CN116955895B - Transformer operation abnormity monitoring method and system - Google Patents
Transformer operation abnormity monitoring method and system Download PDFInfo
- Publication number
- CN116955895B CN116955895B CN202311218284.7A CN202311218284A CN116955895B CN 116955895 B CN116955895 B CN 116955895B CN 202311218284 A CN202311218284 A CN 202311218284A CN 116955895 B CN116955895 B CN 116955895B
- Authority
- CN
- China
- Prior art keywords
- data
- voltage
- temperature
- vibration frequency
- current
- 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
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012544 monitoring process Methods 0.000 title claims abstract description 46
- 230000002159 abnormal effect Effects 0.000 claims abstract description 103
- 230000008859 change Effects 0.000 claims abstract description 47
- 230000000737 periodic effect Effects 0.000 claims abstract description 35
- 230000005856 abnormality Effects 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 7
- 230000009467 reduction Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Protection Of Transformers (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for monitoring abnormal operation of a transformer, and data of each dimension of the transformer are collected; acquiring a periodic sequence of data of each dimension; constructing asynchronous change coefficients according to the period difference of the initial change in each dimension data; obtaining each dimension weighting factor according to the asynchronous change coefficient and each dimension data; obtaining abnormal data according to the normalized weighting factors of the data in each dimension and the local abnormal factors of the data, and analyzing according to the abnormal data to complete monitoring of the abnormal data of the transformer. Therefore, abnormal operation monitoring of the transformer is realized, the accuracy of abnormal analysis of multidimensional data of the transformer is increased, the accuracy of abnormal data acquisition of the transformer is improved, and the abnormal monitoring precision of the transformer is higher.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for monitoring abnormal operation of a transformer.
Background
With the continuous increase of the power demand, the scale of the power system is continuously enlarged, the voltage level is continuously increased, and the safety detection requirement on the power system is continuously increased. The power transformer is core electrical equipment of a power system, the running state of the transformer relates to the running stability of the power system, and in the working process of the transformer, more interference factors influence the stable running of the transformer, and abnormal running of the transformer frequently occurs. At present, a data processing mode is mainly adopted for monitoring the running state of the transformer, abnormal running data of the transformer are detected by carrying out abnormal analysis on monitoring data of all aspects of the working state of the transformer, the running abnormal state of the transformer is analyzed, the transformer is timely maintained and overhauled, and the power system paralysis caused by serious faults is avoided.
However, the traditional LOF (local anomaly factor) algorithm can only cluster data in the same dimension, and is inaccurate in characteristic analysis on multidimensional data, so that the detection result on the abnormal state of the transformer is poor, and the monitoring error on the abnormal operation of the transformer is high.
In summary, the invention provides a method and a system for monitoring abnormal operation of a transformer, which are used for collecting monitoring data of different aspects of the transformer, calculating weighting factors of the monitoring data of different dimensions by analyzing the relevance between the data of different dimensions of the transformer, acquiring the local anomaly factors of the data of different dimensions by combining an LOF (local anomaly factor) algorithm, carrying out weighting and dimension reduction on the local anomaly factors of the data collected at the same moment of different dimensions, and analyzing abnormal operation conditions of the transformer.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method and a system for monitoring abnormal operation of a transformer, wherein the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for monitoring abnormal operation of a transformer, including the steps of:
collecting voltage, current, temperature and vibration frequency data of a transformer;
obtaining a periodic sequence of voltage data according to peak distribution in the voltage data of the transformer; acquiring a periodic sequence of current data; obtaining an asynchronous change coefficient between voltage and current according to the periodic sequence of the voltage data and the current data; taking a period corresponding to the beginning of the change of the elements in the period sequence of the voltage data as a primary change period of the voltage data; obtaining a voltage weighting factor according to the initial change period of the voltage data, the voltage data in each voltage period and the asynchronous change coefficient between the voltage and the current; acquiring an initial change period of current data; acquiring a current weighting factor;
dividing the temperature data and the vibration frequency data to obtain temperature data sets and vibration frequency data sets; obtaining the margin of each temperature set according to the maximum temperature and the minimum temperature in each temperature data set; obtaining a temperature weighting factor according to the margin of each temperature set; acquiring information entropy of each vibration frequency data set, and acquiring a vibration frequency weighting factor according to the information entropy of each vibration frequency set;
and acquiring local abnormality factors of the data of the voltage, the current, the temperature and the vibration frequency by adopting a local abnormality factor algorithm, acquiring the abnormal data according to the weighting factors of the voltage, the current, the temperature and the vibration frequency and the local abnormality factors of the data of the voltage, the current, the temperature and the vibration frequency, and completing the abnormality monitoring of the transformer by combining the abnormal data.
Preferably, the periodic sequence of voltage data is obtained according to peak distribution in the voltage data of the transformer, and the method comprises the following specific steps:
the voltage data between two adjacent peaks in the voltage data of the transformer is taken as one voltage period, the time elapsed by the voltage period is taken as an element of the period sequence of the voltage data, and the time elapsed by each voltage period is taken as each element of the period sequence of the voltage data.
Preferably, the expression for obtaining the asynchronous change coefficient between the voltage and the current according to the periodic sequence of the voltage data and the current data is as follows:
in the method, in the process of the invention,for an asynchronous change coefficient between voltage and current, +.>For the number of elements in the periodic sequence of the voltage data, < >>For the number of elements in the periodic sequence of the current data, < >>To obtain maximum value function>Is the +.>Time interval of each cycle>Is the +.>Time interval of each cycle>Is the jaccard coefficient between the periodic sequence of voltage data and current data.
Preferably, the step of obtaining the voltage weighting factor according to the initial period of the voltage data, the voltage data in each voltage period and the asynchronous change coefficient between the voltage and the current includes the following specific steps:
sequencing the voltage data in each voltage period from large to small according to the value, and taking the sequence formed by the sequencing as a data sequence in each voltage period; the expression for obtaining the voltage weighting factor according to the data sequence in each voltage period, the initial change period of the voltage data and the asynchronous change coefficient is as follows:
in the method, in the process of the invention,is a voltage weighting factor, ">For the sequence number of the initial period in the periodic sequence of the voltage data,for the data sequence in the initial period, +.>Data sequence in the previous period of the initial period, +.>Function of obtaining similarity for dynamic time warping algorithm,/->Abnormal fluctuation coefficient of voltage data, +.>For an asynchronous change coefficient between voltage and current, +.>For the number of elements in the periodic sequence of the voltage data, < >>Is->Data sequence within a single voltage period,/->The periodic sequence of voltage data +.>Time of cycle>As a function of the difference between the maximum and minimum values.
Preferably, the step of obtaining each temperature data set and each vibration frequency data set by dividing the temperature data and the vibration frequency data includes the specific steps of:
dividing temperature data and vibration frequency data into two data sets respectively according to the acquisition time corresponding to last bit data in a voltage data initial change period, and respectively marking the two data sets as a first temperature set and a second temperature set, and a first vibration frequency set and a second vibration frequency set; and dividing the temperature data and the vibration frequency data into two data sets respectively according to the acquisition time corresponding to the last bit data in the initial change period of the current data, and respectively marking the data sets as a third temperature set and a fourth temperature set, and a third vibration frequency set and a fourth vibration frequency set.
Preferably, the specific step of obtaining the margin of each temperature set according to the maximum temperature and the minimum temperature in each temperature data set is as follows:
the margin for each temperature set is inversely proportional to the maximum temperature within each temperature set and directly proportional to the difference between the maximum temperature and the minimum temperature within the temperature set.
Preferably, the step of obtaining the temperature weighting factor according to the margin of each temperature set includes:
calculating a temperature weighted value influenced by current according to the margin of the first temperature set and the margin difference value of the second temperature set; calculating a temperature weighted value influenced by the voltage according to the margin of the third temperature set and the margin difference value of the fourth temperature set; the average value of the temperature weighted values influenced by the voltage and the temperature weighted values influenced by the current is used as a temperature weighted factor.
Preferably, the step of obtaining the vibration frequency weighting factor according to the information entropy of each vibration frequency set comprises the following specific steps:
calculating a vibration frequency weighting value influenced by current according to the information entropy of the first vibration frequency set and the information entropy difference value of the second vibration frequency set; calculating a vibration frequency weighting value influenced by voltage according to the information entropy of the third vibration frequency set and the information entropy difference value of the fourth vibration frequency set; and taking the average value of the vibration frequency weighted values influenced by the voltage and the vibration frequency weighted values influenced by the current as a vibration frequency weighted factor.
Preferably, the obtaining abnormal data according to the weighting factors of the voltage, the current, the temperature and the vibration frequency and the local abnormal factors of each data of the voltage, the current, the temperature and the vibration frequency includes the following specific steps:
multiplying the normalized voltage weighting factors by the local abnormality factors of the data of each voltage to obtain the local abnormality factors of the data of each voltage; acquiring each data weighted local abnormal factor of each current, temperature and vibration frequency; the expression for obtaining the running anomaly degree of the transformer at each moment according to each data weighted local anomaly factor of each voltage, current, temperature and vibration frequency is as follows:
in the method, in the process of the invention,is->Transformer operating anomalies at individual moments, < >>Number of data dimensions>Weighting local anomaly factors for the data of dimension j at the ith moment;
and taking the data acquired at the moment when the running anomaly degree of the transformer is greater than the anomaly threshold value as anomaly data.
In a second aspect, an embodiment of the present invention further provides a transformer abnormal operation monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the steps of any one of the methods described above when executing the computer program.
The embodiment of the invention has at least the following beneficial effects:
according to the invention, the abnormal data of the transformer data is detected by combining the information characteristics of the transformer data, so that abnormal operation monitoring of the transformer is realized. The problem of high monitoring error of abnormal operation of the transformer is solved by weighting and dimension reduction processing of local abnormal factors of each data, the problem of inaccurate characteristic analysis of the multi-dimensional monitoring data of the transformer by a traditional LOF abnormal data detection algorithm is avoided, the accuracy of the abnormal analysis of the multi-dimensional data is improved, and the accuracy of the abnormal data acquisition of the transformer is improved.
In order to solve the problem that the traditional LOF abnormal data detection algorithm is inaccurate in characteristic analysis of multi-dimensional monitoring data of the transformer, the invention provides a method and a system for monitoring abnormal operation of the transformer, monitoring data of different aspects of the transformer are collected, weighting factors of the monitoring data of different dimensions are calculated by analyzing the relevance among the data of different dimensions of the transformer, local abnormal factors of the data of different dimensions are obtained by combining an LOF (local abnormal factor) algorithm, the local abnormal factors of the data collected at the same moment of different dimensions are weighted and reduced, abnormal operation conditions of the transformer are analyzed, and the method has higher abnormal operation monitoring precision of the transformer.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart illustrating steps of a method for monitoring abnormal operation of a transformer according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of a method and a system for monitoring abnormal operation of a transformer according to the present invention by combining the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a method and a system for monitoring abnormal operation of a transformer, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for monitoring abnormal operation of a transformer according to an embodiment of the invention is shown, the method includes the following steps:
step S001, collecting voltage, current, temperature and vibration frequency data of the transformer.
The voltage meter, the ammeter, the temperature sensor and the vibration frequency sensor are adopted to collect data of output voltage, output current, temperature and vibration frequency in the operation process of the transformer respectively, the voltage, the current, the temperature and the vibration frequency of the transformer are collected simultaneously at the same moment, the length of each dimension collection data sequence is 600, and it is to be noted that a specific data sequence length implementer can set the data sequence by himself, and the embodiment is not limited specifically.
Step S002, calculating the weighting factors of the voltage, current, temperature and vibration frequency by analyzing the correlation of the fluctuation among the transformer voltage, current, temperature and vibration frequency data.
The voltage adopted by the transformer is alternating voltage, voltage data is similar to a sine function and changes periodically, when the transformer operates abnormally, the fluctuation amplitude of the output voltage and current of the transformer is abnormally increased or reduced, so that the change period of the voltage and current data is changed, and meanwhile, the temperature of the transformer also rises, and a coil in the transformer senses bad vibration in the process, so that the vibration frequency of the transformer is abnormally changed. In addition, when the transformer vibrates abnormally, the temperature of the transformer rises along with energy conversion. The monitored parameters of the various aspects are thus mutually affected in the event of an abnormal operation of the transformer.
When the operation of the transformer is stable, the current and the voltage are changed periodically, the voltage data between two adjacent peaks in the voltage data of the transformer is taken as a voltage period, and the first voltage periodThe time elapsed for the voltage period is taken as the +.>The elements include a sequence of time elapsed from each voltage cycle as a cycle sequence of voltage data, and the method of acquiring the cycle of voltage data may be set by the practitioner and is not particularly limited. Normally, the voltage and the current are fixed, that is, the voltage and the current are changed synchronously, and when the transformer operates abnormally, such as a short circuit, the voltage and the current may be changed asynchronously. Therefore, the expression for obtaining the asynchronous change coefficient between the voltage and the current according to the periodic sequence of the voltage data and the current data is as follows:
in the method, in the process of the invention,for an asynchronous change coefficient between voltage and current, +.>For the number of elements in the periodic sequence of the voltage data, < >>For the number of elements in the periodic sequence of the current data, < >>To obtain maximum value function>Is the period of the voltage dataStage sequence>Time of cycle>Is the +.>Time of cycle>Is the jaccard coefficient between the periodic sequence of voltage data and current data. Aligning data from left to right in the calculation process of the formula, and if the number of the data in the voltage period sequence and the current period sequence is different, supplementing the tail data in the shorter sequence with 0; when->When the voltage and the current are synchronous; when->At this time, it means that the occurrence of abnormal effects of voltage and current no longer changes synchronously, and +.>The smaller the value of (c) is, the more serious the current and voltage are not synchronized, the +.>The larger the current and the larger the difference in the periodic variation of the voltage, i.e. +.>The greater the value of (2); to sum up, alleviate the symptoms of->The greater the degree of asynchronous variation in voltage and current, the greater the effect of the transformer operating anomalies.
The method for determining the weighting factors of the abnormal voltage and current by comparing the asynchronous change degrees of the periodic changes of the collected voltage and current data to obtain the influence degree of the transformer abnormality on the whole data, and further analyzing the degree of the periodic abnormal change of the voltage and the degree of the periodic abnormal change of the current to determine the weighting factors of the abnormal voltage and current comprises the following steps:
taking a period of which the element value starts to change in a period sequence of the voltage data as a primary change period of the voltage data; taking a sequence formed by voltage data in each voltage period as a data sequence in each voltage period, wherein the ordering mode of the voltage data is arranged according to the data values from big to small;
considering that the influence of different voltage data on the abnormal fluctuation condition of the voltage data is different, the abnormal fluctuation coefficient of the voltage data is calculated first according to the embodiment, and the expression of the abnormal fluctuation coefficient of the voltage data is as follows:
in the method, in the process of the invention,abnormal fluctuation coefficient of voltage data, +.>For an asynchronous change coefficient between voltage and current, +.>For the number of elements in the periodic sequence of the voltage data, < >>For the sequence number of the initial period in the periodic sequence of the voltage data,is->Data sequence within a single voltage period,/->To obtain maximum and minimum valuesA function of the difference between the two,the periodic sequence of voltage data +.>A cycle time.
Further, in this embodiment, a voltage weighting factor of the voltage data is calculated according to an abnormal fluctuation coefficient of the voltage data and a data similarity degree of the voltage cycle data sequence, and an expression of the voltage weighting factor of the voltage data is specifically:
in the method, in the process of the invention,is a voltage weighting factor, ">For the sequence number of the initial period in the periodic sequence of the voltage data,for the data sequence in the initial period, +.>Data sequence in the previous period of the initial period, +.>Function of obtaining similarity for dynamic time warping algorithm,/->Abnormal fluctuation coefficient of the voltage data.
When the period of the voltage data is abnormally varied,the smaller the time of abnormality, the more the abnormality is likely to fluctuate due to accidental factors, the more the number of the collectedThe lower the reliability of the abnormal data in the data; />The larger the time of occurrence of the abnormality is, the more lag is, and the higher the reliability of abnormal data in the acquired data is; since the amplitude of the fluctuation is usually large when an abnormal fluctuation starts to occur, then +.>The value of (2) is larger; the more severe the abnormal fluctuation that persists after the occurrence of the abnormality, the explanation +.>The larger at the same time->The larger the value of (2), the calculated +.>The greater the value of (2); to sum up, the voltage weighting factor->The larger the value of the voltage value is, the more serious the voltage abnormality fluctuation is, and the higher the reference value of the abnormality of the voltage value for detecting the operation abnormality of the transformer is.
Because the current and voltage changes of the transformer and the temperature and vibration frequency are mutually influenced, the acquisition time corresponding to the last voltage data in the initial change period of the voltage data is taken as the first segmentation time; taking the acquisition time corresponding to the last current data in the initial change period of the current data as a second dividing time; the temperature and vibration frequency data are divided respectively through two division moments, specifically:
dividing temperature data into two data sets through a first dividing moment, and recording the two data sets as a first temperature set and a second temperature set; dividing temperature data into two data sets through a second dividing moment, and marking the data sets as a third temperature set and a fourth temperature set;
dividing vibration frequency data into two data sets through a first dividing moment, and recording the two data sets as a first vibration frequency set and a second vibration frequency set; dividing the vibration frequency data into two data sets through the second dividing moment, and recording the data as a third vibration frequency set and a fourth vibration frequency set; the first data set and the second data set in each data set of the two types of data are data sets influenced by voltage, specifically, the first data set is temperature and vibration frequency data when the voltage of the transformer is normal, and the second data set is temperature and vibration frequency data after the voltage of the transformer is abnormally changed; the third and fourth data sets are data sets affected by current, and the division reasons are the same.
The expression for obtaining the margin of each temperature data set according to each temperature data set is as follows:
in the method, in the process of the invention,is->Margin of individual temperature sets,/->Is->The maximum temperature within the set of temperatures is,is->Minimum temperature within the individual temperature sets;
in this embodiment, considering that the temperature data is affected differently by the voltage data and the current data, the temperature weighted value of the temperature data affected by the voltage is obtained first, where the expression is:
in the method, in the process of the invention,temperature weighting value for temperature data affected by voltage, < ->For the data margin of the first temperature set, +.>For the data margin of the second temperature set, +.>To->An exponential function of the base.
And then obtaining a temperature weighted value of temperature data affected by current, wherein the expression is specifically as follows:
in the method, in the process of the invention,temperature weighting value for temperature data influenced by current, +.>For the data margin of the third temperature set, +.>For the fourth temperature set.
Finally, the expression of the temperature weighting factor for calculating the temperature data according to the temperature weighting value affected by the voltage and the temperature weighting value affected by the current in the embodiment specifically includes:
in the method, in the process of the invention,temperature weighting factor for temperature data, +.>As a temperature weighting value affected by the voltage,is a temperature weighted value affected by the current.
Since the change of the vibration frequency data is slightly different from the change of the temperature data, the abnormal change of the vibration frequency can be obtained through the change of the information entropy, so that the information entropy of each vibration frequency data set is firstly obtained, and then the vibration frequency weighting value influenced by the voltage and the current is respectively calculated according to the information entropy of each vibration frequency data set, wherein the specific expression is as follows:
in the method, in the process of the invention,vibration frequency weighting value for the vibration frequency data influenced by the voltage,/->To->An exponential function of the base +.>Information entropy of the first vibration frequency set; />Information entropy of the second vibration frequency set;weighting values for vibration frequencies, for which the vibration frequency data are influenced by the current,/->Entropy of information for the third set of vibration frequencies, +.>Entropy of information for the fourth set of vibration frequencies. Finally, according to the vibration frequency weighting value of the vibration frequency data affected by the voltage and the vibration frequency weighting value affected by the current, the expression for obtaining the vibration frequency weighting factor is as follows:
in the method, in the process of the invention,weighting factors for vibration frequencies>For the vibration frequency weighting value affected by the voltage,is a vibration frequency weighting value affected by the current.
The larger the difference between abnormal changes of the temperature and the vibration frequency is, the larger the difference between the margins of the temperature sets is, and the larger the difference between the information entropies of different vibration frequency sets is, the larger the numerical values of the temperature weighting factors and the vibration frequency weighting factors are.
Step S003, obtaining each abnormal data according to the weighting factors of the voltage, the current, the temperature and the vibration frequency and the local abnormal factors of each data of the voltage, the current, the temperature and the vibration frequency, and completing the abnormal monitoring of the transformer by combining each abnormal data.
Normalizing to obtain weighting factors of voltage, current, temperature and vibration frequency; acquiring local abnormal factors of each data of voltage, current, temperature and vibration frequency by adopting a local abnormal factor algorithm; multiplying the normalized voltage weighting factors by the local abnormality factors of the data of each voltage to obtain the local abnormality factors of the data of each voltage; acquiring each data weighted local abnormal factor of each current, temperature and vibration frequency; the expression for obtaining the running anomaly degree of the transformer at each moment according to each data weighted local anomaly factor of each voltage, current, temperature and vibration frequency is as follows:
in the method, in the process of the invention,is->Transformer operating anomalies at individual moments, < >>For the number of data dimensions +.in this embodiment>Is voltage, current, temperature, vibration frequency, < >>For dimension->In->The data at each instant is weighted by the local anomaly factor.
In order to implement extraction and detection of the abnormal data, the present embodiment sets an abnormal threshold, and it should be noted that, the setting implementation of the abnormal threshold may be selected by the user, and the present embodiment sets the abnormal threshold to 2. And taking the data acquired at the moment when the running abnormality degree of the transformer is greater than the abnormal threshold value as abnormal data, analyzing the cause of the running abnormality of the transformer by related staff according to the abnormal data, and maintaining the transformer according to the analyzed cause.
In summary, the embodiment of the invention provides a method for monitoring abnormal operation of a transformer, which solves the problem of higher monitoring error of abnormal operation of the transformer by weighting and dimension reduction processing of local abnormal factors of each data, avoids the problem of inaccurate characteristic analysis of multidimensional monitoring data of the transformer by a traditional LOF abnormal data detection algorithm, increases the accuracy of multidimensional data abnormal analysis, and improves the accuracy of abnormal data acquisition of the transformer.
In order to avoid the problem that the traditional LOF abnormal data detection algorithm is inaccurate in characteristic analysis of the multi-dimensional monitoring data of the transformer, the embodiment collects monitoring data of different aspects of the transformer, calculates weighting factors of the monitoring data of different dimensions by analyzing the relevance among the data of different dimensions of the transformer, acquires the local abnormal factors of the data of different dimensions by combining with the LOF (local abnormal factor) algorithm, performs weighted dimension reduction on the local abnormal factors of the data collected at the same moment of different dimensions, analyzes abnormal running conditions of the transformer, and has higher abnormal running monitoring precision of the transformer.
Based on the same inventive concept as the above method, the embodiment of the invention further provides a transformer abnormal operation monitoring system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor realizes the steps of any one of the above method for monitoring the transformer abnormal operation when executing the computer program.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (6)
1. A method for monitoring abnormal operation of a transformer, the method comprising the steps of:
collecting voltage, current, temperature and vibration frequency data of a transformer;
obtaining a periodic sequence of voltage data according to peak distribution in the voltage data of the transformer; acquiring a periodic sequence of current data; obtaining an asynchronous change coefficient between voltage and current according to the periodic sequence of the voltage data and the current data; taking a period corresponding to the beginning of the change of the elements in the period sequence of the voltage data as a primary change period of the voltage data; obtaining a voltage weighting factor according to the initial change period of the voltage data, the voltage data in each voltage period and the asynchronous change coefficient between the voltage and the current; acquiring an initial change period of current data; acquiring a current weighting factor;
dividing the temperature data and the vibration frequency data to obtain temperature data sets and vibration frequency data sets; obtaining the margin of each temperature set according to the maximum temperature and the minimum temperature in each temperature data set; obtaining a temperature weighting factor according to the margin of each temperature set; acquiring information entropy of each vibration frequency data set, and acquiring a vibration frequency weighting factor according to the information entropy of each vibration frequency set;
acquiring local abnormality factors of the voltage, the current, the temperature and the vibration frequency by adopting a local abnormality factor algorithm, acquiring the abnormal data according to the weighting factors of the voltage, the current, the temperature and the vibration frequency and the local abnormality factors of the voltage, the current, the temperature and the vibration frequency, and completing the abnormality monitoring of the transformer by combining the abnormal data;
the expression for obtaining the asynchronous change coefficient between the voltage and the current according to the periodic sequence of the voltage data and the current data is as follows:
in the method, in the process of the invention,for an asynchronous change coefficient between voltage and current, +.>For the number of elements in the periodic sequence of the voltage data, < >>For the number of elements in the periodic sequence of the current data, < >>To obtain maximum value function>Is the +.>Time interval of each cycle>Is the +.>Time interval of each cycle>Is the Jaccard coefficient between the periodic sequence of voltage data and current data;
the method for obtaining the voltage weighting factor according to the initial change period of the voltage data, the voltage data in each voltage period and the asynchronous change coefficient between the voltage and the current comprises the following specific steps:
sequencing the voltage data in each voltage period from large to small according to the value, and taking the sequence formed by the sequencing as a data sequence in each voltage period; the expression for obtaining the voltage weighting factor according to the data sequence in each voltage period, the initial change period of the voltage data and the asynchronous change coefficient is as follows:
in the method, in the process of the invention,is a voltage weighting factor, ">For the sequence number of the initial period in the periodic sequence of the voltage data,for the data sequence in the initial period, +.>Data sequence in the previous period of the initial period, +.>Function of obtaining similarity for dynamic time warping algorithm,/->Abnormal fluctuation coefficient of voltage data, +.>For an asynchronous change coefficient between voltage and current, +.>For the number of elements in the periodic sequence of the voltage data, < >>Is->Data sequence within a single voltage period,/->The periodic sequence of voltage data +.>Time of cycle>As a function of the difference between the maximum and minimum values;
the temperature weighting factors are obtained according to the margin of each temperature set, and the specific steps include: calculating a temperature weighted value influenced by current according to the margin of the first temperature set and the margin difference value of the second temperature set; calculating a temperature weighted value influenced by the voltage according to the margin of the third temperature set and the margin difference value of the fourth temperature set; taking the average value of the temperature weighted values influenced by the voltage and the temperature weighted values influenced by the current as a temperature weighted factor;
the vibration frequency weighting factors are obtained according to the information entropy of each vibration frequency set, and the specific steps include: calculating a vibration frequency weighting value influenced by current according to the information entropy of the first vibration frequency set and the information entropy difference value of the second vibration frequency set; calculating a vibration frequency weighting value influenced by voltage according to the information entropy of the third vibration frequency set and the information entropy difference value of the fourth vibration frequency set; and taking the average value of the vibration frequency weighted values influenced by the voltage and the vibration frequency weighted values influenced by the current as a vibration frequency weighted factor.
2. The method for monitoring abnormal operation of a transformer according to claim 1, wherein the periodic sequence of voltage data is obtained according to peak distribution in the voltage data of the transformer, comprising the specific steps of:
the voltage data between two adjacent peaks in the voltage data of the transformer is taken as one voltage period, the time elapsed by the voltage period is taken as an element of the period sequence of the voltage data, and the time elapsed by each voltage period is taken as each element of the period sequence of the voltage data.
3. The method for monitoring abnormal operation of a transformer according to claim 1, wherein the step of obtaining each temperature data set and each vibration frequency data set by dividing the temperature data and the vibration frequency data comprises the steps of:
dividing temperature data and vibration frequency data into two data sets respectively according to the acquisition time corresponding to last bit data in a voltage data initial change period, and respectively marking the two data sets as a first temperature set and a second temperature set, and a first vibration frequency set and a second vibration frequency set; and dividing the temperature data and the vibration frequency data into two data sets respectively according to the acquisition time corresponding to the last bit data in the initial change period of the current data, and respectively marking the data sets as a third temperature set and a fourth temperature set, and a third vibration frequency set and a fourth vibration frequency set.
4. The method for monitoring abnormal operation of a transformer according to claim 1, wherein the specific step of obtaining the margin of each temperature set according to the maximum temperature and the minimum temperature in each temperature data set comprises the following steps:
the margin for each temperature set is inversely proportional to the maximum temperature within each temperature set and directly proportional to the difference between the maximum temperature and the minimum temperature within the temperature set.
5. The method for monitoring abnormal operation of a transformer according to claim 1, wherein the step of obtaining abnormal data according to weighting factors of voltage, current, temperature and vibration frequency and local abnormal factors of each data of voltage, current, temperature and vibration frequency comprises the steps of:
multiplying the normalized voltage weighting factors by the local abnormality factors of the data of each voltage to obtain the local abnormality factors of the data of each voltage; acquiring each data weighted local abnormal factor of each current, temperature and vibration frequency; the expression for obtaining the running anomaly degree of the transformer at each moment according to each data weighted local anomaly factor of each voltage, current, temperature and vibration frequency is as follows:
in the method, in the process of the invention,is->Transformer operating anomalies at individual moments, < >>Number of data dimensions>Weighting local anomaly factors for the data of dimension j at the ith moment;
and taking the data acquired at the moment when the running anomaly degree of the transformer is greater than the anomaly threshold value as anomaly data.
6. A transformer abnormal operation monitoring system comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of the method according to any of claims 1-5 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311218284.7A CN116955895B (en) | 2023-09-21 | 2023-09-21 | Transformer operation abnormity monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311218284.7A CN116955895B (en) | 2023-09-21 | 2023-09-21 | Transformer operation abnormity monitoring method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116955895A CN116955895A (en) | 2023-10-27 |
CN116955895B true CN116955895B (en) | 2023-12-15 |
Family
ID=88442919
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311218284.7A Active CN116955895B (en) | 2023-09-21 | 2023-09-21 | Transformer operation abnormity monitoring method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116955895B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117537749B (en) * | 2023-11-20 | 2024-07-16 | 焦作煤业(集团)新乡能源有限公司 | Cage shoe abrasion monitoring method for mine shaft inspection robot |
CN117272033B (en) * | 2023-11-23 | 2024-03-01 | 智联信通科技股份有限公司 | DC shunt current metering abnormity monitoring method |
CN117851955B (en) * | 2024-03-07 | 2024-05-24 | 辽宁亿金电子有限公司 | Flexible-direct-current capacitor state detection method and system |
CN117870779B (en) * | 2024-03-12 | 2024-05-31 | 深圳市广正弘自动化科技有限公司 | Remote wireless intelligent monitoring method and system for automation equipment |
CN118409166A (en) * | 2024-07-04 | 2024-07-30 | 国网上海市电力公司 | System and method for testing direct-current direct-hanging module of transformer area |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107123989A (en) * | 2017-05-25 | 2017-09-01 | 国网上海市电力公司 | A kind of topology identification method based on improved local outlier factor algorithm |
CN111443259A (en) * | 2020-03-30 | 2020-07-24 | 国网山东省电力公司德州供电公司 | Active power distribution network fault diagnosis method and system based on local abnormal factor detection |
CN113139610A (en) * | 2021-04-29 | 2021-07-20 | 国网河北省电力有限公司电力科学研究院 | Abnormity detection method and device for transformer monitoring data |
CN115656673A (en) * | 2022-10-25 | 2023-01-31 | 云南电网有限责任公司电力科学研究院 | Transformer data processing device and equipment storage medium |
CN116628529A (en) * | 2023-07-21 | 2023-08-22 | 山东科华电力技术有限公司 | Data anomaly detection method for intelligent load control system at user side |
CN116660667A (en) * | 2023-07-26 | 2023-08-29 | 山东金科电气股份有限公司 | Transformer abnormality monitoring method and system |
CN116702080A (en) * | 2023-08-04 | 2023-09-05 | 山东荣信集团有限公司 | Gas system methanol-to-liquid process on-line monitoring system based on multidimensional sensor |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10147049B2 (en) * | 2015-08-31 | 2018-12-04 | International Business Machines Corporation | Automatic generation of training data for anomaly detection using other user's data samples |
-
2023
- 2023-09-21 CN CN202311218284.7A patent/CN116955895B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107123989A (en) * | 2017-05-25 | 2017-09-01 | 国网上海市电力公司 | A kind of topology identification method based on improved local outlier factor algorithm |
CN111443259A (en) * | 2020-03-30 | 2020-07-24 | 国网山东省电力公司德州供电公司 | Active power distribution network fault diagnosis method and system based on local abnormal factor detection |
CN113139610A (en) * | 2021-04-29 | 2021-07-20 | 国网河北省电力有限公司电力科学研究院 | Abnormity detection method and device for transformer monitoring data |
CN115656673A (en) * | 2022-10-25 | 2023-01-31 | 云南电网有限责任公司电力科学研究院 | Transformer data processing device and equipment storage medium |
CN116628529A (en) * | 2023-07-21 | 2023-08-22 | 山东科华电力技术有限公司 | Data anomaly detection method for intelligent load control system at user side |
CN116660667A (en) * | 2023-07-26 | 2023-08-29 | 山东金科电气股份有限公司 | Transformer abnormality monitoring method and system |
CN116702080A (en) * | 2023-08-04 | 2023-09-05 | 山东荣信集团有限公司 | Gas system methanol-to-liquid process on-line monitoring system based on multidimensional sensor |
Non-Patent Citations (3)
Title |
---|
Identification of distribution network topology parameters based on multidimensional operation data;Jiaqiao Li, Di Wu, Weichao Jin, Zhenyue Chu, Shengyuan Liu, Jien Ma, Zhenzhi Lin, Li Yang;ScienceDirect;全文 * |
一种云环境下的高效异常检测策略研究;程云观;台宪青;马治杰;;计算机应用与软件(01);全文 * |
基于改进快速密度峰值聚类算法的电力大数据异常值检测;刘凤魁;邓春宇;王晓蓉;王新迎;;电力信息与通信技术(06);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116955895A (en) | 2023-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116955895B (en) | Transformer operation abnormity monitoring method and system | |
CN108021736B (en) | Load switching action monitoring method based on sliding window residual error model | |
CN116879662B (en) | Transformer fault detection method based on data analysis | |
CN117034043B (en) | Intelligent building comprehensive energy consumption monitoring method and system based on multi-energy Internet of things | |
CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
CN109359665B (en) | Household appliance load identification method and device based on support vector machine | |
CN117572159B (en) | Power failure detection method and system based on big data analysis | |
CN118152967B (en) | Multi-output interface inverter power performance monitoring method and system | |
CN118152836B (en) | Stability evaluation method for operation process of electric energy meter | |
CN117150244B (en) | Intelligent power distribution cabinet state monitoring method and system based on electrical parameter analysis | |
CN117129904B (en) | Industrial power supply rapid switching monitoring method based on data analysis | |
CN113034305B (en) | Non-invasive load monitoring event classification method and storage medium | |
US11378944B2 (en) | System analysis method, system analysis apparatus, and program | |
CN116510223B (en) | Self-identification fire pump electrical parameter inspection monitoring system based on Internet of things | |
CN111091243A (en) | PCA-GM-based power load prediction method, system, computer-readable storage medium, and computing device | |
CN115790944A (en) | Test early warning method and system for linear motor thrust testing machine | |
CN111158974B (en) | Cloud server-oriented hardware-aware CPU energy consumption measuring and calculating method | |
CN118391249B (en) | Method and device for processing running state monitoring data of large water pump | |
CN110187167A (en) | A kind of detection method and device of the load switch event based on manifold classification | |
CN118501720B (en) | Lithium battery abnormality detection system based on big data analysis | |
CN118100446B (en) | Intelligent detection method for node running state of power system | |
CN118244071B (en) | Method and system for detecting partial discharge of dry type iron core reactor | |
CN118243747A (en) | Transformer fault diagnosis method based on gas on-line monitoring | |
CN114841450A (en) | Load identification method based on self-adaptive recursive matrix | |
CN116724475A (en) | Power consumption monitoring device and program |
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 |