CN116660669B - Power equipment fault on-line monitoring system and method - Google Patents
Power equipment fault on-line monitoring system and method Download PDFInfo
- Publication number
- CN116660669B CN116660669B CN202310925117.XA CN202310925117A CN116660669B CN 116660669 B CN116660669 B CN 116660669B CN 202310925117 A CN202310925117 A CN 202310925117A CN 116660669 B CN116660669 B CN 116660669B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- fault
- abnormal
- line
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 241
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000002159 abnormal effect Effects 0.000 claims abstract description 176
- 238000004458 analytical method Methods 0.000 claims abstract description 71
- 238000012806 monitoring device Methods 0.000 claims abstract description 54
- 238000007405 data analysis Methods 0.000 claims abstract description 18
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 230000005540 biological transmission Effects 0.000 claims description 58
- 230000009467 reduction Effects 0.000 claims description 43
- 238000001514 detection method Methods 0.000 claims description 26
- 238000011156 evaluation Methods 0.000 claims description 22
- 230000005856 abnormality Effects 0.000 claims description 21
- 238000013210 evaluation model Methods 0.000 claims description 11
- 230000035772 mutation Effects 0.000 claims description 5
- 238000010223 real-time analysis Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 abstract description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 22
- 238000012549 training Methods 0.000 description 15
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000010301 surface-oxidation reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses an on-line monitoring system and method for power equipment faults, belongs to the technical field of power equipment fault monitoring, and solves the problems of inaccuracy and hysteresis of fault monitoring. The monitoring system comprises a data acquisition module, an equipment data analysis module and a fault monitoring module; the data acquisition module is used for acquiring data of each target monitoring device to obtain monitoring data corresponding to each target monitoring device; the monitoring data comprises single data of each monitoring item; the device data analysis module is used for analyzing the monitoring data of each target monitoring device in real time and identifying the corresponding abnormal data. The monitoring method comprises the steps of determining target monitoring equipment, integrating monitoring data, obtaining abnormal data and transmitting the abnormal data to a fault monitoring module. The invention can perform data acquisition, anomaly identification, fault analysis and positioning on various target monitoring devices, and improves the accuracy, sensitivity and reliability of the power equipment fault on-line monitoring technology.
Description
Technical Field
The invention belongs to the technical field of power equipment fault monitoring, and particularly relates to an on-line power equipment fault monitoring system and method.
Background
The problems of surface oxidation corrosion, loosening of fastening bolts, aging of the joints of the contacts and the bus and the like often occur in the long-term operation process of the power equipment, so that the equipment is overheated and even serious accidents occur; power equipment is an important component in an electrical power system, and its operating state directly affects the safety, stability and economy of the electrical power system.
At present, the fault monitoring technology of the power equipment mainly comprises two modes: off-line monitoring and on-line monitoring. The off-line monitoring is detection under the condition of power equipment outage or power failure, and has the advantages of accurate and reliable detection results, but has the disadvantages of failure finding in time and affecting the operation efficiency and service life of the power equipment. The on-line monitoring is detection under the condition of normal operation or load of the power equipment, and has the advantages of reflecting the operation state of the power equipment in real time and finding out faults and hidden dangers in time, but has the defects that the detection result is influenced by various interference factors, and the fault type and the fault position are difficult to accurately judge.
Aiming at the above situation, the following problems are needed to be solved on the basis of the prior art:
(1) In the electric power field, fault monitoring needs to be performed on various electric power equipment, and the running state of each electric power equipment is known in time.
(2) The power plant monitoring system has hysteresis for fault monitoring.
(3) Some equipment may have some intermittent anomaly information before it has obvious fault characteristics, but these discontinuous anomaly information are not fully utilized.
(4) The accuracy, sensitivity and reliability of the power equipment fault on-line monitoring technology are improved.
Disclosure of Invention
The invention aims to provide a power equipment fault on-line monitoring system and a method, which can perform data acquisition, abnormality identification, fault analysis and positioning on various target monitoring equipment and push abnormal data to a monitoring early-warning terminal, so that the accuracy, sensitivity and reliability of a power equipment fault on-line monitoring technology are improved.
The aim of the invention can be achieved by the following technical scheme:
the power equipment fault on-line monitoring system comprises a data acquisition module, an equipment data analysis module, a fault monitoring module and a monitoring and early warning terminal;
the data acquisition module is used for carrying out data acquisition on each target monitoring device to obtain monitoring data corresponding to each target monitoring device; the monitoring data comprises single data of each monitoring item;
the device data analysis module is used for analyzing the monitoring data of each target monitoring device in real time and identifying corresponding abnormal data, wherein the abnormal data comprise abnormal points and abnormal characteristics; transmitting the identified abnormal data to a fault monitoring module;
the fault monitoring module is used for carrying out fault analysis according to the abnormal data of the target monitoring equipment, analyzing the abnormal values corresponding to the abnormal data of the target monitoring equipment one by one, carrying out corresponding reduction, calculating the comprehensive abnormal value of the target monitoring equipment according to the reduced abnormal value, and judging the equipment fault reason corresponding to the monitoring item when the comprehensive abnormal value is greater than a threshold value X1;
the monitoring and early warning terminal is used for receiving and displaying abnormal data, the comprehensive abnormal value of which is greater than a threshold value X1, pushed by the fault monitoring module.
An on-line monitoring method for power equipment faults comprises the following steps:
s1: determining each target monitoring device, presetting each monitoring item single item under a monitoring item group corresponding to each monitoring device, and installing each acquisition device based on the monitoring item group;
s2: collecting single data of each monitoring item group by using a collecting device, and integrating the collected single data into monitoring data;
s3: transmitting the monitoring data to an equipment data analysis module, and analyzing the monitoring data by the equipment data analysis module to obtain abnormal data in real time;
s4: transmitting the abnormal data to a fault monitoring module, and analyzing the abnormal data by the fault monitoring module to analyze the abnormal values corresponding to the abnormal data of the target monitoring equipment one by one;
s51, pushing the equipment fault reason to a monitoring and early warning terminal when the comprehensive abnormal value is greater than a threshold value X1;
and S52, pushing no equipment fault reason when the comprehensive abnormal value is smaller than the threshold value X1, and continuing online monitoring.
Under the condition of the preferred trial, the data monitoring mode of the target detection device obtained in the steps S1 and S2 is as follows:
,
wherein, the liquid crystal display device comprises a liquid crystal display device,is the firstThe monitoring data of the individual target monitoring devices,is the number of target monitoring devices that are,is the number of monitoring item groups corresponding to each target monitoring device.
Under the condition of better trial, the method for acquiring the abnormal data comprises the following steps:
establishing a corresponding abnormality recognition model based on historical monitoring data of the target monitoring equipment, and monitoring the monitoring data of the corresponding target monitoring equipment through the established abnormality recognition modelReal-time analysis is carried out to obtain corresponding abnormal data，And (3) withThe relationship between these is as follows:
，
wherein, the liquid crystal display device comprises a liquid crystal display device,is the first to target monitoring deviceThe number of data to be monitored is determined,is the corresponding data of the anomaly,is an abnormality recognition model, and is used for recognizing an abnormality,is a random error term; the anomaly identification model is an isolated forest algorithm, and the expression is:the input is the first of the target monitoring devicesIndividual monitoring dataIts output is the corresponding exception data。
Under the condition of better trial, the specific working method of the fault monitoring module comprises the following steps:
analyzing the received abnormal data through a preset abnormal evaluation model to obtain corresponding abnormal values and reduction coefficient curves, matching corresponding dynamically updated reduction coefficients from the reduction coefficient curves based on the time corresponding to the abnormal data, and marking the obtained reduction coefficients and the abnormal values as respectivelyAndi=1, 2, … …, n being a positive integer; according to the comprehensive evaluation formulaThe corresponding comprehensive abnormal value is calculated, and the specific evaluation mode is as followsThe formula:
，，
wherein, the liquid crystal display device comprises a liquid crystal display device,is the firstThe number of the reduction coefficients is one,is a curve of the reduction coefficient,is the firstThe time corresponding to the individual abnormal data is determined,is the firstThe number of outliers that are present in the set,is an abnormality assessment model that is used to evaluate the abnormality,is the firstAnd abnormal data.
Under the condition of better trial, the system further comprises a power transmission line fault analysis module, wherein the power transmission line fault analysis module is used for carrying out fault evaluation on the power transmission line based on a fault evaluation function and judging whether the power transmission line has faults or not; the fault evaluation function judgment logic is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,is a power transmission lineIs a fault evaluation function of (1).
In the preferred test situation, the working method of the power transmission line fault analysis module comprises the following steps:
setting an area display interface, wherein corresponding line information and monitoring device positions are displayed in the area display interface; analyzing the mutation signal detected by the monitoring device, the position of the monitoring device and the line where the monitoring device is positioned to obtain a corresponding line analysis section; the obtained line analysis section is marked correspondingly in a region display interface;
acquiring detection power transmission data of a line analysis section in real time, comparing the acquired detection power transmission data with preset standard power transmission data, calculating a corresponding fault value, and judging that the line analysis section has a fault when the fault value is greater than a threshold value X2; otherwise, it is determined that there is no fault.
In the preferred test case, the method for calculating the fault value includes:
analyzing the detected power transmission data and the standard power transmission data to obtain corresponding voltage singles, current singles and loss singles, respectively marking the obtained voltage singles, current singles and loss singles as DLZ, DYZ and SHZ, and calculating a corresponding fault value GZ according to a fault evaluation formula GZ=DLZ+DYZ+SHZ.
Under the condition of better trial test, the monitoring time length is set, and when the line analysis section is still not judged to have faults after the monitoring time length is exceeded, the monitoring of the line analysis section is stopped.
Under the condition of better trial test, the system also comprises a power transmission line fault positioning module, wherein the power transmission line fault positioning module is used for positioning faults of a line analysis section with faults and dividing the lines by utilizing an infrared detection technologyDetecting the analysis section, determining an abnormal part, and marking the obtained abnormal part in a region display interface; the detection mode is as follows: if each monitoring item of the line analysis section is single dataIf each monitoring item single data has faults, returning to the coordinate set of the abnormal partThe method comprises the steps of carrying out a first treatment on the surface of the If the monitoring items are not blocked, returning to the empty set;
wherein, the liquid crystal display device comprises a liquid crystal display device,is a line analysis sectionIs provided with a fault location function of (a),is a line analysis sectionIs provided with a fault determination function of (a),is a set of coordinates of the abnormal part,is an empty set.
Compared with the prior art, the invention has the beneficial effects that:
(1) The invention provides a power equipment fault on-line monitoring system and a method, which can perform data acquisition, anomaly identification, fault analysis and positioning on various target monitoring equipment and perform visual display in a monitoring and early warning terminal, so that the accuracy, sensitivity and reliability of a power equipment fault on-line monitoring technology are improved.
(2) The invention adopts the abnormal recognition model based on the isolated forest algorithm, can effectively recognize the abnormal data of the target monitoring equipment, including abnormal points and abnormal characteristics, and reduces the possibility of false alarm and missing report.
(3) The invention adopts the abnormal evaluation model based on the dynamic update reduction coefficient curve, can match the corresponding reduction coefficient according to the time corresponding to the abnormal data, comprehensively evaluate the obtained reduction coefficient and abnormal value, calculate the comprehensive abnormal value of the target monitoring equipment, and judge the equipment fault cause corresponding to the monitoring item.
(4) The invention adopts the fault locating module based on the infrared detection technology, can locate the fault of the line analysis section with the fault, determine the abnormal part, mark the obtained abnormal part in the area display interface, and is convenient for maintenance personnel to carry out fault removal and repair.
(5) The invention also provides a monitoring early warning terminal which can receive and display the abnormal data pushed by the fault monitoring module, wherein the comprehensive abnormal value of the abnormal data is greater than the threshold value X1, so that a user is timely reminded of the running condition of the power equipment, and larger loss is avoided.
(6) Through the mutual cooperation between transmission line fault analysis module and the transmission line fault positioning module, realize the real-time supervision to transmission line fault, solve the difficult problem of current transmission line monitoring, through the mutual cooperation between them, assist the location to the fault location that corresponds the staff more quick, improve maintenance efficiency.
(7) Through the mutual cooperation among data acquisition module, equipment data analysis module and the fault monitoring module, realize the high-efficient monitoring to power equipment, carry out the fault evaluation promptly in the early stage of trouble, improve monitoring efficiency, can reserve more time simultaneously and prepare, solve current power equipment monitoring system and have the problem of hysteresis quality to fault monitoring.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in 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 that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a frame diagram of the system structure.
FIG. 2 is a flow chart of the detection method of the system.
FIG. 3 is a flow chart of the abnormal data trend of the present invention.
Fig. 4 is a flow chart of the trend of abnormal data in the case of detecting a power line.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, 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.
Example 1:
as shown in fig. 1 and fig. 2, an on-line power equipment fault monitoring system comprises a data acquisition module, an equipment data analysis module, a fault monitoring module and a monitoring and early warning terminal;
the data acquisition module is used for carrying out data acquisition on each target monitoring device to obtain monitoring data corresponding to each target monitoring device; the monitoring data comprises single data of each monitoring item;
the device data analysis module is used for analyzing the monitoring data of each target monitoring device in real time and identifying corresponding abnormal data, wherein the abnormal data comprise abnormal points and abnormal characteristics; transmitting the identified abnormal data to a fault monitoring module;
the fault monitoring module is used for carrying out fault analysis according to the abnormal data of the target monitoring equipment, analyzing the abnormal values corresponding to the abnormal data of the target monitoring equipment one by one, carrying out corresponding reduction, calculating the comprehensive abnormal value of the target monitoring equipment according to the reduced abnormal value, and judging the equipment fault reason corresponding to the monitoring item when the comprehensive abnormal value is greater than a threshold value X1;
the monitoring and early warning terminal is used for receiving and displaying abnormal data, the comprehensive abnormal value of which is greater than a threshold value X1, pushed by the fault monitoring module.
An on-line monitoring method for power equipment faults comprises the following steps:
s1: determining each target monitoring device, presetting each monitoring item single item under a monitoring item group corresponding to each monitoring device, and installing each acquisition device based on the monitoring item group;
s2: collecting single data of each monitoring item group by using a collecting device, and integrating the collected single data into monitoring data;
s3: transmitting the monitoring data to an equipment data analysis module, and analyzing the monitoring data by the equipment data analysis module to obtain abnormal data in real time;
s4: transmitting the abnormal data to a fault monitoring module, and analyzing the abnormal data by the fault monitoring module to analyze the abnormal values corresponding to the abnormal data of the target monitoring equipment one by one;
s51, pushing the equipment fault reason to a monitoring and early warning terminal when the comprehensive abnormal value is greater than a threshold value X1;
and S52, pushing no equipment fault reason when the comprehensive abnormal value is smaller than the threshold value X1, and continuing online monitoring.
The data monitoring mode of the target detection device obtained in the steps S1 and S2 is as follows:
,
wherein, the liquid crystal display device comprises a liquid crystal display device,is the firstThe monitoring data of the individual target monitoring devices,is the number of target monitoring devices that are,is the number of monitoring item groups corresponding to each target monitoring device.
The method for acquiring the abnormal data comprises the following steps:
establishing a corresponding abnormality recognition model based on historical monitoring data of the target monitoring equipment, and monitoring the monitoring data of the corresponding target monitoring equipment through the established abnormality recognition modelReal-time analysis is carried out to obtain corresponding abnormal data，And (3) withThe relationship between these is as follows:
，
wherein, the liquid crystal display device comprises a liquid crystal display device,is the first to target monitoring deviceThe number of data to be monitored is determined,is the corresponding data of the anomaly,is an abnormality recognition model, and is used for recognizing an abnormality,is a random error term; the anomaly identification model is an isolated forest algorithm, and the expression is:the input is the first of the target monitoring devicesIndividual monitoring dataIts output is the corresponding exception data。
The specific working method of the fault monitoring module comprises the following steps:
analyzing the received abnormal data through a preset abnormal evaluation model to obtain corresponding abnormal values and reduction coefficient curves, matching corresponding dynamically updated reduction coefficients from the reduction coefficient curves based on the time corresponding to the abnormal data, and marking the obtained reduction coefficients and the abnormal values as respectivelyAndi=1, 2, … …, n being a positive integer; according to the comprehensive evaluation formulaThe corresponding comprehensive abnormal value is calculated, and the specific evaluation mode is as follows:
，，
wherein, the liquid crystal display device comprises a liquid crystal display device,is the firstThe number of the reduction coefficients is one,is a curve of the reduction coefficient,is the firstThe time corresponding to the individual abnormal data is determined,is the firstThe number of outliers that are present in the set,is an abnormality assessment model that is used to evaluate the abnormality,is the firstAnd abnormal data.
As shown in fig. 3, an anomaly identification model and each monitoring item single item are preset for the target detection device, each monitoring item single item is collected through the collection device to obtain monitoring data, the monitoring data is compared with the anomaly identification model through the device data analysis model and the formula, the anomaly data is obtained through the anomaly evaluation model, the anomaly data is subjected to threshold value judgment, and when the threshold value is larger than X1, the data are transmitted to the monitoring and early warning terminal.
The concrete explanation is as follows:
the data acquisition module is used for acquiring data of each target monitoring device, namely the power equipment needing to be monitored, which does not comprise a power transmission line, and is generally a generator, a transformer, a circuit breaker and the like; setting corresponding acquisition equipment, such as various sensors, according to parameters to be monitored by combining the current data acquisition mode; setting according to the corresponding monitoring items and combining the related data acquisition modes in the current various monitoring systems; acquiring single data of each monitoring item by using the set acquisition equipment to obtain monitoring data of each target monitoring equipment, wherein the monitoring data comprises the single data of each monitoring item; the monitoring item groups set by different target monitoring devices according to possible faults and expression forms of the target monitoring devices are different, for example, sound, vibration, energy consumption and the like of a generator can be used as monitoring items, and the generator is exemplified in the condition that other parameters are unchanged, the energy consumption is increased or the energy consumption is unchanged at a certain moment or period, but the output is reduced, namely, the abnormal point can be determined later, and the abnormal change of corresponding data is the abnormal feature.
The device data analysis module is used for analyzing the monitoring data of each target monitoring device in real time and identifying corresponding abnormal data, wherein the abnormal data comprise abnormal points and abnormal characteristics; transmitting the identified abnormal data to a fault monitoring module; the specific method comprises the following steps:
the method comprises the steps of acquiring a large amount of historical monitoring data of target monitoring equipment, acquiring the historical monitoring data by combining historical storage data in various existing monitoring systems, sorting a training set for abnormal points in a manual mode according to the change condition of the historical data of each monitoring item when the target monitoring equipment fails, identifying the abnormal points under the condition that the abnormal data of each monitoring item appear, and extracting corresponding abnormal characteristics; or which monitoring items are commonly associated, which data appear and are regarded as abnormal points, and corresponding abnormal characteristics are extracted; establishing a corresponding abnormal recognition model based on the CNN network or the DNN network, wherein the abnormal recognition model is used for analyzing the monitoring data of the target monitoring equipment and analyzing whether the single data of each monitoring item is abnormal, if so, identifying corresponding abnormal points and abnormal characteristics, wherein the abnormal points are the abnormal time of the corresponding monitoring items; training is carried out through the set training set, and the monitoring data is analyzed through the anomaly identification model after the training is successful to obtain corresponding anomaly data; because neural networks are prior art in the art, the specific setup and training process is not described in detail in this disclosure.
The fault monitoring module is used for carrying out fault analysis according to the abnormal data of the target monitoring equipment, judging whether the fault exists, carrying out accumulated iterative analysis, namely analyzing the different data of the target monitoring equipment one by one, determining the abnormal value of the data, carrying out gradual reduction according to the time passage until the abnormal value is zero, calculating the accumulated sum of the abnormal values after the reduction in real time during the period, carrying out comprehensive judgment according to the comprehensive abnormal value, judging that the part of the fault corresponding to the monitoring item is larger than a threshold value X1, and otherwise, judging that the fault is normal; the more frequent abnormal data appear, the easier the abnormal data reach the fault judging standard, or the more obvious the abnormal data are, the fault judgment can be directly carried out according to one abnormal data, and the influence of the abnormal data in the normal condition is eliminated by carrying out time reduction; the monitoring items of different target detection devices are correspondingly reduced and are provided according to the characteristics of whether abnormal data, importance, abnormal values and the like are easy to appear in normal operation conditions.
According to the possible abnormal data of each monitoring item, corresponding abnormal values and corresponding time-varying reduction coefficient curves are manually set, and for the reduction coefficient curves, because other factors are the same for the same monitoring item, an initial unified reduction coefficient curve can be set, and then the initial reduction coefficient curve is corrected and adjusted according to the corresponding abnormal values, and the larger the abnormal value is, the smaller the reduction coefficient is with time smaller amplitude is; sorting to form a training set, establishing a corresponding abnormal evaluation model based on a CNN network or a DNN network, training through the established training set, analyzing each abnormal data through the abnormal evaluation model after successful training to obtain a corresponding abnormal value and a reduction coefficient curve corresponding to the abnormal value, matching corresponding reduction coefficients in real time from the reduction coefficient curve according to the corresponding abnormal data time, and marking the obtained reduction coefficients and the abnormal values as respectivelyAndwherein i represents corresponding abnormal data, i=1, 2, … …, n being a positive integer; according to the comprehensive evaluation formula，，Calculating corresponding comprehensive abnormal valueI=1, 2, … …, n; wherein, the liquid crystal display device comprises a liquid crystal display device,is the firstThe number of the reduction coefficients is one,is a curve of the reduction coefficient,is the firstThe time corresponding to the individual abnormal data is determined,is the firstThe number of outliers that are present in the set,is an abnormality assessment model that is used to evaluate the abnormality,is the firstAnd abnormal data.
Through the mutual cooperation among data acquisition module, equipment data analysis module and the fault monitoring module, realize the high-efficient monitoring to power equipment, carry out the fault evaluation promptly in the early stage of trouble, improve monitoring efficiency, can reserve more time simultaneously and prepare, solve current power equipment monitoring system and have the problem of hysteresis quality to fault monitoring.
Example 2:
as shown in fig. 4, there are two different lines for the power line fault analysis module:
the method comprises the following steps: on the basis of embodiment 1, the power transmission line fault analysis module is used for carrying out fault assessment on the power transmission line based on a fault assessment function and judging whether the power transmission line has faults or not; the fault evaluation function judgment logic is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,is a power transmission lineIs a fault evaluation function of (1).
The second method is as follows: on the basis of embodiment 1, the working method of the power transmission line fault analysis module includes:
setting an area display interface, wherein corresponding line information and monitoring device positions are displayed in the area display interface; analyzing the mutation signal detected by the monitoring device, the position of the monitoring device and the line where the monitoring device is positioned to obtain a corresponding line analysis section; the obtained line analysis section is marked correspondingly in a region display interface;
acquiring detection power transmission data of a line analysis section in real time, comparing the acquired detection power transmission data with preset standard power transmission data, calculating a corresponding fault value, and judging that the line analysis section has a fault when the fault value is greater than a threshold value X2; otherwise, it is determined that there is no fault.
The fault value calculating method comprises the following steps:
analyzing the detected power transmission data and the standard power transmission data to obtain corresponding voltage singles, current singles and loss singles, respectively marking the obtained voltage singles, current singles and loss singles as DLZ, DYZ and SHZ, and calculating a corresponding fault value GZ according to a fault evaluation formula GZ=DLZ+DYZ+SHZ. And setting a monitoring time period, and stopping monitoring the line analysis section when the line analysis section is not judged to have a fault after the monitoring time period is exceeded.
Further explanation of method two:
the power transmission line fault analysis module is used for carrying out fault assessment on a power transmission line, and carrying out assessment by utilizing corresponding signals when sudden faults such as line breakage, foreign object contact conduction, short circuit and the like are utilized, if the normal and good line is powered on, the current transmission state is influenced when the line is just appeared because of the conditions such as sudden line breakage, electricity stealing, foreign object smashing and the like, a variant signal is generated, the power consumption of a line section generating the variant signal is monitored subsequently, the power consumption loss passing through the line section is counted, and the power consumption is compared with the normal period, so that whether the line section has faults is judged; the specific process is as follows:
setting a corresponding monitoring device according to the monitoring requirement of the alien signal, wherein the monitoring device is set by utilizing the prior related technology, and the alien signal is monitored by utilizing the set monitoring device;
acquiring a region diagram for line monitoring, wherein each power transmission line and a corresponding number are marked in the region diagram; corresponding marks are carried out in the area map according to the position of the set monitoring device, and a corresponding area display interface is established based on the current area map; monitoring the mutation signal in real time through a monitoring device, and marking the monitoring device for monitoring the mutation signal in a region display interface; analyzing according to the marked monitoring device position, the corresponding line and the signal intensity, determining a line analysis section, judging a rough power line section according to signal attenuation, specifically, establishing a corresponding line section analysis model based on a CNN network or a DNN network, and establishing a corresponding training set by a manual mode for training, wherein the training set comprises abnormal signals generated by abnormality at each position in a simulation setting and the corresponding line analysis section; analyzing the different data through the trained abnormality evaluation model to obtain a corresponding line analysis section; the obtained line analysis section is marked correspondingly in a region display interface;
acquiring power transmission data of a line analysis section in real time, wherein the power transmission data comprises voltage, current and loss data, and detecting two ends, namely detecting the power transmission data; obtaining standard power transmission data corresponding to a line analysis section, wherein the standard power transmission data is set according to the length, specification and the like of the line analysis section; the detection power transmission data and the standard power transmission data are changed along with time, particularly, loss data are multiplied by corresponding time, corresponding loss is calculated, and the detection power transmission data acquisition time is started; the method comprises the steps of comparing standard power transmission data with detection power transmission data item by item, outputting single values corresponding to all the items, carrying out conversion evaluation according to difference values, carrying out conversion evaluation, wherein the single values are larger when the difference values are larger, but presetting a method for converting each difference value into a single value when the single value is zero in a corresponding normal interval, setting the single value in a manual mode, and multiplying the single value to obtain the corresponding single value;
the method comprises the steps of marking the singles corresponding to voltage, current and loss as voltage singles, current singles and loss singles respectively, marking the obtained voltage singles, current singles and loss singles as DLZ, DYZ and SHZ respectively, calculating a corresponding fault value GZ according to a fault evaluation formula GZ=DLZ+DYZ+SHZ, and judging that the line analysis section has faults when the fault value is larger than a threshold value X2; otherwise, it is determined that there is no fault.
In one embodiment, a monitoring time length can be set for monitoring the line analysis section, namely, corresponding fault values are calculated in real time in the monitoring time length, fault judgment is carried out, and when faults are not judged after the monitoring time length is exceeded, the monitoring of the line analysis section is stopped; the monitoring duration is that a standard duration is set in a manual mode, then the standard duration is adjusted according to the specification and the length of the line analysis section, a corresponding duration analysis model can be specifically built based on a CNN network or a DNN network, a corresponding training set is built in a manual mode for training, and the monitoring duration of the line analysis section is obtained through analysis of the duration analysis model after successful training.
Example 3:
on the basis of embodiment 2, the power transmission line fault positioning module is used for positioning faults of a line analysis section with faults, positioning by utilizing heat and temperature change of the fault, detecting the line analysis section by utilizing the existing infrared detection technology when judging that the line analysis section has faults, determining abnormal parts, and marking the obtained abnormal parts in a region display interface; the detection mode is as follows: if each monitoring item of the line analysis section is single dataIf each monitoring item single data has faults, returning to the coordinate set of the abnormal partThe method comprises the steps of carrying out a first treatment on the surface of the If the monitoring items are not blocked, returning to the empty set;
wherein, the liquid crystal display device comprises a liquid crystal display device,is a line analysis sectionIs provided with a fault location function of (a),is a line analysis sectionIs provided with a fault determination function of (a),is a set of coordinates of the abnormal part,is an empty set.
Through the mutual cooperation between transmission line fault analysis module and the transmission line fault positioning module, realize the real-time supervision to transmission line fault, solve the difficult problem of current transmission line monitoring, through the mutual cooperation between them, assist the location to the fault location that corresponds the staff more quick, improve maintenance efficiency.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (7)
1. The power equipment fault on-line monitoring method is characterized by comprising the following steps of:
s1: determining each target monitoring device, presetting each monitoring item single item under a monitoring item group corresponding to each monitoring device, and installing each acquisition device based on the monitoring item group;
s2: collecting single data of each monitoring item group by using a collecting device, and integrating the collected single data into monitoring data;
s3: transmitting the monitoring data to an equipment data analysis module, and analyzing the monitoring data by the equipment data analysis module to obtain abnormal data in real time;
s4: transmitting the abnormal data to a fault monitoring module, and analyzing the abnormal data by the fault monitoring module to analyze the abnormal values corresponding to the abnormal data of the target monitoring equipment one by one;
s51: pushing the equipment fault reason to a monitoring and early warning terminal when the comprehensive abnormal value is greater than a threshold value X1;
s52: when the comprehensive abnormal value is smaller than the threshold value X1, pushing no equipment fault cause, and continuing online monitoring;
the data monitoring mode of the target detection device obtained in the steps S1 and S2 is as follows:
wherein X is i Is the monitoring data of the ith target monitoring equipment, n is the number of the target monitoring equipment, and m is the number of the monitoring item groups corresponding to each target monitoring equipment;
the method for acquiring the abnormal data comprises the following steps:
establishing a corresponding abnormality recognition model based on historical monitoring data of the target monitoring equipment, and monitoring the monitoring number x of the corresponding target monitoring equipment through the established abnormality recognition model i Real-time analysis is carried out to obtain corresponding abnormal data y i ，y i And x i The relationship between these is as follows:
wherein x is i Is the ith monitoring data of the target monitoring device, y i Is the corresponding exception data, f (x i ) Is an abnormality recognition model, ++>Is a random error term; the anomaly identification model is an isolated forest algorithm, and the expression is: />The input is the ith monitoring data x of the target monitoring device i Its output is the corresponding exception data y i ；
The specific working method of the fault monitoring module comprises the following steps:
an abnormal evaluation model is established, and the abnormal evaluation model is used for analyzing abnormal data to obtain a corresponding abnormal value and a reduction coefficient curve corresponding to the abnormal value; the reduction coefficient curve is used for matching the corresponding reduction coefficient according to the corresponding abnormal data time;
analyzing the received abnormal data through the abnormal evaluation model to obtain corresponding abnormal values and reduction coefficient curves, matching corresponding dynamically updated reduction coefficients from the reduction coefficient curves based on abnormal data time, and marking the obtained reduction coefficients and abnormal values as c respectively i And Y Ci I=1, 2, … …, n being a positive integer; according to the comprehensive evaluation formulaThe corresponding comprehensive abnormal value is calculated, and the specific evaluation mode is as follows:
wherein c i Is the i-th reduction coefficient, g (t i ) Is a reduction coefficient curve, c i =g(t i ) Representing that the corresponding reduction coefficient dynamically changes along with the reduction coefficient curve according to the abnormal data time; t is t i Is the time corresponding to the ith abnormal data, Y Ci Is the i-th outlier, h (y i ) Is an abnormality evaluation model, y i Is the i-th exception data.
2. The power equipment fault on-line monitoring method according to claim 1, further comprising a power transmission line fault analysis module, wherein the power transmission line fault analysis module is used for carrying out fault assessment on a power transmission line based on a fault assessment function, and judging whether the power transmission line has a fault or not; the fault evaluation function judgment logic is as follows:
where E (L) is a fault assessment function of the power line L.
3. The method for on-line monitoring of power equipment faults as claimed in claim 2, wherein the working method of the power line fault analysis module comprises the steps of:
setting an area display interface, wherein corresponding line information and monitoring device positions are displayed in the area display interface; analyzing the mutation signal detected by the monitoring device, the position of the monitoring device and the line where the monitoring device is positioned to obtain a corresponding line analysis section; the obtained line analysis section is marked correspondingly in a region display interface;
acquiring detection power transmission data of a line analysis section in real time, comparing the acquired detection power transmission data with preset standard power transmission data, calculating a corresponding fault value, and judging that the line analysis section has a fault when the fault value is greater than a threshold value X2; otherwise, it is determined that there is no fault.
4. A method for on-line monitoring of a power plant fault as claimed in claim 3, wherein the method for calculating the fault value comprises:
analyzing the detected power transmission data and the standard power transmission data to obtain corresponding voltage singles, current singles and loss singles, respectively marking the obtained voltage singles, current singles and loss singles as DLZ, DYZ and SHZ, and calculating a corresponding fault value GZ according to a fault evaluation formula GZ=DLZ+DYZ+SHZ.
5. The method for on-line monitoring of power equipment faults as claimed in claim 4, wherein the monitoring time is set, and monitoring of the line analysis section is stopped when it is not determined that the line analysis section has faults after the monitoring time is exceeded.
6. The on-line monitoring method for power equipment faults according to claim 5, further comprising a power transmission line fault positioning module, wherein the power transmission line fault positioning module is used for performing fault positioning on a line analysis section with faults, detecting the line analysis section by utilizing an infrared detection technology, determining abnormal parts, and marking the obtained abnormal parts in a region display interface; the detection mode is as follows: if each monitoring item single data of each monitoring item single data S of the line analysis section has faults, returning to the coordinate set P of the abnormal part; if the monitoring items are not blocked, returning to the empty set;
wherein L (S) is a fault location function of the line analysis section S, F (S) is a fault determination function of the line analysis section S, P is a coordinate set of an abnormal part, < ->Is an empty set.
7. An on-line monitoring system for power equipment faults is characterized in that the on-line monitoring method for power equipment faults according to any one of claims 1-6 is executed and comprises a data acquisition module, an equipment data analysis module, a fault monitoring module and a monitoring and early warning terminal;
the data acquisition module is used for carrying out data acquisition on each target monitoring device to obtain monitoring data corresponding to each target monitoring device; the monitoring data comprises single data of each monitoring item;
the device data analysis module is used for analyzing the monitoring data of each target monitoring device in real time and identifying corresponding abnormal data, wherein the abnormal data comprise abnormal points and abnormal characteristics; transmitting the identified abnormal data to a fault monitoring module;
the fault monitoring module is used for carrying out fault analysis according to the abnormal data of the target monitoring equipment, analyzing the abnormal values corresponding to the abnormal data of the target monitoring equipment one by one, carrying out corresponding reduction, calculating the comprehensive abnormal value of the target monitoring equipment according to the reduced abnormal value, and judging the equipment fault reason corresponding to the monitoring item when the comprehensive abnormal value is greater than a threshold value X1;
the monitoring and early warning terminal is used for receiving and displaying abnormal data, the comprehensive abnormal value of which is greater than a threshold value X1, pushed by the fault monitoring module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310925117.XA CN116660669B (en) | 2023-07-26 | 2023-07-26 | Power equipment fault on-line monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310925117.XA CN116660669B (en) | 2023-07-26 | 2023-07-26 | Power equipment fault on-line monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116660669A CN116660669A (en) | 2023-08-29 |
| CN116660669B true CN116660669B (en) | 2023-10-10 |
Family
ID=87724482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310925117.XA Active CN116660669B (en) | 2023-07-26 | 2023-07-26 | Power equipment fault on-line monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116660669B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116860563B (en) * | 2023-09-05 | 2023-12-15 | 山东捷瑞数字科技股份有限公司 | Cloud platform-based database server monitoring method and system |
| CN117008559B (en) * | 2023-10-07 | 2024-01-26 | 同心县京南惠方农林科技有限公司 | Data acquisition and processing method and system applied to organic fertilizer production system |
| CN117077044B (en) * | 2023-10-18 | 2024-02-06 | 深圳市大易电气实业有限公司 | Method and device for judging faults of vacuum circuit breaker for generator |
| CN117477769A (en) * | 2023-10-26 | 2024-01-30 | 国网安徽省电力有限公司合肥供电公司 | Early warning method and system for electric power system |
| CN117458711B (en) * | 2023-10-26 | 2024-05-17 | 国网安徽省电力有限公司马鞍山供电公司 | Power grid dispatching work monitoring management system based on Internet of things |
| CN117171670B (en) * | 2023-11-03 | 2024-02-13 | 海门市缔绣家用纺织品有限公司 | Textile production process fault monitoring method, device and system |
| CN117346842B (en) * | 2023-11-14 | 2024-07-12 | 广东材通实业有限公司 | Fault detection method and system for motor junction box |
| CN117560470B (en) * | 2023-11-17 | 2024-06-11 | 龙滩水电开发有限公司龙滩水力发电厂 | Cloud edge end cooperative distributed industrial television monitoring and identifying system and method |
| CN117650971B (en) * | 2023-12-04 | 2024-06-14 | 武汉烽火技术服务有限公司 | Method and device for preventing equipment failure of communication system |
| CN117590160B (en) * | 2024-01-19 | 2024-05-24 | 国网甘肃省电力公司张掖供电公司 | Method and system for monitoring transmission state of wind power plant current collection circuit |
| CN118013304A (en) * | 2024-02-19 | 2024-05-10 | 国网湖北省电力有限公司襄阳供电公司 | Transformer fault positioning method and system based on clustering algorithm |
| CN117974643B (en) * | 2024-03-28 | 2024-06-18 | 大连海泰轴承制造有限公司 | Monitoring system and method for carburizing heat treatment process of bearing |
| CN117993694B (en) * | 2024-04-07 | 2024-06-28 | 青岛大数华创科技有限公司 | Quick multi-laboratory dynamic inspection system and device |
| CN118035925A (en) * | 2024-04-11 | 2024-05-14 | 国网信息通信产业集团有限公司 | Data processing system based on electric power big model |
| CN118150933A (en) * | 2024-05-09 | 2024-06-07 | 张家港智能电力研究院有限公司 | Electrical fault position confirmation method based on big data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103592575A (en) * | 2013-11-25 | 2014-02-19 | 国家电网公司 | Self-adaptation weighting data fusion fault distance measurement method based on multi-sensor system |
| US10392022B1 (en) * | 2018-02-28 | 2019-08-27 | Calamp Corp. | Systems and methods for driver scoring with machine learning |
| CN111353228A (en) * | 2020-02-28 | 2020-06-30 | 山东大学 | Composite laminated plate impact response modeling method |
| WO2021173140A1 (en) * | 2020-02-27 | 2021-09-02 | Calamp Corp. | Systems and methods for delivering vehicle parameters to a remote device via vehicle module identities |
| CN115170000A (en) * | 2022-09-06 | 2022-10-11 | 浙江万胜智能科技股份有限公司 | Remote monitoring method and system based on electric energy meter communication module |
| WO2023020524A1 (en) * | 2021-08-17 | 2023-02-23 | 华能华家岭风力发电有限公司 | Method and system for optimizing cut-in/cut-out wind speed of wind turbine unit, device, and medium |
| CN115825718A (en) * | 2022-11-21 | 2023-03-21 | 北京华电云通电力技术有限公司 | Partial discharge online monitoring system and method for gas insulated switch |
| CN115987692A (en) * | 2023-03-20 | 2023-04-18 | 广州掌动智能科技有限公司 | Safety protection system and method based on flow backtracking analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3093811B1 (en) * | 2019-03-15 | 2021-05-14 | Safran Electrical & Power | Arc detection by reflectometry |
-
2023
- 2023-07-26 CN CN202310925117.XA patent/CN116660669B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103592575A (en) * | 2013-11-25 | 2014-02-19 | 国家电网公司 | Self-adaptation weighting data fusion fault distance measurement method based on multi-sensor system |
| US10392022B1 (en) * | 2018-02-28 | 2019-08-27 | Calamp Corp. | Systems and methods for driver scoring with machine learning |
| WO2021173140A1 (en) * | 2020-02-27 | 2021-09-02 | Calamp Corp. | Systems and methods for delivering vehicle parameters to a remote device via vehicle module identities |
| CN111353228A (en) * | 2020-02-28 | 2020-06-30 | 山东大学 | Composite laminated plate impact response modeling method |
| WO2023020524A1 (en) * | 2021-08-17 | 2023-02-23 | 华能华家岭风力发电有限公司 | Method and system for optimizing cut-in/cut-out wind speed of wind turbine unit, device, and medium |
| CN115170000A (en) * | 2022-09-06 | 2022-10-11 | 浙江万胜智能科技股份有限公司 | Remote monitoring method and system based on electric energy meter communication module |
| CN115825718A (en) * | 2022-11-21 | 2023-03-21 | 北京华电云通电力技术有限公司 | Partial discharge online monitoring system and method for gas insulated switch |
| CN115987692A (en) * | 2023-03-20 | 2023-04-18 | 广州掌动智能科技有限公司 | Safety protection system and method based on flow backtracking analysis |
Non-Patent Citations (2)
| Title |
|---|
| 基于DWH-FNN的矿山电气设备监测维护决策支持***研究;陈琼;;化工矿物与加工(第06期);全文 * |
| 基于孤立森林算法的电涌保护器异常参数监测研究;马俊彦;杨仲江;王昊;;电子测量与仪器学报(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116660669A (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116660669B (en) | Power equipment fault on-line monitoring system and method | |
| CN113124929A (en) | Transformer substation multi-parameter signal acquisition comprehensive analysis system and method | |
| CN117040138B (en) | Power distribution cabinet operation dynamic safety evaluation system | |
| CN116320832B (en) | Monitoring equipment fault monitoring method and device | |
| CN113532598B (en) | Online fault detection and regulation system of intelligent water meter | |
| CN116360367A (en) | Industrial equipment Internet of things data acquisition method and system | |
| CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN112683521B (en) | Nuclear power plant electric valve state on-line monitoring and fault diagnosis system | |
| CN106228472A (en) | A kind of substation equipment intelligent patrol detection failure analysis methods | |
| CN117233541B (en) | Power distribution network power line running state measurement method and measurement system | |
| CN106443433A (en) | Monitoring system and monitoring method for circuit breaker state based on divide-shut brake coil current | |
| WO2024031855A1 (en) | Remote monitoring system for oil and gas in high-voltage bushing | |
| CN110553789A (en) | state detection method and device of piezoresistive pressure sensor and brake system | |
| CN116315173A (en) | Battery temperature sampling system based on new energy automobile | |
| CN106877503B (en) | risk identification and early warning method in secondary equipment intelligent operation and maintenance system | |
| CN114061770B (en) | Distributed prefabricated optical fiber bus temperature measurement system | |
| CN113987817A (en) | Degradation analysis method for power generation equipment of hydraulic power plant | |
| CN113346622A (en) | Power grid operation risk intelligent warning system based on big data analysis | |
| CN116827264A (en) | Early warning system for photovoltaic power generation | |
| CN116938676A (en) | Communication risk combined early warning method based on data source analysis | |
| CN116840631A (en) | Transformer partial discharge monitoring and positioning method based on joint diagnosis model | |
| CN110926651A (en) | Power distribution cabinet detection method and device | |
| CN115664033A (en) | Method and system for monitoring state of electric control cubicle | |
| CN111986469A (en) | Intelligent diagnosis method for field terminal fault | |
| CN114264902A (en) | Method and system for monitoring working state of lightning protection box, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 264200 No. 160-3, Songshan Road, Xiyuan street, economic and Technological Development Zone, Weihai City, Shandong Province Applicant after: Weihai Shuangcheng Electric Co.,Ltd. Address before: No. 160-3, Songshan Road, Xiyuan Street, Economic District, Weihai City, Shandong Province, 264200 Applicant before: Weihai Shuangcheng Electric Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |