historical metering data of the electric energy meter before the alarm state is analyzed and studied, and an electric energy analysis model is constructed. By inputting the real-time metering data analysis set into the electric energy analysis model, it is determined whether an alarm occurs, and the staff intervenes in advance to prevent power failures and meet the needs of the staff.

[0125] According to an embodiment of the present invention, the present invention further provides an electronic device.

[0126] Figure 7 A schematic block diagram of an electronic device 800 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0127] The electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0128] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0129] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as methods S100 to S600. For example, in some embodiments, methods S100 to S600 may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the methods S100 to S600 described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute methods S100 to S600 in any other appropriate manner (eg, by means of firmware).

[0130] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0132] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0134] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0135] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0136] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0137] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatic analysis and processing of electric energy metering structured data, characterized in that: include: Collect metering data of the electric energy meter in real time, and preprocess the metering data to obtain preprocessed metering data, wherein the preprocessing is missing value filling; Calculate the central tendency and dispersion of pre-processed measurement data, divide the pre-processed measurement data into several groups, and merge the same measurement data; Form a quantitative data analysis set from multiple fused data; Retrieve all historical measurement data before the alarm state occurs from the database, record them as the alarm data set, and annotate and divide the historical measurement data to obtain a training set, a validation set, and a test set; Based on feedforward neural network, construct power analysis model; The metering data analysis set is input into the electric energy analysis model to determine whether to issue an alarm.

2. The method for automatic analysis and processing of electric energy metering structured data according to claim 1, characterized in that: The missing value filling includes: Mark the metering data of all electric energy meters with coordinates (x, y); Arrange the measurement data coordinates (x, y) of all electric energy meters into one column; Retrieve all data coordinates (x, y). If there is a gap in x or y, fill in the data at that position. The data collected is the mean of the adjacent data at the same position.

3. The method for automatic analysis and processing of electric energy metering structured data according to claim 2, characterized in that: The calculation of the central tendency and dispersion of the measurement data includes: Calculate the mean value of measurement data and calculate the variance of data according to the variance formula; Setting the variance as the central tendency of the complete measurement data and assigning a trend identification code to the central tendency; Pair each data in the measurement data with the remaining data in the measurement data to obtain at least one paired group; Calculate the absolute value of the difference between two data in each paired group of measurement data, and accumulate the absolute values ​​of the difference between two data in all paired groups to obtain a discrete value; The discrete value is set as the discrete degree of the data, and a discrete identification code is assigned to the discrete degree.

4. The method for automatic analysis and processing of electric energy metering structured data according to claim 3, characterized in that: The variance is: Among them, D is the variance, n is the number of data, x i is the value of the data, and a is the average value of the data.

5. The method for automatic analysis and processing of electric energy metering structured data according to claim 4, characterized in that: The pre-processed metering data is divided into several groups, including: Retrieve data normalization standard 1 from the database, and obtain the range interval of the central tendency ratio and the range interval of the dispersion ratio in the data normalization standard 1; Calculate the ratio of the central tendency of the data to the mean of the central tendency of the sample data; Calculate the ratio of the degree of dispersion of the data to the mean of the degree of dispersion of the sample data; Ratio 1 is compared with the first preset threshold and ratio 2 is compared with the second preset threshold to determine whether the central trend of the data belongs to the range interval of the central tendency ratio and the range interval of the dispersion ratio in normalization standard 1, and based on the judgment result, the measurement data is fused.

6. The method for automatic analysis and processing of electric energy metering structured data according to claim 5, characterized in that: Based on the judgment results, the measurement data is integrated, including: If the ratio value 1 is greater than or equal to the first preset threshold, it belongs to the range interval of the central tendency ratio in the normalization standard 1; If the ratio value 1 is less than the first preset threshold, it does not belong to the range interval of the central tendency ratio value in the normalization standard 1; If the second ratio is greater than or equal to the second preset threshold, it belongs to the range interval of the discrete degree ratio in the normalization standard one; If the second ratio is less than the second preset threshold, it does not belong to the range interval of the discrete degree ratio in the normalization standard one; The data belonging to the range interval of the central tendency ratio and the range interval of the dispersion ratio in the normalization standard 1 are attributed to the first data; The data that does not belong to the range interval of the central tendency ratio and the range interval of the dispersion ratio in the first normalization standard are classified as the second data; The first data and the second data are fused respectively to obtain first fused data and second fused data.

7. The method for automatic analysis and processing of electric energy metering structured data according to claim 6, characterized in that: The electric energy analysis model is constructed based on the feedforward neural network, including: Based on feedforward neural network, construct power analysis model; Based on machine learning, the multiple historical measurement data are labeled and divided to obtain a training set, a validation set, and a test set; The training set, validation set and test set are used to perform supervised training, validation and testing on the electric energy analysis model to obtain the electric energy analysis model whose accuracy meets the preset accuracy requirements.

8. The method for automatic analysis and processing of electric energy metering structured data according to claim 7, characterized in that: The electric energy analysis model is: Where C is the degree of fit between the characteristic parameters of the input measurement data analysis set and the characteristic parameters of the alarm data set in the system, S i is the i-th characteristic parameter, α i is the weight value of the i-th feature parameter, and m is the total number of feature parameters.

9. An automatic analysis and processing system for electric energy metering structured data, used to implement an automatic analysis and processing method for electric energy metering structured data as claimed in any one of claims 1 to 8, characterized in that: The system comprises: A preprocessing module is used to collect metering data of the electric energy meter in real time, and preprocess the metering data to obtain preprocessed metering data, wherein the preprocessing is missing value filling; The classification and fusion module is used to calculate the central tendency and dispersion degree of the pre-processed measurement data, and to divide the pre-processed measurement data into several groups and fuse the same measurement data; A formation module is used to form a measurement data analysis set from multiple fused data; The retrieval module is used to retrieve all historical measurement data before the alarm state occurs from the database, record them as the alarm data set, and mark and divide the historical measurement data to obtain the training set, verification set and test set; A building block for building an electric energy analysis model based on a feedforward neural network; The processing module is used to input the metering data analysis set into the electric energy analysis model to determine whether to issue an alarm.

10. An electronic device comprising at least one processor; and a memory connected to the at least one processor in communication; characterized in that: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

Images