CN103487682A - Early warning method for sensitive customer electric energy experience quality under voltage sag disturbance - Google Patents
Early warning method for sensitive customer electric energy experience quality under voltage sag disturbance Download PDFInfo
- Publication number
- CN103487682A CN103487682A CN201310419436.XA CN201310419436A CN103487682A CN 103487682 A CN103487682 A CN 103487682A CN 201310419436 A CN201310419436 A CN 201310419436A CN 103487682 A CN103487682 A CN 103487682A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- sensitive
- voltage sag
- disturbance
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000006870 function Effects 0.000 claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 230000009466 transformation Effects 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 abstract description 11
- 230000008569 process Effects 0.000 description 9
- 238000012360 testing method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- HQOWCDPFDSRYRO-CDKVKFQUSA-N CCCCCCc1ccc(cc1)C1(c2cc3-c4sc5cc(\C=C6/C(=O)c7ccccc7C6=C(C#N)C#N)sc5c4C(c3cc2-c2sc3cc(C=C4C(=O)c5ccccc5C4=C(C#N)C#N)sc3c12)(c1ccc(CCCCCC)cc1)c1ccc(CCCCCC)cc1)c1ccc(CCCCCC)cc1 Chemical compound CCCCCCc1ccc(cc1)C1(c2cc3-c4sc5cc(\C=C6/C(=O)c7ccccc7C6=C(C#N)C#N)sc5c4C(c3cc2-c2sc3cc(C=C4C(=O)c5ccccc5C4=C(C#N)C#N)sc3c12)(c1ccc(CCCCCC)cc1)c1ccc(CCCCCC)cc1)c1ccc(CCCCCC)cc1 HQOWCDPFDSRYRO-CDKVKFQUSA-N 0.000 description 2
- 108010076504 Protein Sorting Signals Proteins 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- KEAYESYHFKHZAL-UHFFFAOYSA-N Sodium Chemical compound [Na] KEAYESYHFKHZAL-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention provides a method for early warning of sensitive customer power experience quality under voltage sag disturbance, which comprises the following steps: automatically identifying voltage sag disturbance of sensitive customers based on an S transformation fast algorithm and an incremental SVM classifier; determining voltage tolerance curves of equipment corresponding to several types of sensitive customers under different load levels based on the voltage sag disturbance identification result; and converting historical monitoring data of voltage sag disturbance into sample values of an amplitude severity index MSI and a duration severity index DSI of the voltage sag according to the sample values serving as samples, determining probability density functions of the MSI and the DSI based on a maximum entropy principle, evaluating the fault probability of the sensitive equipment, and obtaining the fault probability of the sensitive equipment corresponding to the sensitive customer under the voltage sag level. By implementing the method and the system, the power quality disturbance condition can be accurately monitored, whether the disturbance possibly affects the load of the client or not is determined according to the load sensitivity of the client, and the potential danger of load operation is discovered.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a method for early warning of sensitive customer electric energy experience quality under voltage sag disturbance.
Background
In recent years, with the development of modern industry and economy, sensitive loads such as computers and power electronic devices are widely applied in various industries, so that power customers are very sensitive to voltage sag, voltage surge, short-time interruption (interruption) and the like, and the failure of a single device or element may cause great economic loss. On the other hand, some arc furnaces, rectifiers, single-phase loads, high-power motors and other fluctuating or impulsive loads are incorporated into the grid, in particular the injection of a large number of harmonic and sub-harmonic components, resulting in severe distortion of the voltage and current waveforms in the grid. In addition, external factors such as lightning, external force damage, branch influence, power grid equipment failure and the like also interfere with the normal operation of the power system, so that the problem of power quality sometimes occurs. At present, more and more loads sensitive to voltage sag are applied to an electric power system, the voltage sag becomes a main reason causing that voltage sensitive equipment cannot work normally, and research shows that customer loss caused by the voltage sag accounts for more than 80% of power quality loss in various power quality problems.
In practical application, the electric load is generally divided into a common load and a sensitive load according to different characteristics of the electric load and requirements and sensitivities on the quality of electric energy. Some power system customers use a large number of sensitive loads, which are referred to as power quality sensitive customers. The objective existence of power quality problems and the sensitive nature of sensitive loads present a significant risk to the power usage of sensitive customers. Even slight power quality problems for such customers can result in significant economic losses.
The form of a Power Quality Disturbance (PQD) signal is complicated, and how to correctly extract the characteristic quantity of a disturbance signal and how to accurately identify the type of the disturbance signal become the primary problems in solving and improving the power quality. In addition, the quality of the experience of the electric energy of the customer is not only dependent on the quality of the power supply, but also closely related to the sensitivity of the customer.
Disclosure of Invention
The method is based on an S transformation fast algorithm and an incremental SVM classifier to realize automatic identification of the voltage sag disturbance, and a maximum entropy method is used for estimating the fault rate of the user sensitive load under the voltage sag disturbance.
Specifically, the early warning method for the experience quality of the sensitive customer electric energy under the voltage sag disturbance provided by the invention comprises the following steps:
automatically identifying voltage sag disturbance of sensitive customers based on an S transformation fast algorithm and an incremental SVM classifier;
determining voltage tolerance curves of equipment corresponding to several types of sensitive customers under different load levels based on the voltage sag disturbance identification result;
and converting historical monitoring data of voltage sag disturbance into sample values of an amplitude severity index MSI and a duration severity index DSI of the voltage sag according to the sample values serving as samples, determining probability density functions of the MSI and the DSI based on a maximum entropy principle, evaluating the fault probability of the sensitive equipment, and obtaining the fault probability of the sensitive equipment corresponding to the sensitive customer under the voltage sag level.
The method for automatically identifying the voltage sag disturbance of the sensitive client based on the S transformation fast algorithm and the incremental SVM classifier comprises the following steps:
determining a sensitive client as a monitoring point, monitoring the power quality disturbance of the sensitive client in real time, and acquiring a voltage signal and a current signal of sensitive equipment as the monitoring point;
for the voltage signal and the current signal of the monitoring point, extracting the characteristics based on an S transformation rapid algorithm, and extracting the standard deviation of the modulus coefficient of each frequency section, the maximum modulus coefficient and the modulus coefficient corresponding to the rated frequency as the characteristic vector of the disturbance signal;
and inputting the characteristic vectors into an incremental SVM classifier to classify the power quality disturbance, and automatically identifying the voltage sag disturbance.
Wherein, the S-transform fast algorithm is as follows:
Inputting the feature vectors into an incremental SVM classifier to classify power quality disturbance, and automatically identifying voltage sag disturbance, wherein the method comprises the following steps:
dividing the characteristic vectors into time windows, and using an incremental learning mechanism to learn the characteristic vectors arriving in one time window in batches;
within the last n time windows, if the number of times a feature vector sample does not become a support vector exceeds ξ, it is removed from the training set.
The sensitive equipment comprises a programmable logic control PLC, an adjustable speed driving device ASD, a computer PC and an AC contactor ACC.
Wherein the maximum entropy model is:
wherein x is a random variable of the voltage sag severity index MSI or DSI of the sensitive equipment, R is a value boundary of a variable x, H (x) is the entropy of the random variable, f (x) is a probability density function of the random variable x, E is the probability density function of the random variable x1And EhThe point distance of 1 st order and the center distance of h order of the severity index of voltage sag.
The method for determining the probability density functions of MSI and DSI based on the maximum entropy principle and evaluating the fault probability of the sensitive equipment to obtain the fault probability of the sensitive equipment corresponding to the sensitive customer under the voltage sag level includes the following steps:
introducing a Lagrange operator into the maximum entropy model, and obtaining a probability density function analytic expression by using a classical partial differential method;
when a voltage sag occurs in an uncertainty region (i, j), the failure rate P (i, j) of the device is:
wherein, <math>
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>λ</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>λ</mi>
<mn>1</mn>
</msub>
<mi>x</mi>
<mo>+</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>h</mi>
<mo>=</mo>
<mn>2</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>λ</mi>
<mi>h</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>-</mo>
<msub>
<mi>E</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mi>h</mi>
</msup>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mi>h</mi>
<mo>=</mo>
<mn>2,3,4,5</mn>
<mo>.</mo>
</mrow>
</math> 
and
the residual voltage amplitude is at the middle of region i and the duration is at the middle of region j, respectively.
By implementing the method and the system, the power quality disturbance condition can be accurately monitored, whether the disturbance possibly affects the load of the client or not is determined according to the load sensitivity of the client, and the potential danger of load operation is discovered. On the basis, the concept of customer electric energy experience is put forward, and the early warning is carried out on the customers with potential danger in load operation. The method is beneficial to reducing the power supply and utilization risks and technical transformation of power enterprises and sensitive customers, and has important significance for customizing the power in a differentiated mode.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a first embodiment of an early warning method for quality of experience of sensitive customer power under voltage sag disturbance according to the present invention;
fig. 2 is a schematic flowchart of a second embodiment of the early warning method for the experience quality of the power of the sensitive customer under the disturbance of the voltage sag according to the present invention;
fig. 3 is a schematic flowchart of a third embodiment of an early warning method for sensitive customer power experience quality under voltage sag disturbance according to the present invention;
fig. 4 is a schematic flowchart of a fourth embodiment of the early warning method for the experience quality of the power of the sensitive customer under the disturbance of the voltage sag according to the present invention;
fig. 5 is a schematic flowchart of a fifth embodiment of an early warning method for quality of experience of sensitive customer power under voltage sag disturbance according to the present invention;
fig. 6 is a schematic flowchart of a sixth embodiment of an early warning method for sensitive customer power experience quality under voltage sag disturbance according to the present invention;
fig. 7 is a flowchart illustrating a seventh embodiment of an early warning method for quality of experience of power of a sensitive client under voltage sag disturbance according to the present invention.
Detailed Description
The following detailed description of specific embodiments of the invention refers to the accompanying drawings.
As shown in fig. 1, a schematic flow chart of a first embodiment of the early warning method for sensitive customer power experience quality under voltage sag disturbance according to the present invention mainly includes the following steps:
As shown in fig. 2, a schematic flow chart of an embodiment of a second early warning method for sensitive customer power experience quality under voltage sag disturbance according to the present invention is shown, where the embodiment mainly describes a specific implementation process of time sequence feature extraction based on an S-transform fast algorithm, and the implementation process includes:
and 200, introducing an S transformation fast algorithm into the feature extraction of the power quality disturbance signal. The S transformation fast algorithm is shown as formula (1).
In the formula (1), ω (τ -t, σ) is a generalized window function for all frequencies v in the unit region.
The method can effectively avoid a large amount of redundant information in the S-transform time-frequency matrix, lay a foundation for accurately extracting the characteristic components of the signals and save the calculation time.
Step 201, processing historical monitoring data of power quality, specifically as follows:
the time sequence lasts for 8 rated periods of 0.16s in total, the number of sampling points is 1024, the sampling frequency is 6.4kHz, and the maximum detectable frequency is 3.2 kHz. The two-dimensional time-frequency relationship corresponding to the one-dimensional mode coefficient obtained by the S transformation fast algorithm can obtain 1024 time sequence points according to the formula (2) and can form 11 frequency segments. The position of a certain value in the one-dimensional S-domain determines the frequency and time represented by the value and the relation between the previous frequency band and the next frequency band at the same time, and the specific frequency band is divided as shown in formula (2).
Wherein, for a time domain signal sequence with the length of N, NindexOne recording point in one-dimensional mode coefficient is transformed for S and satisfies 2<nindex<n-1，nLNumber of layers of the current frequency band, n1And n2The start and end positions of the one-dimensional mode coefficients for the current frequency bin. The start and end positions of the one-dimensional mode coefficient corresponding to each frequency in each frequency segment are the same.
Step 202, establishing a feature vector including a time sequence point, and extracting a standard deviation of a mode coefficient of each frequency segment, a maximum mode coefficient and a mode coefficient corresponding to a rated frequency as a feature component of the disturbance signal.
Specifically, the time window of each time sequence is usually set to 8 nominal periods, the S transform modulus matrix retains the amplitude information of the signal, and the amplitudes of the elements in the S transform matrix correspond to the modulus of the S transform at a certain time and frequency. The column vector is the distribution of the amplitude of a signal at a certain sampling moment along with the change of frequency, and the row vector is the distribution of the amplitude of a signal at a certain frequency along with the change of time.
Step 203, marking the power quality disturbance category to which the signature belongs according to the eigenvector, and marking the power quality disturbance category as T = { (n)1(ti),y1),...,(nn(ti),ym)}. The time sequence feature vector is used as a training set for incremental learning in the SVM algorithm.
As shown in fig. 3, a schematic flow chart of a third embodiment of the early warning method for sensitive customer power experience quality under voltage sag disturbance according to the present invention is shown, where this embodiment mainly describes a specific implementation process of voltage sag automatic identification based on an incremental SVM algorithm, and includes:
and 300, setting a elimination strategy of training samples in the incremental SVM algorithm, and eliminating the samples with low contribution to classification through a threshold value xi. The basic idea is that within the last n time windows, if the number of times a sample does not become a support vector exceeds ξ, it is removed from the training samples in a centralized manner.
Wherein the SVM algorithm is actually performed by a Largrange function <math>
<mrow>
<mi>L</mi>
<mrow>
<mo>(</mo>
<mi>w</mi>
<mo>,</mo>
<mi>b</mi>
<mo>,</mo>
<mi>a</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<msup>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>w</mi>
<mo>|</mo>
<mo>|</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>a</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mo>(</mo>
<mi>w</mi>
<mo>·</mo>
<msub>
<mi>n</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>t</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>b</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
<mo>,</mo>
</mrow>
</math> A quadratic programming problem is transformed into a dual problem as shown in formula (3).
inputting: time slice ti-1Temporal classification hyperplane w0·x+b0=0 and support vector set SVi-1，
Time slice tiSample T = { (n) in (1)1(ti),y1),...,(nn(ti),ym) }, training set sample Ti-1
And (3) outputting: sorting hyperplane w after batch incremental learningnewx+bnew=0,SVnew
As shown in fig. 4, a flowchart of a fourth embodiment of the early warning method for sensitive customer electric energy experience quality under voltage sag disturbance according to the present invention is shown, where this embodiment mainly describes a specific implementation process for calculating a voltage sag tolerance of a customer sensitive device, and includes:
and step 400, determining voltage tolerance curves of several types of sensitive equipment under different load levels for the sensitive equipment of the client under the guidance of an ITIC curve and a SEMI curve and based on a voltage sag disturbance actual measurement method.
Specifically, according to the ITIC curve and the SEMI curve, voltage sag disturbance sensitive areas of various devices shown in table 1 can be obtained. The area A represents a normal area where general sensitive equipment cannot be influenced, the area B represents an uncertain area where a semiconductor manufacturing enterprise is influenced, the area C represents an uncertain area where a computer type device, a PLC, an alternating current relay and the semiconductor manufacturing enterprise are influenced, the area D represents an uncertain area where the semiconductor manufacturing enterprise, a motor driving device and a sodium metal lamp are influenced, and the area E is a fault area of all sensitive equipment. A 6 x 7 division of the sensitive area is thus obtained.
TABLE 1 Voltage sag disturbance sensitive region of various sensitive devices
For loads with unknown customer sensitivity characteristics, the sensitivity characteristics under different operating environments, working conditions and different power quality disturbances are different, and the voltage sag sensitivity characteristics of the loads cannot be obtained due to the influence of a plurality of uncertain factors of a power supply system and the loads, and need to be evaluated through a method of multiple tests.
Load sensitivity is determined by monitoring the voltage sag characteristic of the load supply point and comparing it to the device voltage tolerance level. As shown in fig. 5, the fifth embodiment includes the following specific steps:
and 500, preparing sensitive equipment capable of being tested, and simulating a load operation scene.
TABLE 2 Voltage sag Equipment sensitivity test scheme
As shown in fig. 6, a schematic flow chart of a sixth embodiment of the early warning method for sensitive customer electric energy experience quality under voltage sag disturbance according to the present invention is shown, where this embodiment mainly describes a specific implementation process of sensitive device fault rate evaluation based on a maximum entropy theory, and includes:
The probability density function of the voltage sag severity index (MSI or DSI) is determined based on the maximum entropy principle, and the method has the advantage that the probability density function of the random variable is solved directly according to sample data. When the random variables are distributed continuously, the maximum entropy model is as follows:
in the formula (5), x is a random variable of the voltage sag severity index MSI or DSI of the sensitive equipment, R is a value boundary (a boundary depending on the residual voltage amplitude and the sag duration of the uncertain region of the sensitive load) of the variable x, H (x) is the entropy of the random variable, and f (x) is the random variableProbability density function of quantity x, E1And EhThe 1 st order point distance and the h order center distance which are the voltage sag severity indexes, and the order of the moment is determined to be 5 so as to satisfy the requirement of the evaluation accuracy, that is, N = 5.
wherein, <math>
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>λ</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>λ</mi>
<mn>1</mn>
</msub>
<mi>x</mi>
<mo>+</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>h</mi>
<mo>=</mo>
<mn>2</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>λ</mi>
<mi>h</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>-</mo>
<msub>
<mi>E</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mi>h</mi>
</msup>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mi>h</mi>
<mo>=</mo>
<mn>2,3,4,5</mn>
<mo>.</mo>
</mrow>
</math> 
and
the residual voltage amplitude is at the middle of region i and the duration is at the middle of region j, respectively.
As shown in fig. 7, a flow diagram of a seventh embodiment of the early warning method for sensitive customer power experience quality under voltage sag disturbance according to the present invention is shown, where this embodiment mainly describes a specific implementation process of customer power experience quality analysis and early warning, and includes:
and 701, detecting the power consumption quality possibly threatening the customer by the current power quality disturbance according to the online real-time monitoring result of the power quality disturbance and the sensitivity level of the customer.
By implementing the method and the system, the power quality disturbance condition can be accurately monitored, whether the disturbance possibly affects the load of the client or not is determined according to the load sensitivity of the client, and the potential danger of load operation is discovered. On the basis, the concept of customer electric energy experience is put forward, and the early warning is carried out on the customers with potential danger in load operation. The method is beneficial to reducing the power supply and utilization risks and technical transformation of power enterprises and sensitive customers, and has important significance for customizing the power in a differentiated mode.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (7)
1. A method for early warning of sensitive customer power experience quality under voltage sag disturbance is characterized by comprising the following steps:
automatically identifying voltage sag disturbance of sensitive customers based on an S transformation fast algorithm and an incremental SVM classifier;
determining voltage tolerance curves of equipment corresponding to several types of sensitive customers under different load levels based on the voltage sag disturbance identification result;
and converting historical monitoring data of voltage sag disturbance into sample values of an amplitude severity index MSI and a duration severity index DSI of the voltage sag according to the sample values serving as samples, determining probability density functions of the MSI and the DSI based on a maximum entropy principle, evaluating the fault probability of the sensitive equipment, and obtaining the fault probability of the sensitive equipment corresponding to the sensitive customer under the voltage sag level.
2. The early warning method for the experience quality of the electric energy of the sensitive client under the voltage sag disturbance, according to the claim, is characterized in that the automatic identification of the voltage sag disturbance of the sensitive client is carried out based on an S transformation fast algorithm and an incremental SVM classifier, and comprises the following steps:
determining a sensitive client as a monitoring point, monitoring the power quality disturbance of the sensitive client in real time, and acquiring a voltage signal and a current signal of sensitive equipment as the monitoring point;
for the voltage signal and the current signal of the monitoring point, extracting the characteristics based on an S transformation rapid algorithm, and extracting the standard deviation of the modulus coefficient of each frequency section, the maximum modulus coefficient and the modulus coefficient corresponding to the rated frequency as the characteristic vector of the disturbance signal;
and inputting the characteristic vectors into an incremental SVM classifier to classify the power quality disturbance, and automatically identifying the voltage sag disturbance.
3. The method for early warning of sensitive customer power experience quality under voltage sag disturbance according to claim 2, wherein the fast algorithm of S-transform is as follows:
4. The method for early warning of sensitive customer power experience quality under voltage sag disturbance according to claim 3, wherein the step of inputting the feature vectors into an incremental SVM classifier for power quality disturbance classification and automatically identifying the voltage sag disturbance comprises the following steps:
dividing the characteristic vectors into time windows, and using an incremental learning mechanism to learn the characteristic vectors arriving in one time window in batches;
within the last n time windows, if the number of times a feature vector sample does not become a support vector exceeds ξ, it is removed from the training set.
5. The method for providing an early warning of the quality of experience of sensitive customer electrical energy under voltage sag disturbance according to claim 4, wherein the sensitive devices comprise a Programmable Logic Controller (PLC), a speed-adjustable driving device (ASD), a computer (PC) and an Alternating Current Contactor (ACC).
6. The method for early warning of sensitive customer power quality of experience under voltage sag disturbance according to claim 5, wherein the maximum entropy model is:
wherein x is a random variable of the voltage sag severity index MSI or DSI of the sensitive equipment, R is a value boundary of a variable x, H (x) is the entropy of the random variable, f (x) is a probability density function of the random variable x, E is the probability density function of the random variable x1And EhThe point distance of 1 st order and the center distance of h order of the severity index of voltage sag.
7. The method for early warning of power experience quality of sensitive customers under voltage sag disturbance according to claim 6, wherein the determining probability density functions of MSI and DSI based on the maximum entropy principle, evaluating the fault probability of sensitive equipment, and obtaining the fault probability of the sensitive equipment corresponding to the sensitive customers under the voltage sag level comprises:
introducing a Lagrange operator into the maximum entropy model, and obtaining a probability density function analytic expression by using a classical partial differential method;
when a voltage sag occurs in an uncertainty region (i, j), the failure rate P (i, j) of the device is:
wherein, <math>
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>λ</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>λ</mi>
<mn>1</mn>
</msub>
<mi>x</mi>
<mo>+</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>h</mi>
<mo>=</mo>
<mn>2</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>λ</mi>
<mi>h</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>-</mo>
<msub>
<mi>E</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mi>h</mi>
</msup>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mi>h</mi>
<mo>=</mo>
<mn>2,3,4,5</mn>
<mo>.</mo>
</mrow>
</math> 
and
the residual voltage amplitude is at the middle of region i and the duration is at the middle of region j, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310419436.XA CN103487682A (en) | 2013-09-13 | 2013-09-13 | Early warning method for sensitive customer electric energy experience quality under voltage sag disturbance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310419436.XA CN103487682A (en) | 2013-09-13 | 2013-09-13 | Early warning method for sensitive customer electric energy experience quality under voltage sag disturbance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103487682A true CN103487682A (en) | 2014-01-01 |
Family
ID=49828057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310419436.XA Pending CN103487682A (en) | 2013-09-13 | 2013-09-13 | Early warning method for sensitive customer electric energy experience quality under voltage sag disturbance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103487682A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103777096A (en) * | 2014-01-17 | 2014-05-07 | 华北电力大学 | Sensitive device immunity estimation method based on multiple sag threshold values and duration time |
| CN103995178A (en) * | 2014-05-20 | 2014-08-20 | 江苏大学 | Voltage sag detection method for S-transformation on basis of time-frequency gathering characteristic criteria |
| CN104267310A (en) * | 2014-09-09 | 2015-01-07 | 中国矿业大学 | Voltage dip source positioning method based on disturbance power direction |
| CN106774252A (en) * | 2016-12-14 | 2017-05-31 | 全球能源互联网研究院 | The electrical energy power quality disturbance tolerance level test system and method for programmable logic controller (PLC) |
| CN107171316A (en) * | 2017-05-24 | 2017-09-15 | 清华大学 | A kind of energy back formula voltage dip characteristic sensitive load analogy method |
| CN107515338A (en) * | 2017-08-14 | 2017-12-26 | 广州供电局有限公司 | Sensitive equipment voltage dip immunity test method and system |
| CN107832705A (en) * | 2017-11-08 | 2018-03-23 | 天津大学 | A kind of non-intrusion type load recognition methods based on canonical correlation analysis |
| CN108181527A (en) * | 2017-12-30 | 2018-06-19 | 国网天津市电力公司电力科学研究院 | A kind of appraisal procedure of the voltage dip synthesis severity based on energy indexes |
| CN109283416A (en) * | 2018-11-20 | 2019-01-29 | 广东电网有限责任公司 | A kind of calculation method and device of sensitive equipment failure rate |
| CN109508442A (en) * | 2018-11-13 | 2019-03-22 | 四川大学 | A method of sensitive features temporarily drop in identification study subject and key judges parameter |
| CN109541498A (en) * | 2018-11-30 | 2019-03-29 | 苏州数言信息技术有限公司 | A kind of general lamp failure intelligent detecting method and system |
| CN109799407A (en) * | 2019-03-01 | 2019-05-24 | 深圳供电局有限公司 | Method for obtaining voltage sag immunity of tested equipment and test system |
| CN110133444A (en) * | 2019-06-05 | 2019-08-16 | 国网江苏省电力有限公司检修分公司 | A kind of Fault Locating Method based on positive sequence voltage variable quantity, apparatus and system |
| CN110658409A (en) * | 2019-10-15 | 2020-01-07 | 深圳供电局有限公司 | Sensitive equipment voltage sag fault level evaluation method, computer equipment and storage medium |
| EP3591787A1 (en) * | 2018-07-06 | 2020-01-08 | Schneider Electric USA, Inc. | Systems and methods for managing power quality events in an electrical system |
| EP3591789A1 (en) * | 2018-07-06 | 2020-01-08 | Schneider Electric USA, Inc. | Systems and methods for characterizing power quality events in an electrical system |
| EP3591786A1 (en) * | 2018-07-06 | 2020-01-08 | Schneider Electric USA, Inc. | Dynamic tolerance curves for power monitoring systems |
| WO2020010281A1 (en) | 2018-07-06 | 2020-01-09 | Schneider Electric USA, Inc. | Systems and methods for analyzing and optimizing dynamic tolerance curves |
| EP3591790A3 (en) * | 2018-07-06 | 2020-03-04 | Schneider Electric USA, Inc. | Supplemental techniques for characterizing power quality events in an electrical system |
| CN110907754A (en) * | 2019-12-02 | 2020-03-24 | 国网福建省电力有限公司莆田供电公司 | Fault line severity evaluation method based on PSD-BPA |
| CN111276981A (en) * | 2020-05-08 | 2020-06-12 | 广东电网有限责任公司佛山供电局 | Voltage sag comprehensive treatment method for power grid side |
| CN112686549A (en) * | 2020-12-31 | 2021-04-20 | 华南理工大学 | Node voltage sag severity evaluation method, device, equipment and storage medium |
| CN114297255A (en) * | 2021-12-17 | 2022-04-08 | 中电信数智科技有限公司 | Network quality work order fault early warning method based on log analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102901895A (en) * | 2012-09-29 | 2013-01-30 | 上海市电力公司 | Method for evaluating voltage dip sensitivity of sensitive equipment |
| CN102982347A (en) * | 2012-12-12 | 2013-03-20 | 江西省电力科学研究院 | Method for electric energy quality disturbance classification based on KL distance |
-
2013
- 2013-09-13 CN CN201310419436.XA patent/CN103487682A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102901895A (en) * | 2012-09-29 | 2013-01-30 | 上海市电力公司 | Method for evaluating voltage dip sensitivity of sensitive equipment |
| CN102982347A (en) * | 2012-12-12 | 2013-03-20 | 江西省电力科学研究院 | Method for electric energy quality disturbance classification based on KL distance |
Non-Patent Citations (9)
| Title |
|---|
| XIANYONG XIAO等: "Stochastic Estimation Trip Frequency of Sensitive Equipment Due to Voltage Sag", 《IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS,2008》 * |
| 占勇等: "基于S变换的电能质量扰动支持向量机分类识别", 《中国电机工程学报》 * |
| 廖东平等: "一种支持向量机增量学习淘汰算法", 《国防科技大学学报》 * |
| 张忠平等: "TRA：改进的SVM增量学习淘汰算法", 《计算机工程与设计》 * |
| 朱成骐等: "基于最大信息熵原理的短期负荷预测综合模型", 《中国电机工程学报》 * |
| 满蔚仕等: "利用快速S变换的电能质量扰动识别方法", 《西安交通大学学报》 * |
| 申晓勇等: "一种SVM增量学习淘汰算法", 《计算机工程与应用》 * |
| 肖先勇等: "敏感设备电压暂降故障水平的多不确定性评估", 《中国电机工程学报》 * |
| 肖先勇等: "用电压暂降严重程度和最大熵评估负荷电压暂降敏感度", 《中国电机工程学报》 * |
Cited By (55)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103777096A (en) * | 2014-01-17 | 2014-05-07 | 华北电力大学 | Sensitive device immunity estimation method based on multiple sag threshold values and duration time |
| CN103777096B (en) * | 2014-01-17 | 2016-06-29 | 华北电力大学 | Based on how to drop threshold value and persistent period sensitive equipment immunocompetence appraisal procedure temporarily |
| CN103995178A (en) * | 2014-05-20 | 2014-08-20 | 江苏大学 | Voltage sag detection method for S-transformation on basis of time-frequency gathering characteristic criteria |
| CN104267310A (en) * | 2014-09-09 | 2015-01-07 | 中国矿业大学 | Voltage dip source positioning method based on disturbance power direction |
| CN104267310B (en) * | 2014-09-09 | 2017-03-08 | 中国矿业大学 | A kind of voltage sag source localization method based on power of disturbance direction |
| CN106774252A (en) * | 2016-12-14 | 2017-05-31 | 全球能源互联网研究院 | The electrical energy power quality disturbance tolerance level test system and method for programmable logic controller (PLC) |
| CN107171316A (en) * | 2017-05-24 | 2017-09-15 | 清华大学 | A kind of energy back formula voltage dip characteristic sensitive load analogy method |
| CN107515338A (en) * | 2017-08-14 | 2017-12-26 | 广州供电局有限公司 | Sensitive equipment voltage dip immunity test method and system |
| CN107515338B (en) * | 2017-08-14 | 2020-02-18 | 广州供电局有限公司 | Method and system for testing voltage sag immunity of sensitive equipment |
| CN107832705A (en) * | 2017-11-08 | 2018-03-23 | 天津大学 | A kind of non-intrusion type load recognition methods based on canonical correlation analysis |
| CN108181527A (en) * | 2017-12-30 | 2018-06-19 | 国网天津市电力公司电力科学研究院 | A kind of appraisal procedure of the voltage dip synthesis severity based on energy indexes |
| EP3855593A1 (en) * | 2018-07-06 | 2021-07-28 | Schneider Electric USA, Inc. | Systems and methods for analyzing power quality events in an electrical system |
| CN112654874A (en) * | 2018-07-06 | 2021-04-13 | 施耐德电气美国股份有限公司 | System and method for analyzing and optimizing dynamic tolerance curves |
| EP3818383A4 (en) * | 2018-07-06 | 2022-03-23 | Schneider Electric USA, Inc. | Systems and methods for analyzing and optimizing dynamic tolerance curves |
| EP4365607A3 (en) * | 2018-07-06 | 2024-06-12 | Schneider Electric USA, Inc. | Systems and methods for analyzing effects of electrical perturbations on equipment in an electrical system |
| AU2022200275B2 (en) * | 2018-07-06 | 2024-02-29 | Schneider Electric USA, Inc. | Systems and methods for analyzing power quality events in an electrical system |
| EP3591787A1 (en) * | 2018-07-06 | 2020-01-08 | Schneider Electric USA, Inc. | Systems and methods for managing power quality events in an electrical system |
| EP3591789A1 (en) * | 2018-07-06 | 2020-01-08 | Schneider Electric USA, Inc. | Systems and methods for characterizing power quality events in an electrical system |
| EP3591786A1 (en) * | 2018-07-06 | 2020-01-08 | Schneider Electric USA, Inc. | Dynamic tolerance curves for power monitoring systems |
| WO2020010281A1 (en) | 2018-07-06 | 2020-01-09 | Schneider Electric USA, Inc. | Systems and methods for analyzing and optimizing dynamic tolerance curves |
| CN110690698A (en) * | 2018-07-06 | 2020-01-14 | 施耐德电气美国股份有限公司 | Dynamic tolerance curve of power monitoring system |
| CN110687367A (en) * | 2018-07-06 | 2020-01-14 | 施耐德电气美国股份有限公司 | System and method for characterizing power quality events in an electrical system |
| EP3818386A4 (en) * | 2018-07-06 | 2022-03-23 | Schneider Electric USA, Inc. | Systems and methods for analyzing effects of electrical perturbations on equipment in an electrical system |
| EP3591790A3 (en) * | 2018-07-06 | 2020-03-04 | Schneider Electric USA, Inc. | Supplemental techniques for characterizing power quality events in an electrical system |
| EP3618214A1 (en) * | 2018-07-06 | 2020-03-04 | Schneider Electric USA, Inc. | Systems and methods for analyzing power quality events in an electrical system |
| US11870242B2 (en) | 2018-07-06 | 2024-01-09 | Schneider Electric USA, Inc. | Supplemental techniques for characterizing power quality events in an electrical system |
| US11852660B2 (en) | 2018-07-06 | 2023-12-26 | Schneider Electric USA, Inc. | Systems and methods for analyzing effects of electrical perturbations on equipment in an electrical system |
| US11733273B2 (en) | 2018-07-06 | 2023-08-22 | Schneider Electric USA, Inc. | Systems and methods for analyzing power quality events in an electrical system |
| US11221353B2 (en) | 2018-07-06 | 2022-01-11 | Schneider Electric USA, Inc. | Systems and methods for analyzing power quality events in an electrical system |
| AU2021236534B2 (en) * | 2018-07-06 | 2022-12-08 | Schneider Electric USA, Inc. | Systems and methods for analyzing power quality events in an electrical system |
| AU2019204826B2 (en) * | 2018-07-06 | 2021-06-17 | Schneider Electric USA, Inc. | Systems and methods for managing power quality events in an electrical system |
| US11043810B2 (en) | 2018-07-06 | 2021-06-22 | Schneider Electric USA, Inc. | Systems and methods for managing power quality events in an electrical system |
| AU2019204821B2 (en) * | 2018-07-06 | 2021-07-08 | Schneider Electric USA, Inc. | Dynamic tolerance curves for power monitoring systems |
| CN110687367B (en) * | 2018-07-06 | 2022-07-19 | 施耐德电气美国股份有限公司 | System and method for characterizing power quality events in an electrical system |
| US11099221B2 (en) | 2018-07-06 | 2021-08-24 | Schneider Electric USA, Inc. | Dynamic tolerance curves for power monitoring systems |
| EP3869653A1 (en) * | 2018-07-06 | 2021-08-25 | Schneider Electric USA, Inc. | Systems and methods for managing power quality events in an electrical system |
| US11493540B2 (en) | 2018-07-06 | 2022-11-08 | Schneider Electric USA, Inc. | Systems and methods for analyzing and optimizing dynamic tolerance curves |
| US11211792B2 (en) | 2018-07-06 | 2021-12-28 | Schneider Electric USA, Inc. | Supplemental techniques for characterizing power quality events in an electrical system |
| AU2019204827B2 (en) * | 2018-07-06 | 2021-10-28 | Schneider Electric USA, Inc. | Systems and methods for analyzing power quality events in an electrical system |
| AU2019204823B2 (en) * | 2018-07-06 | 2021-10-28 | Schneider Electric USA, Inc. | Supplemental techniques for characterizing power quality events in an electrical system |
| US11209467B2 (en) | 2018-07-06 | 2021-12-28 | Schneider Electric USA, Inc. | Systems and methods for characterizing power quality events in an electrical system |
| CN109508442A (en) * | 2018-11-13 | 2019-03-22 | 四川大学 | A method of sensitive features temporarily drop in identification study subject and key judges parameter |
| CN109283416A (en) * | 2018-11-20 | 2019-01-29 | 广东电网有限责任公司 | A kind of calculation method and device of sensitive equipment failure rate |
| CN109541498B (en) * | 2018-11-30 | 2021-10-15 | 苏州数言信息技术有限公司 | Universal lamp fault intelligent detection method and system |
| CN109541498A (en) * | 2018-11-30 | 2019-03-29 | 苏州数言信息技术有限公司 | A kind of general lamp failure intelligent detecting method and system |
| CN109799407A (en) * | 2019-03-01 | 2019-05-24 | 深圳供电局有限公司 | Method for obtaining voltage sag immunity of tested equipment and test system |
| CN110133444A (en) * | 2019-06-05 | 2019-08-16 | 国网江苏省电力有限公司检修分公司 | A kind of Fault Locating Method based on positive sequence voltage variable quantity, apparatus and system |
| CN110658409A (en) * | 2019-10-15 | 2020-01-07 | 深圳供电局有限公司 | Sensitive equipment voltage sag fault level evaluation method, computer equipment and storage medium |
| CN110907754B (en) * | 2019-12-02 | 2021-10-01 | 国网福建省电力有限公司莆田供电公司 | Fault line severity evaluation method based on PSD-BPA |
| CN110907754A (en) * | 2019-12-02 | 2020-03-24 | 国网福建省电力有限公司莆田供电公司 | Fault line severity evaluation method based on PSD-BPA |
| CN111276981B (en) * | 2020-05-08 | 2020-09-25 | 广东电网有限责任公司佛山供电局 | Voltage sag comprehensive treatment method for power grid side |
| CN111276981A (en) * | 2020-05-08 | 2020-06-12 | 广东电网有限责任公司佛山供电局 | Voltage sag comprehensive treatment method for power grid side |
| CN112686549A (en) * | 2020-12-31 | 2021-04-20 | 华南理工大学 | Node voltage sag severity evaluation method, device, equipment and storage medium |
| CN114297255A (en) * | 2021-12-17 | 2022-04-08 | 中电信数智科技有限公司 | Network quality work order fault early warning method based on log analysis |
| CN114297255B (en) * | 2021-12-17 | 2024-04-19 | 中电信数智科技有限公司 | Network quality work order fault early warning method based on log analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103487682A (en) | Early warning method for sensitive customer electric energy experience quality under voltage sag disturbance | |
| Moradzadeh et al. | Locating inter-turn faults in transformer windings using isometric feature mapping of frequency response traces | |
| CN108593260B (en) | Optical cable line fault positioning and detecting method and terminal equipment | |
| US10324132B2 (en) | Systems and methods for power line event zone identification | |
| Bhui et al. | Application of recurrence quantification analysis to power system dynamic studies | |
| CN109029959B (en) | Method for detecting mechanical state of transformer winding | |
| CN109800660B (en) | Voltage sag source identification method and system based on big data clustering | |
| Liu et al. | Prognosis of underground cable via online data-driven method with field data | |
| Krátký et al. | A novel method for detection of covered conductor faults in medium voltage overhead line systems | |
| CN111398679B (en) | Sub-synchronous oscillation identification and alarm method based on PMU (phasor measurement Unit) | |
| CN113742993B (en) | Method, device, equipment and storage medium for predicting life loss of dry-type transformer | |
| CN104966161A (en) | Electric energy quality recording data calculating analysis method based on Gaussian mixture model | |
| CN102495949A (en) | Fault prediction method based on air data | |
| CN109766912A (en) | A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines | |
| CN103577695A (en) | Method and device for detecting suspect data in power quality data | |
| Ismail et al. | Remaining useful life estimation for thermally aged power insulated gate bipolar transistors based on a modified maximum likelihood estimator | |
| CN105699806A (en) | A multi-source harmonic wave responsibility division method | |
| US20220413032A1 (en) | Machine learning based method and device for disturbance classification in a power transmission line | |
| Chang et al. | A hybrid approach for detection and classification of power quality disturbances | |
| Liu et al. | Dynamic security assessment of western Danish power system based on ensemble decision trees | |
| CN115130550A (en) | Distribution transformer fault identification method based on gradient lifting decision tree | |
| CN115238733A (en) | Method for evaluating operation state of switching-on and switching-off coil of high-voltage circuit breaker and related equipment | |
| CN106096494B (en) | A kind of traveling wave fault based on information fusion framework and interference recorder data discrimination method | |
| Baraldi et al. | A procedure for practical prognostics and health monitoring of fully electric vehicles for enhanced safety and reliability | |
| Ali | Inter-area power oscillation identification using synchronized ambient and ringdown data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140101 |
|
| RJ01 | Rejection of invention patent application after publication |