CN110967585B - Malignant load identification method and device - Google Patents
Malignant load identification method and device Download PDFInfo
- Publication number
- CN110967585B CN110967585B CN201911329342.7A CN201911329342A CN110967585B CN 110967585 B CN110967585 B CN 110967585B CN 201911329342 A CN201911329342 A CN 201911329342A CN 110967585 B CN110967585 B CN 110967585B
- Authority
- CN
- China
- Prior art keywords
- identified
- malignant load
- time period
- data samples
- instantaneous power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The invention provides a malignant load identification method and device, and relates to the field of malignant load identification. The method can be integrated in an identification device, and the identification device can acquire the interruption times of the electric energy meter in each period by taking a preset time period as a period after the electric equipment to be identified is accessed to the electric energy meter; the identification device acquires a sampling data sample of the electric equipment to be identified according to the interruption times in each period; the identification device can calculate the variation trend of instantaneous power according to the sampling data sample and determine whether the electric equipment to be identified is suspected load; if so, the identification device compares the learned malignant load data sample with the sampling data sample according to a preset algorithm to determine whether the suspected malignant load is the malignant load, and through two judgment processes, the purpose of accurately distinguishing the malignant load from the non-malignant load can be achieved, and the accuracy rate of identifying the malignant load is improved.
Description
Technical Field
The invention relates to the field of malignant load identification, in particular to a malignant load identification method and device.
Background
At present, with the increase of campus electric equipment, campus electric safety accidents are frequently reported, and campus electric safety hidden dangers and waste become problems which need to be solved urgently by campus managers. Aiming at the problem, in recent years, a method of externally connecting a current limiter (limiting the power load capacity) or a judgment algorithm for increasing the power increment of an electric energy meter is adopted to solve the problem, but the externally connecting current limiter increases the installation difficulty, the number of the electric energy meters installed in the same meter box is reduced, and the resource is wasted; although the power increment algorithm can effectively prevent the use of high-power electric equipment, the power increment algorithm also limits the high-power equipment with non-malignant loads, such as an air conditioner and the like.
In the prior art, the main algorithms in the malignant load identification algorithm are a power factor method, an instantaneous power increment method, a harmonic discrimination method and the like. The power factor method is to detect a malignant load by measuring the power factor of the load; the instantaneous power increment method is used for detecting a malignant load by a method of monitoring the power of a circuit in real time; the harmonic discrimination method is to identify a malignant load by calculating the conduction angle of the fundamental wave and the higher harmonic of the load.
However, the above algorithms are all based on the steady-state characteristics of the connected electric devices, and although some illegal electric devices can be identified, the effect is not ideal, and the purpose of accurately distinguishing the malignant load from the non-malignant load cannot be achieved.
Disclosure of Invention
The invention aims to provide a malignant load identification method and a malignant load identification device, which can accurately distinguish a malignant load from a non-malignant load.
The embodiment of the invention is realized by the following steps:
in one aspect of the embodiments of the present invention, a method for identifying a malignant load is provided, including: after the identification device acquires that the electric equipment to be identified is connected to the electric energy meter, acquiring the interruption times of the electric energy meter in each period by taking a preset time period as a period, wherein the preset time period is 200ms and 280 ms; the identification device acquires sampling data samples for identifying the electric equipment according to the interruption times in each period, wherein the sampling data samples comprise instantaneous power data samples and/or voltage data samples, current data samples and voltage-current phase difference data samples; and the identification device calculates the variation trend of the instantaneous power according to the sampling data samples, determines whether the electric equipment to be identified is suspected malignant load, and if so, compares the learned malignant load data samples with the sampling data samples according to a preset algorithm to determine whether the suspected malignant load is the malignant load.
As above, the identifying device calculates the variation trend of the instantaneous power according to the sampling data samples, and determines whether the electric equipment to be identified is a suspected malignant load, including: the identification device calculates and obtains the instantaneous power variation trend of the electric equipment to be identified according to the sampling data samples; the identification device acquires a difference value between the instantaneous power of the previous period and the instantaneous power of the period to be identified in a first judgment time period, wherein the first judgment time period comprises m preset time periods, and m is an integer greater than 1; when the difference is larger than a first preset threshold, the identification device determines that the electric equipment to be identified is not suspected to be a malignant load; or when the difference is not greater than the first preset threshold, the identification device judges whether the electric equipment to be identified is a suspected malignant load again in a second judgment time period, wherein the second judgment time period comprises m preset time periods, and m is an integer greater than 1.
As described above, the identifying device determines again whether the electrical device to be identified is a suspected malignant load in the second determination time period, including:
the identification device acquires n1 difference values between the instantaneous power of the period to be identified in the second judgment time period and the instantaneous power of the previous n periods respectively;
if no k1 continuous difference values of the n1 difference values are all larger than a second preset threshold, the electric equipment to be identified is a non-suspected malignant load; if k1 continuous difference values of the n1 difference values are all larger than a second preset threshold, the electric equipment to be identified needs to enter a third judgment time period;
in a third judgment time period, the identification device obtains n1 difference values between the instantaneous power of the period to be identified in the third judgment time period and the instantaneous power of the previous n periods again, and if k2 difference values in the n1 difference values are smaller than a third preset threshold, the identification device determines that the electric equipment to be identified is a suspected malignant load; or if k3 difference values in the n1 difference values are larger than a third preset threshold, the identification device obtains a first absolute value of a power difference between the instantaneous power of the period to be identified in the third judgment time period and the instantaneous power of the first period in the third judgment time period and a second absolute value of a power difference between the instantaneous power of the period to be identified in the second judgment time period and the instantaneous power of the first period in the second judgment time period; the identification device judges whether the first absolute value and the second absolute value meet preset conditions or not, if so, the electric equipment to be identified is determined to be suspected malignant load, and if not, the electric equipment to be identified is determined to be not suspected malignant load; n1 is more than or equal to n, k1 is more than or equal to 0 and less than or equal to n1, k2 is more than 0 and less than or equal to n1, k3 is more than 0 and less than or equal to k2, and k1, k2 and k3 are integers.
As above, after the identification device obtains the electric energy meter accessed to the electric equipment to be identified, the identification device collects the interruption times of the electric energy meter in each period by taking the preset time period as the period, and the identification device includes: the identification device adopts a formula after the electric energy meter is connected to the electric equipment to be identified
Calculating the interruption times H of the electric energy meter in each period; wherein, P is power accuracy, C is the pulse constant of the electric energy meter, t is the preset time period, and 1kWh is 1 degree electricity.
As above, the preset time period is 220 ms.
Optionally, the comparing, by the identification device, the learned data sample of the malignant load with the sampled data sample according to a preset algorithm to determine whether the suspected malignant load is a malignant load includes:
calculating the Euclidean distance between the sampling data sample and the malignant load data sample; determining the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample according to the Euclidean distance and the preset Euclidean distance; and confirming whether the suspected malignant load is the malignant load or not according to the type and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample.
Optionally, the method further includes:
acquiring a plurality of training sample sets of the electric equipment to be identified, wherein each training sample set comprises a plurality of instantaneous power data samples and/or a plurality of voltage data samples, current data samples and voltage-current phase difference data samples; calculating the sum of the minimum values of the distances between the data samples in any two training sample sets according to the training sample sets; according to the sum of the distance minimum values between the data samples in any two training sample sets, acquiring two training sample sets corresponding to the minimum distance minimum value sum as a first training sample set, and acquiring two training sample sets corresponding to the maximum distance minimum value sum as a second training sample set; taking the training sample set belonging to the first training sample set but not to the second training sample set as the already learned malignant load data sample.
A second aspect of an embodiment of the present invention provides an apparatus for identifying a malignant load, including:
the first acquisition module is used for acquiring the interruption times of the electric energy meter in each period by taking a preset time period as a period after the electric equipment to be identified is accessed to the electric energy meter, wherein the preset time period is (200ms, 280 ms); the second acquisition module is used for acquiring sampling data samples of the electric equipment to be identified according to the interruption times in each period, wherein the sampling data samples comprise instantaneous power data samples and/or voltage data samples, current data samples and voltage-current phase difference data samples; the pre-judging module is used for calculating the change trend of the instantaneous power according to the sampling data samples and determining whether the electric equipment to be identified is suspected malignant load;
and the confirming module is used for comparing the learned malignant load data sample with the sampling data sample according to a preset algorithm if the suspected malignant load is the malignant load.
As above, the prejudging module is specifically configured to calculate and obtain the instantaneous power of the to-be-identified electrical device according to the sample data; acquiring a difference value between the instantaneous power of the previous period and the instantaneous power of the period to be identified in a first judgment time period, wherein the first judgment time period comprises m preset time periods, and m is an integer greater than 1; when the difference is larger than a first preset threshold, determining that the electric equipment to be identified is a non-suspected malignant load; or when the difference is not greater than the first preset threshold, judging whether the electric equipment to be identified is suspected to be a malignant load again in a second judgment time period, wherein the second judgment time period comprises m preset time periods, and m is an integer greater than 1.
As above, the pre-determining module is specifically configured to obtain n1 differences between the instantaneous power of the period to be identified in the second determination time period and the instantaneous powers of the previous n periods, respectively; if no k1 continuous difference values of the n1 difference values are larger than a second preset threshold, the electric equipment to be identified is a non-suspected malignant load; if k1 continuous difference values of the n1 difference values are all larger than a second preset threshold, the electric equipment to be identified needs to enter a third judgment time period;
in a third judgment time period, n1 difference values between the instantaneous power of the cycle to be identified in the third judgment time period and the instantaneous power of the previous n1 cycles are obtained again, and if k2 difference values in the n1 difference values are smaller than a third preset threshold, the electric equipment to be identified is determined to be a suspected malignant load; or if k3 difference values of the n1 difference values are larger than a third preset threshold, acquiring a first absolute value of a power difference between the instantaneous power of the cycle to be identified in the third judgment time period and the instantaneous power of the first cycle in the third judgment time period, and a second absolute value of a power difference between the instantaneous power of the cycle to be identified in the second judgment time period and the instantaneous power of the first cycle in the second judgment time period; judging whether the first absolute value and the second absolute value meet a preset condition, if so, determining that the electric equipment to be identified is suspected malignant load, and if not, determining that the electric equipment to be identified is not suspected malignant load; wherein n is an integer larger than 0, n1 is larger than n, k1 is larger than 0 and is larger than n1, k2 is larger than 0 and is smaller than n1, k3 is larger than 0 and is smaller than k2, and k1, k2 and k3 are integers.
As described above, the first obtaining module is specifically configured to adopt a formula after the electrical device to be identified is connected to the electric energy meter
Calculating the interruption times H of the electric energy meter in each period; wherein, P is power accuracy, C is the pulse constant of the electric energy meter, t is the preset time period, and 1kWh is 1 degree electricity.
As above, the preset time period is 220 ms.
As above, the confirmation module is specifically configured to calculate the euclidean distance between the sampled data samples and the malignant load data samples; determining the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample according to the Euclidean distance and the preset Euclidean distance; and confirming whether the suspected malignant load is the malignant load or not according to the type and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample.
Optionally, the apparatus further comprises: the device comprises a calculation module, a detection module and a recognition module, wherein the calculation module is used for acquiring a plurality of training sample sets of the electric equipment to be recognized, and each training sample set comprises a plurality of instantaneous power data samples and/or a plurality of voltage data samples, current data samples and voltage-current phase difference data samples; calculating the sum of the minimum values of the distances between the data samples in any two training sample sets according to the plurality of training sample sets; according to the sum of the minimum values of the distances between the data samples in any two training sample sets, acquiring two training sample sets corresponding to the minimum value of the distances as a first training sample set, and acquiring two training sample sets corresponding to the maximum value of the distances as a second training sample set; a training sample set belonging to the first training sample set, but not to the second training sample set, is taken as a malignant load data sample that has been learned.
The invention has the beneficial effects that: in the identification method and the identification device for the malignant load, the method can be integrated in the identification device, and the identification device can acquire the interruption times of the electric energy meter in each period by taking a preset time period as a period after the electric equipment to be identified is accessed to the electric energy meter; the identification device acquires a sampling data sample of the electric equipment to be identified according to the interruption times in each period; the identification device can further determine whether the electric equipment to be identified is a suspected malignant load according to the sampling data sample; if so, the identification device compares the learned malignant load data sample with the sampling data sample according to a preset algorithm to determine whether the suspected malignant load is the malignant load, and through two judgment processes, the purpose of accurately distinguishing the malignant load from the non-malignant load can be achieved, and the accuracy rate of identifying the malignant load is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flowchart illustrating a method for identifying a malignant load according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for identifying a malignant load according to another embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for identifying a malignant load according to another embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for identifying a malignant load according to another embodiment of the present invention;
FIG. 5 is a schematic diagram of an apparatus for identifying a malignant load according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a malignant load identification apparatus according to another embodiment of the present invention.
Detailed Description
First embodiment
Fig. 1 is a schematic flow chart of a method for identifying a malignant load according to an embodiment of the present invention, and as shown in fig. 1, the embodiment of the present invention provides a method for identifying a malignant load, including:
s101, after the identification device acquires that the electric equipment to be identified is connected to the electric energy meter, the interruption times of the electric energy meter in each period are collected by taking a preset time period as a period.
Wherein the preset time period is (200ms, 280 ms); specifically, a metering chip in the electric energy meter samples voltage and current in real time, when the value of an active power count register, a reactive power count register and an apparent power count register (PFcnt/QFcnt/SFcnt) of the metering chip is greater than or equal to a high-frequency pulse frequency (HFconst) of the metering chip, a corresponding PF/QF/SF pulse overflows, a PF/QF/SF pin is connected with an external interrupt port of a single chip microcomputer, when the PF/QF/SF pulse overflows, a program enters a corresponding interrupt program, the electric energy meter performs current interrupt operation, and then an identification device acquires the number of times of interruption of the electric energy meter in each period, wherein it needs to be noted that the identification device is a malignant load identification device, is connected in a circuit to be identified, and is used for identifying whether a malignant load exists in the circuit.
S102, the identification device obtains sampling data samples of the electric equipment to be identified according to the interruption times in each period.
The sampled data samples may include instantaneous power data samples, and/or voltage data samples, current data samples, and voltage-current phase difference data samples. Specifically, in each period, the accumulated value of the interruption times can be adjusted in the program, the times of interruption of the identification device in a preset time period are recorded, and then the sampling data samples of the electric equipment to be identified can be obtained according to the interruption times.
S103, the identification device calculates the change trend of the instantaneous power according to the sampling data samples, and determines whether the electric equipment to be identified is a suspected malignant load.
And S104, if so, comparing the learned malignant load data sample with the sampling data sample by the identification device according to a preset algorithm, and determining whether the suspected malignant load is a malignant load.
Alternatively, the variation trend of the instantaneous power can be calculated according to the instantaneous power data samples included in the sampling data samples; the variation trend of the instantaneous power can also be calculated according to a voltage data sample, a current data sample and a voltage-current phase difference data sample which are included in the sampling data sample, the application is not limited herein, and further whether the electric equipment to be identified is a suspected malignant load can be determined according to some characteristics of the instantaneous power, whether the electric equipment to be identified is the suspected malignant load is determined in each determination time period, the determination result is more accurate through the determination of a plurality of determination time periods, and the high-power equipment of the non-malignant load is prevented from being identified by mistake.
In the method provided in this embodiment, the number of times of entering the interrupt is accumulated, the data is taken every preset time period, the number of times of the current preset time period is now _ cnt, the number of times of interrupt of the previous first preset time period is old _ cnt0, the number of times of interrupt of the previous second preset time period is old _ cnt1, the number of times of interrupt of the previous third preset time period is old _ cnt2, the number of times of interrupt of the previous fourth preset time period is old _ cnt3, and the instantaneous power may be regarded as equal to cnt 20W, that is: the instantaneous power of the current preset time period is equal to now _ cnt 20W; the instantaneous power of the first preset time period is equal to old _ cnt0 × 20W; the instantaneous power of the first second preset time period is equal to old _ cnt1 × 20W; the instantaneous power of the first third preset time period is equal to old _ cnt2 × 20W; the instantaneous power of the first fourth preset time period is equal to old _ cnt3 × 20W, and generally, the range of the preset time period is: (200ms, 280ms), judging the instantaneous power of each preset time period to further obtain whether the electric equipment to be identified is a suspected malignant load.
For example, optionally, a method of identifying a malignant load may include: and (4) program initialization, and current interrupt count and the previous 4 interrupt counts are cleared. When the program detects that the first judgment time period reaches a preset time period, whether the electric equipment to be identified is suspected to be a malignant load is judged, when the program judges that the electric equipment to be identified is suspected to be the malignant load, the flow is directly ended, when the program judges that the electric equipment to be identified is possibly the suspected malignant load, the second judgment time period is carried out to execute the same content as the first judgment time period, then a third judgment time period is entered, the third judgment time period judges whether the electric equipment to be identified is the suspected malignant load, the interruption times of each judgment time period are reset, if the program judges that the electric equipment to be identified is the suspected to be the malignant load, the program controls the electric equipment to be identified to be powered off, and if the program judges that the electric equipment to be identified is the suspected to be the malignant load, the current flow is ended.
Specifically, the preset time is obtained by a relationship between the power accuracy, a pulse constant of the electric energy meter, the number of times of interruption of the electric energy meter, and the electric energy and the preset time.
In summary, the present application provides a method for identifying a malignant load, which may be integrated in an identification device, where the identification device may acquire the number of times of interruption of an electric energy meter in each period by taking a preset time period as a period after an electric device to be identified is connected to the electric energy meter; the identification device acquires sampling data samples of the electric equipment to be identified according to the interruption times in each period, wherein the sampling data samples comprise instantaneous power data samples and/or voltage data samples, current data samples and voltage-current phase difference data samples; the identification device calculates the variation trend of instantaneous power according to the sampling data samples, and can determine whether the electric equipment to be identified is suspected malignant load; if so, the identification device compares the learned malignant load data sample with the sampling data sample according to a preset algorithm to determine whether the suspected malignant load is the malignant load, and through two judgment processes, the purpose of accurately distinguishing the malignant load from the non-malignant load can be achieved, and the accuracy rate of identifying the malignant load is improved.
Fig. 2 is a schematic flow chart of a method for identifying a malignant load according to another embodiment of the present invention, and as shown in fig. 2, the identifying device calculates and obtains an instantaneous power variation trend of an electrical device to be identified according to a sample of sampled data, and determines whether the electrical device to be identified is a suspected malignant load, including:
s201, the identification device obtains a difference value between the instantaneous power of the previous period and the instantaneous power of the period to be identified in a first judgment time period, wherein the first judgment time period comprises m preset time periods, and m is an integer larger than 1.
S202, the identification device judges whether the difference value is larger than a first preset threshold.
If so, go to step S203, otherwise, go to step S204.
S203, the identification device determines that the electric equipment to be identified is not suspected to be a malignant load.
And S204, the identification device judges whether the electric equipment to be identified is suspected to be a malignant load again in a second judgment time period, wherein the second judgment time period comprises m preset time periods, and m is an integer greater than 1.
Specifically, the identification device obtains a difference value between the instantaneous power of the previous cycle and the instantaneous power of the cycle to be identified in a first judgment time period, the first judgment time period is uniformly divided into m, and m is an integer greater than or equal to 1, then judges whether the electric equipment to be identified is a suspected malignant load, and if the difference value between the instantaneous power of the previous preset time period and the instantaneous power of the current preset time period is greater than a first preset threshold value, judges that the electric equipment to be identified is a non-suspected malignant load, and ends the current program. Or if the difference is not greater than the first preset threshold, continuing to determine whether the load is suspected to be a malignant load in a second determination time period, where in practical application, the first preset threshold may be 80W.
Fig. 3 is a flowchart illustrating a method for identifying a malignant load according to another embodiment of the present invention. As shown in fig. 3, the determining, by the identifying device, whether the electrical device to be identified is a suspected malignant load again in the second determination time period includes:
s301, the identification device obtains n1 difference values between the instantaneous power of the period to be identified and the instantaneous power of the previous n periods in the second judgment time period.
S302, judging whether k1 continuous difference values of the n1 difference values are all larger than a second preset threshold.
And S303, if not, determining that the electric equipment to be identified is a non-suspected malignant load.
And S304, if so, the electric equipment to be identified enters a third judgment time period, and in the third judgment time period, the identification device acquires n1 difference values between the instantaneous power of the period to be identified in the third judgment time period and the instantaneous power of the previous n periods respectively.
S305, judging whether k2 difference values in the n1 difference values are smaller than a third preset threshold.
And S306, if so, determining the electric equipment to be identified as a suspected malignant load.
S307, if not, if k3 difference values in the n1 difference values are larger than a third preset threshold, the identification device obtains a first absolute value of a power difference between the instantaneous power of the period to be identified in the third judgment time period and the instantaneous power of the first period in the third judgment time period, and a second absolute value of a power difference between the instantaneous power of the period to be identified in the second judgment time period and the instantaneous power of the first period in the second judgment time period.
And S308, the identification device judges whether the first absolute value and the second absolute value meet preset conditions, if so, the electric equipment to be identified is determined to be suspected malignant load, and if not, the electric equipment to be identified is determined to be not suspected malignant load.
n is an integer larger than 0, n1 is larger than n, k1 is larger than 0 and is larger than n1, k2 is larger than 0 and is larger than n1, k3 is larger than 0 and is larger than k2, and k1, k2 and k3 are integers.
It should be noted that the n1 difference values in the second determination time period are updated in real time, and each time the preset time period is reached, a difference value is calculated, and each determination is performed by using the newly calculated difference value.
In a specific application, in a second judgment time period, the identification device obtains a first difference value between the instantaneous power of the period to be identified in the second judgment time period and the instantaneous power of the previous period respectively, compares the difference value with a second preset threshold, if the first difference value is greater than the second preset threshold, records the difference value as 1 time, then, judging a second difference value between the instantaneous power of the next period and the instantaneous power of the previous period, comparing the second difference value with a second preset threshold, if the first difference value is larger than the second preset threshold, recording for 2 times, if a third difference value between the instantaneous power of the next period and the instantaneous power of the previous period is obtained to be larger than a second preset threshold, if the difference value between the instantaneous power of one period and the instantaneous power of the previous period is greater than a second preset threshold for 3 times continuously, continuing to judge for the third judgment time; if one difference value among the first difference value, the second difference value and the third difference value is not larger than a second preset threshold, the electric equipment to be identified is a non-suspected malignant load, namely within a second judgment time, if the difference values of instantaneous power of one cycle and instantaneous power of the previous cycle for three consecutive times are larger than the second preset threshold, the electric equipment to be identified enters a third judgment time period for judgment; and if the difference value between the instantaneous power of one period and the instantaneous power of the previous period is not greater than the second preset threshold for three times, the electric equipment to be identified is a non-suspected malignant load.
Specifically, in a steady state, the power of the malignant load is very stable, the difference is close to 0, but the power of the non-malignant load fluctuates greatly or continues to increase, and the algorithm distinguishes the malignant load from the non-malignant load through the detail.
In the second judgment time period, the current power difference is equal to the power obtained by subtracting the last 3 times from the current power, if the judgment is still continued after the second judgment time period is finished, a time delay is needed at the moment, after the power of the electric equipment to be used is stable, the difference is obtained every 220ms in sequence, and then the third judgment time period is started;
in a third judgment time period, continuously judging 5 difference values, and if the three difference values are smaller than a third preset threshold, considering the accessed equipment as a suspected malignant load; if the difference value is not less than the third preset threshold, continuing to judge whether the difference value is more than half of the difference value judged in the second step, if so, considering the accessed equipment as suspected malignant load, and if not, considering the accessed equipment as non-suspected malignant load.
And the value of the second preset threshold is set according to the actual situation and the experience of the staff, and is not specifically limited, the value of the third preset threshold is set according to the actual situation and the experience of the staff, and is not specifically limited, and the judgment of the first absolute value and the second absolute value by the identification device needs to meet the preset condition, is not limited, and can be set according to the actual situation and the experience of the staff.
Specifically, the identification device obtains, in the second determination time period, if the time is greater than the preset time, n1 difference values between the instantaneous power of the current cycle and the instantaneous power of the previous n cycles respectively, where the starting time count is 0, n and n1 are positive integers greater than 1, n is greater than n1, if the difference value is greater than the second preset threshold, the starting time count is 0, the starting time count is n and n1 are positive integers greater than 1, the starting time count is n1, if the difference value is greater than the second preset threshold, the starting time count is incremented, if the difference value is not greater than the second preset threshold, the starting time count is decremented by one, and the time count is determined, if the starting time count is equal to 3, the instantaneous power of the current time and the instantaneous power of the previous 3 times are assigned to the power increment, the first power increment is PW1, and the third determination time period is entered, and in the third determination time period: defining the extension time as t at the beginning, judging the times as m, wherein the initial m is equal to 0, judging the result feedback times as Q, wherein the initial Q is equal to 0, judging whether the preset time period is met, if so, judging whether m is smaller than 5, if m is smaller than 5, adding 1 to m, continuing whether the absolute value of the difference value between the instantaneous power of the current preset time period and the instantaneous power of the previous fourth preset time period is larger than a third preset threshold value, and if so, adding 1 to Q; if m is not less than 5, judging whether Q is less than 3, and if Q is less than 3, obtaining that the electric equipment to be identified is a suspected malignant load; if Q is not less than 3, assigning the absolute value of the difference value between the instantaneous power of the current preset time period and the instantaneous power of the previous fourth preset time period as a second power variation PW2, then judging whether the second power variation PW2 which is 2 times larger than the first power variation PW1, if so, judging that the electric equipment to be identified is suspected malignant load, if not, judging that the electric equipment to be identified is non-malignant load, and setting n, n1, m and Q to zero after judging that the type of the electric equipment to be identified is finished.
Optionally, after the third judgment time period is judged to be finished, resetting the times of the preset time period and the instantaneous power of the preset time period, and if the program judges that the electric equipment to be identified is a non-suspected malignant load, ending the program; and if the program judges that the electric equipment to be identified is the suspected malignant load, the program identification device compares the learned data sample of the malignant load with the sampling data sample according to a preset algorithm to determine whether the suspected malignant load is the malignant load.
Further, after the identification device acquires that the electric equipment to be identified is connected to the electric energy meter, the identification device acquires the interruption times of the electric energy meter in each period by taking a preset time period as a period, and the method comprises the following steps:
the identification device adopts a formula after the electric energy meter is connected to the electric equipment to be identified
Calculating the interruption times H of the electric energy meter in each period; wherein, P is power accuracy, C is the pulse constant of the electric energy meter, t is the preset time period, and 1kWh is 1 degree electricity. The larger the H value is, the higher the precision of the represented instantaneous power value is, optionally, the preset time period t may be 220ms, the value of the pulse constant C of the electric energy meter may be 1600, and the value of the power precision P may be 20w, so that the value of the H may be obtained through calculation. Of course, the application does not limit the specific values of the parameters, and the specific values can be set according to the actual application.
Fig. 4 is a flowchart illustrating a method for identifying a malignant load according to another embodiment of the present invention. Optionally, as shown in fig. 4, the comparing, by the identification device, the learned data sample of the malignant load with the sampled data sample according to a preset algorithm to determine whether the suspected malignant load is a malignant load includes:
s501, calculating the Euclidean distance between the sampling data sample and the malignant load data sample.
And S502, determining the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample according to the Euclidean distance.
S503, according to the type and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample, determining whether the suspected malignant load is a malignant load.
Specifically, the preset algorithm may be based on an artificial intelligence recognition algorithm, analyze and process the sampled data sample through a dedicated artificial intelligence recognition algorithm, compare the sampled data sample with the learned data sample of the malignant load, obtain a comparison result, determine that the suspected malignant load is the malignant load if the comparison result is within a comparison range, and exclude the suspected malignant load if the comparison result is not within the comparison range. Optionally, the specific process is as follows:
step one, calculating Euclidean distances between a sample array of sampling data and corresponding elements of a training sample array of learned malignant load data; assigning the calculated data of the Euclidean distance to an array to form a Euclidean distance array; and sequencing the elements of the Euclidean distance array from large to small to form a new Euclidean distance array with good sequencing.
And step two, assuming that K samples are matched, taking the Euclidean distance corresponding to the Kth element sample of the element of the new Euclidean distance array as the reference Euclidean distance.
Step three, acquiring a sampling data sample array and a training sample corresponding to the training sample array, wherein the Euclidean distance between the sampling data sample array and the corresponding element of the training sample array is smaller than the training sample corresponding to the reference Euclidean distance; counting the occurrence frequency N of the corresponding preset malignant load sample category in the training sample; according to different application scenarios, the preset malignant load sample category may be divided according to power consumption parameters of the electric devices, for example, a total power consumption value or an instantaneous step power value, and optionally, the electric devices may include a heat exchanger, an electric cup, an electric cooker, a computer, and the like, which is not limited herein.
And step four, selecting the malignant load type with the maximum occurrence frequency N, judging whether the frequency N is greater than the preset frequency B, if so, determining that the electric equipment to be identified corresponding to the sampling data sample is the malignant load, and otherwise, determining that the electric equipment to be identified is the non-malignant load.
According to the field power grid load condition, one vicious load can carry out multiple times of learning under multiple power grid load conditions, and multiple learning training sample sets can be saved aiming at the same vicious load. Alternatively, the above-mentioned malignant load data samples that have been learned can be obtained by using the following process learning training:
acquiring a plurality of training sample sets of the electric equipment to be identified, wherein each training sample set comprises a plurality of instantaneous power data samples and/or a plurality of voltage data samples, current data samples and voltage-current phase difference data samples; calculating the sum of the minimum values of the distances between the data samples in any two training sample sets according to the training sample sets; according to the sum of the distance minimum values between the data samples in any two training sample sets, acquiring two training sample sets corresponding to the minimum distance minimum value sum as a first training sample set, and acquiring two training sample sets corresponding to the maximum distance minimum value sum as a second training sample set; taking the training sample set belonging to the first training sample set but not to the second training sample set as the already learned malignant load data sample.
Optionally, the number of the training sample sets may be 3, or may be other numbers, and the present application is not limited herein. For example, when a certain to-be-identified electric device is accessed, a learning training function may be started, a plurality of corresponding training sample sets (learning sample sets) may be obtained through multiple times of learning, optionally, a first training sample set (first learning sample set) may be obtained through the first time of learning, the learning is resumed twice after the learning is completed, so as to obtain 3 training sample sets, the results are sorted from large to small by calculating the sum of the minimum values of the distances between the data in any two training sample sets, optionally, a comparison algorithm may be used to perform validity judgment on the 3 training sample sets, and an effective learning training sample set may be stored according to the judgment result, and may be used as a learned malignant load data sample.
Optionally, the alignment algorithm flow is as follows:
assume that the first learning sample set is X ═ a1,a2,…,an}TCorresponding to the A set ai(i ═ 1,2, … n), and the second learning sample set is Y ═ b1,b2,…,bn}TCorresponding to the B set Bj(j ═ 1,2, … n), and the third learning sample set is Z ═ { c1,c2,…,cn}TCorresponding to the set C ═ C1,c2,…,cnIs (n isThe number of samples processed by calculation after sampling can be n samples corresponding to one sampling), then a point a in the set A is obtainedi(i-1, 2, … n) to a point B in the B setjThe distance of (j ═ 1,2, … n) can be expressed as:
wherein
Is ai,bjThe abscissa of the (c) axis of the (c),
is ai,bjThe ordinate of (c).
Assume that a set, B set, and C set are a ═ a, respectively1,a2,…,an}，B＝{b1,b2,…,bn}，C＝{c1,c2,…,cnDefine a point a in the A seti(i-1, 2, … n) the distance to each point in the B set takes the minimum value, i.e.:
then dmin(A, B) represents the distance from each point in the A set to two sets in the B set, and the sum is accumulated by adopting the minimum value:
it can also be found that the sum of the distance minima from the A set to the C set:
sum of distance minimum from B set to C set:
comparison dmin(A,B)，dmin(A,C)，dmin(B, C), taking the minimum value to obtain two sample sets T1,T2(T1,T2E (A, B, C)), taking the maximum value to obtain two sample sets T2,T3(T2,T3E (A, B, C)), the sample set obtained by removing the maximum value from the two sample sets obtained by the minimum value is the learned malignant load data sample, namely the learned malignant load data sample is T1(T1E (A, B, C)), for example:
if d ismin(A,B)>dmin(A,C)>dmin(B, C), the minimum value is dmin(B, C), and obtaining sample sets B and C; maximum value of dmin(A, B), the sample set is obtained as the set of A, B, B belonging to the minimum value and the maximum value, so the set C belonging to the minimum value but not belonging to the maximum value can be used as the learned malignant load data sample after elimination.
In the identification method for the malignant load provided by this embodiment, the instantaneous power of the electrical equipment to be identified may be calculated according to the number of times of interruption in each cycle, so as to identify whether the electrical equipment is a suspected malignant load first according to the instantaneous power of the identification device, and finally, a preset algorithm is used to perform confirmation, so as to achieve the purpose of accurately determining whether the electrical equipment to be identified is the malignant load.
Second embodiment
Fig. 5 is a schematic structural diagram of a malignant load identification apparatus provided in an embodiment of the present invention, the malignant load identification apparatus is integrated into a terminal device having a computing function, and the computing device may be electrically connected to an electric energy meter. As shown in fig. 5, the identification means of the malignant load may include: the first obtaining module 110 is configured to obtain the interruption times of the electric energy meter in each period by taking a preset time period as a period after the electric equipment to be identified is accessed to the electric energy meter, where the preset time period is (200ms, 280 ms); the second obtaining module 120 is configured to obtain a sampling data sample of the to-be-identified electrical device according to the number of interrupts in each period, where the sampling data sample includes an instantaneous power data sample, and/or a voltage data sample, a current data sample, and a voltage-current phase difference data sample; the prejudging module 130 is configured to calculate a variation trend of the instantaneous power according to the sample data, and determine whether the electrical device to be identified is a suspected malignant load; and the confirming module 140 is configured to, if yes, compare the learned data sample of the malignant load with the sampled data sample according to a preset algorithm, and confirm whether the suspected malignant load is a malignant load.
As above, the pre-judging module 130 is specifically configured to calculate and obtain the instantaneous power of the to-be-identified electrical device according to the sample data sample; acquiring a difference value between the instantaneous power of the previous period and the instantaneous power of the period to be identified in a first judgment time period, wherein the first judgment time period comprises m preset time periods, and m is an integer greater than 1; when the difference is larger than a first preset threshold, determining that the electric equipment to be identified is a non-suspected malignant load; or when the difference is not greater than the first preset threshold, judging whether the electric equipment to be identified is suspected to be a malignant load again in a second judgment time period, wherein the second judgment time period comprises m preset time periods, and m is an integer greater than 1.
As above, the pre-determining module 130 is specifically configured to obtain n1 differences between the instantaneous power of the period to be identified in the second determination time period and the instantaneous powers of the previous n periods, respectively; if no k1 continuous difference values of the n1 difference values are larger than a second preset threshold, the electric equipment to be identified is a non-suspected malignant load; if k1 continuous difference values of the n1 difference values are all larger than a second preset threshold, the electric equipment to be identified needs to enter a third judgment time period;
in a third judgment time period, n1 difference values between the instantaneous power of the cycle to be identified in the third judgment time period and the instantaneous power of the previous n1 cycles are obtained again, and if k2 difference values in the n1 difference values are smaller than a third preset threshold, the electric equipment to be identified is determined to be a suspected malignant load; or if k3 difference values of the n1 difference values are larger than a third preset threshold, acquiring a first absolute value of a power difference between the instantaneous power of the cycle to be identified in the third judgment time period and the instantaneous power of the first cycle in the third judgment time period, and a second absolute value of a power difference between the instantaneous power of the cycle to be identified in the second judgment time period and the instantaneous power of the first cycle in the second judgment time period; judging whether the first absolute value and the second absolute value meet a preset condition, if so, determining that the electric equipment to be identified is suspected malignant load, and if not, determining that the electric equipment to be identified is not suspected malignant load; wherein n is an integer larger than 0, n1 is larger than n, k1 is larger than 0 and is larger than n1, k2 is larger than 0 and is smaller than n1, k3 is larger than 0 and is smaller than k2, and k1, k2 and k3 are integers.
As described above, the first obtaining module 110 is specifically configured to adopt a formula after the to-be-identified electric device is connected to the electric energy meter
Calculating the interruption times H of the electric energy meter in each period; wherein, P is power accuracy, C is the pulse constant of the electric energy meter, t is the preset time period, and 1kWh is 1 degree electricity.
As above, the validation module 140 is specifically configured to calculate the euclidean distance between the sampled data samples and the malignant load data samples; determining the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample according to the Euclidean distance and the preset Euclidean distance; and confirming whether the suspected malignant load is the malignant load or not according to the type and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample.
Optionally, the apparatus further comprises: the device comprises a calculation module, a detection module and a recognition module, wherein the calculation module is used for acquiring a plurality of training sample sets of the electric equipment to be recognized, and each training sample set comprises a plurality of instantaneous power data samples and/or a plurality of voltage data samples, current data samples and voltage-current phase difference data samples; calculating the sum of the minimum values of the distances between the data samples in any two training sample sets according to the training sample sets; according to the sum of the distance minimum values between the data samples in any two training sample sets, acquiring two training sample sets corresponding to the minimum distance minimum value sum as a first training sample set, and acquiring two training sample sets corresponding to the maximum distance minimum value sum as a second training sample set; taking the training sample set belonging to the first training sample set but not to the second training sample set as the already learned malignant load data sample.
The apparatus may be configured to execute the method provided by the method embodiment, and the specific implementation manner and the technical effect are similar and will not be described herein again.
These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 6 is a schematic structural diagram of an identification apparatus for identifying a malignant load according to another embodiment of the present invention, as shown in fig. 6, the apparatus includes: a processor 601 and a memory 602, wherein: the memory 602 is used for storing programs, and the processor 601 calls the programs stored in the memory 602 to execute the above-mentioned method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
Optionally, the invention also provides a program product, for example a computer-readable storage medium, comprising a program which, when being executed by a processor, is adapted to carry out the above-mentioned method embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Claims (8)
1. A method for identifying a malignant load, comprising:
after the identification device acquires that the electric equipment to be identified is accessed to the electric energy meter, acquiring the interruption times of the electric energy meter in each period by taking a preset time period as a period, wherein the preset time period is (200ms, 280 ms);
the identification device acquires sampling data samples of the electric equipment to be identified according to the interruption times in each period, wherein the sampling data samples comprise instantaneous power data samples and/or voltage data samples, current data samples and voltage-current phase difference data samples;
the identification device calculates the variation trend of instantaneous power according to the sampling data samples, and determines whether the electric equipment to be identified is a suspected malignant load;
if so, the identification device compares the learned malignant load data sample with the sampling data sample according to a preset algorithm to determine whether the suspected malignant load is a malignant load;
the method further comprises the following steps:
acquiring a plurality of training sample sets of the electric equipment to be identified, wherein each training sample set comprises a plurality of instantaneous power data samples and/or a plurality of voltage data samples, current data samples and voltage-current phase difference data samples;
calculating the sum of the minimum values of the distances between the data samples in any two training sample sets according to the training sample sets;
according to the sum of the distance minimum values between the data samples in any two training sample sets, acquiring two training sample sets corresponding to the minimum distance minimum value sum as a first training sample set, and acquiring two training sample sets corresponding to the maximum distance minimum value sum as a second training sample set;
taking the training sample set belonging to the first training sample set but not to the second training sample set as the already learned malignant load data sample.
2. The method for identifying a malignant load according to claim 1, wherein the identifying device calculates a trend of change of instantaneous power according to the sampled data samples, and determines whether the electrical device to be identified is a suspected malignant load, comprising:
the identification device calculates and obtains the instantaneous power of the electric equipment to be identified according to the sampling data samples;
the identification device acquires a difference value between the instantaneous power of the previous period and the instantaneous power of the period to be identified in a first judgment time period, wherein the first judgment time period comprises m preset time periods, and m is an integer greater than 1;
when the difference is larger than a first preset threshold, the identification device determines that the electric equipment to be identified is not suspected to be a malignant load; or, when the difference is not greater than the first preset threshold, the identification device determines again whether the electrical equipment to be identified is a suspected malignant load in a second determination time period, where the second determination time period includes m preset time periods, and m is an integer greater than 1.
3. The method according to claim 2, wherein the determining, by the identifying device, whether the electrical device to be identified is a suspected malignant load again in a second determination period includes:
the identification device acquires n1 difference values between the instantaneous power of the period to be identified and the instantaneous power of the previous n periods in the second judgment time period;
if no k1 continuous difference values of the n1 difference values are larger than a second preset threshold, the electric equipment to be identified is a non-suspected malignant load; if k1 continuous difference values of the n1 difference values are all larger than a second preset threshold, the electric equipment to be identified needs to enter a third judgment time period;
in the third judgment time period, the identification device obtains n1 difference values between the instantaneous power of the cycle to be identified in the third judgment time period and the instantaneous power of the previous n cycles, respectively, and if k2 difference values in the n1 difference values are smaller than a third preset threshold, the identification device determines that the electric equipment to be identified is a suspected malignant load;
or, if k3 difference values of the n1 difference values are greater than the third preset threshold, the identification device obtains a first absolute value of a power difference between the instantaneous power of the cycle to be identified in the third judgment time period and the instantaneous power of the first cycle in the third judgment time period, and a second absolute value of a power difference between the instantaneous power of the cycle to be identified in the second judgment time period and the instantaneous power of the first cycle in the second judgment time period;
the identification device judges whether the first absolute value and the second absolute value meet preset conditions or not, if yes, the electric equipment to be identified is determined to be suspected malignant load, and if not, the electric equipment to be identified is determined to be not suspected malignant load;
n is an integer larger than 0, n1 is larger than n, k1 is larger than 0 and is larger than n1, k2 is larger than 0 and is larger than n1, k3 is larger than 0 and is larger than k2, and k1, k2 and k3 are integers.
4. The method for identifying the malignant load according to claim 1, wherein the step of collecting the number of times of interruption of the electric energy meter in each period by taking a preset time period as a period after the identification device acquires that the electric equipment to be identified is connected to the electric energy meter comprises:
the identification device adopts a formula after the electric energy meter is connected to the electric equipment to be identified
Calculating the interruption times H of the electric energy meter in each period;
wherein p is power accuracy, C is a pulse constant of the electric energy meter, t is the preset time period, and 1kWh is 1 degree electricity.
5. The method according to claim 1, wherein the identifying device compares the learned data sample of the malignant load with the sampled data sample according to a preset algorithm to determine whether the suspected malignant load is a malignant load, and comprises:
calculating Euclidean distances between the sampling data samples and the malignant load data samples;
determining the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample according to the Euclidean distance and a preset Euclidean distance;
and determining whether the suspected malignant load is a malignant load according to the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample.
6. An apparatus for identifying a malignant load, comprising:
the first acquisition module is used for acquiring the interruption times of the electric energy meter in each period by taking a preset time period as a period after the electric equipment to be identified is accessed to the electric energy meter, wherein the preset time period is (200ms, 280 ms);
the second acquisition module is used for acquiring sampling data samples of the electric equipment to be identified according to the interruption times in each period, wherein the sampling data samples comprise instantaneous power data samples and/or voltage data samples, current data samples and voltage-current phase difference data samples;
the prejudging module is used for calculating the change trend of the instantaneous power according to the sampling data samples and determining whether the electric equipment to be identified is a suspected malignant load;
the confirmation module is used for comparing the learned malignant load data sample with the sampling data sample according to a preset algorithm if the suspected malignant load is the malignant load;
the identification device further comprises: the calculation module is used for acquiring a plurality of training sample sets of the electric equipment to be identified, wherein each training sample set comprises a plurality of instantaneous power data samples and/or a plurality of voltage data samples, current data samples and voltage-current phase difference data samples;
calculating the sum of the minimum values of the distances between the data samples in any two training sample sets according to the training sample sets;
according to the sum of the distance minimum values between the data samples in any two training sample sets, acquiring two training sample sets corresponding to the minimum distance minimum value sum as a first training sample set, and acquiring two training sample sets corresponding to the maximum distance minimum value sum as a second training sample set;
taking the training sample set belonging to the first training sample set but not to the second training sample set as the already learned malignant load data sample.
7. The device for identifying a malignant load according to claim 6, wherein the prejudging module is specifically configured to calculate and obtain an instantaneous power variation trend of the electrical equipment to be identified according to the sample data;
acquiring a difference value between the instantaneous power of the previous period and the instantaneous power of the period to be identified in a first judgment time period, wherein the first judgment time period comprises m preset time periods, and m is an integer greater than 1; when the difference is larger than a first preset threshold, determining that the electric equipment to be identified is a non-suspected malignant load; or, when the difference is not greater than the first preset threshold, judging again whether the electrical equipment to be identified is a suspected malignant load in a second judgment time period, where the second judgment time period includes m preset time periods, and m is an integer greater than 1.
8. The device for identifying malignant loads according to claim 6, wherein the validation module is specifically configured to calculate Euclidean distances between the sampled data samples and the malignant load data samples;
determining the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample according to the Euclidean distance and a preset Euclidean distance;
and determining whether the suspected malignant load is a malignant load according to the category and the corresponding frequency of the suspected malignant load corresponding to the sampling data sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911329342.7A CN110967585B (en) | 2019-12-20 | 2019-12-20 | Malignant load identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911329342.7A CN110967585B (en) | 2019-12-20 | 2019-12-20 | Malignant load identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110967585A CN110967585A (en) | 2020-04-07 |
| CN110967585B true CN110967585B (en) | 2022-03-15 |
Family
ID=70035668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911329342.7A Active CN110967585B (en) | 2019-12-20 | 2019-12-20 | Malignant load identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110967585B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112816816A (en) * | 2020-12-31 | 2021-05-18 | 无锡小净共享网络科技有限公司 | Malignant load identification method, device, equipment and storage medium |
| CN115795323B (en) * | 2023-02-03 | 2023-05-05 | 深圳市北电仪表有限公司 | Malignant load identification method, equipment and storage medium |
| CN115825634B (en) * | 2023-02-16 | 2023-05-26 | 上海红檀智能科技有限公司 | Malignant load identification method based on load complex impedance characteristics |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201210176Y (en) * | 2008-06-12 | 2009-03-18 | 武汉盛帆电子股份有限公司 | Intelligent load identification module |
| CN201383670Y (en) * | 2009-04-23 | 2010-01-13 | 张显中 | Digital-type intelligent malignant load recognizer |
| CN105675946A (en) * | 2016-03-18 | 2016-06-15 | 江苏联宏自动化系统工程有限公司 | Double-controlled intelligent single-phase electric energy meter with malignant load identification function |
| CN205335811U (en) * | 2016-02-05 | 2016-06-22 | 上海用悦信息技术服务中心 | Pernicious load recognition device |
| CN106841773A (en) * | 2016-12-26 | 2017-06-13 | 深圳市科陆电子科技股份有限公司 | Recognize the method and system of bad load |
| CN107422218A (en) * | 2017-09-26 | 2017-12-01 | 深圳市北电仪表有限公司 | Bad load recognizer and recognition methods |
| CN108573288A (en) * | 2018-05-29 | 2018-09-25 | 福建新开普信息科技有限公司 | A kind of resistive load identification and learning method based on electric energy meter |
-
2019
- 2019-12-20 CN CN201911329342.7A patent/CN110967585B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201210176Y (en) * | 2008-06-12 | 2009-03-18 | 武汉盛帆电子股份有限公司 | Intelligent load identification module |
| CN201383670Y (en) * | 2009-04-23 | 2010-01-13 | 张显中 | Digital-type intelligent malignant load recognizer |
| CN205335811U (en) * | 2016-02-05 | 2016-06-22 | 上海用悦信息技术服务中心 | Pernicious load recognition device |
| CN105675946A (en) * | 2016-03-18 | 2016-06-15 | 江苏联宏自动化系统工程有限公司 | Double-controlled intelligent single-phase electric energy meter with malignant load identification function |
| CN106841773A (en) * | 2016-12-26 | 2017-06-13 | 深圳市科陆电子科技股份有限公司 | Recognize the method and system of bad load |
| CN107422218A (en) * | 2017-09-26 | 2017-12-01 | 深圳市北电仪表有限公司 | Bad load recognizer and recognition methods |
| CN108573288A (en) * | 2018-05-29 | 2018-09-25 | 福建新开普信息科技有限公司 | A kind of resistive load identification and learning method based on electric energy meter |
Non-Patent Citations (2)
| Title |
|---|
| 基于谐波分离的学生公寓负载特性识别;郑宇 等;《电气应用》;20071231;第26卷(第8期);第113-116页 * |
| 电器恶性负载识别方法研究与仿真;张淼特 等;《计算机仿真》;20130228;第30卷(第2期);第213-216页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110967585A (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110967585B (en) | Malignant load identification method and device | |
| CN109977535B (en) | Line loss abnormality diagnosis method, device, equipment and readable storage medium | |
| CN110381126B (en) | Electric equipment identification method, system, equipment and medium based on edge calculation | |
| US9563530B2 (en) | Device state estimation apparatus, device power consumption estimation apparatus, and program | |
| KR20160097029A (en) | Method and apparatus for estimating state of battery | |
| CN111766462B (en) | Non-invasive load identification method based on V-I track | |
| JP2013109742A (en) | Method and system for detecting electrical appliances based on user feedback information | |
| CN111626360B (en) | Method, apparatus, device and storage medium for detecting boiler fault type | |
| CN112684401A (en) | Method and system for processing running error data of electric energy meter in light load area | |
| CN115664038B (en) | Intelligent power distribution operation and maintenance monitoring system for electrical safety management | |
| CN117312997B (en) | Intelligent diagnosis method and system for power management system | |
| CN113533910A (en) | Method and system suitable for converter transformer partial discharge early warning | |
| CN112701675A (en) | Distribution station user phase identification method and system based on screening voltage data | |
| CN112582978B (en) | Leakage protection method and device and charging pile | |
| CN109587145B (en) | False data intrusion detection method, device and equipment in power network | |
| CN108896805B (en) | Chopped wave signal verification method and system and electric energy detection device | |
| CN115343579B (en) | Power grid fault analysis method and device and electronic equipment | |
| CN116165596A (en) | Special transformer user metering abnormity monitoring method | |
| CN115456097A (en) | Power utilization detection method and detection terminal suitable for high-power-supply low-count special transformer users | |
| CN115144765A (en) | Method and device for detecting short-circuit fault in battery | |
| CN115248906A (en) | State error identification method and system for double current transformers on outgoing line of generator | |
| CN112129989B (en) | Voltage sag segmentation depicting method based on adaptive clustering | |
| CN115133659A (en) | On-line monitoring method and system for low-voltage line loss of low-voltage distribution network | |
| CN110187167B (en) | Method and device for detecting load switch event based on manifold classification | |
| CN110277834B (en) | Power grid response building internal load monitoring method and system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |