Electricity utilization safety monitoring method and system, electronic equipment and storage medium

Abstract

The invention provides an electricity utilization safety monitoring method and system, electronic equipment and a storage medium. The method comprises the steps of extracting and analyzing load features to obtain a feature data set; on the basis of the calculation window, the detection extraction window and the start-stop threshold detection feature data set, start-stop event features are obtained; identifying a preliminary load type of the start-stop event feature; performing hierarchical channel identification on the preliminary load type based on the starting point and the ending point; taking the difference of the center frequency of each modal component as an arc characteristic; forming a feature vector; and based on the trained integrated depth RVFL neural network, identifying the arc features to obtain power utilization safety condition information, and detecting the determined load type. According to the method, the situation that the electric equipment is not monitored in place can be effectively reduced, the situation of misjudgment and missed judgment is effectively avoided, and the problem that monitoring cannot be conducted due to the fact that the randomness of series connection arcs is high can also be avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity monitoring, and in particular to a method, system, electronic equipment and storage medium for monitoring electricity safety. Background Art

[0002] People use electrical equipment more and more diversely and widely, but the safety and standardization of electricity use are often ignored. In addition, improper use of electricity is one of the important causes of fire in electrical fire accidents. The monitoring of electricity safety mostly uses threshold values ​​such as leakage current and temperature to determine whether an electrical fault has occurred, but it can only be detected after the fault occurs or when the fault characteristics are more obvious, which is insufficient for the detection of hidden electrical safety hazards and hidden electrical faults.

[0003] The existing technology cannot identify the type of electrical appliances, and there are errors in the detection of low-power appliances and complex environments, which can easily lead to misjudgment and missed judgment. Due to the complexity of the low-voltage AC electrical system, the high randomness of the series arc, and the increase of various nonlinear loads in the circuit, the fault arc characteristics of the line under different load conditions and at different times may vary greatly. At the same time, due to the limitation of hardware costs, complex algorithms are difficult to implement in actual projects, resulting in poor results in power safety monitoring and inability to provide timely warnings. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide a method, system, electronic device and storage medium for monitoring power safety to solve the deficiencies in the above-mentioned prior art.

[0005] In a first aspect, the present invention provides a method for monitoring power safety, the method comprising:

[0006] Collecting power consumption data in real time, obtaining load characteristics in the power consumption data, extracting and analyzing the load characteristics to obtain a characteristic data set;

[0007] A sliding detection window is defined in the power consumption time series, and a start-stop threshold is set, wherein the sliding detection window includes a calculation window and a detection extraction window, and the feature data set is detected based on the calculation window, the detection extraction window and the start-stop threshold to obtain the start-stop event feature;

[0008] Using the SVM model combined with the second-order oscillating particle swarm algorithm and based on multi-feature loads to identify the preliminary load type of the start-stop event characteristics;

[0009] Setting a moving strategy for the detection and extraction window, moving the detection and extraction window based on the moving strategy and performing hierarchical channel identification on the preliminary load type to obtain a determined load type;

[0010] Counting the zero-crossing points in the characteristic data set as current data of the series arc, normalizing the current data to obtain processed current data, performing VDM decomposition on the processed current data to obtain the center frequency of each modal component, and using the difference of the center frequency of each modal component as the arc feature;

[0011] Extracting the current increment coefficient and the fuzzy entropy value of each modal component in the arc feature, forming a feature vector according to the fuzzy entropy value and the center frequency, and inputting the feature vector into an integrated deep RVFL neural network, so that the integrated deep RVFL neural network is trained based on the feature vector to obtain a trained integrated deep RVFL neural network;

[0012] The arc characteristics are identified based on the trained integrated deep RVFL neural network to obtain power safety information, and the determined load type is detected through the continuous moving variation method to obtain the current condition type.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: the start-stop event characteristics are obtained by detecting the feature data set through the detection extraction window, and the preliminary load type of the electrical equipment can be obtained through the SVM model combined with the second-order oscillation particle swarm algorithm, so that the load situation of the electrical equipment can be obtained, and the situation of inadequate monitoring of the electrical equipment can be effectively reduced. The difference in center frequency is used as the arc feature to avoid the situation where other features cannot extract the electrical equipment when monitoring the power consumption of the electrical equipment. The layered channel identification is performed through the detection extraction window to determine the load type, and the arc characteristics are identified through the trained integrated deep RVFL neural network, which can effectively avoid misjudgment and missed judgment, and can also avoid the problem of high randomness of the series arc that makes it impossible to monitor, thereby avoiding the problem of difficulty in monitoring the fault arc characteristics of the line under different load conditions and at different times.

[0014] Furthermore, the steps of collecting power consumption data in real time, obtaining load characteristics in the power consumption data, extracting and analyzing the load characteristics to obtain a characteristic data set include:

[0015] Collecting an electric power signal based on a collection sensor, and converting the electric power signal by a preset multiple to collect current data;

[0016] Acquire a steady-state characteristic of the current based on the current amplitude, the current harmonic component, the steady-state active power and the steady-state reactive power in the current data;

[0017] The transient characteristics of the current are acquired based on the transient current, transient active power, transient reactive power, voltage noise and duration in the current data.

[0018] Furthermore, the calculation expression of the steady-state active power is:

[0019]

[0020] In the formula, P represents steady-state active power, k represents harmonic order, V k Indicates the effective value of the kth voltage harmonic, I k represents the effective value of the kth current harmonic, θ k represents the kth harmonic phase difference;

[0021] The calculation expression of the steady-state reactive power is:

[0022]

[0023] Where Q represents the steady-state reactive power.

[0024] Further, the step of defining a sliding detection window in the power consumption time series and setting a start-stop threshold, wherein the sliding detection window includes a calculation window and a detection extraction window, and detecting the feature data set based on the calculation window, the detection extraction window and the start-stop threshold to obtain the start-stop event feature includes:

[0025] Defining a calculation window and a detection and extraction window in the power consumption time series, and setting the window lengths of the calculation window and the detection and extraction window;

[0026] Calculate the effective average current value of the characteristic data set based on the calculation window;

[0027] Set a start / stop threshold, and compare the start / stop threshold with the effective average current value. If the effective average current value is greater than the start / stop threshold, it is determined that a transient event has occurred, and the starting point of the power consumption event is recorded.

[0028] The detection and extraction window is continuously slid, and current data of several cycles in the feature data set is detected based on the sliding detection and extraction window to detect voltage transient values, and the start-stop event features in the feature data set are obtained based on the starting point of the power consumption event and the voltage transient value.

[0029] Furthermore, the calculation expression of the start-stop threshold is:

[0030]

[0031] In the formula, H min , H maxrespectively represent the maximum value of the start / stop threshold and the minimum value of the start / stop threshold, L1 represents the number of sampling points of fluctuation increase, L2 represents the number of sampling points of the current increase of the electrical equipment, L represents the length of the calculation window, I min It represents the minimum change amplitude in identifying electrical equipment, f represents the combination of the average value of the effective value fluctuation of the current and the safety margin, and λ represents the noise level.

[0032] Furthermore, the step of using the SVM model in combination with the second-order oscillating particle swarm algorithm to identify the preliminary load type of the start-stop event characteristics based on multi-feature loads includes:

[0033] Assigning a random position and a random speed to each particle in the second-order oscillation particle swarm, and updating the speed and direction of each particle by comparing the fitness value of the objective function of the second-order oscillation particle swarm algorithm, the particle optimal value and the global optimal value;

[0034] The movement process of the particles is corrected according to the updated speed magnitude and speed direction of each particle, so that each particle gradually approaches the global optimal value, and the preliminary load type of the start-stop event characteristics is identified based on the global optimal value combined with the SVM model.

[0035] Furthermore, the step of setting a movement strategy of the detection and extraction window, moving the detection and extraction window based on the movement strategy, and performing hierarchical channel identification on the preliminary load type to obtain a determined load type includes:

[0036] Setting a moving strategy of the detection and extraction window according to the current trajectory diagram of the characteristic data set, so that the detection and extraction window covers the current trajectory diagram based on the moving strategy;

[0037] Filtering high-power loads in the start-stop event characteristics based on the detection extraction window and the current effective value;

[0038] The load type is determined based on the steady-state fundamental wave, harmonic amplitude, transient active power, transient reactive power and transient duration as load type characteristics, and based on the load type characteristics.

[0039] In a second aspect, the present invention further provides an electricity safety monitoring system, the system comprising:

[0040] A real-time acquisition module is used to collect power consumption data in real time, obtain load characteristics in the power consumption data, extract and analyze the load characteristics to obtain a characteristic data set;

[0041] A detection module is defined, which is used to define a sliding detection window in the power consumption time series and set a start-stop threshold, wherein the sliding detection window includes a calculation window and a detection extraction window, and the feature data set is detected based on the calculation window, the detection extraction window and the start-stop threshold to obtain the start-stop event feature;

[0042] Combined with an identification module, it is used to use the SVM model in combination with a second-order oscillating particle swarm algorithm and identify the preliminary load type of the start-stop event characteristics based on multi-feature loads;

[0043] A detection module is set to set a moving strategy of the detection and extraction window, move the detection and extraction window based on the moving strategy, and perform hierarchical channel identification on the preliminary load type to obtain a determined load type;

[0044] A statistical processing module, used for counting the zero-crossing points in the characteristic data set as current data of the series arc, normalizing the current data to obtain processed current data, performing VDM decomposition on the processed current data to obtain the center frequency of each modal component, and using the difference of the center frequency of each modal component as the arc feature;

[0045] An extraction training module is used to extract the current increment coefficient and the fuzzy entropy value of each modal component in the arc feature, form a feature vector according to the fuzzy entropy value and the center frequency, and input the feature vector into an integrated deep RVFL neural network so that the integrated deep RVFL neural network is trained based on the feature vector to obtain a trained integrated deep RVFL neural network;

[0046] An identification and detection module is used to identify the arc characteristics based on the trained integrated deep RVFL neural network to obtain power safety information, and to detect the determined load type through a continuous moving variation method to obtain a current condition type.

[0047] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned power safety monitoring method when executing the computer program.

[0048] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, which implements the above-mentioned electricity safety monitoring method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of a method for monitoring power safety in a first embodiment of the present invention;

[0050] Figure 2is a structural block diagram of an electricity safety monitoring system in a second embodiment of the present invention;

[0051] Figure 3 FIG. 4 is a schematic diagram of the hardware structure of an electronic device in a third embodiment of the present invention.

[0052] Description of main component symbols:

[0053] 10. Real-time acquisition module;

[0054] 20. Define the detection module;

[0055] 30. Combined with recognition module;

[0056] 40. Set the detection module;

[0057] 50. Statistical processing module;

[0058] 60. Extract training module;

[0059] 70. Identification and detection module;

[0060] 80. Bus; 81. Processor; 82. Memory; 83. Communication interface.

[0061] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0062] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0063] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0065] Embodiment 1

[0066] See also Figure 1 , which shows a method for monitoring power safety in a first embodiment of the present invention, and the method includes steps S1 to S7:

[0067] S1, collecting power consumption data in real time, obtaining load characteristics in the power consumption data, extracting and analyzing the load characteristics to obtain a characteristic data set;

[0068] Specifically, the step S1 includes steps S11 to S13:

[0069] S11, collecting an electric power signal based on a collection sensor, and converting the electric power signal by a preset multiple to collect current data;

[0070] It is understandable that the data acquisition device of the electrical equipment collects the measured values ​​of the electrical equipment, including voltage and current, etc. The actual residential power load generally works at a voltage of 220V, so the actual voltage data and current data need to be converted by corresponding multiples to achieve normal collection of load data.

[0071] It is worth noting that, in this embodiment, the expression for conversion is:

[0072] V0=G×(V IN +-V IN- );

[0073]

[0074] In the formula, V0 represents the voltage at the output of the op amp, V IN+ Represents the voltage at the non-inverting input terminal, V IN- represents the inverting input voltage, G represents the gain, R G Represents the resistance of the non-inverting and inverting input terminals.

[0075] S12, acquiring steady-state characteristics of the current based on the current amplitude, current harmonic components, steady-state active power, and steady-state reactive power in the current data;

[0076] It can be understood that the steady-state characteristics are mainly continuous characteristics reflected when the electrical equipment is in steady-state operation, such as current effective value, current amplitude, current harmonic component, steady-state active power, steady-state reactive power and VI curve, etc. In this embodiment, the calculation expression of the steady-state active power is:

[0077]

[0078] In the formula, P represents steady-state active power, k represents harmonic order, V k Indicates the effective value of the kth voltage harmonic, Ik represents the effective value of the kth current harmonic, θ k represents the kth harmonic phase difference;

[0079] The calculation expression of the steady-state reactive power is:

[0080]

[0081] Where Q represents the steady-state reactive power.

[0082] S13, acquiring transient characteristics of the current based on the transient current, transient active power, transient reactive power, voltage noise, and duration in the current data;

[0083] It can be understood that transient characteristics are mainly the changing characteristics of electrical quantities such as current, voltage, power, etc. during the state conversion process of electrical equipment, mainly including transient current, transient active power, transient reactive power, voltage noise and duration, etc.

[0084] S2, defining a sliding detection window in the power consumption time series and setting a start-stop threshold, wherein the sliding detection window includes a calculation window and a detection extraction window, and detecting the feature data set based on the calculation window, the detection extraction window and the start-stop threshold to obtain a start-stop event feature;

[0085] It needs to be explained that the feature data set can be modeled as a changing state statistical graph. Therefore, two sliding windows are defined in the time series of electricity consumption. The two sliding windows are a calculation window and a detection and extraction window. The feature data set modeled as a changing state statistical graph is detected through the calculation window and the detection and extraction window, and combined with the start-stop threshold, the start-stop event characteristics of the electrical equipment can be detected, that is, the current and voltage change characteristics when the electrical equipment starts and stops.

[0086] Specifically, the step S2 includes steps S21 to S24:

[0087] S21, defining a calculation window and a detection and extraction window in the power consumption time series, and setting the window lengths of the calculation window and the detection and extraction window;

[0088] It is understandable that the calculation window and the detection extraction window are defined within the time period when the device uses electricity, and the lengths of the calculation window and the detection extraction window are set according to the size of the feature data set modeled as a statistical graph of the changing state.

[0089] S22, calculating the effective average current value of the characteristic data set based on the calculation window;

[0090] It can be understood that by calculating the characteristic data in the change state statistical diagram through the calculation window, the effective average current of the electrical equipment during the power consumption period can be calculated. The specific calculation process is to count the power consumption current at each time point in the change state statistical diagram, and then calculate the effective average current.

[0091] S23, setting a start / stop threshold, and comparing the start / stop threshold with the effective average current value. If the effective average current value is greater than the start / stop threshold, it is determined that a transient event has occurred, and the starting point of the power consumption event is recorded;

[0092] It can be understood that, in this embodiment, the calculation expression of the start-stop threshold is:

[0093]

[0094] In the formula, H min , H max respectively represent the maximum value of the start / stop threshold and the minimum value of the start / stop threshold, L1 represents the number of sampling points of fluctuation increase, L2 represents the number of sampling points of the current increase of the electrical equipment, L represents the length of the calculation window, I min It represents the minimum change amplitude in identifying electrical equipment, f represents the combination of the average value of the effective value fluctuation of the current and the safety margin, and λ represents the noise level.

[0095] It should be noted that by comparing the start-stop threshold with the effective average current, that is, comparing the effective average current of the electrical equipment with the start and stop current threshold, when the start-stop threshold is less than the effective average current, it is judged that a transient event has occurred, and the time node when the transient event occurs is calculated and recorded as the starting point of the power consumption time.

[0096] S24, continuously sliding the detection and extraction window, and detecting current data of several cycles in the feature data set based on the sliding detection and extraction window to detect a voltage transient value, and acquiring a start-stop event feature in the feature data set based on the starting point of the power consumption event and the voltage transient value;

[0097] It can be understood that by making the detection and extraction window repeatedly cycle through the characteristic data in the change state statistical diagram, the current data of several power consumption cycles of the electrical equipment can be extracted. Based on the current data of several cycles, the voltage transient value of the electrical equipment can be detected. The current data has more electrical characteristics relative to the power data. The subtraction of the current before and after the event requires the same phase, while the phase of the mains voltage is relatively stable during operation. The phase is unified using the voltage transient value sampled synchronously with the current. The data before and after the event are all based on the zero crossing of the voltage cycle value as the starting phase of the total current, and the current data of five cycles are taken to extract the steady-state load characteristics, and the transient characteristics are extracted using the current data between the start and end points of the load.

[0098] S3, using the SVM model in combination with the second-order oscillating particle swarm algorithm and identifying the preliminary load type of the start-stop event characteristics based on multi-feature loads;

[0099] Specifically, the step S3 includes steps S31 to S32:

[0100] S31, assigning a random position and a random speed to each particle in the second-order oscillation particle swarm, and updating the speed and direction of each particle by comparing the fitness value of the objective function of the second-order oscillation particle swarm algorithm, the particle optimal value and the global optimal value;

[0101] It can be understood that each particle in the particle swarm algorithm has its own position and velocity information. At the beginning of the algorithm, a random position and velocity are assigned to each particle. The size and direction of the particle velocity are updated by comparing the fitness value of its own objective function with the particle optimal value and the global optimal value, and the particle movement process is corrected so that the particle gradually approaches the global optimal value.

[0102] In addition, the second-order oscillation particle swarm optimization algorithm introduces a second-order oscillation link in the particle velocity update formula. The algorithm oscillates and converges in the early stage, with good global search capabilities, and converges gradually in the later stage, with good global search capabilities, so it can find the global optimal value faster and more accurately. At this time, the particle velocity update formula is:

[0103] V i (t+1)=ω×V i (t)+c1r1(p i -x i (t))+c2r2(p g -x i (t));

[0104] Where V i (t+1) represents the speed of particle update, ω represents the inertia weight, c1 and c2 represent the first learning factor and the second learning factor respectively, r1 and r2 represent two different random numbers uniformly distributed between 0 and 1 respectively, V i (t) represents the velocity of the ith particle, p i represents the individual optimal value of the particle, p g represents the global optimal value, x i represents the position of the ith particle.

[0105] S32, correcting the movement process of the particles according to the updated speed magnitude and speed direction of each particle, so that each particle gradually approaches the global optimal value, and identifying the preliminary load type of the start-stop event characteristics based on the global optimal value combined with the SVM model;

[0106] It can be understood that the SVM model is a two-classification model. Compared with manually setting the model parameters of the SVM model, the second-order oscillating particle swarm optimization algorithm can find more suitable parameters to make the recognition accuracy higher and avoid falling into the local optimum.

[0107] S4, setting a moving strategy of the detection and extraction window, moving the detection and extraction window based on the moving strategy and performing hierarchical channel identification on the preliminary load type to obtain a determined load type;

[0108] Specifically, the step S4 includes steps S41 to S43:

[0109] S41, setting a moving strategy of the detection and extraction window according to the current trajectory diagram of the characteristic data set, so that the detection and extraction window covers the current trajectory diagram based on the moving strategy;

[0110] It can be understood that the feature data set can be modeled as a power consumption data graph of various related electrical equipment, the power consumption data graph includes data such as current and voltage, and the current data in the feature data set is extracted and then modeled as a current trajectory graph. The movement strategy of the detection and extraction window is set through the current trajectory graph of the feature data set. In this embodiment, the movement strategy of the detection and extraction window is that the moving path direction of the detection and extraction window needs to be able to cover the current trajectory graph.

[0111] S42, screening high-power loads in the start-stop event characteristics based on the detection extraction window and the current effective value;

[0112] It can be understood that by detecting the extraction window and the effective current value to screen out high-power loads in the start-stop event characteristics, in a specific implementation, the effective current value is used as a threshold, and then the current characteristics in the start-stop event characteristics and the effective current value as a threshold are compared through the detection extraction window, so that the high-power loads in the start-stop event characteristics can be screened out, completing the first step of identification.

[0113] S43, determining the load type based on the steady-state fundamental wave, harmonic amplitude, transient active power, transient reactive power and transient duration as load type characteristics, and based on the load type characteristics;

[0114] It can be understood that the steady-state fundamental wave, harmonic amplitude, transient active power, transient reactive power and transient duration are used as feature vectors and input into the SVM model for feature learning, thereby forming a load identification model. The load type characteristics are identified through the load identification model, so that the load type can be confirmed to complete the second step of identification.

[0115] S5, counting the zero-crossing points in the characteristic data set as current data of the series arc, normalizing the current data to obtain processed current data, performing VDM decomposition on the processed current data to obtain the center frequency of each modal component, and using the difference of the center frequency of each modal component as the arc feature;

[0116] It is understandable that due to the burning characteristics of the arc, a temporary "zero rest" phenomenon will occur when the current passes through zero. According to this characteristic of the arc, the number of zero-crossing points in the periodic current data can be counted as a steady-state feature, and the current data is first normalized, and the current amplitude of the processed current data is limited to between -1 and 1, so as to facilitate the subsequent extraction and analysis of fault features. The line current data when the load is operating normally and when there is a series fault arc is decomposed by VMD to obtain the corresponding IMF components, and the fuzzy entropy is calculated. The greater the degree of confusion of each IMF component waveform, the greater its fuzzy entropy value. In this embodiment, the obtained data is decomposed by the VMD algorithm to obtain 5 different IMF components, and the fuzzy entropy value and center frequency of the IMF component of each load are calculated respectively, and the time domain characteristic current increment coefficient is combined to form a feature vector to form the feature vector library required for the integrated deep RVFL neural network training. It is worth noting that there are large differences in the center frequency of different loads, which can be used as a feature vector composed of arc features for arc recognition, thereby obtaining arc features.

[0117] S6, extracting the current increment coefficient and the fuzzy entropy value of each modal component in the arc feature, forming a feature vector according to the fuzzy entropy value and the center frequency, and inputting the feature vector into an integrated deep RVFL neural network, so that the integrated deep RVFL neural network is trained based on the feature vector to obtain a trained integrated deep RVFL neural network;

[0118] It can be understood that the current increment coefficient and the fuzzy entropy value and center frequency of each modal component are extracted to form a feature vector, which is input into the integrated deep RVFL neural network for fault arc feature learning to achieve a better recognition effect.

[0119] It is worth noting that when the current periodicity of the electrical equipment is poor, the current harmonic content is high, the complexity of its modal components is high when there is no arc, the fuzzy entropy value is large, the current distortion is serious when there is an arc, the IMF1 waveform is difficult to maintain normal fluctuations, the fuzzy entropy value is small, the waveform uncertainty of the other modal components increases, the high-frequency harmonic components increase, the waveform complexity continues to rise, and the fuzzy entropy value is larger; the electric kettle current waveform is a sine wave with less harmonic content, but there is also some noise interference. When there is no arc, the IMF fuzzy entropy value is large, and the other IMFs are fuzzy. When there is an arc, the harmonic content increases, the waveform complexity increases, and the fuzzy entropy value increases. This shows that the change in fuzzy entropy is consistent with the waveform change and can better reflect the waveform complexity index.

[0120] S7, identifying the arc characteristics based on the trained integrated deep RVFL neural network to obtain power safety information, and detecting the determined load type through a continuous moving variation method to obtain a current condition type;

[0121] It is understandable that the trained integrated deep RVFL neural network can better identify the fault conditions of arc characteristics, and detect the sudden leakage current at the moment of determining the load type through the continuous moving variation method. First, it is necessary to record the residual current of each power cycle and the residual current at a fixed time interval in the previous period, and then compare and calculate to obtain the calculation result. The residual current values ​​of each power cycle detected are recorded as I0, I1, I2, ..., I m , we can get the current change at any time t, that is, the new fault leakage current generated in each cycle, and the expression is:

[0122] I Δt =I t -I m ;

[0123] In the formula, I Δt Represents the new leakage current generated at time t, I t Represents the residual current at time t, I m Represents the residual current at time m.

[0124] In summary, the electricity safety monitoring method in the above-mentioned embodiment of the present invention obtains the start-stop event characteristics by detecting the feature data set through the detection extraction window, and obtains the preliminary load type of the electrical equipment through the SVM model combined with the second-order oscillation particle swarm algorithm, so as to obtain the load condition of the electrical equipment, effectively reducing the situation where the electrical equipment is not monitored properly, and uses the difference in center frequency as the arc characteristic to avoid the situation where other characteristics cannot extract the electrical equipment when monitoring the power consumption of the electrical equipment, and performs hierarchical channel identification through the detection extraction window to obtain the determined load type, and identifies the arc characteristics through the trained integrated deep RVFL neural network, which can effectively avoid misjudgment and missed judgment, and can also avoid the problem of high randomness of the series arc resulting in the inability to monitor, thereby avoiding the problem of difficulty in monitoring the fault arc characteristics of the line under different load conditions and at different times.

[0125] Embodiment 2

[0126] See also Figure 2 , which shows a power safety monitoring system in a second embodiment of the present invention, the system comprises:

[0127] The real-time acquisition module 10 is used to collect power consumption data in real time, obtain load characteristics in the power consumption data, extract and analyze the load characteristics to obtain a characteristic data set;

[0128] A detection module 20 is defined, which is used to define a sliding detection window in the power consumption time series and set a start-stop threshold, wherein the sliding detection window includes a calculation window and a detection extraction window, and the feature data set is detected based on the calculation window, the detection extraction window and the start-stop threshold to obtain the start-stop event feature;

[0129] Combined with the identification module 30, it is used to use the SVM model in combination with the second-order oscillating particle swarm algorithm and identify the preliminary load type of the start-stop event characteristics based on multi-feature loads;

[0130] A detection module 40 is configured to set a moving strategy for the detection and extraction window, move the detection and extraction window based on the moving strategy, and perform hierarchical channel identification on the preliminary load type to obtain a determined load type;

[0131] A statistical processing module 50 is used to count the zero-crossing points in the characteristic data set as current data of the series arc, perform normalization processing on the current data to obtain processed current data, and perform VDM decomposition on the processed current data to obtain the center frequency of each modal component, and use the difference of the center frequency of each modal component as the arc feature;

[0132] An extraction training module 60 is used to extract the current increment coefficient and the fuzzy entropy value of each modal component in the arc feature, form a feature vector according to the fuzzy entropy value and the center frequency, and input the feature vector into an integrated deep RVFL neural network so that the integrated deep RVFL neural network is trained based on the feature vector to obtain a trained integrated deep RVFL neural network;

[0133] The identification and detection module 70 is used to identify the arc characteristics based on the trained integrated deep RVFL neural network to obtain power safety information, and detect the determined load type through the continuous moving variation method to obtain the current condition type.

[0134] In some optional embodiments, the real-time acquisition module 10 includes:

[0135] A collection and conversion unit, used to collect power usage signals based on the collection sensor, and convert the power usage signals by a preset multiple to collect current data;

[0136] A first acquisition unit, configured to acquire a steady-state characteristic of the current based on a current amplitude, a current harmonic component, a steady-state active power, and a steady-state reactive power in the current data;

[0137] The calculation expression of the steady-state active power is:

[0138]

[0139] In the formula, P represents steady-state active power, k represents harmonic order, V k Indicates the effective value of the kth voltage harmonic, I k represents the effective value of the kth current harmonic, θ k represents the kth harmonic phase difference;

[0140] The calculation expression of the steady-state reactive power is:

[0141]

[0142] In the formula, Q represents steady-state reactive power;

[0143] The second acquisition unit acquires the transient characteristics of the current based on the transient current, transient active power, transient reactive power, voltage noise and duration in the current data.

[0144] In some optional embodiments, the definition detection module 20 includes:

[0145] A definition setting unit, used to define a calculation window and a detection extraction window in the power consumption time series, and set the window lengths of the calculation window and the detection extraction window;

[0146] A calculation unit, configured to calculate an effective average current value of the characteristic data set based on the calculation window;

[0147] A setting judgment unit is used to set a start-stop threshold and compare the start-stop threshold with the effective average current. If the effective average current is greater than the start-stop threshold, it is judged that a transient event has occurred and the starting point of the power consumption event is recorded;

[0148] The calculation expression of the start-stop threshold is:

[0149]

[0150] In the formula, H min , H max respectively represent the maximum value of the start / stop threshold and the minimum value of the start / stop threshold, L1 represents the number of sampling points of fluctuation increase, L2 represents the number of sampling points of the current increase of the electrical equipment, L represents the length of the calculation window, I min It indicates the minimum change amplitude in the electrical equipment, f indicates the combination of the average value of the current effective value fluctuation and the safety margin, and λ indicates the noise level;

[0151] A detection acquisition unit is used to continuously slide the detection extraction window, and detect current data of several cycles in the feature data set based on the sliding detection extraction window to detect voltage transient values, and acquire the start-stop event characteristics in the feature data set based on the starting point of the power consumption event and the voltage transient value.

[0152] In some optional embodiments, the combination identification module 30 includes:

[0153] An allocation update unit is used to allocate a random position and a random speed to each particle in the second-order oscillation particle swarm, and update the speed size and speed direction of each particle by comparing the fitness value of the objective function of the second-order oscillation particle swarm algorithm, the particle optimal value and the global optimal value;

[0154] The correction identification unit is used to correct the movement process of the particles according to the updated speed size and speed direction of each particle, so that each particle gradually approaches the global optimal value, and identify the preliminary load type of the start-stop event characteristics based on the global optimal value combined with the SVM model.

[0155] In some optional embodiments, the setting detection module 40 includes:

[0156] An extraction unit, configured to set a movement strategy of the detection and extraction window according to the current trajectory diagram of the characteristic data set, so that the detection and extraction window covers the current trajectory diagram based on the movement strategy;

[0157] A screening unit, configured to screen the high-power load in the start-stop event characteristics based on the detection extraction window and the current effective value;

[0158] A determination unit is used to determine the load type based on the steady-state fundamental wave, harmonic amplitude, transient active power, transient reactive power and transient duration as load type characteristics, and based on the load type characteristics.

[0159] The functions or operation steps implemented when the above modules and units are executed are generally the same as those in the above method embodiments, and will not be repeated here.

[0160] The power safety monitoring system provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0161] Embodiment 3

[0162] See also Figure 3 , which is a schematic diagram of the hardware structure of the electronic device in the third embodiment of the present invention.

[0163] The electronic device may include a processor 81 and a memory 82 storing computer program instructions.

[0164] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the present application.

[0165] Among them, the memory 82 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 82 may be inside or outside the data processing device. In a specific embodiment, the memory 82 is a non-volatile memory. In a specific embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable ProgrammableRead-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable ProgrammableRead-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0166] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0167] The processor 81 implements the electricity safety monitoring method of the first embodiment by reading and executing the computer program instructions stored in the memory 82 .

[0168] In some of the embodiments, the electronic device may further include a communication interface 83 and a bus 80. Figure 3 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0169] The communication interface 83 is used to realize the communication between the modules, devices, units and / or equipment in the present application. The communication interface 83 can also realize data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage and image / data processing workstations.

[0170] The bus 80 includes hardware, software or both, and couples the components of the device to each other. The bus 80 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although this application describes and illustrates a particular bus, this application contemplates any suitable bus or interconnect.

[0171] The electronic device can obtain the power safety monitoring system and execute the power safety monitoring method of the first embodiment.

[0172] In addition, in combination with the power safety monitoring method in the first embodiment, the present application can provide a storage medium for implementation. The storage medium stores computer program instructions; when the computer program instructions are executed by the processor, the power safety monitoring method in the first embodiment is implemented.

[0173] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0174] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for monitoring power safety, characterized in that: The method comprises: Collecting power consumption data in real time, obtaining load characteristics in the power consumption data, extracting and analyzing the load characteristics to obtain a characteristic data set; A sliding detection window is defined in the power consumption time series, and a start-stop threshold is set, wherein the sliding detection window includes a calculation window and a detection extraction window, and the feature data set is detected based on the calculation window, the detection extraction window and the start-stop threshold to obtain the start-stop event feature; Using the SVM model combined with the second-order oscillating particle swarm algorithm and based on multi-feature loads to identify the preliminary load type of the start-stop event characteristics; Setting a moving strategy for the detection and extraction window, moving the detection and extraction window based on the moving strategy and performing hierarchical channel identification on the preliminary load type to obtain a determined load type; Counting the zero-crossing points in the characteristic data set as current data of the series arc, normalizing the current data to obtain processed current data, performing VDM decomposition on the processed current data to obtain the center frequency of each modal component, and using the difference of the center frequency of each modal component as the arc feature; Extracting the current increment coefficient and the fuzzy entropy value of each modal component in the arc feature, forming a feature vector according to the fuzzy entropy value and the center frequency, and inputting the feature vector into an integrated deep RVFL neural network, so that the integrated deep RVFL neural network is trained based on the feature vector to obtain a trained integrated deep RVFL neural network; The arc characteristics are identified based on the trained integrated deep RVFL neural network to obtain power safety information, and the determined load type is detected through the continuous moving variation method to obtain the current condition type.

2. The method for monitoring power safety according to claim 1, characterized in that: The steps of collecting power consumption data in real time, obtaining load characteristics in the power consumption data, extracting and analyzing the load characteristics to obtain a characteristic data set include: Collecting an electric power signal based on a collection sensor, and converting the electric power signal by a preset multiple to collect current data; Acquire a steady-state characteristic of the current based on the current amplitude, the current harmonic component, the steady-state active power and the steady-state reactive power in the current data; The transient characteristics of the current are acquired based on the transient current, transient active power, transient reactive power, voltage noise and duration in the current data.

3. The method for monitoring power safety according to claim 2, characterized in that: The calculation expression of the steady-state active power is: In the formula, P represents steady-state active power, k represents harmonic order, V k Indicates the effective value of the kth voltage harmonic, I k represents the effective value of the kth current harmonic, θ k represents the kth harmonic phase difference; The calculation expression of the steady-state reactive power is: Where Q represents the steady-state reactive power.

4. The method for monitoring power safety according to claim 1, characterized in that: The step of defining a sliding detection window in the power consumption time series and setting a start-stop threshold, wherein the sliding detection window includes a calculation window and a detection extraction window, and detecting the feature data set based on the calculation window, the detection extraction window and the start-stop threshold to obtain the start-stop event feature includes: Defining a calculation window and a detection and extraction window in the power consumption time series, and setting the window lengths of the calculation window and the detection and extraction window; Calculate the effective average current value of the characteristic data set based on the calculation window; Set a start / stop threshold, and compare the start / stop threshold with the effective average current value. If the effective average current value is greater than the start / stop threshold, it is determined that a transient event has occurred, and the starting point of the power consumption event is recorded. The detection and extraction window is continuously slid, and current data of several cycles in the feature data set is detected based on the sliding detection and extraction window to detect voltage transient values, and the start-stop event features in the feature data set are obtained based on the starting point of the power consumption event and the voltage transient value.

5. The method for monitoring power safety according to claim 4, characterized in that: The calculation expression of the start-stop threshold is: In the formula, H min , H max respectively represent the maximum value of the start / stop threshold and the minimum value of the start / stop threshold, L1 represents the number of sampling points of fluctuation increase, L2 represents the number of sampling points of the current increase of the electrical equipment, L represents the length of the calculation window, I min It represents the minimum change amplitude in identifying electrical equipment, f represents the combination of the average value of the effective value fluctuation of the current and the safety margin, and λ represents the noise level.

6. The method for monitoring power safety according to claim 1, characterized in that: The step of using the SVM model in combination with the second-order oscillating particle swarm algorithm to identify the preliminary load type of the start-stop event characteristics based on multi-feature loads includes: Assigning a random position and a random speed to each particle in the second-order oscillation particle swarm, and updating the speed and direction of each particle by comparing the fitness value of the objective function of the second-order oscillation particle swarm algorithm, the particle optimal value and the global optimal value; The movement process of the particles is corrected according to the updated speed magnitude and speed direction of each particle, so that each particle gradually approaches the global optimal value, and the preliminary load type of the start-stop event characteristics is identified based on the global optimal value combined with the SVM model.

7. The method for monitoring power safety according to claim 1, characterized in that: The step of setting a movement strategy of the detection and extraction window, moving the detection and extraction window based on the movement strategy, and performing hierarchical channel identification on the preliminary load type to obtain a determined load type includes: Setting a moving strategy of the detection and extraction window according to the current trajectory diagram of the characteristic data set, so that the detection and extraction window covers the current trajectory diagram based on the moving strategy; Filtering high-power loads in the start-stop event characteristics based on the detection extraction window and the current effective value; The load type is determined based on the steady-state fundamental wave, harmonic amplitude, transient active power, transient reactive power and transient duration as load type characteristics, and based on the load type characteristics.

8. An electricity safety monitoring system, characterized in that: The system comprises: A real-time acquisition module, used to collect power consumption data in real time, obtain load characteristics in the power consumption data, extract and analyze the load characteristics to obtain a characteristic data set; A detection module is defined, which is used to define a sliding detection window in the power consumption time series and set a start-stop threshold, wherein the sliding detection window includes a calculation window and a detection extraction window, and the feature data set is detected based on the calculation window, the detection extraction window and the start-stop threshold to obtain the start-stop event feature; Combined with an identification module, it is used to use the SVM model in combination with a second-order oscillating particle swarm algorithm and identify the preliminary load type of the start-stop event characteristics based on multi-feature loads; A detection module is set to set a moving strategy of the detection and extraction window, move the detection and extraction window based on the moving strategy, and perform hierarchical channel identification on the preliminary load type to obtain a determined load type; A statistical processing module, used for counting the zero-crossing points in the characteristic data set as current data of the series arc, normalizing the current data to obtain processed current data, performing VDM decomposition on the processed current data to obtain the center frequency of each modal component, and using the difference of the center frequency of each modal component as the arc feature; An extraction training module is used to extract the current increment coefficient and the fuzzy entropy value of each modal component in the arc feature, form a feature vector according to the fuzzy entropy value and the center frequency, and input the feature vector into an integrated deep RVFL neural network so that the integrated deep RVFL neural network is trained based on the feature vector to obtain a trained integrated deep RVFL neural network; An identification and detection module is used to identify the arc characteristics based on the trained integrated deep RVFL neural network to obtain power safety information, and to detect the determined load type through a continuous moving variation method to obtain a current condition type.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the power safety monitoring method according to any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the power safety monitoring method according to any one of claims 1 to 7 is implemented.

Images