A method for intelligent monitoring of safe electricity use

Abstract

The present invention relates to the technical field of electricity safety, and discloses an intelligent monitoring instrument for safe electricity use, including: collecting current waveforms of different electrical equipment, and preprocessing the collected current waveforms to remove noise data in the current waveforms; using FFTs of different frequencies to decompose the preprocessed current waveforms, and storing the decomposition results in a database; obtaining the waveforms of the electrical equipment to be monitored, and preprocessing and FFT decomposing the waveforms of the electrical equipment, constructing a similarity measurement function between the decomposition results of the waveforms of the electrical equipment to be monitored and the decomposition results in the database, and solving the similarity measurement function using a flower pollination algorithm; selecting the electrical equipment category with the highest similarity measurement result in the database as the electrical equipment category to be monitored, and judging whether the load of the electrical equipment to be monitored is abnormal. If the load is abnormal, the equipment is a malicious device and there is a risk of electricity use. The present invention uses an intelligent monitoring instrument for safe electricity use to realize real-time monitoring of electrical equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity safety, and in particular to an intelligent monitoring method for safe electricity use. Background Art

[0002] In recent years, due to the use of a large number of high-power illegal electrical appliances, fires have frequently occurred in places such as student dormitories and construction sites. The issue of electrical safety in places such as student dormitories and construction sites has become a focus of increasing attention. How to use effective methods to accurately identify whether electrical equipment has safety risks has become a hot topic in current research.

[0003] Traditional monitoring methods for electrical equipment are not automated, require large amounts of computation, are inefficient, and have poor adaptability to the randomness and nonlinearity of electrical equipment loads, making them unsuitable for real-time monitoring needs.

[0004] In view of this, how to achieve real-time monitoring of the power safety of electrical equipment has become an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0005] The present invention provides an intelligent monitoring method for safe electricity use, the purpose of which is to (1) simplify the safety monitoring process of electrical equipment; and (2) achieve real-time monitoring of the safety of electricity use of electrical equipment.

[0006] To achieve the above object, the present invention provides a safe electricity intelligent monitoring method, comprising the following steps:

[0007] S1: Collect current waveforms of different electrical equipment, and pre-process the collected current waveforms to remove noise data in the current waveforms;

[0008] S2: Decompose the preprocessed current waveform using FFT of different frequencies to obtain decomposition results of the electrical equipment at different frequencies, and store the decomposition results in a database;

[0009] S3: Obtain the waveform of the electrical equipment to be monitored, preprocess and perform FFT decomposition on the waveform of the electrical equipment, construct a similarity measurement function between the decomposition result of the waveform of the electrical equipment to be monitored and the decomposition result in the database, solve the similarity measurement function using the flower pollination algorithm, and obtain the similarity measurement result between the electrical equipment to be monitored and the electrical equipment in the database;

[0010] S4: Select the electrical equipment category with the highest similarity measurement result in the database as the electrical equipment category to be monitored, and determine whether the load of the electrical equipment to be monitored is abnormal. If the load is abnormal, the device is a malicious device and there is a risk of electricity consumption.

[0011] As a further improvement method of the present invention:

[0012] In the step S1, current waveforms of different types of electrical equipment are collected, and the collected current waveforms are pre-processed by pre-emphasis, including:

[0013] The current waveforms of different types of electrical equipment are collected using the safe electricity intelligent monitoring instrument. The collected current waveforms are in the form of:

[0014] ;

[0015] in:

[0016] is the current waveform of the electrical equipment i, n-1 represents the time domain information of the current waveform, Represents the signal value at time n-1;

[0017] The collected current waveform is pre-processed by pre-emphasis, and the formula for the pre-emphasis processing is:

[0018] ;

[0019] in:

[0020] Indicates the pre-emphasis coefficient, set it to 0.96;

[0021] Represents the signal value of electrical device i at time j.

[0022] In the step S1, the current waveform after the pre-emphasis processing is pre-processed for signal denoising to obtain the denoised current waveform, including:

[0023] Establish the signal function of the current waveform signal:

[0024] ;

[0025] in:

[0026] It is the current waveform signal after pre-emphasis preprocessing;

[0027] is the preprocessed current waveform signal after signal denoising;

[0028] is the noise signal in the current waveform signal;

[0029] Perform short-time Fourier transform on both sides of the signal function:

[0030] ;

[0031] in:

[0032] H represents the total number of frames of the current waveform signal, and h represents the index of the time frame of the current waveform signal;

[0033] K represents the total number of frequency points of the current waveform signal, and k represents the index of the frequency point;

[0034] Respectively represent the frequency domain representation of the noisy current waveform signal, the pure current waveform signal and the noise signal;

[0035] The signal power spectrum is obtained by squaring the signal function after short-time Fourier transform processing:

[0036] ;

[0037] in:

[0038] Represents the phase angle of the pure current waveform signal and the noise signal, then:

[0039] ;

[0040] Determine the frequency domain representation of the current waveform signal after denoising:

[0041] ;

[0042] The frequency domain representation of the denoised current waveform signal is performed using the short-time inverse Fourier transform algorithm. Perform signal reconstruction to obtain the pre-processed current waveform with signal denoising .

[0043] In the step S2, the pre-processed current waveform is decomposed using FFT algorithms of different frequencies to obtain decomposition results of the electrical equipment at different frequencies, including:

[0044] The pre-processed current waveform is decomposed using FFT algorithms of different frequencies:

[0045] ;

[0046] in:

[0047] Indicates the sampling frequency of the current waveform;

[0048] represents the FFT decomposition result of electrical equipment i;

[0049] represents the Fast Fourier Transform algorithm;

[0050] Get the decomposition results of electrical equipment at different frequencies:

[0051] ;

[0052] in:

[0053] represents the decomposition result of electrical equipment i at the sth frequency;

[0054] The decomposition results of different electrical equipment at different frequencies are stored in the database.

[0055] In the step S3, a similarity measurement function is constructed between the waveform decomposition result of the electric equipment to be monitored and the decomposition result in the database, including:

[0056] Obtain the waveform of the power equipment to be monitored, preprocess and perform FFT decomposition on the waveform of the power equipment, and construct a similarity measurement function between the decomposition result of the waveform of the power equipment to be monitored and the decomposition result in the database. The constructed similarity measurement function for;

[0057] ;

[0058] in:

[0059] represents the decomposition result of the electrical equipment k in the database at the jth frequency, and t represents the time domain information of the decomposition result;

[0060] s represents the number of decomposed frequencies, i represents the number of electrical devices in the database, and both s and i are integers;

[0061] represents the similarity parameter;

[0062] Represents the similarity measurement result between the decomposition result of the electric device to be monitored at the jth frequency and the decomposition structure of the electric device k in the database at the jth frequency;

[0063] It represents the decomposition result of the electrical equipment to be monitored at the jth frequency.

[0064] In the step S3, the flower pollination algorithm is used to solve the similarity measurement function, including:

[0065] The similarity parameter of the similarity metric function is solved by using the flower pollination algorithm, and the process of the flower pollination algorithm is as follows:

[0066] 1) Initialize parameters, set the pollen population size to N, and the maximum number of iterations to Max, where ;

[0067] 2) Set the similarity parameter interval to , randomly generate N data as pollen within the similarity parameter interval, and the pollen is the similarity parameter;

[0068] 3) Calculate each decomposition result The similarity measurement results are:

[0069] ;

[0070] Find the best value and optimal solution in the current pollen population , the optimal value is the value with the highest similarity measurement result, and the optimal solution is the similarity parameter corresponding to the optimal value; wherein j represents the decomposition result at the jth frequency, and k represents the electrical device k in the database;

[0071] 4) According to the movement form of pollinators in flower pollination, set the global iteration formula of pollen:

[0072] ;

[0073] in:

[0074] represents the value of the e-th pollen at the w-th iteration;

[0075] represents the optimal solution at the wth iteration;

[0076] represents the path of Levy flight, r represents the step size, and r is a random number in [0,1] that follows a uniform distribution;

[0077] Set the local iteration formula of pollen:

[0078] ;

[0079] r represents the step size, which is a random number in [0,1] that follows a uniform distribution;

[0080] Set conversion probability , for any pollen, if r>p, the global iteration method of pollen is used, otherwise the local iteration method of pollen is used;

[0081] 5) Repeat steps 3)-4) until the number of iterations reaches the preset maximum number of iterations Max, and use the final pollen result as the similarity parameter.

[0082] In the step S4, the category of the electrical equipment to be monitored is determined according to the similarity measurement result, including:

[0083] According to the determined similarity parameters, the decomposition results of the electrical equipment to be monitored at different frequencies are calculated, and the similarity measurement results of the decomposition results of the electrical equipment in the database at different frequencies are compared, and the electrical equipment category with the highest similarity measurement result in the database is selected as the electrical equipment category to be monitored.

[0084] In the step S4, determining whether the load of the electrical equipment to be monitored is abnormal includes:

[0085] According to the category of the electrical equipment to be monitored, the load type of the electrical equipment to be monitored is determined. If only a pure resistive load exists in the circuit of the electrical equipment to be monitored, the power factor of the load should be 1. When the power factor of the load of the electrical equipment to be monitored is not 1, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage. If only an inductive load or only a capacitive load exists in the circuit of the electrical equipment to be monitored, the power factor of the load should be 0. When the power factor of the load of the electrical equipment to be monitored is not 0, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage. When a mixed load exists in the circuit of the electrical equipment to be monitored, the power factor should be less than 1. If the power factor of the load of the electrical equipment to be monitored is greater than or equal to 1, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage.

[0086] The present invention also provides an intelligent monitoring instrument for safe electricity use, characterized in that the monitoring instrument comprises:

[0087] An electric equipment collection device for collecting current waveforms of electric equipment;

[0088] A data processor is used to perform denoising on the current waveform of the electric equipment, perform FFT decomposition on the current waveform, and store the decomposition results of the collected current waveform of the electric equipment in a database;

[0089] The power safety monitoring device is used to measure the similarity between the current waveform of the power equipment to be monitored and the current waveform in the database, determine the category of the power equipment to be monitored based on the similarity measurement result, and judge whether the load of the power equipment to be monitored is abnormal. If it is abnormal, the power risk is monitored.

[0090] Compared with the prior art, the present invention proposes an intelligent monitoring instrument for safe electricity use, which has the following advantages:

[0091] First, this solution uses FFT algorithms of different frequencies to decompose the current waveform of the collected electrical equipment to obtain the decomposition results of the electrical equipment at different frequencies, including: using FFT algorithms of different frequencies to decompose the current waveform of the collected electrical equipment:

[0092] ;

[0093] in: Indicates the sampling frequency of the current waveform; represents the FFT decomposition result of electrical equipment i; Represents the fast Fourier transform algorithm; the decomposition results of electrical equipment at different frequencies are obtained:

[0094] ;

[0095] in: Represents the decomposition result of the electrical device i at the sth frequency; the decomposition results of different electrical devices at different frequencies are stored in the database, so as to obtain the FFT decomposition results of the electrical devices at different frequencies, avoiding the difference in current waveforms caused by different frequencies of the same electrical device in the actual scene. Obtain the waveform of the electrical device to be monitored, preprocess and FFT decompose the waveform of the electrical device, and construct a similarity measurement function between the decomposition result of the waveform of the electrical device to be monitored and the decomposition result in the database. The constructed similarity measurement function for;

[0096] ;

[0097] in: represents the decomposition result of the electric device k in the database at the jth frequency, t represents the time domain information of the decomposition result; s represents the number of decomposed frequencies, i represents the number of electric devices in the database, and s and i are both integers; represents the similarity parameter; Represents the similarity measurement result between the decomposition result of the electric device to be monitored at the jth frequency and the decomposition structure of the electric device k in the database at the jth frequency; It represents the decomposition result of the electrical equipment to be monitored at the jth frequency. By calculating the decomposition results of the electrical equipment to be monitored at different frequencies and the similarity measurement results of the decomposition results of the electrical equipment in the database at different frequencies, the electrical equipment category with the highest similarity measurement result in the database is selected as the electrical equipment category to be monitored, so as to accurately identify the category of the electrical equipment to be monitored, and judge whether the load of the electrical equipment to be monitored is abnormal according to the category of the electrical equipment to be monitored. If abnormal, it means that the detector has detected electricity risk.

[0098] At the same time, this scheme solves the similarity parameters of the similarity measurement function by combining a heuristic search algorithm. The heuristic search algorithm process is as follows: initialize the parameters, set the pollen population size to N, and the maximum number of iterations to Max, where ; Set the similarity parameter interval to , randomly generate N data as pollen within the similarity parameter interval, and the pollen is the similarity parameter; calculate each decomposition result The similarity measurement results are:

[0099] ;

[0100] Find the best value and optimal solution in the current pollen population , the optimal value is the value with the highest similarity measurement result, and the optimal solution is the similarity parameter corresponding to the optimal value; where j represents the decomposition result at the jth frequency, and k represents the electrical device k in the database; according to the movement form of the pollinator in flower pollination, the global iteration formula of pollen is set:

[0101] ;

[0102] in: represents the value of the e-th pollen at the w-th iteration; represents the optimal solution at the wth iteration; represents the path of Levy flight, r represents the step size, and r is a random number in [0,1] that obeys a uniform distribution; set the local iteration formula of pollen:

[0103] ;

[0104] r represents the step size, r is a random number in [0,1] that follows a uniform distribution; set the conversion probability , for any pollen, if r>p, the global iterative method of pollen is used, otherwise the local iterative method of pollen is used; repeat the above steps until the number of iterations reaches the preset maximum number of iterations Max, and use the final pollen result as the similarity parameter. Compared with the traditional scheme, the heuristic search algorithm described in this scheme sets up a local iterative search method and a global iterative search method, which has the advantages of local fast optimization iteration and obtaining a global stable solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] Figure 1 A schematic diagram of a process flow of an intelligent monitoring instrument for safe electricity use provided by one embodiment of the present invention;

[0106] Figure 2 A schematic diagram of the structure of an intelligent monitoring instrument for safe electricity use provided by one embodiment of the present invention;

[0107] 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

[0108] 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.

[0109] S1: Collect current waveforms of different electrical equipment, and pre-process the collected current waveforms to remove noise data in the current waveforms.

[0110] In the step S1, current waveforms of different types of electrical equipment are collected, and the collected current waveforms are pre-processed by pre-emphasis, including:

[0111] The current waveforms of different types of electrical equipment are collected using the safe electricity intelligent monitoring instrument. The collected current waveforms are in the form of:

[0112] ;

[0113] in:

[0114] is the current waveform of the electrical equipment i, n-1 represents the time domain information of the current waveform, Represents the signal value at time n-1;

[0115] The collected current waveform is pre-processed by pre-emphasis, and the formula for the pre-emphasis processing is:

[0116] ;

[0117] in:

[0118] Indicates the pre-emphasis coefficient, set it to 0.96;

[0119] Represents the signal value of electrical device i at time j.

[0120] In the step S1, the current waveform after the pre-emphasis processing is pre-processed for signal denoising to obtain the denoised current waveform, including:

[0121] Establish the signal function of the current waveform signal:

[0122] ;

[0123] in:

[0124] It is the current waveform signal after pre-emphasis preprocessing;

[0125] is the preprocessed current waveform signal after signal denoising;

[0126] is the noise signal in the current waveform signal;

[0127] Perform short-time Fourier transform on both sides of the signal function:

[0128] ;

[0129] in:

[0130] H represents the total number of frames of the current waveform signal, and h represents the index of the time frame of the current waveform signal;

[0131] K represents the total number of frequency points of the current waveform signal, and k represents the index of the frequency point;

[0132] Respectively represent the frequency domain representation of the noisy current waveform signal, the pure current waveform signal and the noise signal;

[0133] The signal power spectrum is obtained by squaring the signal function after short-time Fourier transform processing:

[0134] ;

[0135] in:

[0136] Represents the phase angle of the pure current waveform signal and the noise signal, then:

[0137] ;

[0138] Determine the frequency domain representation of the current waveform signal after denoising:

[0139] ;

[0140] The frequency domain representation of the denoised current waveform signal is performed using the short-time inverse Fourier transform algorithm. Perform signal reconstruction to obtain the pre-processed current waveform with signal denoising .

[0141] S2: Decompose the preprocessed current waveform using FFTs of different frequencies to obtain decomposition results of the electrical equipment at different frequencies, and store the decomposition results in a database.

[0142] In the step S2, the pre-processed current waveform is decomposed using FFT algorithms of different frequencies to obtain decomposition results of the electrical equipment at different frequencies, including:

[0143] The pre-processed current waveform is decomposed using FFT algorithms of different frequencies:

[0144] ;

[0145] in:

[0146] Indicates the sampling frequency of the current waveform;

[0147] represents the FFT decomposition result of electrical equipment i;

[0148] represents the Fast Fourier Transform algorithm;

[0149] Get the decomposition results of electrical equipment at different frequencies:

[0150] ;

[0151] in:

[0152] represents the decomposition result of electrical equipment i at the sth frequency;

[0153] The decomposition results of different electrical equipment at different frequencies are stored in the database.

[0154] S3: Obtain the waveform of the electrical equipment to be monitored, and perform preprocessing and FFT decomposition on the waveform of the electrical equipment, construct a similarity measurement function between the decomposition result of the waveform of the electrical equipment to be monitored and the decomposition result in the database, use the flower pollination algorithm to solve the similarity measurement function, and obtain the similarity measurement result between the electrical equipment to be monitored and the electrical equipment in the database.

[0155] Obtain the waveform of the power equipment to be monitored, preprocess and perform FFT decomposition on the waveform of the power equipment, and construct a similarity measurement function between the decomposition result of the waveform of the power equipment to be monitored and the decomposition result in the database. The constructed similarity measurement function for;

[0156] ;

[0157] in:

[0158] represents the decomposition result of the electrical equipment k in the database at the jth frequency, and t represents the time domain information of the decomposition result;

[0159] s represents the number of decomposed frequencies, i represents the number of electrical devices in the database, and both s and i are integers;

[0160] represents the similarity parameter;

[0161] Represents the similarity measurement result between the decomposition result of the electric device to be monitored at the jth frequency and the decomposition structure of the electric device k in the database at the jth frequency;

[0162] It represents the decomposition result of the electrical equipment to be monitored at the jth frequency.

[0163] In the step S3, the flower pollination algorithm is used to solve the similarity measurement function, including:

[0164] The similarity parameter of the similarity metric function is solved by using the flower pollination algorithm, and the process of the flower pollination algorithm is as follows:

[0165] 1) Initialize parameters, set the pollen population size to N, and the maximum number of iterations to Max, where ;

[0166] 2) Set the similarity parameter interval to , randomly generate N data as pollen within the similarity parameter interval, and the pollen is the similarity parameter;

[0167] 3) Calculate each decomposition result The similarity measurement results are:

[0168] ;

[0169] Find the best value and optimal solution in the current pollen population , the optimal value is the value with the highest similarity measurement result, and the optimal solution is the similarity parameter corresponding to the optimal value; wherein j represents the decomposition result at the jth frequency, and k represents the electrical device k in the database;

[0170] 4) According to the movement form of pollinators in flower pollination, set the global iteration formula of pollen:

[0171] ;

[0172] in:

[0173] represents the value of the e-th pollen at the w-th iteration;

[0174] represents the optimal solution at the wth iteration;

[0175] represents the path of Levy flight, r represents the step size, and r is a random number in [0,1] that follows a uniform distribution;

[0176] Set the local iteration formula of pollen:

[0177] ;

[0178] r represents the step size, which is a random number in [0,1] that follows a uniform distribution;

[0179] Set conversion probability , for any pollen, if r>p, the global iteration method of pollen is used, otherwise the local iteration method of pollen is used;

[0180] 5) Repeat steps 3)-4) until the number of iterations reaches the preset maximum number of iterations Max, and use the final pollen result as the similarity parameter.

[0181] S4: Select the electrical equipment category with the highest similarity measurement result in the database as the electrical equipment category to be monitored, and determine whether the load of the electrical equipment to be monitored is abnormal. If the load is abnormal, the device is a malicious device and there is a risk of electricity consumption.

[0182] In the step S4, the category of the electrical equipment to be monitored is determined according to the similarity measurement result, including:

[0183] According to the determined similarity parameters, the decomposition results of the electrical equipment to be monitored at different frequencies are calculated, and the similarity measurement results of the decomposition results of the electrical equipment in the database at different frequencies are compared, and the electrical equipment category with the highest similarity measurement result in the database is selected as the electrical equipment category to be monitored.

[0184] In the step S4, determining whether the load of the electrical equipment to be monitored is abnormal includes:

[0185] According to the category of the electrical equipment to be monitored, the load type of the electrical equipment to be monitored is determined. If only a pure resistive load exists in the circuit of the electrical equipment to be monitored, the power factor of the load should be 1. When the power factor of the load of the electrical equipment to be monitored is not 1, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage. If only an inductive load or only a capacitive load exists in the circuit of the electrical equipment to be monitored, the power factor of the load should be 0. When the power factor of the load of the electrical equipment to be monitored is not 0, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage. When a mixed load exists in the circuit of the electrical equipment to be monitored, the power factor should be less than 1. If the power factor of the load of the electrical equipment to be monitored is greater than or equal to 1, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage.

[0186] The invention also provides an intelligent monitoring instrument for safe electricity use. Figure 2 , which is a schematic diagram of the internal structure of an intelligent monitoring instrument for safe electricity use provided in one embodiment of the present invention.

[0187] In this embodiment, the safe electricity use intelligent monitor 1 at least includes an electricity equipment collection device 11 , a data processor 12 , an electricity safety monitoring device 13 , a communication bus 14 , and a network interface 15 .

[0188] The power consumption equipment collection device 11 may be a PC (Personal Computer) or a terminal device such as a smart phone, a tablet computer, or a portable computer.

[0189] The data processor 12 includes at least one type of readable storage medium, which includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the data processor 12 can be an internal storage unit of the safe power intelligent monitor 1, such as the hard disk of the safe power intelligent monitor 1. In other embodiments, the data processor 12 can also be an external storage device of the safe power intelligent monitor 1, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the safe power intelligent monitor 1. Further, the data processor 12 can also include both the internal storage unit and the external storage device of the safe power intelligent monitor 1. The data processor 12 can be used not only to store the application software and various types of data installed in the safe power intelligent monitor 1, but also to temporarily store the data that has been output or is to be output.

[0190] In some embodiments, the power safety monitoring device 13 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, including a monitoring unit, for running program codes stored in the data processor 12 or processing data.

[0191] The communication bus 14 is used to realize the connection and communication between these components.

[0192] The network interface 15 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and is generally used to establish a communication connection between the system 1 and other electronic devices.

[0193] Figure 2 Only components 11-15 and the safe electricity intelligent monitoring device 1 are shown. It can be understood by those skilled in the art that Figure 2 The structure shown does not constitute a limitation on the safe electricity use intelligent monitoring instrument 1, and may include fewer or more components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0194] It should be noted that the serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or monitor 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, device, article or monitor. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the existence of other identical elements in the process, device, article or monitor including the element.

[0195] Through the description of the above implementation methods, those skilled in the art can clearly understand that the monitoring instrument of the above-mentioned embodiment can be implemented by means of software plus a necessary general hardware platform, and of course it can also be implemented 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, in essence, 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 ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the monitoring instrument described in each embodiment of the present invention.

[0196] 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.

Claims

1. A method for intelligent monitoring of safe electricity use, characterized in that: The method comprises: S1: Collect current waveforms of different electrical equipment, and pre-process the collected current waveforms to remove noise data in the current waveforms; S2: Decompose the preprocessed current waveform using FFT of different frequencies to obtain decomposition results of the electrical equipment at different frequencies, and store the decomposition results in a database; S3: Obtain the waveform of the electrical equipment to be monitored, preprocess and perform FFT decomposition on the waveform of the electrical equipment, construct a similarity measurement function between the decomposition result of the waveform of the electrical equipment to be monitored and the decomposition result in the database, solve the similarity measurement function using the flower pollination algorithm, and obtain the similarity measurement result between the electrical equipment to be monitored and the electrical equipment in the database; The waveform of the electric equipment to be monitored is obtained, and the waveform of the electric equipment is preprocessed and FFT decomposed, and a similarity measurement function between the decomposition result of the waveform of the electric equipment to be monitored and the decomposition result in the database is constructed. The constructed similarity measurement function for; ； in: represents the decomposition result of the electrical equipment k in the database at the jth frequency, and t represents the time domain information of the decomposition result; s represents the number of decomposed frequencies, i represents the number of electrical devices in the database, and both s and i are integers; represents the similarity parameter; Represents the similarity measurement result between the decomposition result of the electric device to be monitored at the jth frequency and the decomposition structure of the electric device k in the database at the jth frequency; Indicates the decomposition result of the electrical equipment to be monitored at the jth frequency; Among them, the flower pollination algorithm is used to solve the similarity parameter of the similarity measurement function, and the flower pollination algorithm process is: 1) Initialize parameters, set the pollen population size to N, and the maximum number of iterations to Max, where ; 2) Set the similarity parameter interval to , randomly generate N data as pollen within the similarity parameter interval, and the pollen is the similarity parameter; 3) Calculate each decomposition result The similarity measurement results are: ； Find the best value and optimal solution in the current pollen population , the optimal value is the value with the highest similarity measurement result, and the optimal solution is the similarity parameter corresponding to the optimal value; wherein j represents the decomposition result at the jth frequency, and k represents the electrical device k in the database; 4) According to the movement form of pollinators in flower pollination, set the global iteration formula of pollen: ； in: represents the value of the e-th pollen at the w-th iteration; represents the optimal solution at the wth iteration; represents the path of Levy flight, r represents the step size, and r is a random number in [0,1] that follows a uniform distribution; Set the local iteration formula of pollen: ； r represents the step size, which is a random number in [0,1] that follows a uniform distribution; Set conversion probability , for any pollen, if r>p, the global iteration method of pollen is used, otherwise the local iteration method of pollen is used; 5) Repeat steps 3)-4) until the number of iterations reaches the preset maximum number of iterations Max, and use the final pollen result as the similarity parameter in the similarity measurement function; S4: Select the electrical equipment category with the highest similarity measurement result in the database as the electrical equipment category to be monitored, and determine whether the load of the electrical equipment to be monitored is abnormal. If the load is abnormal, the device is a malicious device and there is a risk of electricity consumption.

2. The method for intelligent monitoring of safe electricity use according to claim 1, characterized in that: In the step S1, current waveforms of different electrical devices are collected and preprocessed, including: The current waveforms of different types of electrical equipment are collected using the safe electricity intelligent monitoring instrument. The collected current waveforms are in the form of: ； in: is the current waveform of the electrical equipment i, n-1 represents the time domain information of the current waveform, Represents the signal value at time n-1; The collected current waveform is pre-processed by pre-emphasis, and the formula for the pre-emphasis processing is: ； in: Indicates the pre-emphasis coefficient, set it to 0.96; Represents the signal value of electrical device i at time j.

3. A safe electricity intelligent monitoring method as claimed in claim 2, characterized in that: In the step S1, the current waveform after the pre-emphasis processing is pre-processed for signal denoising to obtain the denoised current waveform, including: Establish the signal function of the current waveform signal: ； in: It is the current waveform signal after pre-emphasis preprocessing; is the preprocessed current waveform signal after signal denoising; is the noise signal in the current waveform signal; Perform short-time Fourier transform on both sides of the signal function: ； in: H represents the total number of frames of the current waveform signal, and h represents the index of the time frame of the current waveform signal; K represents the total number of frequency points of the current waveform signal, and k represents the index of the frequency point; Respectively represent the frequency domains of the noisy current waveform signal, the pure current waveform signal and the noise signal; The signal power spectrum is obtained by squaring the signal function after short-time Fourier transform processing: ； in: Represents the phase angle of the pure current waveform signal and the noise signal, then: ； Determine the frequency domain representation of the current waveform signal after denoising: ； The frequency domain representation of the denoised current waveform signal is performed using the short-time inverse Fourier transform algorithm. Perform signal reconstruction to obtain the pre-processed current waveform with signal denoising .

4. A safe electricity intelligent monitoring method as claimed in claim 3, characterized in that: In the step S2, the pre-processed current waveform is decomposed using FFT algorithms of different frequencies to obtain decomposition results of the electrical equipment at different frequencies, including: The pre-processed current waveform is decomposed using FFT algorithms of different frequencies: ； in: Indicates the sampling frequency of the current waveform; represents the FFT decomposition result of electrical equipment i; represents the Fast Fourier Transform algorithm; Get the decomposition results of electrical equipment at different frequencies: ； in: represents the decomposition result of electrical equipment i at the sth frequency; The decomposition results of different electrical equipment at different frequencies are stored in the database.

5. The method for intelligent monitoring of safe electricity use according to claim 4, characterized in that: In the step S4, the category of the electrical equipment to be monitored is determined according to the similarity measurement result, including: According to the determined similarity parameters, the decomposition results of the electrical equipment to be monitored at different frequencies are calculated, and the similarity measurement results of the decomposition results of the electrical equipment in the database at different frequencies are compared, and the electrical equipment category with the highest similarity measurement result in the database is selected as the electrical equipment category to be monitored.

6. A safe electricity intelligent monitoring method as claimed in claim 5, characterized in that: In the step S4, determining whether the load of the electrical equipment to be monitored is abnormal includes: According to the category of the electrical equipment to be monitored, the load type of the electrical equipment to be monitored is determined. If only a pure resistive load exists in the circuit of the electrical equipment to be monitored, the power factor of the load should be 1. When the power factor of the load of the electrical equipment to be monitored is not 1, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage. If only an inductive load or only a capacitive load exists in the circuit of the electrical equipment to be monitored, the power factor of the load should be 0. When the power factor of the load of the electrical equipment to be monitored is not 0, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage. When a mixed load exists in the circuit of the electrical equipment to be monitored, the power factor should be less than 1. If the power factor of the load of the electrical equipment to be monitored is greater than or equal to 1, the electrical equipment to be monitored is determined to be a malicious device and there is a risk of power usage.

Images