CN116593829B - Transmission line hidden danger on-line monitoring system based on data analysis - Google Patents
Transmission line hidden danger on-line monitoring system based on data analysis Download PDFInfo
- Publication number
- CN116593829B CN116593829B CN202310868603.2A CN202310868603A CN116593829B CN 116593829 B CN116593829 B CN 116593829B CN 202310868603 A CN202310868603 A CN 202310868603A CN 116593829 B CN116593829 B CN 116593829B
- Authority
- CN
- China
- Prior art keywords
- component
- period
- imf
- current signal
- imf component
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 238000007405 data analysis Methods 0.000 title claims abstract description 11
- 238000005070 sampling Methods 0.000 claims abstract description 55
- 238000000034 method Methods 0.000 claims abstract description 30
- 239000004480 active ingredient Substances 0.000 claims abstract description 14
- 238000000354 decomposition reaction Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 8
- 239000005414 inactive ingredient Substances 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000750 progressive effect Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 229940029329 intrinsic factor Drugs 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013024 troubleshooting 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
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- 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
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to the technical field of data processing, and provides a hidden danger online monitoring system of a power transmission line based on data analysis, which comprises the following components: acquiring historical current data and real-time current data; decomposing the historical current data to obtain an IMF component; obtaining the strong effective component possibility of each period in the component according to the current signal values of the sampling points and the adjacent sampling points in the component period; acquiring the possibility of invalid components of each period of each component according to the fluctuation degree current signal value distribution characteristics of the current signal value in each period of each component; identifying each component of each cycle based on the strong active ingredient likelihood and the inactive ingredient likelihood; acquiring contribution ratio of the invalid component and the strong effective component according to the components of the strong effective component and the invalid component; and judging faults according to the faults, and completing online fault monitoring by combining real-time current data. The invention recognizes normal components with obvious characteristics, so that the whole calculation process is simple and the recognition effect is accurate.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an on-line monitoring system for hidden danger of a power transmission line based on data analysis.
Background
The modern society has increasingly increased demand for electric power, and the environment where the electric transmission line is located is complex, and during electric power transmission, because of the influence of some environmental factors (insulator pollution, hardware floating discharge, etc.) and natural factors (wind, snow and lightning weather), there are some potential safety hazards (such as partial discharge) on the electric transmission line, and these potential safety hazards often cause greater loss after being unable to be timely processed, so the electric transmission line needs to be monitored to reduce the generation of potential safety hazards. In the prior art, the hidden trouble of the line is usually detected, but the transient trouble is usually difficult to detect because of a long fault period, and the transient trouble detection method such as traveling wave monitoring is not good. Therefore, the invention provides an on-line monitoring system for hidden danger of a power transmission line based on data analysis, which is characterized in that current signals of the power transmission line are collected, then the collected current signals are decomposed, components in the current signals are defined, and normal components in the current signals are utilized to conduct troubleshooting.
Disclosure of Invention
The invention provides an on-line monitoring system for hidden danger of a power transmission line based on data analysis, which aims to solve the problem that gradual faults have a longer fault period, so that investigation is difficult, and adopts the following technical scheme:
the embodiment of the invention provides a power transmission line hidden danger online monitoring system based on data analysis, which comprises the following modules:
the data acquisition module acquires historical current data and real-time current data;
the current data decomposition module is used for decomposing the acquired historical current data to acquire an IMF component;
the strong effective component possibility acquisition module acquires the current signal value of each sampling point of the IMF component, and acquires the strong effective component possibility of each period in each IMF component according to the current signal values of the sampling points and adjacent sampling points in each period of the IMF component;
the component identification module is used for acquiring the possibility of invalid components of each period of each IMF component according to the fluctuation degree of the current signal value in each period of each IMF component and the distribution characteristics of different current signal values; identifying each IMF component of each period according to the strong effective component possibility and the ineffective component possibility of each period in each IMF component to obtain an IMF component of the strong effective component and an IMF component of the ineffective component;
the on-line monitoring module is used for acquiring contribution ratio of the invalid component and the strong effective component according to the IMF component of the strong effective component and the IMF component of the invalid component in each period; and judging fault current data and fault-free current data in the historical current data according to the obtained contribution ratio, and completing online fault monitoring of the power transmission line according to the real-time current data, the fault current data and the fault-free current data in the historical current data.
Preferably, the method for decomposing the acquired historical current data to acquire the IMF component includes:
and obtaining a plurality of IMF components by using empirical mode decomposition according to the number of historical current data periods, wherein each sampling point in each IMF component corresponds to a current signal value.
Preferably, the method for obtaining the probability of the strong active ingredient of each period in each IMF component according to the current signal values of the sampling point and the adjacent sampling point in each period of the IMF component comprises the following steps:
;
;
in the method, in the process of the invention,a current signal value representing an mth sampling point of an nth period of the ith IMF component,a current signal value representing the m-1 st sample point of the nth period of the ith IMF component,current signal value of (m+1) th sampling point representing the nth period of the ith IMF component, +.>Local change rate of the mth sampling point representing the nth period of the ith IMF component, +.>Representing the number of sampling points in the nth period of the ith IMF component, +.>Represents an exponential function based on natural constants, < ->Representing a strong active ingredient likelihood for the nth period of the ith IMF component.
Preferably, the method for obtaining the probability of the invalid component of each period of each IMF component according to the fluctuation degree of the current signal value in each period of each IMF component and the distribution characteristics of different current signal values comprises the following steps:
for each period of each IMF component, acquiring a current signal value of each sampling point, acquiring the occurrence number of each current signal value in the period, taking the ratio of the occurrence number to the number of all sampling points in the period as the occurrence probability of the current signal value, calculating the variance of the current signal values of all sampling points in each period as the fluctuation degree of the current signal value, and acquiring the possibility of invalid components of each period of each IMF component according to the fluctuation degree of the current signal value in each period and the occurrence probability of each current signal value in each IMF component.
Preferably, the method for obtaining the probability of invalid components in each period of each IMF component according to the fluctuation degree of the current signal value in each period and the occurrence probability of each current signal value in each IMF component comprises the following steps:
;
in the method, in the process of the invention,a current signal value representing an mth sampling point of an nth period of the ith IMF component,representing the mean value of the current signal values of all sampling points in the nth period of the ith IMF component,/->Representing the number of sampling points in the nth period of the ith IMF component, +.>Mth of nth period representing ith IMF componentThe probability of occurrence of the current signal value for each sample point, and (2)>The degree of fluctuation of the current signal value is shown,representing a linear normalization function, ++>Indicating the likelihood of invalid components for the nth period of the ith IMF component.
Preferably, the method for obtaining the contribution ratio of the invalid component to the strong effective component according to the IMF component of the strong effective component and the IMF component of the invalid component in each period comprises the following steps:
according to the number of IMF components which are strong effective components and IMF components which are ineffective components in each period, current signal contribution rates of IMF components corresponding to the strong effective components and current signal contribution rates of IMF components corresponding to the ineffective components are obtained, current signal rates corresponding to the IMF components of the strong effective components and the IMF components of the ineffective components are accumulated and recorded as first characteristics, the current signal contribution rates of the IMF components in each period are accumulated to obtain second characteristics, and the ratio of the first characteristics to the second characteristics is used as the contribution rate ratio of the ineffective components to the strong effective components.
The beneficial effects of the invention are as follows: according to the method, EMD decomposition is carried out on the current signal of the power transmission line, normal components with obvious characteristics are identified, then the current of the power transmission line is analyzed by the normal components to identify gradual faults of the power transmission line, and the method is simple in overall calculation process and accurate in identification effect because the normal components with obvious characteristics are identified.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of an online monitoring system for hidden danger of a power transmission line based on data analysis according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of an online monitoring system for hidden danger of a power transmission line based on data analysis according to an embodiment of the present invention is shown, where the system includes: the device comprises a data acquisition module, a current data decomposition module, a strong effective component possibility acquisition module, a component identification module and an online monitoring module.
The data acquisition module acquires current data of the power transmission line in real time by using a current sensor, wherein the acquired current data exists in a signal form, and the current data acquired by using the current sensor in the past is used as historical current data, wherein each sampling point acquires one current data, and the value of each sampling point is a current signal value. In the embodiment, the fault monitoring of the power transmission line is realized by performing model calculation according to the historical current data in the historical current set.
Thus, historical current data and real-time current data are obtained.
The current data decomposition module is used for dividing the general faults into two cases in fault monitoring of the power transmission line, wherein the first case is an instantaneous fault and the second case is a gradual fault, and when the instantaneous fault is detected, the current data in the circuit has larger fluctuation, so that the current data can be easily identified. However, for the progressive fault, since the fault has a long duration and the corresponding current data is slightly different from the normal current data within the duration, the fault identification of the power transmission line cannot be effectively identified. Therefore, the present embodiment first decomposes all the historical current data of the transmission line.
Specifically, since the historical current data of the power transmission line has periodicity, in an ideal state, the historical current data completely accords with the periodicity, wherein the period size of the historical current data is known, and the historical current data is obtained through the current input end of the current power transmission line. However, in an actual power transmission line, current data is relatively complex and is affected by various factors, so that the calculation amount is relatively large when the historical current data is subjected to overall analysis, the historical current data is subjected to adaptive decomposition by using empirical mode decomposition of a signal decomposition algorithm, the number of periods of the historical current data is obtained according to the period size of the power transmission line, a plurality of IMF components are obtained according to the number of periods of the historical current data, each obtained IMF component contains a part of current data, data points in the IMF components are identical to the historical current data, and the analysis of the IMF components is relatively simple compared with the overall analysis of the historical current data. The empirical mode decomposition is known in the art, and will not be described in detail herein.
So far, according to the periodicity of the historical current data, decomposition is carried out to obtain a plurality of IMF components.
The strong effective component possibility acquisition module is used for distinguishing different composition components of the historical current data when the historical current data is subjected to fault monitoring, and distinguishing the current data in a single period into an effective component and an ineffective component, wherein the effective component comprises a strong effective component of a fundamental wave and inherent factors, the inherent factors are current signal values of sampling points, and the effective component also comprises a weak effective component which possibly contains inter-harmonic waves, traveling waves and the like and represents fault waveform factors of a power transmission line, and the ineffective component mainly comprises noise factors. Both the strong and the ineffective components have distinct characteristics, whereas the weak effective components are less distinct due to the long periodicity of the progressive failure.
The intrinsic factor of the current data in the strong active component is generally and similarly, while the noise in the inactive component is very characteristic of being identified by randomness, and is basically disordered and random. Therefore, a fault monitoring model of the power transmission line is established for the analysis of the strong effective components and the ineffective components of each IMF component after the empirical mode decomposition. First, the strong active ingredient was analyzed.
Specifically, for the current data difference between all sampling points in each IMF component and the adjacent sampling points, the probability of obtaining a strong effective component in each period in each IMF component is as follows:
;
;
in the method, in the process of the invention,a current signal value representing an mth sampling point of an nth period of the ith IMF component,a current signal value representing the m-1 st sample point of the nth period of the ith IMF component,current signal value of (m+1) th sampling point representing the nth period of the ith IMF component, +.>Local change rate of the mth sampling point representing the nth period of the ith IMF component, +.>Representing the number of sampling points in the nth period of the ith IMF component, +.>Represents an exponential function based on natural constants, < ->Representing a strong active ingredient likelihood for the nth period of the ith IMF component.
For strong effectiveness Cheng Fenlai, the change of the current data values of two adjacent sampling points is regular, that is, the local change rate of each sampling point and the adjacent sampling points should be relatively close, so the embodiment analyzes by quantifying the local change rate of all sampling points in each period of each IMF component, determines whether the IMF component has higher similarity of local change rate according to the local change rate, and the higher the similarity of the local change rate, the higher the corresponding strong effective component probability. The similarity of the local change rates is that deviation calculation is carried out through the local change rate of each sampling point and the average value of the local change rates of all sampling points, and then accumulation is carried out, and the larger the value is, the lower the similarity of the local change rates is, and the greater the probability of strong effective components is.
To this end, the strong effective component probability for each cycle in each IMF component is obtained.
The component identifying module is used for identifying invalid components in each period of each IMF component after analyzing strong effective components, because in normal current data, the current signal values corresponding to each sampling point in one period are independent, namely the number of occurrences of the same current signal value is less, but the signal values corresponding to noise are more complex, and the distribution intervals are the same, so that more repeated signal values can occur, besides, the signal values corresponding to noise are very random, therefore, the probability of occurrence of the current signal value of each sampling point in the period and the variance of all the current signal values in the period are obtained, and the probability of the invalid components of each component in each period is obtained according to the probability and the variance of the current signal values in the period, and the formula is as follows:
;
in the method, in the process of the invention,a current signal value representing an mth sampling point of an nth period of the ith IMF component,representing the mean value of the current signal values of all sampling points in the nth period of the ith IMF component,/->Representing the number of sampling points in the nth period of the ith IMF component, +.>Representing the probability of occurrence of the current signal value of the mth sample point of the nth period of the ith IMF component,/->Representing a linear normalization function, ++>Indicating the likelihood of invalid components for the nth period of the ith IMF component.
Wherein,,the variance of the current signal value is shown, and the probability of whether or not the IMF component is an invalid component is calculated using the variance as a weight value, and a larger value indicates that there are more repeated signal values in the IMF component and that the disturbance is disordered, so that the probability of noise is higher, and therefore the probability of an invalid component is higher.
Identifying IMF component according to obtained invalid component probability and strong effective component probability, and setting judgment threshold valueIn this embodiment let +.>Because the local change of the strong effective component is regular and the overall distribution of the ineffective component is irregular, the method is suitable forThe two values obtained for each IMF are not both large at the same time, so in this embodiment, if +.>Then the nth period of the ith IMF component is described as the component of the strong active ingredient if +.>Then the nth cycle of the ith IMF component is described as the component of the inactive ingredient, and neither is satisfied as the component of the weak active ingredient.
Thus, component identification for each cycle is completed, and component division of each IMF component for each cycle is completed.
The on-line monitoring module completes the identification of the strong effective component and the ineffective component of the IMF component in each period according to the operation, and the contribution rates of all IMF components to the current data are different for the current data collected at the beginning, but the sum of the contribution rates of all IMF components to the current data is constant, so the embodiment obtains the duty ratio of the strong effective component and the ineffective component through the duty ratio of the contribution rates of the strong effective component and the ineffective component to the current data.
Specifically, for each period, a plurality of IMF components are provided, and the contribution rate of the IMF component corresponding to the strong effective component and the contribution rate of the IMF component corresponding to the ineffective component in each period are obtained according to the IMF component of the strong effective component and the IMF component of the ineffective component corresponding to each period, wherein the calculation mode of the contribution rate is the existing calculation, the calculation method of the variance contribution rate of the IMF is obtained, and details are omitted herein, and based on the calculation method, the contribution rate ratio of the ineffective component and the strong effective component is obtained, and the formula is as follows:
;
in the method, in the process of the invention,representing the current signal contribution rate of the IMF component corresponding to the jth strong active ingredient to the nth period,/for the jth period>Indicate->IMF component corresponding to the invalid component for +.>Contribution rate of the current signal of each cycle, +.>Indicate->The IMF component is for the->Contribution rate of the current signal of each cycle, +.>Indicate->The number of IMF components of the strong active ingredient present in a cycle, < >>Indicate->Number of IMF components of inactive ingredient present in each cycle,/->Represent the firstNumber of IMF components in each period, +.>Expressed +.>Strong active ingredient and inactive ingredient in one cycleThe contribution ratio of (2).
For the firstSince it is difficult to directly detect faults by current data and to satisfy the conditions of on-line monitoring, the present embodiment monitors the strong active ingredient and the inactive ingredient which are more obvious, and then monitors faults by using the contribution ratio of the strong active ingredient and the inactive ingredient in the total current>The greater the duty ratio in the current data of each cycle, the less likely a fault will occur in that cycle, whereas the conversely, a given fault threshold will indicate that no fault has occurred if the duty ratio is greater than the fault threshold, and that a fault has occurred if the duty ratio is less than the fault threshold, which in this embodiment is set to 0.4.
After the historical current data is detected, fault current data in the historical current data are obtained, at the moment, a neural network is used for training the current data, a current signal value of the current data is input and output as a fault value, the current data with faults are marked as 1 during training, no-fault current data are marked as 0 for training, and a loss function of the neural network is a mean square error loss function. And after the network training is finished, inputting the real-time current data to judge whether the real-time current data is obtained by faults. Thereby completing the online fault monitoring of the power transmission line. The neural network used in this embodiment is an LSTM network, which is a known technology, and the network structure and specific training process are not described in detail in this embodiment.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (2)
1. The power transmission line hidden danger on-line monitoring system based on data analysis is characterized by comprising the following modules:
the data acquisition module acquires historical current data and real-time current data;
the current data decomposition module is used for decomposing the acquired historical current data to acquire an IMF component;
the strong effective component possibility acquisition module acquires the current signal value of each sampling point of the IMF component, and acquires the strong effective component possibility of each period in each IMF component according to the current signal values of the sampling points and adjacent sampling points in each period of the IMF component;
the component identification module is used for acquiring the possibility of invalid components of each period of each IMF component according to the fluctuation degree of the current signal value in each period of each IMF component and the distribution characteristics of different current signal values; identifying each IMF component of each period according to the strong effective component possibility and the ineffective component possibility of each period in each IMF component to obtain an IMF component of the strong effective component and an IMF component of the ineffective component;
the on-line monitoring module is used for acquiring contribution ratio of the invalid component and the strong effective component according to the IMF component of the strong effective component and the IMF component of the invalid component in each period; judging fault current data and fault-free current data in the historical current data according to the obtained contribution ratio, and completing online fault monitoring on the power transmission line according to the real-time current data, the fault current data and the fault-free current data in the historical current data;
the method for obtaining the probability of the strong effective component of each period in each IMF component according to the current signal values of the sampling points and the adjacent sampling points in each period of the IMF component comprises the following steps:
;
in the method, in the process of the invention,electric representing the mth sampling point of the nth period of the ith IMF componentThe value of the stream signal is set,current signal value of (m-1) th sampling point representing the nth period of the ith IMF component, +.>Current signal value of (m+1) th sampling point representing the nth period of the ith IMF component, +.>Local change rate of the mth sampling point representing the nth period of the ith IMF component, +.>Representing the number of sampling points in the nth period of the ith IMF component, +.>Represents an exponential function based on natural constants, < ->A strong active ingredient likelihood representing the nth period of the ith IMF component;
the method for acquiring the probability of invalid components of each period of each IMF component according to the fluctuation degree of the current signal value in each period of each IMF component and the distribution characteristics of different current signal values comprises the following steps:
for each period of each IMF component, acquiring a current signal value of each sampling point, acquiring the occurrence number of each current signal value in the period, taking the ratio of the occurrence number to the number of all sampling points in the period as the occurrence probability of the current signal value, calculating the variance of the current signal values of all sampling points in each period as the fluctuation degree of the current signal value, and acquiring the possibility of invalid components of each period of each IMF component according to the fluctuation degree of the current signal value in each period and the occurrence probability of each current signal value in each IMF component;
the method for acquiring the probability of invalid components of each period of each IMF component according to the fluctuation degree of the current signal value of each period and the occurrence probability of each current signal value in each IMF component comprises the following steps:
;
in the method, in the process of the invention,current signal value of mth sampling point representing nth period of ith IMF component, +.>Representing the mean value of the current signal values of all sampling points in the nth period of the ith IMF component,/->Representing the number of sampling points in the nth period of the ith IMF component, +.>Representing the probability of occurrence of the current signal value of the mth sample point of the nth period of the ith IMF component,/->Indicating the degree of fluctuation of the current signal value, < >>Representing a linear normalization function, ++>An invalid component probability representing an nth period of an ith IMF component;
the method for acquiring the contribution ratio of the invalid component and the strong effective component according to the IMF component of the strong effective component and the IMF component of the invalid component in each period comprises the following steps:
acquiring current signal contribution rates of IMF components corresponding to strong effective components and current signal contribution rates of IMF components corresponding to ineffective components according to the number of IMF components serving as strong effective components and IMF components serving as ineffective components in each period, accumulating the current signal rates corresponding to the IMF components of the strong effective components and the ineffective components to be marked as first characteristics, accumulating the current signal contribution rates of each IMF component in the period to obtain second characteristics, and enabling the ratio of the first characteristics to the second characteristics to be used as the contribution rate ratio of the ineffective components to the strong effective components;
identifying each IMF component of each cycle based on the strong active component likelihood and the inactive component likelihood of each cycle in each IMF component to obtain an IMF component of the strong active component and an IMF component of the inactive component includes:
setting a judgment thresholdIf->The nth period of the ith IMF component is the IMF component of the strong active ingredient, if +.>The nth period of the ith IMF component is the IMF component of the invalid component.
2. The online monitoring system for hidden danger of power transmission line based on data analysis of claim 1, wherein the method for decomposing the acquired historical current data to acquire IMF component comprises:
and obtaining a plurality of IMF components by using empirical mode decomposition according to the number of historical current data periods, wherein each sampling point in each IMF component corresponds to a current signal value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310868603.2A CN116593829B (en) | 2023-07-17 | 2023-07-17 | Transmission line hidden danger on-line monitoring system based on data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310868603.2A CN116593829B (en) | 2023-07-17 | 2023-07-17 | Transmission line hidden danger on-line monitoring system based on data analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116593829A CN116593829A (en) | 2023-08-15 |
CN116593829B true CN116593829B (en) | 2023-10-20 |
Family
ID=87601226
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310868603.2A Active CN116593829B (en) | 2023-07-17 | 2023-07-17 | Transmission line hidden danger on-line monitoring system based on data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116593829B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117554681B (en) * | 2024-01-08 | 2024-03-22 | 银河航天(西安)科技有限公司 | Power monitoring method and device applied to satellite and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1227599A2 (en) * | 2000-12-20 | 2002-07-31 | Ascom Energy Systems AG | Method for data transmission over AC power line network |
CN101551433A (en) * | 2009-05-05 | 2009-10-07 | 昆明理工大学 | Distribution network feed out circuit fault circuit selection method by using HHT detection technology |
CN102129010A (en) * | 2011-01-12 | 2011-07-20 | 云南电网公司楚雄供电局 | Fault line selection method of distribution network based on empirical mode decomposition (EMD) |
CN103956756A (en) * | 2014-05-23 | 2014-07-30 | 福州大学 | Electric system low-frequency oscillating mode identification method |
EP3460496A1 (en) * | 2017-09-26 | 2019-03-27 | Siemens Aktiengesellschaft | A method and apparatus for automatic localization of a fault |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112731051B (en) * | 2020-12-18 | 2021-10-08 | 武汉大学 | Single-ended fault positioning method and system for high-voltage direct-current transmission line of hybrid network |
-
2023
- 2023-07-17 CN CN202310868603.2A patent/CN116593829B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1227599A2 (en) * | 2000-12-20 | 2002-07-31 | Ascom Energy Systems AG | Method for data transmission over AC power line network |
CN101551433A (en) * | 2009-05-05 | 2009-10-07 | 昆明理工大学 | Distribution network feed out circuit fault circuit selection method by using HHT detection technology |
CN102129010A (en) * | 2011-01-12 | 2011-07-20 | 云南电网公司楚雄供电局 | Fault line selection method of distribution network based on empirical mode decomposition (EMD) |
CN103956756A (en) * | 2014-05-23 | 2014-07-30 | 福州大学 | Electric system low-frequency oscillating mode identification method |
EP3460496A1 (en) * | 2017-09-26 | 2019-03-27 | Siemens Aktiengesellschaft | A method and apparatus for automatic localization of a fault |
Non-Patent Citations (1)
Title |
---|
基于EMD⁃XGBoost 模型的交流输电线路可听噪声有效数据预测方法研究;李振华 等;高压电器;第59卷(第6期);180-187 * |
Also Published As
Publication number | Publication date |
---|---|
CN116593829A (en) | 2023-08-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108802525A (en) | Equipment fault intelligent Forecasting based on small sample | |
CN116593829B (en) | Transmission line hidden danger on-line monitoring system based on data analysis | |
CN109029959B (en) | Method for detecting mechanical state of transformer winding | |
CN108802535B (en) | Screening method, main interference source identification method and device, server and storage medium | |
CN110259648B (en) | Fan blade fault diagnosis method based on optimized K-means clustering | |
CN112505500B (en) | Partial discharge severity evaluation method based on ultrahigh frequency detection mode | |
CN112417763A (en) | Defect diagnosis method, device and equipment for power transmission line and storage medium | |
CN108594156B (en) | Improved current transformer saturation characteristic identification method | |
CN108333443B (en) | Method for alarming intermittent defects of power equipment | |
CN117194171A (en) | Heterogeneous cloud resource panoramic anomaly detection system | |
CN117172601A (en) | Non-invasive load monitoring method based on residual total convolution neural network | |
CN117074852A (en) | Power distribution network electric energy monitoring and early warning management method and system | |
CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
CN116502043A (en) | Finish rolling motor state analysis method based on isolated forest algorithm | |
Peter et al. | Wind turbine generator prognostics using field SCADA data | |
CN114689321A (en) | Bearing fault diagnosis method and device for wind generating set and electronic equipment | |
CN115326393A (en) | Wind turbine generator bearing pair fault diagnosis method based on temperature information | |
CN114372047A (en) | Wind turbine generator system wind speed sensing abnormal data identification method based on speed correlation constraint | |
CN112820090A (en) | Alarm system based on big data and implementation method thereof | |
CN113218653A (en) | Offshore wind power gear box monitoring method and device based on low-frequency disturbance elimination | |
CN115834364B (en) | Power consumption information monitoring system and method based on power big data | |
CN117894317B (en) | Box-type transformer on-line monitoring method and system based on voiceprint analysis | |
CN109102001A (en) | A kind of gene improve the rotor on-line fault diagnosis method of neural network | |
CN115711206B (en) | Wind driven generator blade icing state monitoring system based on clustering weight | |
CN112327216B (en) | Cable health state assessment device and method based on edge calculation |
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 |