CN110716133A - High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology - Google Patents
High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology Download PDFInfo
- Publication number
- CN110716133A CN110716133A CN201910843651.XA CN201910843651A CN110716133A CN 110716133 A CN110716133 A CN 110716133A CN 201910843651 A CN201910843651 A CN 201910843651A CN 110716133 A CN110716133 A CN 110716133A
- Authority
- CN
- China
- Prior art keywords
- fault
- voltage circuit
- circuit breaker
- data
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
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
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3275—Fault detection or status indication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to the technical field of power grid equipment maintenance, in particular to a high-voltage circuit breaker fault studying and judging method based on the Internet of things and big data technology, which comprises the following steps: A) establishing a high-voltage circuit breaker state monitoring table; B) detecting the fault retired high-voltage circuit breaker for multiple times to obtain constructed fault sample data; C) training a fault recognition neural network model; D) and inputting the state data of the high-voltage circuit breaker to be researched into the fault recognition neural network model, and taking the output of the fault recognition neural network model as the fault research and judgment result of the high-voltage circuit breaker to be researched and judged. The substantial effects of the invention are as follows: the fault analysis and judgment efficiency and accuracy of the detection data are greatly improved by establishing a fault identification neural network model, meanwhile, the abnormity which is not obvious enough can be found in time, operation and maintenance personnel are assisted to process in time, and the high-voltage circuit breaker is guaranteed to work in a good state all the time.
Description
Technical Field
The invention relates to the technical field of power grid equipment maintenance, in particular to a high-voltage circuit breaker fault studying and judging method based on the Internet of things and a big data technology.
Background
Along with the development of the society, the requirements of people on the safety and reliability of electricity utilization are higher and higher, the high-voltage circuit breaker is responsible for double tasks of control and protection in a power system, and the quality of the performance of the high-voltage circuit breaker is directly related to the safe operation of the power system. The mechanical characteristic parameter is one of important parameters for judging the performance of the circuit breaker. However, the high-voltage circuit breaker has many detection items, the detection process is time-consuming and labor-consuming, and the efficiency is low. The operation and maintenance work of the high-voltage circuit breaker is seriously influenced. Although some technologies appear at present, the detection efficiency of the high-voltage circuit breaker is accelerated, and the detection time is shortened. However, the judgment of the detected data still depends on manual judgment. The accuracy of manually carrying out data research and judgment depends on the experience and quality of the manual work, and the reliability is poor. And the data is manually researched and judged, and only the data with obvious abnormity can be found. For abnormal data which is not obvious enough, manual study and judgment are very difficult. The appearance of the internet of things enables the detection data of the high-voltage circuit breaker to be uploaded and summarized, but the summarized data are not effectively utilized at present.
For example, chinese patent CN102928069B, published 2014, 11/5, a vibration detection system and a detection method for a high-voltage circuit breaker, the system includes vibration sensors installed at a plurality of positions of the high-voltage circuit breaker, and a charge-voltage conversion module, a low-pass filtering module, a potential raising module, an isolation unit module, a single chip microcomputer and an upper computer connected thereto, wherein a fracture signal detection module connected to the high-voltage circuit breaker is also in communication connection with the single chip microcomputer and the upper computer in sequence through the isolation unit module, and further includes a current transformer, a low-pass filtering module and a trigger circuit module which are sequentially connected to the high-voltage circuit breaker, and the trigger circuit module is also sequentially connected to the single chip microcomputer and the upper computer through the isolation unit module; the detection method comprises the following steps: installing vibration sensors at a plurality of positions on the high-voltage circuit breaker to acquire opening and closing vibration signals, processing the opening and closing vibration signals, and then selecting a waveform which can best reflect the opening and closing action process of the high-voltage circuit breaker, so as to determine the optimal installation position of the vibration sensors; the purpose of conveniently realizing the on-line monitoring of the high-voltage circuit breaker with the voltage level of 110kV and above is achieved. The vibration sensor is required to be installed on the high-voltage circuit breaker, the mechanical characteristic interference of the high-voltage circuit breaker is large, and the technical scheme cannot carry out fault study and judgment on the data of the high-voltage circuit breaker, so that the problems of low study and judgment efficiency and poor reliability of the detection data of the conventional high-voltage circuit breaker cannot be effectively solved.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the technical problems of low fault studying and judging efficiency and poor reliability of detection data of the existing high-voltage circuit breaker are solved. The high-voltage circuit breaker fault studying and judging method based on the Internet of things and the big data technology is high in studying and judging efficiency and good in accuracy based on the big data technology.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a high-voltage circuit breaker fault studying and judging method based on the Internet of things and big data technology comprises the following steps: A) according to daily detection items of the high-voltage circuit breaker, a high-voltage circuit breaker state monitoring table is established, and data of the state monitoring table represents state data of the high-voltage circuit breaker; B) the method comprises the steps of obtaining N fault retired high-voltage circuit breakers, wherein the fault retired high-voltage circuit breakers are high-voltage circuit breakers which are in bad states due to faults and still can work, detecting multiple daily detection items of the fault retired high-voltage circuit breakers, obtaining state data in the fault, associating the state data in the fault with fault types of fault retired high-voltage short circuits to form fault sample data, wherein the fault sample data comprises a plurality of groups of fault-free state data, and the fault types associated with the fault-free state data are fault-free; C) training a fault recognition neural network model by using the fault sample data in the step B; D) and inputting the state data of the high-voltage circuit breaker to be researched into the fault recognition neural network model, and taking the output of the fault recognition neural network model as the fault research and judgment result of the high-voltage circuit breaker to be researched and judged. The fault analysis and judgment efficiency and accuracy of the detection data are greatly improved by establishing a fault identification neural network model, meanwhile, the abnormity which is not obvious enough can be found in time, operation and maintenance personnel are assisted to process in time, and the high-voltage circuit breaker is guaranteed to work in a good state all the time.
Preferably, the state of the high-voltage circuit breaker comprises closing time, opening time, closing speed just, opening speed just, three-phase different degrees of synchronism, same-phase different degrees of synchronism, golden short time, no-current time, maximum speed of the movable contact, average speed of the movable contact, action time of the movable contact, bounce time, bounce times, bounce maximum amplitude, opening and closing stroke, current waveform curve of the opening and closing process, time-speed stroke dynamic curve in the opening and closing stroke of the movable contact, opening distance and contact resistance. By acquiring various data of the high-voltage circuit breaker, the state data of the high-voltage circuit breaker is more comprehensive, the accuracy of fault research and judgment is improved, and conditions are provided for discovering unobvious abnormal data.
Preferably, in the step B, the detecting of multiple daily detection items of the fault retired high-voltage circuit breaker includes: B11) detecting a plurality of daily detection items of the fault retired high-voltage circuit breaker; B12) according to the maintenance requirements of the high-voltage circuit breaker, one maintenance requirement is selected in sequence to enable the maintenance requirement not to reach the standard, and after the electrified opening and closing action is carried out for a plurality of times, a plurality of daily detection items are detected; B13) sequentially selecting two maintenance requirements to enable the maintenance requirements not to reach the standard, and carrying out detection on a plurality of daily detection items after carrying out a plurality of times of electrified opening and closing actions; B14) and (3) rapidly cooling the fault retired high-voltage circuit breaker by using liquid nitrogen or dry ice, and performing a mechanical characteristic test on the circuit breaker to obtain detection data of the mechanical characteristic test. The fault is generated actively, so that fault data is collected, and the problem that a fault data sample is insufficient is solved effectively. And after the test is finished, the lubricating performance of the lubricant or the lubricating oil is recovered, so that the jamming fault type of the mechanical part can be simulated without damage, and the state data under the fault type can be obtained. Natural mechanical parts jam due to poor lubrication or the entry of dust particles.
Preferably, in step B, the method for associating the status data at the time of the fault with the fault type of the fault retired high-voltage short circuit includes: B21) acquiring state data detected in historical operation and maintenance of a normally-operated high-voltage circuit breaker as historical state data; B22) comparing a plurality of groups of state data obtained by detection for a plurality of times in the steps B12) and B13) with historical state data in sequence, if the difference between the state data and the historical state data is larger than a preset threshold value, associating the group of state data with the maintenance requirement which does not reach the standard, and if the maintenance requirement which does not reach the standard has a unique corresponding fault type, associating the reorganized state data with the fault type; B23) comparing a plurality of sets of state data obtained by a plurality of mechanical characteristic tests in the step B14) with historical state data, and if the difference between the state data and the historical state data is larger than a preset threshold value, associating the set of state data with the jamming fault of the mechanical part. The fault type is increased, the accuracy of fault type study and judgment is improved, meanwhile, the data abnormity can be caused by the unqualified maintenance requirement, but the fault can not be caused immediately, so that when the study and judgment result is the unqualified maintenance requirement, the fault can be avoided by performing timely maintenance, and the fault prejudgment effect is achieved.
Preferably, in step C, before training the fault recognition neural network model using the fault sample data, normalization processing is performed on the fault sample data, and the normalization processing includes: C11) enumerating numerical data in the fault sample data, obtaining a theoretical boundary value of the numerical data as a boundary value, if the theoretical boundary value does not exist, obtaining a historical boundary value of the data as the boundary value, regarding a left boundary value of the boundary value as 0, regarding a right boundary value of the boundary value as 1, and subtracting a difference of the left boundary value and the right boundary value from the numerical data to divide the difference of the left boundary value and the right boundary value to obtain a normalized value of the numerical data; C12) splitting the state quantity data into a plurality of Boolean data; C13) the boolean data were converted to numerical values and normalized. Through data normalization processing, the training efficiency of the fault recognition neural network model is improved.
Preferably, in step C12, the method for splitting the state quantity data into several boolean data includes: C121) obtaining all state values of the state quantity data; C122) splitting the state quantity field into a plurality of fields by taking the state value as a field name; C123) setting the field with the same field name and state quantity data value, and setting the rest splitting fields to zero to complete the splitting of the state quantity data into Boolean quantity data. And the state quantity is converted into a numerical type, so that the training efficiency of the fault recognition neural network model is improved.
Preferably, in the step B), before the daily detection items of the fault decommissioned high-voltage circuit breaker are detected, a non-contact displacement sensor is mounted on each mechanical moving part of the fault decommissioned high-voltage circuit breaker, and displacement data measured by the non-contact displacement sensors is added to state data of the high-voltage circuit breaker. At present, for the detection of the mechanical characteristics of the high-voltage circuit breaker, contact measurement is generally adopted, and the contact measurement can interfere the mechanical characteristics of the high-voltage circuit breaker and reduce the accuracy of a detection result. In the non-contact displacement sensing technology, the photoelectric sensor has the characteristics of non-contact, quick response, reliable performance and the like, so that the photoelectric sensor is widely applied to industrial automation devices and robots. The photoelectric sensor is a sensor using a photoelectric device as a conversion element, and the photoelectric device is a device converting an optical signal into an electrical signal. It can be used for detecting non-electric physical quantity directly causing light quantity change, such as light intensity, illuminance, radiation temperature measurement, gas component analysis, etc.; other non-electrical quantities that can be converted into changes in the amount of light can also be detected, such as part diameter, surface roughness, strain, displacement, vibration, velocity, acceleration, and identification of the shape of the object, operating conditions, etc. And can work along with high voltage circuit breaker after detecting the installation, need not to demolish, therefore can further improve the efficiency that high voltage circuit breaker mechanical properties detected.
Preferably, in step D), a non-contact displacement sensor is installed on each mechanical moving part of the high-voltage circuit breaker to be evaluated, displacement data measured by the non-contact displacement sensor is obtained, and the state data of the high-voltage circuit breaker to be evaluated and the displacement data measured by the non-contact displacement sensor are input into the fault recognition neural network model for fault evaluation.
Preferably, in the step B), a non-contact displacement sensor is installed on each mechanical moving part of the normal high-voltage circuit breaker, the switching-on and switching-off test is continuously repeated on the high-voltage circuit breaker under the condition of power failure until the mechanical part of the high-voltage circuit breaker is damaged, the switching-on and switching-off times N in the test process and displacement data of each mechanical moving part in the switching-on and switching-off process are recorded as historical displacement data; in the step D), if the fault research result of the high-voltage circuit breaker to be researched and judged is no fault, mounting a non-contact displacement sensor on each mechanical motion part of the high-voltage circuit breaker to be researched and judged, performing one-time opening and closing on the high-voltage circuit breaker to be researched and judged to obtain displacement data measured by the non-contact displacement sensors, comparing the displacement data with historical displacement data to obtain the opening and closing test times N corresponding to the closest historical displacement data, and taking (N-N) as the remaining service life of the high-voltage circuit breaker to be researched and judged.
Alternatively, step B), a non-contact displacement sensor is mounted on each mechanical moving part of the normal high-voltage circuit breaker; according to the maintenance requirements of the high-voltage circuit breaker, one maintenance requirement is selected in sequence to enable the high-voltage circuit breaker not to reach the standard, and the opening and closing tests are continuously repeated on the high-voltage circuit breaker under the power-off condition until mechanical parts of the high-voltage circuit breaker are damaged; recording displacement data of each mechanical motion part in the opening and closing process in the test process, associating corresponding faults with corresponding maintenance requirements which do not reach the standard, repairing the high-voltage circuit breaker, and performing a next test with the maintenance requirements which do not reach the standard; in the step D), a non-contact displacement sensor is arranged on each mechanical motion part of the high-voltage circuit breaker to be researched and judged, the high-voltage circuit breaker to be researched and judged is switched on and off once to obtain displacement data measured by the non-contact displacement sensor, and the state data of the high-voltage circuit breaker to be researched and judged and the displacement data measured by the non-contact displacement sensor are input into a fault recognition neural network model for fault research and judgment; and if the fault research and judgment result of the high-voltage circuit breaker to be researched and judged is no fault, comparing the displacement data obtained by the detection with the historical displacement data to obtain the opening and closing test frequency N corresponding to the closest historical displacement data, and taking (N-N) as the residual service life of the high-voltage circuit breaker to be researched and judged.
The non-contact displacement sensor comprises a laser transmitter, a current-limiting resistor, a photoresistor, a power supply module, a reflection sticker, a voltage sensor and a communication module, wherein the laser transmitter is fixedly arranged in a shell of the high-voltage circuit breaker and is aligned to an alignment point on the outer surface of a mechanical motion part in a normal direction, an included angle is formed between emergent light of the laser transmitter and the normal direction of the outer surface of the mechanical motion part by adjustment, the alignment point of the laser transmitter moves along the outer surface of the mechanical motion part in the stroke of the mechanical motion part to form a moving range, the reflection sticker is attached to the mechanical motion part and covers the moving range of the alignment point, the reflection sticker is provided with a plurality of high reflection areas which are arranged at equal intervals along the stroke of the mechanical motion part, a low reflection area is arranged between adjacent high reflection areas, the width of the high reflection area is equal to that of, the photoresistor is installed and the other side that laser emitter is symmetrical about the outer surface normal of mechanical motion part, and photoresistor one end ground connection, the other end passes through current-limiting resistor and is connected with power module, and voltage sensor gathers the voltage of photoresistor and current-limiting resistor tie point, and voltage sensor is connected with communication module.
The substantial effects of the invention are as follows: the fault analysis and judgment efficiency and accuracy of detection data are greatly improved by establishing a fault identification neural network model, meanwhile, the abnormality which is not obvious enough can be found in time, operation and maintenance personnel are assisted to process in time, and the high-voltage circuit breaker is ensured to work in a good state all the time; through data normalization processing, the training efficiency of the fault recognition neural network model is improved.
Drawings
FIG. 1 is a flow diagram of an embodiment.
Fig. 2 is a block diagram illustrating a flow of a method for obtaining fault sample data according to an embodiment.
Fig. 3 is a schematic structural diagram of a non-contact displacement sensor according to an embodiment.
Fig. 4 and 5 are schematic diagrams of a noncontact displacement sensor according to an embodiment of the present invention.
Wherein: 1. the device comprises a linear reflection sticker, 2, a laser emitter, 3, a cylindrical surface reflection sticker, 4, a cam, 5, a cylindrical end surface reflection sticker, 6, a moving part, 7, an alignment dot track, 8, an arc reflection sticker, 100, a voltage sensor, 200 and a communication module.
Detailed Description
The following provides a more detailed description of the present invention, with reference to the accompanying drawings.
The first embodiment is as follows:
a high-voltage circuit breaker fault studying and judging method based on the Internet of things and big data technology is disclosed, as shown in FIG. 1, the embodiment comprises the following steps: A) according to daily detection items of the high-voltage circuit breaker, a high-voltage circuit breaker state monitoring table is established, and data of the state monitoring table represents state data of the high-voltage circuit breaker.
B) Obtaining N fault retired high-voltage circuit breakers, wherein the fault retired high-voltage circuit breakers are high-voltage circuit breakers which are in bad states due to faults and still can work, installing non-contact displacement sensors on each mechanical moving part 6 of the fault retired high-voltage circuit breakers, and adding displacement data measured by the non-contact displacement sensors into state data of the high-voltage circuit breakers. The detection of multiple daily detection items is performed on the fault retired high-voltage circuit breaker, and state data during fault is obtained, as shown in fig. 2, the method comprises the following steps: B11) detecting a plurality of daily detection items of the fault retired high-voltage circuit breaker; B12) according to the maintenance requirements of the high-voltage circuit breaker, one maintenance requirement is selected in sequence to enable the maintenance requirement not to reach the standard, and after the electrified opening and closing action is carried out for a plurality of times, a plurality of daily detection items are detected; B13) sequentially selecting two maintenance requirements to enable the maintenance requirements not to reach the standard, and carrying out detection on a plurality of daily detection items after carrying out a plurality of times of electrified opening and closing actions; B14) and (3) rapidly cooling the fault retired high-voltage circuit breaker by using liquid nitrogen or dry ice, and performing a mechanical characteristic test on the circuit breaker to obtain detection data of the mechanical characteristic test. The fault is generated actively, so that fault data is collected, and the problem that a fault data sample is insufficient is solved effectively.
Associating status data at fault with fault type of fault decommissioned high voltage short circuit, comprising: B21) acquiring state data detected in historical operation and maintenance of a normally-operated high-voltage circuit breaker as historical state data; B22) comparing a plurality of groups of state data obtained by detection for a plurality of times in the steps B12) and B13) with historical state data in sequence, if the difference between the state data and the historical state data is larger than a preset threshold value, associating the group of state data with the maintenance requirement which does not reach the standard, and if the maintenance requirement which does not reach the standard has a unique corresponding fault type, associating the reorganized state data with the fault type; B23) comparing a plurality of sets of state data obtained by a plurality of mechanical characteristic tests in the step B14) with historical state data, and if the difference between the state data and the historical state data is larger than a preset threshold value, associating the set of state data with the jamming fault of the mechanical part. The fault type is increased, the accuracy of fault type study and judgment is improved, meanwhile, the data abnormity can be caused by the unqualified maintenance requirement, but the fault can not be caused immediately, so that when the study and judgment result is the unqualified maintenance requirement, the fault can be avoided by performing timely maintenance, and the fault prejudgment effect is achieved.
And obtaining fault sample data, wherein the fault sample data comprises a plurality of groups of fault-free state data, and the fault type associated with the fault-free state data is fault-free.
C) Carrying out normalization processing on fault sample data, wherein the normalization processing comprises the following steps: C11) enumerating numerical data in the fault sample data, obtaining a theoretical boundary value of the numerical data as a boundary value, if the theoretical boundary value does not exist, obtaining a historical boundary value of the data as the boundary value, regarding a left boundary value of the boundary value as 0, regarding a right boundary value of the boundary value as 1, and subtracting a difference of the left boundary value and the right boundary value from the numerical data to divide the difference of the left boundary value and the right boundary value to obtain a normalized value of the numerical data; C12) splitting the state quantity data into a plurality of Boolean data; C13) the boolean data were converted to numerical values and normalized. Through data normalization processing, the training efficiency of the fault recognition neural network model is improved.
In step C12, the method for splitting state quantity data into a plurality of boolean data includes: C121) obtaining all state values of the state quantity data; C122) splitting the state quantity field into a plurality of fields by taking the state value as a field name; C123) setting the field with the same field name and state quantity data value, and setting the rest splitting fields to zero to complete the splitting of the state quantity data into Boolean quantity data. And the state quantity is converted into a numerical type, so that the training efficiency of the fault recognition neural network model is improved. And B, training a fault recognition neural network model by using the fault sample data in the step B.
D) And installing a non-contact displacement sensor on each mechanical motion part 6 of the high-voltage circuit breaker to be researched, acquiring displacement data measured by the non-contact displacement sensors, inputting the state data of the high-voltage circuit breaker to be researched and judged and the displacement data measured by the non-contact displacement sensors into a fault recognition neural network model for fault research and judgment, and taking the output of the fault recognition neural network model as a fault research and judgment result of the high-voltage circuit breaker to be researched and judged. The fault analysis and judgment efficiency and accuracy of the detection data are greatly improved by establishing a fault identification neural network model, meanwhile, the abnormity which is not obvious enough can be found in time, operation and maintenance personnel are assisted to process in time, and the high-voltage circuit breaker is guaranteed to work in a good state all the time.
The state of the high-voltage circuit breaker comprises closing time, opening time, rigid closing speed, rigid opening speed, three-phase different degrees of synchronism, in-phase different degrees of synchronism, golden short time, no-current time, maximum speed of a moving contact, average speed of the moving contact, action time of the moving contact, bounce time, bounce times, bounce maximum amplitude, opening and closing stroke, current waveform curve in the opening and closing process, time speed stroke dynamic curve in the opening and closing stroke of the moving contact, opening distance and contact resistance. By acquiring various data of the high-voltage circuit breaker, the state data of the high-voltage circuit breaker is more comprehensive, the accuracy of fault research and judgment is improved, and conditions are provided for discovering unobvious abnormal data.
As shown in fig. 3, the non-contact displacement sensor includes a laser emitter 2, a current limiting resistor, a photo resistor, a power supply module, a reflective sticker, a voltage sensor 100 and a communication module 200, the laser emitter 2 is fixedly installed in a housing of the high voltage circuit breaker, and is aligned with an alignment point on an outer surface of the mechanical motion component 6 in a normal direction, an angle is formed between an emergent light of the laser emitter 2 and the normal direction of the outer surface of the mechanical motion component 6 by adjustment, in a stroke of the mechanical motion component 6, the alignment point of the laser emitter 2 moves along the outer surface of the mechanical motion component 6 to form a moving range, the reflective sticker is attached to the mechanical motion component 6 and covers the moving range of the alignment point, the reflective sticker has a plurality of high reflection areas arranged at equal intervals along the stroke of the mechanical motion component 6, a low reflection area is arranged between adjacent high reflection areas, and, the diameter of the light spot of the laser emitter 2 is equal to integral multiple of the interval width, the photoresistor is arranged on the other side of the laser emitter 2 which is symmetrical with the outer surface of the mechanical motion part 6 in the normal direction, one end of the photoresistor is grounded, the other end of the photoresistor is connected with the power supply module through the current-limiting resistor, the voltage sensor 100 collects the voltage of the connecting point of the photoresistor and the current-limiting resistor, and the voltage sensor 100 is connected with the communication. Fig. 3 shows a linear reflective sticker 1, in which a mechanical moving part 6 to be detected moves linearly, such as a moving contact, an unlocking lock catch, and the like. As shown in fig. 4, when the non-contact displacement detection of the displacement is performed on the rotating component, such as the shaft and the cam 4, the cylindrical reflective sticker 3 may be attached to the outer surface of the shaft or the equal radius arc portion of the cam 4, so as to avoid the blurring of the picture, and the distance between the high reflection area and the low reflection area in the figure is distorted to some extent. When the arc portion of the cam 4 with the same radius is also the working surface, the cylindrical end surface reflection sticker 5 may be attached to the end surface of the cam 4. As shown in fig. 5, when the moving component 6 to be detected has a complex planar motion, that is, both a translational motion and a rotational motion are involved, a suitable alignment point is selected on the moving component 6 to be detected, so that the alignment point is always on the moving component 6 during the stroke of the moving component 6, the alignment point track 7 will be an arc, a suitable arc-shaped reflective sticker 8 is attached, the arc-shaped reflective sticker 8 is provided with high-reflection areas and low-reflection areas at intervals along the arc, and the edges of the high-reflection areas and the low-reflection areas are perpendicular to the arc at the corresponding position. The present embodiment provides an implementation of a non-contact displacement sensor, which is well known in the art for detecting vibration and displacement, and those skilled in the art can design other types of non-contact displacement sensors to perform displacement detection.
Example two:
in this embodiment, on the basis of the first embodiment, the further service life prediction is performed on the high-voltage circuit breaker with a failure-free determination result, including: in the step B), a non-contact displacement sensor is arranged on each mechanical motion part 6 of the normal high-voltage circuit breaker, the opening and closing test is continuously repeated on the high-voltage circuit breaker under the condition of power failure until the mechanical parts of the high-voltage circuit breaker are damaged, the opening and closing times N in the test process and the displacement data of each mechanical motion part 6 in the opening and closing process are recorded as historical displacement data; in the step D), if the fault research result of the high-voltage circuit breaker to be researched and judged is no fault, a non-contact displacement sensor is installed on each mechanical motion part 6 of the high-voltage circuit breaker to be researched and judged, the high-voltage circuit breaker to be researched and judged is switched on and off once, displacement data measured by the non-contact displacement sensors is obtained, the displacement data is compared with historical displacement data, the switching-on and switching-off test frequency N corresponding to the closest historical displacement data is obtained, and the (N-N) is used as the remaining service life of the high-voltage circuit breaker to be researched and judged. The rest steps are the same as the first embodiment.
Example three:
the present embodiment is an alternative to the second embodiment, and includes: in the step B), a non-contact displacement sensor is arranged on each mechanical motion part 6 of the normal high-voltage circuit breaker; according to the maintenance requirements of the high-voltage circuit breaker, one maintenance requirement is selected in sequence to enable the high-voltage circuit breaker not to reach the standard, and the opening and closing tests are continuously repeated on the high-voltage circuit breaker under the power-off condition until mechanical parts of the high-voltage circuit breaker are damaged; recording displacement data of each mechanical motion part 6 in the opening and closing process in the test process, associating corresponding faults with corresponding maintenance requirements which do not reach the standard, repairing the high-voltage circuit breaker, and performing a next test with the maintenance requirements which do not reach the standard; in the step D), a non-contact displacement sensor is arranged on each mechanical motion part 6 of the high-voltage circuit breaker to be researched and judged, the high-voltage circuit breaker to be researched and judged is switched on and off once to obtain displacement data measured by the non-contact displacement sensor, and the state data of the high-voltage circuit breaker to be researched and judged and the displacement data measured by the non-contact displacement sensor are input into a fault recognition neural network model for fault research and judgment; and if the fault research and judgment result of the high-voltage circuit breaker to be researched and judged is no fault, comparing the displacement data obtained by the detection with the historical displacement data to obtain the opening and closing test frequency N corresponding to the closest historical displacement data, and taking (N-N) as the residual service life of the high-voltage circuit breaker to be researched and judged. The rest steps are the same as the first embodiment.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (10)
1. A high-voltage circuit breaker fault studying and judging method based on the Internet of things and big data technology is characterized in that,
the method comprises the following steps:
A) according to daily detection items of the high-voltage circuit breaker, a high-voltage circuit breaker state monitoring table is established, and data of the state monitoring table represents state data of the high-voltage circuit breaker;
B) the method comprises the steps of obtaining N fault retired high-voltage circuit breakers, wherein the fault retired high-voltage circuit breakers are high-voltage circuit breakers which are in bad states due to faults and still can work, detecting multiple daily detection items of the fault retired high-voltage circuit breakers, obtaining state data in the fault, associating the state data in the fault with fault types of fault retired high-voltage short circuits to form fault sample data, wherein the fault sample data comprises a plurality of groups of fault-free state data, and the fault types associated with the fault-free state data are fault-free;
C) training a fault recognition neural network model by using the fault sample data in the step B;
D) and inputting the state data of the high-voltage circuit breaker to be researched into the fault recognition neural network model, and taking the output of the fault recognition neural network model as the fault research and judgment result of the high-voltage circuit breaker to be researched and judged.
2. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and the big data technology as claimed in claim 1,
the state of the high-voltage circuit breaker comprises closing time, opening time, closing speed, opening speed, three-phase different degrees, same-phase different degrees, golden short time, no-current time, maximum speed of a moving contact, average speed of the moving contact, action time of the moving contact, bounce time, bounce times, bounce maximum amplitude, opening and closing stroke, current waveform curve in the opening and closing process, time speed stroke dynamic curve in the opening and closing stroke of the moving contact, opening distance and contact resistance.
3. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 1 or 2,
in the step B, the detection of multiple daily detection items is carried out on the fault retired high-voltage circuit breaker, and the method comprises the following steps:
B11) detecting a plurality of daily detection items of the fault retired high-voltage circuit breaker;
B12) according to the maintenance requirements of the high-voltage circuit breaker, one maintenance requirement is selected in sequence to enable the maintenance requirement not to reach the standard, and after the electrified opening and closing action is carried out for a plurality of times, a plurality of daily detection items are detected;
B13) sequentially selecting two maintenance requirements to enable the maintenance requirements not to reach the standard, and carrying out detection on a plurality of daily detection items after carrying out a plurality of times of electrified opening and closing actions;
B14) and (3) rapidly cooling the fault retired high-voltage circuit breaker by using liquid nitrogen or dry ice, and performing a mechanical characteristic test on the circuit breaker to obtain detection data of the mechanical characteristic test.
4. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 3,
in the step B, the method for associating the state data during the fault with the fault type of the fault retired high-voltage short circuit comprises the following steps:
B21) acquiring state data detected in historical operation and maintenance of a normally-operated high-voltage circuit breaker as historical state data;
B22) comparing a plurality of groups of state data obtained by detection for a plurality of times in the steps B12) and B13) with historical state data in sequence, if the difference between the state data and the historical state data is larger than a preset threshold value, associating the group of state data with the maintenance requirement which does not reach the standard, and if the maintenance requirement which does not reach the standard has a unique corresponding fault type, associating the group of state data with the fault type;
B23) comparing a plurality of sets of state data obtained by a plurality of mechanical characteristic tests in the step B14) with historical state data, and if the difference between the state data and the historical state data is larger than a preset threshold value, associating the set of state data with the jamming fault of the mechanical part.
5. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 3,
in step C, before training the fault recognition neural network model by using fault sample data, normalization processing is carried out on the fault sample data, and the method comprises the following steps:
C11) enumerating numerical data in the fault sample data, obtaining a theoretical boundary value of the numerical data as a boundary value, if the theoretical boundary value does not exist, obtaining a historical boundary value of the data as the boundary value, regarding a left boundary value of the boundary value as 0, regarding a right boundary value of the boundary value as 1, and subtracting a difference of the left boundary value and the right boundary value from the numerical data to divide the difference of the left boundary value and the right boundary value to obtain a normalized value of the numerical data;
C12) splitting the state quantity data into a plurality of Boolean data;
C13) the boolean data were converted to numerical values and normalized.
6. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 5,
in step C12, the method for splitting state quantity data into a plurality of boolean data includes:
C121) obtaining all state values of the state quantity data;
C122) splitting the state quantity field into a plurality of fields by taking the state value as a field name;
C123) setting the field with the same field name and state quantity data value, and setting the rest splitting fields to zero to complete the splitting of the state quantity data into Boolean quantity data.
7. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 1 or 2,
in the step B), before the daily detection items of the fault retired high-voltage circuit breaker are detected, a non-contact displacement sensor is installed on each mechanical moving part of the fault retired high-voltage circuit breaker, and displacement data measured by the non-contact displacement sensors are added into state data of the high-voltage circuit breaker.
8. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 7,
in the step D), a non-contact displacement sensor is arranged on each mechanical moving part of the high-voltage circuit breaker to be researched, displacement data measured by the non-contact displacement sensors are obtained, and the state data of the high-voltage circuit breaker to be researched and judged and the displacement data measured by the non-contact displacement sensors are input into a fault recognition neural network model for fault research and judgment.
9. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 7,
in the step B), a non-contact displacement sensor is arranged on each mechanical moving part of the normal high-voltage circuit breaker, the opening and closing test is continuously repeated on the high-voltage circuit breaker under the condition of power failure until the mechanical part of the high-voltage circuit breaker is damaged, the opening and closing times N in the test process and the displacement data of each mechanical moving part in the opening and closing process are recorded as historical displacement data;
in the step D), if the fault research result of the high-voltage circuit breaker to be researched and judged is no fault, mounting a non-contact displacement sensor on each mechanical motion part of the high-voltage circuit breaker to be researched and judged, performing one-time opening and closing on the high-voltage circuit breaker to be researched and judged to obtain displacement data measured by the non-contact displacement sensors, comparing the displacement data with historical displacement data to obtain the opening and closing test times N corresponding to the closest historical displacement data, and taking (N-N) as the remaining service life of the high-voltage circuit breaker to be researched and judged.
10. The method for studying and judging the fault of the high-voltage circuit breaker based on the Internet of things and big data technology as claimed in claim 7,
in the step B), a non-contact displacement sensor is arranged on each mechanical moving part of the normal high-voltage circuit breaker; according to the maintenance requirements of the high-voltage circuit breaker, one maintenance requirement is selected in sequence to enable the high-voltage circuit breaker not to reach the standard, and the opening and closing tests are continuously repeated on the high-voltage circuit breaker under the power-off condition until mechanical parts of the high-voltage circuit breaker are damaged; recording displacement data of each mechanical motion part in the opening and closing process in the test process, associating corresponding faults with corresponding maintenance requirements which do not reach the standard, repairing the high-voltage circuit breaker, and performing a next test with the maintenance requirements which do not reach the standard;
in the step D), a non-contact displacement sensor is arranged on each mechanical motion part of the high-voltage circuit breaker to be researched and judged, the high-voltage circuit breaker to be researched and judged is switched on and off once to obtain displacement data measured by the non-contact displacement sensor, and the state data of the high-voltage circuit breaker to be researched and judged and the displacement data measured by the non-contact displacement sensor are input into a fault recognition neural network model for fault research and judgment; and if the fault research and judgment result of the high-voltage circuit breaker to be researched and judged is no fault, comparing the displacement data obtained by the detection with the historical displacement data to obtain the opening and closing test frequency N corresponding to the closest historical displacement data, and taking (N-N) as the residual service life of the high-voltage circuit breaker to be researched and judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843651.XA CN110716133B (en) | 2019-09-06 | 2019-09-06 | High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843651.XA CN110716133B (en) | 2019-09-06 | 2019-09-06 | High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110716133A true CN110716133A (en) | 2020-01-21 |
| CN110716133B CN110716133B (en) | 2022-03-15 |
Family
ID=69210329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910843651.XA Active CN110716133B (en) | 2019-09-06 | 2019-09-06 | High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110716133B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114118404A (en) * | 2021-10-20 | 2022-03-01 | 广西电网有限责任公司 | Electric energy meter phase unbalance state syndrome research and judgment method based on neural network |
| CN117872124A (en) * | 2024-03-12 | 2024-04-12 | 杭州布雷科电气有限公司 | Off-line testing system and method for circuit breaker based on neural network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103675669A (en) * | 2013-12-17 | 2014-03-26 | 北京合锐清合电气有限公司 | Breaker electrical endurance monitoring system and method |
| CN106199412A (en) * | 2016-07-01 | 2016-12-07 | 太原理工大学 | A kind of permanent magnet mechanism high-pressure vacuum breaker method of fault pattern recognition |
| CN107490760A (en) * | 2017-08-22 | 2017-12-19 | 西安工程大学 | The circuit breaker failure diagnostic method of fuzzy neural network is improved based on genetic algorithm |
| CN107607303A (en) * | 2017-09-13 | 2018-01-19 | 河海大学 | Mechanical Failure of HV Circuit Breaker recognition methods based on wavelet packet Yu SOM networks |
| CN109270442A (en) * | 2018-08-21 | 2019-01-25 | 西安工程大学 | High-voltage circuitbreaker fault detection method based on DBN-GA neural network |
| CN209280879U (en) * | 2018-12-25 | 2019-08-20 | 国网重庆市电力公司电力科学研究院 | A kind of fuser belt electrical measurement test system and breaker based on noncontacting proximity sensor |
-
2019
- 2019-09-06 CN CN201910843651.XA patent/CN110716133B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103675669A (en) * | 2013-12-17 | 2014-03-26 | 北京合锐清合电气有限公司 | Breaker electrical endurance monitoring system and method |
| CN106199412A (en) * | 2016-07-01 | 2016-12-07 | 太原理工大学 | A kind of permanent magnet mechanism high-pressure vacuum breaker method of fault pattern recognition |
| CN107490760A (en) * | 2017-08-22 | 2017-12-19 | 西安工程大学 | The circuit breaker failure diagnostic method of fuzzy neural network is improved based on genetic algorithm |
| CN107607303A (en) * | 2017-09-13 | 2018-01-19 | 河海大学 | Mechanical Failure of HV Circuit Breaker recognition methods based on wavelet packet Yu SOM networks |
| CN109270442A (en) * | 2018-08-21 | 2019-01-25 | 西安工程大学 | High-voltage circuitbreaker fault detection method based on DBN-GA neural network |
| CN209280879U (en) * | 2018-12-25 | 2019-08-20 | 国网重庆市电力公司电力科学研究院 | A kind of fuser belt electrical measurement test system and breaker based on noncontacting proximity sensor |
Non-Patent Citations (2)
| Title |
|---|
| LI BING 等: "Machinery Fault Diagnosis Method of HV Circuit Breaker Based on EEMD and RBF Neural Network", 《2017 29TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC)》 * |
| 张博: "10kV开关的电气与机械特性运行状态试验研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114118404A (en) * | 2021-10-20 | 2022-03-01 | 广西电网有限责任公司 | Electric energy meter phase unbalance state syndrome research and judgment method based on neural network |
| CN117872124A (en) * | 2024-03-12 | 2024-04-12 | 杭州布雷科电气有限公司 | Off-line testing system and method for circuit breaker based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110716133B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110716133B (en) | High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology | |
| CN107270970A (en) | Towering power equipment vibration monitoring device and its method for carrying out fault diagnosis | |
| CN107728509A (en) | A kind of breaker mechanic property on-line expert diagnostic system based on Multidimensional Data Model | |
| El-Hag | Application of machine learning in outdoor insulators condition monitoring and diagnostics | |
| CN112924861A (en) | Capacitor switching circuit breaker state monitoring method | |
| CN111487491A (en) | Health state detection and evaluation system and method for oil immersed smoothing reactor | |
| CN110690699A (en) | Transformer substation intelligent detection system based on ubiquitous power Internet of things | |
| CN110673024B (en) | High-voltage circuit breaker fault early warning method based on power Internet of things | |
| CN205581259U (en) | GIS local discharge on -line monitoring system with little meteorological monitoring | |
| CN116796261B (en) | Closed switch equipment mechanical characteristic prediction method based on artificial intelligence | |
| CN110705038A (en) | Life cycle evaluation and fault early warning method for high-voltage circuit breaker | |
| CN113567845A (en) | High-voltage circuit breaker life cycle intelligent evaluation method based on deep belief network | |
| CN207148285U (en) | A kind of switchgear Intelligent Measurement terminal | |
| CN103364669B (en) | GIS equipment operational condition online test method and system | |
| CN116952507A (en) | Miniature motor performance test evaluation system based on artificial intelligence | |
| CN105629144A (en) | High voltage switchgear partial discharge diagnosis method and system based on fingerprint database | |
| CN115855754A (en) | System and method for online monitoring of latent metal particles in GIS (gas insulated switchgear) related to action state of circuit breaker | |
| CN110703075B (en) | High-voltage circuit breaker quick overhaul method based on big data technology | |
| US11867763B2 (en) | Method for monitoring circuit breaker and apparatus and internet of things using the same | |
| CN114895163A (en) | Cable inspection positioning device and method based on cable insulation performance | |
| CN104808137B (en) | A kind of online method for judging circuit breaker failure | |
| CN108896850B (en) | Detection method of sulfur hexafluoride closed type combined electrical apparatus based on triaxial vibration technology | |
| CN208140883U (en) | The CAN bus system of high-voltage circuitbreaker running state real-time monitoring | |
| CN106443238A (en) | High-voltage equipment state evaluation method, high-voltage equipment on-line monitoring device evaluation method and apparatuses | |
| CN111199254A (en) | High-voltage electrical equipment real-time detection method based on RBF neural network and Bayesian network |
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 |