CN117421687A - Method for monitoring running state of digital power ring main unit - Google Patents
Method for monitoring running state of digital power ring main unit Download PDFInfo
- Publication number
- CN117421687A CN117421687A CN202311736193.2A CN202311736193A CN117421687A CN 117421687 A CN117421687 A CN 117421687A CN 202311736193 A CN202311736193 A CN 202311736193A CN 117421687 A CN117421687 A CN 117421687A
- Authority
- CN
- China
- Prior art keywords
- voltage
- data
- time sequence
- voltage data
- sequence interval
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012544 monitoring process Methods 0.000 title claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims description 78
- 230000005856 abnormality Effects 0.000 claims description 78
- 230000008569 process Effects 0.000 claims description 12
- 230000014509 gene expression Effects 0.000 claims description 9
- 238000013450 outlier detection Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 238000010977 unit operation Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 7
- 238000002790 cross-validation Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052755 nonmetal Inorganic materials 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Human Computer Interaction (AREA)
- Probability & Statistics with Applications (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to the field of operation monitoring of electric power cabinets, and provides a digital electric power ring main unit operation state monitoring method. The invention aims to improve the accuracy of monitoring the running state of the electric power ring main unit and realize the efficient and safe monitoring of the running state of the electric power ring main unit.
Description
Technical Field
The invention relates to the field of operation monitoring of power cabinets, in particular to a method for monitoring the operation state of a digital power ring main unit.
Background
The ring main unit is a group of electric equipment (high-voltage switch equipment) which is arranged in a metal or nonmetal insulating cabinet body or is made into an assembled spacing ring main power supply unit, has the advantages of simple structure, small volume occupation ratio and low price, can improve power supply parameters and performance, ensures power supply safety, and is widely applied to power distribution stations and box-type substations of load centers such as urban residential communities, high-rise buildings, large public buildings, factory enterprises and the like. However, in the long-term operation of the electric power ring main unit, the ring main unit fails due to various objective reasons, so that the environment temperature in the ring main unit is abnormal, and the fluctuation phenomenon of the power supply voltage and the power supply current is generated, thereby bringing hidden danger to the reliable operation of the power grid.
The isolated forest algorithm is sensitive to feature selection, and proper features are selected to improve the monitoring effect, but in the operation state monitoring of the digital power ring main unit, parameters of the ring main unit are not unique, and if only single features are extracted and analyzed, the performance of the isolated forest algorithm can be possibly affected. Meanwhile, the isolated forest algorithm is an algorithm based on outlier detection, and judges whether the isolated forest algorithm belongs to a normal state or not by searching an abnormal value in a sample. However, during the operation state detection of the digital power ring main unit, the fault or abnormal condition is continuous under the normal condition and cannot be simply classified as an abnormal value, so that the related parameters in the operation state of the power ring main unit need to be comprehensively considered, and the defects are avoided.
In summary, the invention provides a method for monitoring the running state of a digital power ring main unit, which improves the abnormal data score in an isolated forest algorithm by analyzing the voltage data, the current data and the temperature data of the power ring main unit and combining the isolated forest algorithm, thereby improving the accuracy of the running state monitoring of the ring main unit.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method for monitoring the running state of a digital power ring main unit, which aims to solve the existing problems.
The invention discloses a method for monitoring the running state of a digital power ring main unit, which adopts the following technical scheme:
the embodiment of the invention provides a method for monitoring the running state of a digital power ring main unit, which comprises the following steps:
collecting voltage data, current data and temperature data of the electric ring main unit at each moment;
respectively calculating the association degree of voltage data, current data and temperature data by combining a gray association degree theory; obtaining local deviation amplitude values of the voltage data at each moment according to the mean deviation of the voltage data at each moment; taking the absolute value of the difference value between the voltage data at each moment and the average value of all the voltage data as the local average voltage difference of the voltage data at each moment; obtaining local voltage deviation factors of the voltage data at each moment according to the local deviation amplitude values and the local average voltage difference of the voltage data at each moment; dividing the voltage data into time sequence intervals according to fixed time intervals; combining the region growing algorithm with local voltage deviation factors of the voltage data at each moment to obtain each voltage abnormal cluster of the voltage data in each time sequence interval; obtaining the voltage anomaly distance of the voltage data at each moment according to the relation between the voltage data at each moment and the voltage anomaly cluster; acquiring an average outlier index of each time sequence interval of the voltage data; combining the average outlier index of each time sequence interval with the voltage abnormality distance of the voltage data at each time to obtain the comprehensive voltage abnormality index of each time sequence interval;
acquiring a comprehensive current abnormality index of each time sequence interval by combining current data; combining the comprehensive current abnormality index, the comprehensive voltage abnormality index and the association degree of the voltage data, the current data and the temperature data of each time sequence interval to obtain the ring main unit temperature abnormality coefficient of each time sequence interval; obtaining abnormal data score of a real-time sequence interval by combining an isolated forest algorithm and ring main unit temperature abnormal coefficients of each time sequence interval; and finishing the monitoring of the running state of the electric ring main unit according to the abnormal data score of the real-time sequence interval.
Preferably, the obtaining the local deviation amplitude of the voltage data at each time according to the mean deviation of the voltage data at each time includes:
and calculating the absolute value of the difference between the voltage data at the current moment and the voltage data at the previous moment and the next moment according to the voltage data at each moment, and taking the average value of the absolute values of the two difference values as the local deviation amplitude value of the voltage data at the current moment.
Preferably, the obtaining the local voltage deviation factor of the voltage data at each time according to the local deviation amplitude and the local average voltage difference of the voltage data at each time includes:
setting a time neighborhood for the voltage data, and recording the average value of the local deviation amplitude values of the voltage data of all the time before each time without the time neighborhood as the average value of the previous local deviation amplitude values; recording the average value of the local deviation amplitude values of all the time voltage data which do not contain the time neighborhood after each time as a post local deviation amplitude value average value, calculating the ratio of the pre local deviation amplitude value average value to the post local deviation amplitude value average value, taking the local average voltage difference of the time voltage data as an index of an exponential function based on a natural constant, and taking the product of the calculation result of the exponential function and the ratio as a local voltage deviation factor of the time voltage data.
Preferably, the step of combining the local voltage deviation factor of the voltage data at each time with the region growing algorithm to obtain each voltage abnormal cluster of the voltage data in each time sequence interval includes:
setting a voltage abnormality threshold for each time sequence interval, using a region growing algorithm, wherein an initial seed point is the first voltage data of each time sequence interval, a growing criterion is that a local voltage deviation factor of the voltage data is larger than or equal to the voltage abnormality threshold, a growing cut-off condition is that the local voltage deviation factor of the voltage data is smaller than the voltage abnormality threshold or the voltage data of the time sequence interval is completely traversed, if the voltage data of the time sequence interval is not completely traversed and the local voltage deviation factor of the voltage data is smaller than the voltage abnormality threshold to cause the growth cut-off, the voltage data at the next time of the growth cut-off time is used as a new seed point, and the growing is regrown until all the voltage data of the time sequence interval are completely traversed, and each data set after the growth is used as each voltage abnormality cluster.
Preferably, the voltage anomaly distance of the voltage data at each time is obtained according to the relationship between the voltage data at each time and the voltage anomaly cluster, and the expression is:
in the method, in the process of the invention,is->The voltage abnormality distance at the i-th moment in the time sequence interval; />Representing a set of voltage anomaly clusters, ">Indicate->Voltage data at each time, ">The average value of all voltage data in the voltage abnormal cluster to which the voltage data at the ith moment belongs; />The total number of voltage data in the voltage abnormal cluster to which the ith moment belongs is +.>Indicate->Distance between voltage data at each moment and nearest voltage abnormality cluster in left moment direction, +.>Indicate->Distance between voltage data at each moment and nearest voltage abnormality cluster in right moment direction, +.>Respectively belonging to and not belonging to the symbol.
Preferably, the acquiring an average outlier index of each time sequence interval of the voltage data includes:
and obtaining local outlier factors of each voltage data by using an LOF outlier detection algorithm, and taking the average value of the local outlier factors of all the voltage data in each time sequence interval as the average outlier index of each time sequence interval.
Preferably, the average outlier index of each time sequence interval and the voltage abnormality distance of the voltage data at each time are combined to obtain the comprehensive voltage abnormality index of each time sequence interval, and the expression is:
in the method, in the process of the invention,is->Comprehensive voltage abnormality indexes of the time sequence intervals; />Is->The total number of voltage abnormal clusters in each time sequence interval; />Is->Maximum value of voltage data in each voltage anomaly cluster, +.>Is->Minimum values of voltage data in the voltage anomaly clusters; />Is->Total time count of each time sequence interval, +.>Is->The voltage abnormality distance at the i-th moment in the time sequence interval; />Is->Average outlier index of each timing interval, +.>Is a natural constant.
Preferably, the loop network cabinet temperature anomaly coefficient of each time sequence section is obtained by combining the comprehensive current anomaly index and the comprehensive voltage anomaly index of each time sequence section and the correlation degree of the voltage data, the current data and the temperature data, and the loop network cabinet temperature anomaly coefficient comprises:
the association degree of the voltage data and the temperature data is marked as a first association degree, the association degree of the current data and the temperature data is marked as a second association degree, the product of the integrated voltage abnormality index and the first association degree is marked as a first product for each time sequence interval, the product of the integrated current abnormality index and the second association degree is marked as a second product, and the sum of the first product and the second product is used as the ring main unit temperature abnormality coefficient of each time sequence interval.
Preferably, the obtaining the abnormal data score of the real-time sequence interval by combining the isolated forest algorithm and the ring main unit temperature abnormal coefficient of each time sequence interval includes:
and inputting voltage data, current data and temperature data based on the time sequence interval into an isolated forest algorithm for training, collecting a group of time sequence interval data in real time, calculating the score of the real-time sequence interval data by utilizing the trained isolated forest algorithm, and taking the normalized product of the score and the ring main unit temperature anomaly coefficient of the real-time sequence interval as the anomaly data score of the real-time sequence interval.
Preferably, the monitoring of the operation state of the power ring main unit according to the abnormal data score of the real-time sequence interval includes:
setting an optimal threshold, if the abnormal data score of the real-time sequence interval is greater than or equal to the optimal threshold, operating the electric power ring main unit in a dangerous state, and if the abnormal data score of the real-time sequence interval is less than the threshold, operating the electric power ring main unit in a controllable state.
The invention has at least the following beneficial effects:
according to the method, local deviation factors are obtained through the power supply voltage data and the power supply current data characteristics of the power ring main unit, the data abnormal clusters of the data sequences are divided by setting the threshold value, so that the ring main unit temperature abnormal coefficient based on the time sequence interval is obtained, and the abnormal data score in the isolated forest algorithm is improved subsequently;
further, the invention comprehensively analyzes the related data of the power ring main unit, avoids the defect that abnormal data classification is inaccurate due to continuous occurrence of fault conditions in the process of monitoring the operation state of the digital power ring main unit due to local similarity, can monitor the operation state of the digital power ring main unit data more accurately and comprehensively, and solves the problem that the operation state monitoring is difficult due to complex influence factors of the power ring main unit and similar fault characteristics as an auxiliary reference for subsequent decision processing. The method has the advantages of high safety, high reliability, high accuracy and the like in monitoring the running state of the power ring main unit.
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 a method for monitoring an operation state of a digital power ring main unit according to an embodiment of the present invention;
fig. 2 is a flowchart of abnormal data score acquisition.
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 is given below of a digital power ring main unit operation state monitoring method according to the invention, which is provided by combining the accompanying drawings and the preferred embodiment. 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 specific scheme of a digital power ring main unit operation state monitoring method, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating a method for monitoring an operation state of a digital power ring main unit according to an embodiment of the present invention is shown, where the method includes the following steps:
and S001, collecting related data of the electric power ring main unit, and preprocessing the collected data.
Specifically, firstly, the embodiment obtains the power supply voltage and the power supply current data in the power ring main unit by using the voltage and current sensors, secondly, obtains the temperature data in the power ring main unit by using the temperature sensors, sets the acquisition time interval of the sensors to be 3s, and sets the total acquisition time length to be 10h, so that the power supply voltage data sequence, the power supply current data sequence and the temperature data sequence based on time sequence can be respectively recorded as、/>And +.>Wherein t represents the number of acquired data, +.in this embodiment>The implementation can be set by the user according to the actual situation.
Because abnormal conditions may occur in the data acquisition and transmission processes of the sensor, data value deletion exists in each data sequence, and in order to avoid the influence of different dimensions among different data on subsequent analysis processing, the acquired data sequence is required to be subjected to missing value processing by using a data filling algorithm, and then standard normalization processing is performed on each filled data element. Respectively marking the power supply voltage data sequence, the power supply current data sequence and the temperature data sequence after pretreatment as、/>And +.>The data filling algorithm used in this embodiment is a mean interpolation method, and the normalization processing is Z-score, so that the value ranges of the data elements in each data sequence are in [0,1]]All of themThe value interpolation method and the Z-score normalization algorithm are well known in the art, and the embodiment will not be described here.
The preprocessed power supply voltage data sequence, the preprocessed power supply current data sequence and the preprocessed temperature data sequence can be obtained according to the method of the embodiment and used as a data basis for monitoring the running state of the subsequent power ring main unit.
Step S002, local deviation factors are obtained through the data characteristics of the ring main unit power supply voltage data and the power supply current data, the data abnormal clusters are divided based on the local deviation factors, the ring main unit temperature abnormal coefficient based on the time sequence interval is obtained, and abnormal data scores in an isolated forest algorithm are improved.
Specifically, in this embodiment, local voltage deviation factors of voltage data at each time are obtained according to mean deviation of a voltage data sequence, each voltage anomaly cluster of each time sequence interval is obtained by combining an area growth algorithm and the local voltage deviation factors of the voltage data at each time, voltage anomaly distances of the voltage data at each time are obtained according to distribution of the voltage data in each voltage anomaly cluster, comprehensive voltage anomaly indexes of each time sequence interval are obtained by combining an LOF outlier detection algorithm and the voltage anomaly distances, ring main unit anomaly coefficients of each time sequence interval are obtained according to the comprehensive voltage anomaly indexes, monitoring of the running state of the electric ring main unit is achieved by combining an isolated forest algorithm, and a specific anomaly data score obtaining flow chart is shown in fig. 2. The construction process of the ring main unit temperature anomaly coefficient based on the time sequence interval specifically comprises the following steps:
when the running state of the electric power ring main unit is abnormal, the power supply voltage and the power supply current of the electric power ring main unit can have abnormal fluctuation, and in normal cases, when the power supply voltage and the power supply current of the electric power ring main unit abnormally fluctuate, the electronic equipment in the electric power ring main unit can be overloaded, and equipment damage and even fire disaster can be caused; secondly, when looped netowrk cabinet supply voltage and supply current are unusual undulant, can make the inside equipment work load increase of electric power looped netowrk cabinet, produce more heat, this can lead to the inside temperature rise of looped netowrk cabinet, surpasses electronic equipment and bears the scope, and then influences the normal operating of equipment. When the power supply voltage and the power supply current of the power ring main unit abnormally fluctuate, the temperature of local electronic elements can be increased, and the operation state of the power ring main unit is abnormal.
First, a power supply voltage data sequence, a power supply current data sequence, and a temperature data sequence obtained based on the above steps、/>、/>Analyzing, namely acquiring a power supply voltage data sequence and the association degree between the power supply current data sequence and the temperature data sequence through gray association analysis GRA based on gray association degree theory, and marking the association degree as first association degree +.>Second degree of association->. The degree of correlation is a measure of the degree of correlation of the temperature data with the power supply voltage data and the power supply current data, i.e. the time-dependent change of the degree of correlation, but due to the degree of correlation +>、/>Only the correlation degree between the corresponding data sequence (namely the power supply voltage data sequence and the power supply current data sequence) and the temperature data sequence is considered, but the correlation degree obtained by single use cannot accurately reflect the abnormal condition generated in the running state of the power ring main unit without comprehensively considering the correlation degree of the power supply voltage data sequence and the power supply current data sequence to perform common analysis>、/>And respectively serving as initial values of influences of the power supply voltage and the power supply current on the temperature of the power ring main unit, and further analyzing the power supply voltage data sequence and the power supply current data sequence.
Based on supply voltage data sequencesAnalyzing, calculating average value of all data elements, namely all voltage elements, in the power supply voltage data sequence to be marked as average power supply voltage +.>The local average voltage difference VD is obtained from the difference between the supply voltage at each instant and the average supply voltage. Calculating the absolute difference value of the power supply voltage values at the ith moment and the ith-1 and the (i+1) th moment and marking the absolute difference value as +.>、/>By->、/>The local deviation amplitude at the i-th moment obtained by averaging is marked as +.>. In order to avoid the local similarity in the power supply voltage data sequence, which results in that the local deviation amplitude obtained by calculation at each time is not greatly different, the subsequent calculation accuracy is reduced, a time neighborhood K is set, and in the embodiment +.>The practitioner can set according to the actual situation by himself, calculate the mean value of the local deviation amplitude values at all times before the ith time K and the mean value of the local deviation amplitude values at all times after the K times as the previous local deviation amplitude mean value ∈ ->Post local deviation amplitude mean +.>Obtaining local voltage deviation factors at all moments according to the data, wherein the specific expression of the local voltage deviation factors is as follows:
in the method, in the process of the invention,is the local average voltage difference at the i-th moment; />Indicate->Voltage data at each instant; />The average value of the voltage data at all moments; />Is the local voltage deviation factor at the ith moment; />For the mean value of the previous local deviation amplitude of the voltage data at the ith moment,/>For the mean value of the post-local deviation amplitude of the voltage data at the ith moment,/>Is a natural constant.
And carrying out normalization processing on the obtained local voltage deviation factor to enable the value range to be in the range of 0 and 1.
When the fluctuation condition of the power supply voltage of the power ring main unit is more serious, the difference between the power supply voltage at each moment and the average power supply voltage is larger,the larger the local mean voltage difference +.>The larger; if the fluctuation degree of the power supply voltage of the power ring main unit is larger at the ith moment, namely the power supply voltage is more unstable, and the internal temperature of the power ring main unit is more likely to be abnormal, the ratio of the local deviation amplitude mean value before the ith moment K to the local deviation amplitude mean value after the ith moment K is larger, namely->The larger the local average voltage difference at instant i +.>The larger, further, the local voltage deviation factor at the ith moment +.>The larger.
Each will beThe data acquired during the time interval min is divided into a time sequence interval, in this embodiment +.>The implementation can be set by the user according to the actual situation. Acquiring each abnormal voltage cluster in each time sequence interval by using a region growing algorithm, wherein an initial seed point of the region growing algorithm is set as first power supply voltage data in each time sequence interval, and if a local voltage deviation factor LVD of the initial seed point is greater than or equal to a voltage abnormal threshold E, starting growth, in the embodiment, the initial seed point is equal to or greater than a voltage abnormal threshold E>Setting the moment as a voltage abnormality moment, dividing adjacent voltage abnormality moments into the same voltage abnormality cluster (subtracting the moment number of the voltage), wherein when the absolute value of the difference value of the two moments is 1, the two moments are adjacent moments, and if the voltage data corresponding to the two moments are both greater than or equal to a voltage abnormality threshold E, the two moments are adjacent voltage abnormality moments), and stopping growing until the local voltage deviation factor LVD of the corresponding moment is smaller than the voltage abnormality threshold; and then, the voltage data at the next moment of the voltage data point of which the growth is stopped is used as a new initial seed point again, and the growth is continued until all the power supply voltage data of the time sequence interval are traversed. The area growth algorithm in this embodiment is input as a power supply voltage data sequence of the power ring main unit based on the time sequence interval, and output as a power supply voltage data sequence with a plurality of voltage abnormal clusters and rest voltage data.
For the voltage data of each time sequence interval, if the voltage data at the ith moment does not belong to any voltage abnormality cluster, respectively calculating the distances between the voltage data at the ith moment and the left nearest voltage abnormality cluster and between the voltage data at the ith moment and the right nearest voltage abnormality cluster, specifically, searching the corresponding moment of the voltage data at the ith moment and the rightmost voltage data in the left nearest voltage abnormality cluster, calculating the absolute value of the difference between the ith moment and the corresponding moment, and recording asSimilarly, searching the corresponding time of the voltage data at the ith moment and the leftmost voltage data in the leftmost voltage abnormal cluster at the right side, calculating the absolute value of the difference between the ith moment and the corresponding moment, and marking the absolute value as +.>. If the voltage data corresponding to the ith moment belongs to a voltage abnormal cluster, calculating the absolute value of the difference between the voltage at the moment and the average voltage in the abnormal cluster, and counting the voltage dataThe number of voltage data in the voltage anomaly cluster to which the moment belongs is AN, and the voltage anomaly distance at each moment in the time sequence interval can be obtained based on the data, wherein the specific expression of the voltage anomaly distance is as follows:
in the method, in the process of the invention,is->The voltage abnormality distance at the i-th moment in the time sequence interval; />Representing a set of voltage anomaly clusters, ">Indicate->Voltage data at each time, ">Indicating that the ith voltage data belongs to a voltage anomaly cluster, and vice versa,indicating that the ith voltage data does not belong to the voltage abnormality cluster, +.>The average value of all voltage data in the voltage abnormal cluster to which the voltage data at the ith moment belongs; />The total number of voltage data in the voltage abnormal cluster to which the ith moment belongs is +.>Indicate->Distance between voltage data at each moment and nearest voltage abnormality cluster in left moment direction, +.>Indicate->Distance between voltage data at each moment and nearest voltage abnormality cluster in right moment direction, +.>Respectively belonging to and not belonging to the symbol.
If the voltage data at the ith moment belongs to a voltage abnormal cluster, and the voltage data at the ith moment is more abnormal, the mean value difference of the voltage data in the ith moment and the voltage abnormal cluster is larger, the number of the data in the abnormal cluster to which the voltage data belongs is larger,the bigger the->Smaller (less)>The larger the voltage abnormality distance at the ith moment is, the smaller the voltage abnormality distance at the ith moment is; if the voltage data at the ith moment does not belong to the voltage abnormality cluster and the voltage data at the ith moment is more abnormal, the number of moments between the nearest voltage abnormality cluster in the direction of the ith moment and the left-right moment is smaller, namely +.>、/>Smaller (less)>The smaller the voltage abnormality distance at the i-th time is, the smaller the voltage abnormality distance is.
The maximum value and the minimum value of the voltages in each abnormal voltage cluster in the statistical time sequence interval are respectively recorded as、/>If only one voltage value exists in the voltage abnormal cluster, the voltage maximum value and the voltage minimum value in the voltage abnormal cluster are both the voltage values. The total number of voltage abnormal clusters in a time sequence interval is set as H, and local outlier factors of the ith data element in the power supply voltage data sequence of the whole power ring main unit are obtained through an LOF outlier detection algorithm and are marked as +.>The neighborhood distance K can be determined according to one-leave-one-out cross-validation, and because the LOF outlier detection algorithm and the one-leave-one-out cross-validation are all known techniques, and not described in detail herein, the local outlier factors of all the voltage data elements in one time sequence interval are averaged to obtain an average outlier index based on the time sequence interval->Obtaining a comprehensive voltage abnormality index based on a time sequence interval according to the data, wherein the specific expression of the comprehensive voltage abnormality index is as follows:
in the method, in the process of the invention,is->Comprehensive voltage abnormality indexes of the time sequence intervals; />Is->The total number of voltage abnormal clusters in each time sequence interval; />Is->Maximum value of voltage data in each voltage anomaly cluster, +.>Is->Minimum values of voltage data in the voltage anomaly clusters; />Is->Total time count of each time interval +.in this embodiment>The implementer can set the device according to the actual situation; />Is->The voltage abnormality distance at the i-th moment in the time sequence interval; />Is->Average outlier index of each timing interval, +.>Is a natural constant.
When the fluctuation degree of the power supply voltage of the power ring main unit is larger, namely the abnormal condition of the power supply voltage is more serious, further, the abnormal condition of the temperature of the power ring main unit is more serious, the power supply voltage is between the maximum voltage value and the minimum voltage value in each voltage abnormal cluster in the time sequence intervalThe larger the difference, the smaller the voltage abnormality distance based on the time of day is further,the bigger the->The smaller, correspondingly, the n-th time sequence interval's integrated voltage abnormality index +.>The larger; when the local outlier factor at each time in the time sequence interval is smaller than 1, the higher the voltage data value density at the time is, the higher the overall voltage data is, the more dense the time sequence interval is, the more slight the voltage abnormality is, and further the average outlier index of the time sequence interval is->The smaller the composite voltage anomaly index CVA is, the smaller it is; conversely, when the local outlier factor at each time in the time sequence interval is larger than 1, the voltage data value density at the time is lower than the whole voltage data, the voltage data abnormal condition of the power ring main unit corresponding to the time is more serious, and correspondingly, the temperature abnormal condition of the power ring main unit may be more serious, based on the average outlier index of the time sequence interval>The larger the composite voltage anomaly index CVA is, the larger it is.
Similarly, the comprehensive current abnormality index CCA based on the time sequence interval can be obtained according to the mode, and the initial value of the influence of the obtained comprehensive voltage abnormality index CVA, the obtained comprehensive current abnormality index CCA and the power supply voltage and the power supply current on the temperature of the power ring main unit is obtained、/>The ring main unit temperature anomaly coefficient based on the time sequence interval can be obtained, and the ring main unit temperature anomaly coefficient concretely comprises the following expression:
in the method, in the process of the invention,is->Ring main unit temperature anomaly coefficients of each time sequence interval; />、/>The integrated voltage abnormality index and the integrated current abnormality index of the nth time sequence interval are respectively; />、/>The first association degree and the second association degree of the voltage data, the current data and the temperature data are respectively.
When the comprehensive voltage abnormality index CVA and the comprehensive current abnormality index CCA based on the time sequence interval are larger, the fluctuation degree of the power supply voltage and the current of the power ring main unit is larger, namely the abnormal conditions of the power supply voltage and the current are more serious, and further, the temperature abnormality degree of the power ring main unit based on the time sequence interval is larger, and the TAC is larger.
And obtaining the temperature anomaly coefficient of the power ring main unit based on the time sequence interval for subsequently improving the anomaly score in the isolated forest algorithm.
And step S003, the ring main unit temperature anomaly coefficient based on the real-time sequence interval is used as a correction coefficient, the anomaly data score in the isolated forest algorithm is improved, and the improved isolated forest algorithm is utilized to obtain the anomaly data score of the real-time power ring main unit temperature data, so that the digital power ring main unit operation state monitoring method is realized.
By means of electricity based on time intervalsThe power ring main unit data (voltage data, current data and temperature data) train the isolated forest, and the number of the isolated trees in the isolated forest is set asBased on each time sequence interval, the samples are characterized by power supply voltage data, power supply current data and temperature data, the optimal tree depth is selected in a K-fold cross verification mode in the training process, and the number of samples extracted each time is +.>Since the K-fold cross validation method and the isolated forest algorithm are known in the art, the description thereof will not be repeated here, in this embodiment +.>，/>The implementation can be set by the user according to the actual situation.
The method comprises the steps of taking a real-time acquired ring main unit temperature anomaly coefficient TAC based on a time sequence interval as a correction coefficient, and improving anomaly data scores in an isolated forest algorithm, wherein the anomaly data scores specifically comprise the following expressions:
obtaining abnormal data scores for the real-time temperature data through an improved isolated forest algorithm; />The temperature anomaly coefficient of the ring main unit based on a time sequence interval (namely a sample in an isolated forest) is acquired in real time; />Obtaining abnormal data obtained from real-time temperature data through an original isolated forest algorithm; norm ()'s return to homeUnifying the function so that the modified abnormal data is scored +.>The value range of (2) is at [0,1]]Is not limited in terms of the range of (a). The greater the ring main unit temperature anomaly coefficient TAC based on time sequence interval is, the improved anomaly data score +.>The closer to 1, the more serious the ring main unit temperature abnormality is.
Obtaining an optimal threshold U of abnormal data scores of all sample data in an isolated forest through an Ojin threshold method, taking real-time power ring main unit temperature data based on a time sequence interval as input of an isolated forest algorithm, obtaining real-time power ring main unit temperature abnormal data scores based on the time sequence interval, and if the abnormal data scores of the corresponding time sequence intervals are larger than or equal to the optimal threshold U, indicating that the temperature abnormal condition of the power ring main unit in the time sequence interval is in a dangerous state, and sending related personnel to close the power ring main unit in time for maintenance; if the abnormal data score of the corresponding time sequence interval is smaller than the optimal threshold U, the abnormal condition of the temperature of the electric power ring main unit in the time sequence interval is in a controllable stage, and the temperature can be regulated and controlled in time through regulating equipment in the electric power ring main unit, so that fire accidents are avoided. The Ojin thresholding method is a known technique, and the present embodiment is not described here in detail.
In summary, the embodiment of the invention solves the problem of difficult operation state monitoring caused by complex influence factors and similar fault characteristics of the power ring main unit, and improves the safety and reliability of the operation state monitoring of the power ring main unit by combining an isolated forest algorithm.
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 (10)
1. The method for monitoring the running state of the digital power ring main unit is characterized by comprising the following steps of:
collecting voltage data, current data and temperature data of the electric ring main unit at each moment;
respectively calculating the association degree of voltage data, current data and temperature data by combining a gray association degree theory; obtaining local deviation amplitude values of the voltage data at each moment according to the mean deviation of the voltage data at each moment; taking the absolute value of the difference value between the voltage data at each moment and the average value of all the voltage data as the local average voltage difference of the voltage data at each moment; obtaining local voltage deviation factors of the voltage data at each moment according to the local deviation amplitude values and the local average voltage difference of the voltage data at each moment; dividing the voltage data into time sequence intervals according to fixed time intervals; combining the region growing algorithm with local voltage deviation factors of the voltage data at each moment to obtain each voltage abnormal cluster of the voltage data in each time sequence interval; obtaining the voltage anomaly distance of the voltage data at each moment according to the relation between the voltage data at each moment and the voltage anomaly cluster; acquiring an average outlier index of each time sequence interval of the voltage data; combining the average outlier index of each time sequence interval with the voltage abnormality distance of the voltage data at each time to obtain the comprehensive voltage abnormality index of each time sequence interval;
acquiring a comprehensive current abnormality index of each time sequence interval by combining current data; combining the comprehensive current abnormality index, the comprehensive voltage abnormality index and the association degree of the voltage data, the current data and the temperature data of each time sequence interval to obtain the ring main unit temperature abnormality coefficient of each time sequence interval; obtaining abnormal data score of a real-time sequence interval by combining an isolated forest algorithm and ring main unit temperature abnormal coefficients of each time sequence interval; and finishing the monitoring of the running state of the electric ring main unit according to the abnormal data score of the real-time sequence interval.
2. The method for monitoring the running state of the digital power ring main unit according to claim 1, wherein the obtaining the local deviation amplitude of the voltage data at each moment according to the mean deviation of the voltage data at each moment comprises:
and calculating the absolute value of the difference between the voltage data at the current moment and the voltage data at the previous moment and the next moment according to the voltage data at each moment, and taking the average value of the absolute values of the two difference values as the local deviation amplitude value of the voltage data at the current moment.
3. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the obtaining the local voltage deviation factor of the voltage data at each time according to the local deviation amplitude and the local average voltage difference of the voltage data at each time comprises:
setting a time neighborhood for the voltage data, and recording the average value of the local deviation amplitude values of the voltage data of all the time before each time without the time neighborhood as the average value of the previous local deviation amplitude values; recording the average value of the local deviation amplitude values of all the time voltage data which do not contain the time neighborhood after each time as a post local deviation amplitude value average value, calculating the ratio of the pre local deviation amplitude value average value to the post local deviation amplitude value average value, taking the local average voltage difference of the time voltage data as an index of an exponential function based on a natural constant, and taking the product of the calculation result of the exponential function and the ratio as a local voltage deviation factor of the time voltage data.
4. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the step of obtaining each voltage anomaly cluster of the voltage data in each time sequence interval by combining the local voltage deviation factor of the voltage data at each time and the region growth algorithm comprises the steps of:
setting a voltage abnormality threshold for each time sequence interval, using a region growing algorithm, wherein an initial seed point is the first voltage data of each time sequence interval, a growing criterion is that a local voltage deviation factor of the voltage data is larger than or equal to the voltage abnormality threshold, a growing cut-off condition is that the local voltage deviation factor of the voltage data is smaller than the voltage abnormality threshold or the voltage data of the time sequence interval is completely traversed, if the voltage data of the time sequence interval is not completely traversed and the local voltage deviation factor of the voltage data is smaller than the voltage abnormality threshold to cause the growth cut-off, the voltage data at the next time of the growth cut-off time is used as a new seed point, and the growing is regrown until all the voltage data of the time sequence interval are completely traversed, and each data set after the growth is used as each voltage abnormality cluster.
5. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the voltage anomaly distance of the voltage data at each moment is obtained according to the relationship between the voltage data at each moment and the voltage anomaly cluster, and the expression is as follows:
in the method, in the process of the invention,is->The voltage abnormality distance at the i-th moment in the time sequence interval; />Representing a set of voltage anomaly clusters,indicate->Voltage data at each time, ">The average value of all voltage data in the voltage abnormal cluster to which the voltage data at the ith moment belongs; />The total number of voltage data in the voltage abnormal cluster to which the ith moment belongs is +.>Indicate->Distance between voltage data at each moment and nearest voltage abnormality cluster in left moment direction, +.>Indicate->Distance between voltage data at each moment and nearest voltage abnormality cluster in right moment direction, +.>Respectively belonging to and not belonging to the symbol.
6. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the step of obtaining the average outlier index of each time sequence interval of the voltage data comprises the steps of:
and obtaining local outlier factors of each voltage data by using an LOF outlier detection algorithm, and taking the average value of the local outlier factors of all the voltage data in each time sequence interval as the average outlier index of each time sequence interval.
7. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the integrated voltage abnormality index of each time sequence interval is obtained by combining the average outlier index of each time sequence interval and the voltage abnormality distance of the voltage data at each time, and the expression is as follows:
in the method, in the process of the invention,is->Comprehensive voltage abnormality indexes of the time sequence intervals; />Is->The total number of voltage abnormal clusters in each time sequence interval; />Is->Maximum value of voltage data in each voltage anomaly cluster, +.>Is->Minimum values of voltage data in the voltage anomaly clusters; />Is->Total time count of each time sequence interval, +.>Is->The voltage abnormality distance at the i-th moment in the time sequence interval; />Is->Average outlier index of each timing interval, +.>Is a natural constant.
8. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the step of obtaining the ring main unit temperature anomaly coefficient of each time sequence interval by combining the comprehensive current anomaly index, the comprehensive voltage anomaly index and the association degree of the voltage data, the current data and the temperature data of each time sequence interval comprises the following steps:
the association degree of the voltage data and the temperature data is marked as a first association degree, the association degree of the current data and the temperature data is marked as a second association degree, the product of the integrated voltage abnormality index and the first association degree is marked as a first product for each time sequence interval, the product of the integrated current abnormality index and the second association degree is marked as a second product, and the sum of the first product and the second product is used as the ring main unit temperature abnormality coefficient of each time sequence interval.
9. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the step of obtaining the abnormal data score of the real-time sequence interval by combining the isolated forest algorithm and the ring main unit temperature abnormal coefficient of each time sequence interval comprises the following steps:
and inputting voltage data, current data and temperature data based on the time sequence interval into an isolated forest algorithm for training, collecting a group of time sequence interval data in real time, calculating the score of the real-time sequence interval data by utilizing the trained isolated forest algorithm, and taking the normalized product of the score and the ring main unit temperature anomaly coefficient of the real-time sequence interval as the anomaly data score of the real-time sequence interval.
10. The method for monitoring the operation state of the digital power ring main unit according to claim 1, wherein the method for monitoring the operation state of the power ring main unit according to the abnormal data score of the real-time sequence interval comprises the following specific steps:
setting an optimal threshold, if the abnormal data score of the real-time sequence interval is greater than or equal to the optimal threshold, operating the electric power ring main unit in a dangerous state, and if the abnormal data score of the real-time sequence interval is less than the threshold, operating the electric power ring main unit in a controllable state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311736193.2A CN117421687B (en) | 2023-12-18 | 2023-12-18 | Method for monitoring running state of digital power ring main unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311736193.2A CN117421687B (en) | 2023-12-18 | 2023-12-18 | Method for monitoring running state of digital power ring main unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117421687A true CN117421687A (en) | 2024-01-19 |
| CN117421687B CN117421687B (en) | 2024-03-15 |
Family
ID=89523374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311736193.2A Active CN117421687B (en) | 2023-12-18 | 2023-12-18 | Method for monitoring running state of digital power ring main unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117421687B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117786371A (en) * | 2024-02-27 | 2024-03-29 | 聊城市检验检测中心 | Temperature monitoring data optimization prediction analysis method and system |
| CN117782364A (en) * | 2024-02-28 | 2024-03-29 | 西瑞思创(西安)实验仪器有限公司 | Real-time monitoring method and system for high-flux automatic material rapid screening reactor |
| CN117828516A (en) * | 2024-03-06 | 2024-04-05 | 湖南大学 | On-site data optimization acquisition system for digital pressure tank production workshop |
| CN117851766A (en) * | 2024-03-08 | 2024-04-09 | 济宁万生环保材料有限公司 | Temperature data monitoring method for DOTP crude ester continuous distillation process |
| CN117851955A (en) * | 2024-03-07 | 2024-04-09 | 辽宁亿金电子有限公司 | Flexible-direct-current capacitor state detection method and system |
| CN117892095A (en) * | 2024-03-14 | 2024-04-16 | 山东泰开电力电子有限公司 | Intelligent detection method for faults of heat dissipation system for energy storage system |
| CN117970168A (en) * | 2024-03-29 | 2024-05-03 | 国网山东省电力公司莱芜供电公司 | High-efficiency processing method for monitoring data of dual-power conversion device |
| CN118067202A (en) * | 2024-04-18 | 2024-05-24 | 深圳市安科讯电子制造有限公司 | Novel intelligent energy storage station electric energy monitoring method |
| CN118100446A (en) * | 2024-04-24 | 2024-05-28 | 国网黑龙江省电力有限公司绥化供电公司 | Intelligent detection method for node running state of power system |
| CN118210273A (en) * | 2024-05-21 | 2024-06-18 | 山东惠硕重工机械有限公司 | Numerical control center anti-collision processing state monitoring method based on data driving |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110243599A (en) * | 2019-07-02 | 2019-09-17 | 西南交通大学 | Multidimensional peels off train EMU axle box bearing temperature anomaly state monitoring method |
| US10509847B1 (en) * | 2019-02-11 | 2019-12-17 | Sas Institute Inc. | Local outlier factor hyperparameter tuning for data outlier detection |
| US20200143292A1 (en) * | 2018-11-01 | 2020-05-07 | General Electric Company | Signature enhancement for deviation measurement-based classification of a detected anomaly in an industrial asset |
| CN112211794A (en) * | 2020-09-02 | 2021-01-12 | 五凌电力有限公司新能源分公司 | Cabin temperature abnormity early warning method, device, equipment and medium of wind turbine generator |
| CN112505549A (en) * | 2020-11-26 | 2021-03-16 | 西安电子科技大学 | New energy automobile battery abnormity detection method based on isolated forest algorithm |
| CN112862760A (en) * | 2021-01-19 | 2021-05-28 | 浙江大学 | Bearing outer ring surface defect area detection method |
| CN114153888A (en) * | 2020-09-08 | 2022-03-08 | 大连理工大学 | Abnormal value detection method and device for time series data |
| CN114609546A (en) * | 2022-03-10 | 2022-06-10 | 东南大学 | Modularized multi-level converter open-circuit fault diagnosis method based on isolated forest |
| CN115792681A (en) * | 2022-03-01 | 2023-03-14 | 浙江凌骁能源科技有限公司 | Single battery consistency detection algorithm based on Internet of vehicles big data platform |
| CN115809405A (en) * | 2022-12-05 | 2023-03-17 | 河北工业大学 | Fan main shaft gear box temperature anomaly detection method based on multi-feature fusion |
| CN116911806A (en) * | 2023-09-11 | 2023-10-20 | 湖北华中电力科技开发有限责任公司 | Internet + based power enterprise energy information management system |
-
2023
- 2023-12-18 CN CN202311736193.2A patent/CN117421687B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200143292A1 (en) * | 2018-11-01 | 2020-05-07 | General Electric Company | Signature enhancement for deviation measurement-based classification of a detected anomaly in an industrial asset |
| US10509847B1 (en) * | 2019-02-11 | 2019-12-17 | Sas Institute Inc. | Local outlier factor hyperparameter tuning for data outlier detection |
| CN110243599A (en) * | 2019-07-02 | 2019-09-17 | 西南交通大学 | Multidimensional peels off train EMU axle box bearing temperature anomaly state monitoring method |
| CN112211794A (en) * | 2020-09-02 | 2021-01-12 | 五凌电力有限公司新能源分公司 | Cabin temperature abnormity early warning method, device, equipment and medium of wind turbine generator |
| CN114153888A (en) * | 2020-09-08 | 2022-03-08 | 大连理工大学 | Abnormal value detection method and device for time series data |
| CN112505549A (en) * | 2020-11-26 | 2021-03-16 | 西安电子科技大学 | New energy automobile battery abnormity detection method based on isolated forest algorithm |
| CN112862760A (en) * | 2021-01-19 | 2021-05-28 | 浙江大学 | Bearing outer ring surface defect area detection method |
| CN115792681A (en) * | 2022-03-01 | 2023-03-14 | 浙江凌骁能源科技有限公司 | Single battery consistency detection algorithm based on Internet of vehicles big data platform |
| CN114609546A (en) * | 2022-03-10 | 2022-06-10 | 东南大学 | Modularized multi-level converter open-circuit fault diagnosis method based on isolated forest |
| CN115809405A (en) * | 2022-12-05 | 2023-03-17 | 河北工业大学 | Fan main shaft gear box temperature anomaly detection method based on multi-feature fusion |
| CN116911806A (en) * | 2023-09-11 | 2023-10-20 | 湖北华中电力科技开发有限责任公司 | Internet + based power enterprise energy information management system |
Non-Patent Citations (2)
| Title |
|---|
| JING LUO 等: "Detection of abnormal power consumption patterns of power users based on machine learning", 《2022 IEEE 5TH ADVANCED INFORMATION MANAGEMENT, COMMUNICATES, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IMCEC)》, 18 December 2022 (2022-12-18), pages 679 - 683, XP034282404, DOI: 10.1109/IMCEC55388.2022.10019957 * |
| 向绍斌 等: "基于孤立森林算法与大数据挖掘的配电网故障 距离估计方法", 《电气工程学报》, vol. 17, no. 1, 31 March 2022 (2022-03-31), pages 179 - 185 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117786371A (en) * | 2024-02-27 | 2024-03-29 | 聊城市检验检测中心 | Temperature monitoring data optimization prediction analysis method and system |
| CN117786371B (en) * | 2024-02-27 | 2024-05-10 | 聊城市检验检测中心 | Temperature monitoring data optimization prediction analysis method and system |
| CN117782364B (en) * | 2024-02-28 | 2024-05-03 | 西瑞思创(西安)实验仪器有限公司 | Real-time monitoring method and system for high-flux automatic material rapid screening reactor |
| CN117782364A (en) * | 2024-02-28 | 2024-03-29 | 西瑞思创(西安)实验仪器有限公司 | Real-time monitoring method and system for high-flux automatic material rapid screening reactor |
| CN117828516A (en) * | 2024-03-06 | 2024-04-05 | 湖南大学 | On-site data optimization acquisition system for digital pressure tank production workshop |
| CN117828516B (en) * | 2024-03-06 | 2024-05-24 | 湖南大学 | On-site data optimization acquisition system for digital pressure tank production workshop |
| CN117851955A (en) * | 2024-03-07 | 2024-04-09 | 辽宁亿金电子有限公司 | Flexible-direct-current capacitor state detection method and system |
| 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 |
| CN117851766A (en) * | 2024-03-08 | 2024-04-09 | 济宁万生环保材料有限公司 | Temperature data monitoring method for DOTP crude ester continuous distillation process |
| CN117892095A (en) * | 2024-03-14 | 2024-04-16 | 山东泰开电力电子有限公司 | Intelligent detection method for faults of heat dissipation system for energy storage system |
| CN117892095B (en) * | 2024-03-14 | 2024-05-28 | 山东泰开电力电子有限公司 | Intelligent detection method for faults of heat dissipation system for energy storage system |
| CN117970168A (en) * | 2024-03-29 | 2024-05-03 | 国网山东省电力公司莱芜供电公司 | High-efficiency processing method for monitoring data of dual-power conversion device |
| CN117970168B (en) * | 2024-03-29 | 2024-05-28 | 国网山东省电力公司莱芜供电公司 | High-efficiency processing method for monitoring data of dual-power conversion device |
| CN118067202A (en) * | 2024-04-18 | 2024-05-24 | 深圳市安科讯电子制造有限公司 | Novel intelligent energy storage station electric energy monitoring method |
| CN118067202B (en) * | 2024-04-18 | 2024-07-02 | 深圳市安科讯电子制造有限公司 | Novel intelligent energy storage station electric energy monitoring method |
| CN118100446A (en) * | 2024-04-24 | 2024-05-28 | 国网黑龙江省电力有限公司绥化供电公司 | Intelligent detection method for node running state of power system |
| CN118210273A (en) * | 2024-05-21 | 2024-06-18 | 山东惠硕重工机械有限公司 | Numerical control center anti-collision processing state monitoring method based on data driving |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117421687B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117421687B (en) | Method for monitoring running state of digital power ring main unit | |
| CN117093879B (en) | Intelligent operation management method and system for data center | |
| CN108320043B (en) | Power distribution network equipment state diagnosis and prediction method based on electric power big data | |
| CN109598451B (en) | Non-invasive load identification method based on PCA (principal component analysis) and LSTM (least Square TM) neural network | |
| CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
| CN103617568B (en) | Setting method for abnormal data determination threshold in steady-state power quality early-warning mechanism | |
| CN109491339B (en) | Big data-based substation equipment running state early warning system | |
| CN117332215B (en) | High-low voltage power distribution cabinet abnormal fault information remote monitoring system | |
| CN110969306A (en) | Power distribution low-voltage distribution area load prediction method and device based on deep learning | |
| CN110766313A (en) | Cable tunnel comprehensive state evaluation method based on operation and maintenance system | |
| CN106845711A (en) | Processing method and processing device for power supply reliability data | |
| CN112001644A (en) | Power distribution network operation reliability detection method, device, terminal and storage medium | |
| CN115907461A (en) | Electric power engineering method based on mechanism derivation equation | |
| CN114626487A (en) | Line-variable relation checking method based on random forest classification algorithm | |
| CN103928923B (en) | A kind of network stationary power quality method for early warning based on sensitivity analysis | |
| CN109784777B (en) | Power grid equipment state evaluation method based on time sequence information fragment cloud similarity measurement | |
| CN114782214A (en) | Safety load identification method based on coal-to-electricity power consumption data | |
| CN114861969A (en) | LSTM-based electric power system oscillation risk prediction method | |
| CN114358160A (en) | Data anomaly detection method in power system | |
| CN115224684A (en) | Intelligent power distribution network risk state identification method and system based on immune hazard theory | |
| Wei et al. | Research on transmission line trip prediction based on logistic regression algorithm under icing condition | |
| CN117171548B (en) | Intelligent network security situation prediction method based on power grid big data | |
| Lingang et al. | Research on integrated calculation method of theoretical line loss of MV and LV distribution Network based on Adaboost integrated learning | |
| CN116796213B (en) | Power distribution network line transformation relation identification method based on clustering algorithm | |
| Zhengganzhe et al. | Risk forecast assessment of transmission line capacity increase under cyberattacks |
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 |