Electricity utilization behavior monitoring method and device based on electricity utilization acquisition terminal
By acquiring and processing current data on the power consumption acquisition terminal and building an intelligent identification model, the timeliness and accuracy of power consumption behavior monitoring in the existing technology are solved, and the accurate identification of user load and timely power consumption behavior are achieved. Monitoring reduces the risk of electrical fires.
Patent Information
- Application Number
- CN202411554137.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-04
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When monitoring electricity usage behavior, the prior art has poor timeliness and low accuracy when facing a large user group, especially in the monitoring of load use, which leads to the occurrence of electrical fires.
The original current data of the load is obtained by using the power acquisition terminal, Fourier transform processing is performed to extract current harmonic data, build an intelligent recognition model for pattern recognition analysis, determine load classification information, and filter out the target load from the load database to obtain The results of the user's electricity use behavior.
It realizes timely and accurate identification of users' electricity usage behavior, improves the accuracy of load use monitoring, and reduces the risk of electrical fires.
Smart Images

Figure CN119070486A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power systems, and in particular to a method and device for monitoring power consumption behavior based on a power consumption collection terminal. Background Art
[0002] Regarding electricity safety, there are two main reasons for electrical fire accidents. On the one hand, it is the aging of the circuit itself, overcurrent, overload, short circuit and other reasons. On the other hand, it is the improper use of the load by the user, overloading the load, and the failure of the electrical safety quality to meet the standards. For overcurrent and short circuit situations, the circuit usually has air switches and other current limiting safety devices that can play a good protective role and can prevent fires caused by such situations. The lack of accurate and reliable equipment for monitoring the use of loads is also a major cause of electrical fires.
[0003] Currently, the monitoring of electricity usage behavior is mainly aimed at electricity safety. The most common method is to detect overcurrent and overload in the circuit. When overcurrent or overload occurs, the user's electricity usage behavior is identified. This method has the problems of poor timeliness and low accuracy in the face of a large user group.
[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of the present invention is to provide a method and device for monitoring electricity consumption behavior based on an electricity consumption collection terminal, aiming to solve the technical problems of poor timeliness and low accuracy in the current method facing a large user group.
[0006] To achieve the above object, the present invention provides a method for monitoring electricity consumption behavior based on an electricity consumption collection terminal, the method comprising the following steps: The original current data of the user's load during the electricity consumption process is obtained through the electricity consumption collection terminal; Processing the original current data to obtain current harmonic data of the load; Constructing an intelligent recognition model, and performing pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain classification information of the load; Determining a plurality of matching loads based on the classification information of the load; Filtering a target load from a load database based on the plurality of matching loads; The user's electricity usage behavior result is obtained according to the target load.
[0007] In some embodiments, the current harmonic data includes a harmonic coefficient of the current, and the processing of the original current data to obtain the current harmonic data of the load includes: Perform Fourier transform on the original data f(t) to obtain the harmonic component data of the signal, the expression is: ; The harmonic component data of the signal is processed to obtain: ; Let A0=a0 / 2, a n =A n cosφ n , b n =A n sinφ n , we get: ; Among them, a n , b n are the harmonic coefficients of f(t), is the fundamental frequency of the signal, and n is the fundamental multiple; make , , we get: ; Among them, F0=a0, F n =(a n -j n ) / 2, and get the discrete signal ; According to the discrete signal Get the harmonic coefficient of current .
[0008] In some embodiments, the method further comprises: Performing discrete Fourier transform on the raw current data and taking the first 15 harmonic coefficients; The modulus of the Fourier coefficients is formed into a vector group , and normalize the vector group to obtain .
[0009] In some embodiments, the constructing of the intelligent recognition model includes: Initialize the input and output node numbers and the hidden layer node number of the neural network according to the input and output of the system, initialize the connection weights between the hidden layer and the input layer, between the hidden layer and the output layer, and the thresholds corresponding to the hidden layer and the output layer, and determine the preset data of the neural network, including the activation function, learning rate, number of iterations, and error accuracy; The weighted result is calculated according to the input data and connection weight of the input layer and then combined with the hidden layer threshold to obtain the hidden layer calculation result; Calculating the hidden layer calculation result and the output layer threshold to obtain the output layer calculation result; Based on the calculation result of the output layer, the error between the calculated output of each output layer and the actual output is calculated, the output within the error accuracy allowable range is used as the predicted output, and the output exceeding the error accuracy is subjected to error reverse propagation processing; When the error output by the output layer of the system does not meet the error requirement, the weights and thresholds of each layer are updated inversely, and the input is calculated according to the new weights and thresholds until the iteration is completed to obtain an intelligent recognition model.
[0010] In some embodiments, the number of neurons in the hidden layer is , where a ranges from 0 to 10, m and n represent the number of nodes adjacent to the hidden layer, respectively. The target learning rate corresponding to the reverse transfer process is ,in, and They represent the maximum learning rate and the minimum learning rate respectively, and t represents the number of iterations.
[0011] In some embodiments, the determining a plurality of matching loads based on the classification information of the load includes: Constructing a first multidimensional feature vector based on the current harmonic data and sequentially constructing second multidimensional feature vectors corresponding to different types of loads based on the classification information; Calculating the distance between the first multidimensional feature vector and the second multidimensional feature vector; A second multidimensional feature vector corresponding to the minimum distance is determined according to the calculated distance, and a plurality of matching loads are determined based on the second multidimensional feature vector corresponding to the minimum distance.
[0012] In some embodiments, the step of selecting a target load from a load database based on the plurality of matching loads includes: Query the harmonic order threshold corresponding to each load from the load database; Comparing the current harmonic data with each harmonic order threshold; Based on the comparison result, a load whose harmonic order threshold satisfies the current harmonic data is taken as a target load, wherein the current harmonic order contained in the current harmonic data does not exceed the harmonic order threshold.
[0013] In addition, to achieve the above-mentioned purpose, the present invention also proposes a power consumption behavior monitoring device based on a power consumption collection terminal, and the power consumption behavior monitoring device based on a power consumption collection terminal comprises: An acquisition module is used to acquire the original current data of the user's load during the power consumption process through the power consumption collection terminal; A processing module, used for processing the original current data to obtain current harmonic data of the load; A construction module, used for constructing an intelligent recognition model, and performing pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain classification information of the load; A matching module, configured to determine a plurality of matching loads based on the classification information of the loads; A screening module, used for screening out a target load from a load database based on the plurality of matching loads; The identification module is used to obtain the user's power consumption behavior results according to the target load.
[0014] In some embodiments, the current harmonic data includes harmonic coefficients of the current, and the processing module is used to perform Fourier transform on the original data f(t) to obtain harmonic component data of the signal, expressed as: ; The harmonic component data of the signal is processed to obtain: ; Let A0=a0 / 2, a n =A n cosφ n , b n =A n sinφ n , we get: ; Among them, a n , b n are the harmonic coefficients of f(t), is the fundamental frequency of the signal, and n is the fundamental multiple; make , , we get: ; Among them, F0=a0, F n =(a n -j n ) / 2, and get the discrete signal ; According to the discrete signal Get the harmonic coefficient of current .
[0015] In some embodiments, the processing module is used to perform a discrete Fourier transform on the raw current data and obtain the first 15 harmonic coefficients; The modulus of the Fourier coefficients is formed into a vector group , and normalize the vector group to obtain .
[0016] The present invention obtains the original current data of the user's load during the electricity use process through the electricity collection terminal; processes the original current data to obtain the current harmonic data of the load; constructs an intelligent recognition model, and performs pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain the classification information of the load; determines a number of matching loads based on the classification information of the load; screens out the target load from the load database based on the several matching loads; and obtains the user's electricity use behavior results based on the target load. In the above manner, the load current data is used to identify the load used by the user, and the user's electricity use behavior can be timely and accurately identified based on the identified load. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 It is a flow chart of a first embodiment of a method for monitoring electricity consumption behavior based on an electricity consumption collection terminal according to the present invention; Figure 2 It is a schematic diagram of the BP neural network structure in the power consumption behavior monitoring method based on the power consumption collection terminal of the present invention; Figure 3 This is a structural block diagram of a first embodiment of a power consumption behavior monitoring device based on a power consumption collection terminal according to the present invention.
[0018] 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
[0019] 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.
[0020] The embodiment of the present invention provides a method for monitoring electricity consumption behavior based on an electricity consumption collection terminal, referring to Figure 1 , Figure 1 The figure is a flow chart of a first embodiment of a method for monitoring electricity consumption behavior based on an electricity consumption collection terminal according to the present invention.
[0021] In this embodiment, the electricity consumption behavior monitoring method based on the electricity consumption collection terminal includes the following steps: Step S10: obtaining the original current data of the user's load during the power consumption process through the power consumption collection terminal.
[0022] In this embodiment, the executor of this embodiment is an electricity consumption behavior monitoring device based on an electricity consumption collection terminal, wherein the electricity consumption behavior monitoring device based on an electricity consumption collection terminal has functions such as data processing, data communication and program running. The electricity consumption behavior monitoring device based on an electricity consumption collection terminal can be a computer terminal device or other network device, and of course it can also be other devices with similar functions, and this embodiment does not limit this.
[0023] It should be noted that the current monitoring of electricity usage behavior is mainly aimed at electricity safety. The most commonly used method is to achieve it through circuit overcurrent, overload, etc. When overcurrent or overload occurs, the user's electricity usage behavior is identified. Faced with a large user group, this method has the problems of poor timeliness and low accuracy.
[0024] In order to solve the above technical problems, in this embodiment, the original current data of the user's load during the electricity use process is obtained through the electricity collection terminal; the original current data is processed to obtain the current harmonic data of the load; an intelligent recognition model is constructed, and the current harmonic data is subjected to pattern recognition analysis through the intelligent recognition model to obtain the classification information of the load; a number of matching loads are determined based on the classification information of the load; a target load is screened out from the load database based on the several matching loads; and the user's electricity use behavior results are obtained based on the target load. In the above manner, the load current data is used to identify the load used by the user, and the user's electricity use behavior can be timely and accurately identified based on the identified load. Specifically, it can be implemented in the following manner.
[0025] In the specific implementation, it is first necessary to obtain the original current data of the user's load during the power consumption process through the power consumption collection terminal.
[0026] Step S20: Processing the original current data to obtain current harmonic data of the load.
[0027] It should be noted that the amount of raw current data is large, and the amount of calculation when using the raw current data for load classification and identification is too large, which will affect the processing speed in practical applications and have high requirements for hardware processing equipment. In addition, too much data as input to the neural network will also reduce the training speed and efficiency of the network, so in this embodiment, the raw current data is first processed to extract key information, that is, the current harmonic data of the load.
[0028] The processing process in this embodiment is to first perform Fourier transform on the original data to obtain the harmonic component data of the signal, and then obtain , further processing of the obtained data can be obtained .
[0029] Continue to set A0=a0 / 2, a n =A n cosφ n , b n =A n sinφ n , we can get: ; Among them, a n , b n are the harmonic coefficients of f(t), is the fundamental frequency of the signal, and n is the fundamental multiple; make , , we get: ; Among them, F0=a0, F n =(a n -j n ) / 2, and get the discrete signal ; According to the discrete signal Get the harmonic coefficient of current The harmonic coefficient of the current obtained in this embodiment can be used as a characteristic parameter of the load for subsequent identification of the load.
[0030] It should be noted that in this embodiment, the original current data is subjected to discrete Fourier transform, and the first 15 harmonic coefficients are obtained. Since the power of different electrical appliances varies greatly, the obtained Fourier coefficients are normalized to avoid the difference caused by the power size during data processing and identification. For example, the vector group composed of the modulus value of the Fourier coefficient is , after normalization, we can get .
[0031] Step S30: constructing an intelligent recognition model, and performing pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain classification information of the load.
[0032] In this embodiment, the load being used by the user is identified through the intelligent recognition model, so as to monitor the user's electricity consumption behavior. The specific construction process of the intelligent recognition model is to initialize the input and output node numbers and the hidden layer node numbers of the neural network according to the input and output of the system, and initialize the connection weights between the hidden layer and the input layer, the hidden layer and the output layer, and the thresholds corresponding to the hidden layer and the output layer, and determine the preset data of the neural network at the same time. The preset data includes an activation function, a learning rate, the number of iterations, and an error accuracy; Calculate the weighted result according to the input data and the connection weight of the input layer and calculate it with the hidden layer threshold to obtain the hidden layer calculation result; The hidden layer calculation result and the output layer threshold are calculated to obtain the output layer calculation result; based on the output layer calculation result, the error between the calculated output of each output layer and the actual output is calculated, the output within the error accuracy range is used as the predicted output, and the output exceeding the error accuracy will be processed by error reverse transmission; when the error of the output layer output of the system does not meet the error requirement, the weights and thresholds of each layer are reversely updated, and the input is calculated according to the new weights and thresholds until the iteration is completed to obtain an intelligent recognition model, wherein the system is a system of a neural network structure, and the BP neural network model is used in this embodiment. The specific structure can be referred to Figure 2 As shown. Among them, the number of neurons in the hidden layer is , where a ranges from 0 to 10, and m and n represent the number of nodes adjacent to the hidden layer.
[0033] It should be noted that, from the error back propagation analysis, the learning rate is of great significance to the weight modification of the system. The initial learning rate setting has a significant impact on the training process of the BP neural network. The learning rate η∈[0,1] of the BP neural network, the size of the neural network learning rate determines the speed of the neural network learning during the training phase. The larger the value, the greater the modification of the weights during the neural network error back propagation process, and the faster the network learning speed. At the same time, too fast a network learning rate can easily cause oscillations in the weight learning process. On the contrary, the smaller the learning rate value, the smaller the modification of the weights during each iteration of the training data during the neural network training process. The most direct impact is that the neural network has too many iterations and converges too slowly. In order to adapt to different stages of training, a learning algorithm with a variable learning rate is adopted in this embodiment. By changing the learning rate, problems such as system instability and slow convergence caused by inappropriate learning rate settings can be avoided. The calculation formula for the target learning rate corresponding to the reverse transfer processing in this embodiment is: ,in, and Respectively represent the maximum learning rate and the minimum learning rate, and t represents the number of iterations. After completing the construction of the above intelligent recognition model, the classification information of the load can be obtained by performing pattern recognition analysis on the current harmonic data through the intelligent recognition model.
[0034] Step S40: Determine a number of matching loads based on the classification information of the loads.
[0035] A first multidimensional feature vector x(x1, x2, ..., xm) is constructed according to the extracted current harmonic data, and then second multidimensional feature vectors y(y1, y2, ..., ym) corresponding to different types of loads are constructed in sequence according to the classification information, and then the distance between the first multidimensional feature vector and the second multidimensional feature vector is calculated. For example , and finally the second multi-dimensional feature vector corresponding to the minimum distance can be calculated, thereby obtaining several matching loads.
[0036] Step S50: Filtering out a target load from a load database based on the plurality of matching loads.
[0037] It should be noted that the load types in this embodiment include, for example, pure resistive type, capacitive type, inductive type and mixed type, but there are multiple loads corresponding to each load type. For example, the loads corresponding to the pure resistive type include water heaters, electric kettles and soldering irons, and the loads corresponding to the capacitive type include fluorescent lamps and computers. Because in this embodiment, after obtaining several matching loads according to the classification information, it is necessary to further accurately locate the target load.
[0038] Specifically, the harmonic order threshold corresponding to each load can be queried from the load database, the current harmonic data can be compared with each harmonic order threshold, and based on the comparison result, the load whose harmonic order threshold meets the current harmonic data is taken as the target load, and the current harmonic number of the target load does not exceed the corresponding harmonic order threshold.
[0039] Step S60: Obtaining the user's electricity usage behavior results according to the target load.
[0040] After identifying the load that the user is using, the user's electricity usage behavior can be identified. After detecting the load that the user is using, the load state change can be obtained based on the load power change and the current and voltage change, thereby determining whether the user has abnormal electricity usage behavior. For example, taking a student dormitory as an example, the above method can be used to identify whether the student is using high-power electrical appliances based on the load power change and the current and voltage change.
[0041] This embodiment obtains the original current data of the user's load during the power consumption process through the power consumption collection terminal; processes the original current data to obtain the current harmonic data of the load; constructs an intelligent recognition model, and performs pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain the classification information of the load; determines a number of matching loads based on the classification information of the load; screens out the target load from the load database based on the several matching loads; and obtains the user's power consumption behavior results based on the target load. In the above manner, the load current data is used to identify the load used by the user, and the user's power consumption behavior can be timely and accurately identified based on the identified load.
[0042] Reference Figure 3 , Figure 3 This is a structural block diagram of a first embodiment of a power consumption behavior monitoring device based on a power consumption collection terminal according to the present invention.
[0043] like Figure 3 As shown, the power consumption behavior monitoring device based on the power consumption collection terminal proposed in the embodiment of the present invention includes: The acquisition module 10 is used to acquire the original current data of the load during the user's electricity consumption process through the electricity consumption collection terminal.
[0044] The processing module 20 is used to process the original current data to obtain the current harmonic data of the load.
[0045] The construction module 30 is used to construct an intelligent recognition model, and perform pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain classification information of the load.
[0046] The matching module 40 is used to determine a number of matching loads based on the classification information of the loads.
[0047] The screening module 50 is used to screen out a target load from the load database based on the plurality of matching loads.
[0048] The identification module 60 is used to obtain the user's power consumption behavior results according to the target load.
[0049] This embodiment obtains the original current data of the user's load during the power consumption process through the power consumption collection terminal; processes the original current data to obtain the current harmonic data of the load; constructs an intelligent recognition model, and performs pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain the classification information of the load; determines a number of matching loads based on the classification information of the load; screens out the target load from the load database based on the several matching loads; and obtains the user's power consumption behavior results based on the target load. In the above manner, the load current data is used to identify the load used by the user, and the user's power consumption behavior can be timely and accurately identified based on the identified load.
[0050] In some embodiments, the current harmonic data includes harmonic coefficients of the current, and the processing module 20 is used to perform Fourier transform on the original data f(t) to obtain harmonic component data of the signal, which is expressed as: ; The harmonic component data of the signal is processed to obtain: ; Let A0=a0 / 2, a n =A n cosφ n , b n =A n sinφ n , we get: ; Among them, a n , b n are the harmonic coefficients of f(t), is the fundamental frequency of the signal, and n is the fundamental multiple; make , , we get: ; Among them, F0=a0, F n =(a n -j n ) / 2, and get the discrete signal ; According to the discrete signal Get the harmonic coefficient of current .
[0051] In some embodiments, the processing module 20 is used to perform a discrete Fourier transform on the raw current data and obtain the first 15 harmonic coefficients; The modulus of the Fourier coefficients is formed into a vector group , and normalize the vector group to obtain .
[0052] In some embodiments, the construction module 30 is used to initialize the input and output node numbers and the hidden layer node number of the neural network according to the input and output of the system, and initialize the connection weights between the hidden layer and the input layer, the hidden layer and the output layer, and the thresholds corresponding to the hidden layer and the output layer, and determine the preset data of the neural network, the preset data including the activation function, the learning rate, the number of iterations, and the error accuracy; The weighted result is calculated according to the input data and connection weight of the input layer and then combined with the hidden layer threshold to obtain the hidden layer calculation result; Calculating the hidden layer calculation result and the output layer threshold to obtain the output layer calculation result; Based on the calculation result of the output layer, the error between the calculated output of each output layer and the actual output is calculated, the output within the error accuracy allowable range is used as the predicted output, and the output exceeding the error accuracy is subjected to error reverse propagation processing; When the error output by the output layer of the system does not meet the error requirement, the weights and thresholds of each layer are updated inversely, and the input is calculated according to the new weights and thresholds until the iteration is completed to obtain an intelligent recognition model.
[0053] In some embodiments, the number of neurons in the hidden layer is , where a ranges from 0 to 10, m and n represent the number of nodes adjacent to the hidden layer, respectively. The target learning rate corresponding to the reverse transfer process is ,in, and They represent the maximum learning rate and the minimum learning rate respectively, and t represents the number of iterations.
[0054] In some embodiments, the matching module 40 is used to construct a first multidimensional feature vector based on the current harmonic data and to sequentially construct second multidimensional feature vectors corresponding to different types of loads based on the classification information; calculate the distance between the first multidimensional feature vector and the second multidimensional feature vector; A second multidimensional feature vector corresponding to the minimum distance is determined according to the calculated distance, and a plurality of matching loads are determined based on the second multidimensional feature vector corresponding to the minimum distance.
[0055] In some embodiments, the screening module 50 is used to query the harmonic order threshold corresponding to each load from the load database; Comparing the current harmonic data with each harmonic order threshold; Based on the comparison result, a load whose harmonic order threshold satisfies the current harmonic data is taken as a target load, wherein the current harmonic order contained in the current harmonic data does not exceed the harmonic order threshold.
[0056] An embodiment of the present application also provides an electricity consumption behavior monitoring device based on an electricity consumption collection terminal, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, and the memory is used to store computer programs; the processor is used to implement the above-mentioned electricity consumption behavior monitoring method based on the electricity consumption collection terminal when executing the program stored in the memory.
[0057] The communication bus mentioned in the above-mentioned power consumption behavior monitoring device based on the power consumption collection terminal can be a peripheral component interconnect standard (English: Peripheral Component Interconnect, referred to as: PCI) bus or an extended industry standard architecture (English: Extended Industry Standard Architecture, referred to as: EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.
[0058] The communication interface is used for communication between the above-mentioned electricity consumption behavior monitoring device based on the electricity consumption collection terminal and other devices.
[0059] 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.
[0060] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.
[0061] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.
[0062] 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.
[0063] 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.
[0064] 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.
[0065] 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.
[0066] 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.
[0067] In addition, for technical details not fully described in this embodiment, reference can be made to the power consumption behavior monitoring method based on the power consumption collection terminal provided in any embodiment of the present invention, and will not be repeated here.
[0068] 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.
[0069] 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.
[0070] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0071] 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.
[0072] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.
Claims
1. A method for monitoring electricity consumption behavior based on an electricity consumption collection terminal, characterized in that: The electricity consumption behavior monitoring method based on the electricity consumption collection terminal includes: The original current data of the user's load during the electricity consumption process is obtained through the electricity consumption collection terminal; Processing the original current data to obtain current harmonic data of the load, wherein the current harmonic data includes a harmonic coefficient of the current; Wherein, the processing of the original current data to obtain the current harmonic data of the load further includes: Perform Fourier transform on the original data f(t) to obtain the harmonic component data of the signal, the expression is: ; The harmonic component data of the signal is processed to obtain: ; Let A0=a0 / 2, a n =A n cosφ n , b n =A n sinφ n , we get: ; Among them, a n , b n are the harmonic coefficients of f(t), is the fundamental frequency of the signal, and n is the fundamental multiple; make , , we get: ; Among them, F0=a0, F n =(a n -j n ) / 2, and get the discrete signal ; According to the discrete signal Get the harmonic coefficient of current ; Constructing an intelligent recognition model, and performing pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain classification information of the load; Determining a plurality of matching loads based on the classification information of the load; Filtering a target load from a load database based on the plurality of matching loads; The user's electricity usage behavior result is obtained according to the target load.
2. The method for monitoring electricity consumption behavior based on an electricity consumption collection terminal according to claim 1, characterized in that: The method further comprises: Performing discrete Fourier transform on the raw current data and taking the first 15 harmonic coefficients; The modulus of the Fourier coefficients is formed into a vector group , and normalize the vector group to obtain .
3. The method for monitoring electricity consumption behavior based on an electricity consumption collection terminal according to claim 1, characterized in that: The constructing of the intelligent recognition model includes: Initialize the input and output node numbers and the hidden layer node number of the neural network according to the input and output of the system, initialize the connection weights between the hidden layer and the input layer, between the hidden layer and the output layer, and the thresholds corresponding to the hidden layer and the output layer, and determine the preset data of the neural network, including the activation function, learning rate, number of iterations, and error accuracy; The weighted result is calculated according to the input data and connection weight of the input layer and then combined with the hidden layer threshold to obtain the hidden layer calculation result; Calculating the hidden layer calculation result and the output layer threshold to obtain the output layer calculation result; Based on the calculation result of the output layer, the error between the calculated output of each output layer and the actual output is calculated, the output within the error accuracy allowable range is used as the predicted output, and the output exceeding the error accuracy is subjected to error reverse propagation processing; When the error output by the output layer of the system does not meet the error requirement, the weights and thresholds of each layer are updated inversely, and the input is calculated according to the new weights and thresholds until the iteration is completed to obtain an intelligent recognition model.
4. The method for monitoring electricity consumption behavior based on an electricity consumption collection terminal according to claim 3, characterized in that: The number of neurons in the hidden layer is , where a ranges from 0 to 10, m and n represent the number of nodes adjacent to the hidden layer, respectively. The target learning rate corresponding to the reverse transfer process is ,in, and They represent the maximum learning rate and the minimum learning rate respectively, and t represents the number of iterations.
5. The method for monitoring electricity consumption behavior based on an electricity consumption collection terminal according to claim 1, characterized in that: The determining a plurality of matching loads based on the classification information of the loads includes: Constructing a first multidimensional feature vector based on the current harmonic data and sequentially constructing second multidimensional feature vectors corresponding to different types of loads based on the classification information; Calculating the distance between the first multidimensional feature vector and the second multidimensional feature vector; A second multidimensional feature vector corresponding to the minimum distance is determined according to the calculated distance, and a plurality of matching loads are determined based on the second multidimensional feature vector corresponding to the minimum distance.
6. The method for monitoring electricity consumption behavior based on an electricity consumption collection terminal according to any one of claims 1 to 5, characterized in that: The step of selecting a target load from a load database based on the plurality of matching loads includes: Query the harmonic order threshold corresponding to each load from the load database; Comparing the current harmonic data with each harmonic order threshold; Based on the comparison result, a load whose harmonic order threshold satisfies the current harmonic data is taken as a target load, wherein the current harmonic order contained in the current harmonic data does not exceed the harmonic order threshold.
7. A power consumption behavior monitoring device based on a power consumption collection terminal, characterized in that: The electricity consumption behavior monitoring device based on the electricity consumption collection terminal includes: An acquisition module is used to acquire the original current data of the user's load during the power consumption process through the power consumption collection terminal; A processing module, used for processing the original current data to obtain current harmonic data of the load, wherein the current harmonic data includes a harmonic coefficient of the current; The processing module is further used to perform Fourier transform on the original data f(t) to obtain the harmonic component data of the signal, which is expressed as: ; The harmonic component data of the signal is processed to obtain: ; Let A0=a0 / 2, a n =A n cosφ n , b n =A n sinφ n , we get: ; Among them, a n , b n are the harmonic coefficients of f(t), is the fundamental frequency of the signal, and n is the fundamental multiple; make , , we get: ; Among them, F0=a0, F n =(a n -j n ) / 2, and get the discrete signal ; According to the discrete signal Get the harmonic coefficient of current ; A construction module, used for constructing an intelligent recognition model, and performing pattern recognition analysis on the current harmonic data through the intelligent recognition model to obtain classification information of the load; A matching module, configured to determine a plurality of matching loads based on the classification information of the loads; A screening module, used for screening out a target load from a load database based on the plurality of matching loads; The identification module is used to obtain the user's power consumption behavior results according to the target load.
8. The power consumption behavior monitoring device based on the power consumption collection terminal according to claim 7, characterized in that: The processing module is used to perform discrete Fourier transform on the original current data and obtain the first 15 harmonic coefficients; The modulus of the Fourier coefficients is formed into a vector group , and normalize the vector group to obtain .
9. The power consumption behavior monitoring device based on the power consumption collection terminal according to claim 7, characterized in that: The construction module is used to initialize the input and output node numbers and the hidden layer node number of the neural network according to the input and output of the system, and initialize the connection weights between the hidden layer and the input layer, the hidden layer and the output layer, and the thresholds corresponding to the hidden layer and the output layer, and determine the preset data of the neural network, the preset data including the activation function, the learning rate, the number of iterations, and the error accuracy; The weighted result is calculated according to the input data and connection weight of the input layer and then combined with the hidden layer threshold to obtain the hidden layer calculation result; Calculating the hidden layer calculation result and the output layer threshold to obtain the output layer calculation result; Based on the calculation result of the output layer, the error between the calculated output of each output layer and the actual output is calculated, the output within the error accuracy allowable range is used as the predicted output, and the output exceeding the error accuracy is subjected to error reverse propagation processing; When the error output by the output layer of the system does not meet the error requirement, the weights and thresholds of each layer are updated inversely, and the input is calculated according to the new weights and thresholds until the iteration is completed to obtain an intelligent recognition model.
10. The power consumption behavior monitoring device based on the power consumption collection terminal according to claim 9, characterized in that: The number of neurons in the hidden layer is , where a ranges from 0 to 10, m and n represent the number of nodes adjacent to the hidden layer, respectively. The target learning rate corresponding to the reverse transfer process is ,in, and They represent the maximum learning rate and the minimum learning rate respectively, and t represents the number of iterations.
Citation Information
Patent Citations
A user power consumption load characteristic analysis method
CN109815994A
Load identification and power frequency series arc fault detection method
CN110118900A
