CN110648315B - High-voltage circuit breaker state evaluation method based on big data technology - Google Patents

High-voltage circuit breaker state evaluation method based on big data technology Download PDF

Info

Publication number
CN110648315B
CN110648315B CN201910842869.3A CN201910842869A CN110648315B CN 110648315 B CN110648315 B CN 110648315B CN 201910842869 A CN201910842869 A CN 201910842869A CN 110648315 B CN110648315 B CN 110648315B
Authority
CN
China
Prior art keywords
voltage circuit
detection data
circuit breaker
data
historical
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
Application number
CN201910842869.3A
Other languages
Chinese (zh)
Other versions
CN110648315A (en
Inventor
周刚
韩中杰
傅进
高惠新
戚中译
蔡亚楠
钱伟杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiaxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Jiaxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiaxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd filed Critical Jiaxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority to CN201910842869.3A priority Critical patent/CN110648315B/en
Publication of CN110648315A publication Critical patent/CN110648315A/en
Application granted granted Critical
Publication of CN110648315B publication Critical patent/CN110648315B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/0008—Industrial image inspection checking presence/absence
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Quality & Reliability (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Arc-Extinguishing Devices That Are Switches (AREA)

Abstract

The invention relates to the technical field of power equipment maintenance, in particular to a high-voltage circuit breaker state evaluation method based on a big data technology, which comprises the following steps: A) acquiring detection data of historical maintenance time of high-voltage circuit breakers of the same type; B) establishing a fault evaluation model of the high-voltage circuit breaker; C) establishing a correlation model of mechanical characteristics of the high-voltage circuit breakers of the same type and a life cycle of mechanical parts; D) obtaining an association model of the electrified switching-on and switching-off times and contact resistance of the high-voltage circuit breakers of the same type; E) acquiring detection data of a high-voltage circuit breaker to be evaluated, and acquiring a fault evaluation result of the high-voltage circuit breaker; F) obtaining a life cycle evaluation result of a mechanical part of the high-voltage circuit breaker to be evaluated; G) the evaluation result of the contact resistance was obtained. The substantial effects of the invention are as follows: through acquiring historical detection data and detection data under faults of the high-voltage circuit breaker, a fault evaluation model is established, and faults existing in the high-voltage circuit breaker can be rapidly judged.

Description

High-voltage circuit breaker state evaluation method based on big data technology
Technical Field
The invention relates to the technical field of power equipment maintenance, in particular to a high-voltage circuit breaker state evaluation method based on a big data technology.
Background
The high-voltage circuit breaker, also called high-voltage switch, not only can cut off or close the no-load current and load current in the high-voltage circuit, but also can cut off the overload current and short-circuit current by the action of the relay protection device when the system has a fault, and has quite perfect arc extinguishing structure and enough current breaking capacity. The high-voltage circuit breaker is used for controlling a high-voltage circuit and is one of important electrical components in the high-voltage circuit. The circuit breaker is used for switching on or switching off a circuit in normal operation, and a fault condition rapidly switches off the circuit under the action of a relay protection device and reliably switches on short-circuit current under special conditions. A high-voltage circuit breaker is a special electric appliance that turns on or off a high-voltage circuit under normal or fault conditions, and can be classified into: oil circuit breakers, sulfur hexafluoride circuit breakers, compressed air circuit breakers, vacuum circuit breakers, etc. In the maintenance of the power grid, the detection and maintenance of the high-voltage circuit breaker are important contents. The number of high-voltage circuit breakers in the power grid is large, and the detection projects are numerous. The detection and maintenance of the high-voltage circuit breaker comprise a plurality of items such as secondary circuit detection, mechanical characteristic detection, contact resistance detection and the like, and after the detection is completed, the detection data is required to be analyzed and judged, so that whether the detected high-voltage circuit breaker has potential safety hazards or not is determined, and the state of the high-voltage circuit breaker is evaluated. Although some technologies exist at present to reduce the number of wiring times in the detection process, the detection efficiency is accelerated to a certain extent. However, the evaluation of the detection data of the high-voltage circuit breaker still depends on manual work, the requirements on manual experience and quality are high, and the problems of low efficiency and poor reliability exist.
For example, chinese patent CN104965170A, published 2015, 6 months and 1 days, an online detection system and method for a high-voltage circuit breaker includes a sensor module, a first switching power supply, a second switching power supply, a central processing circuit and an upper computer, wherein the sensor module is disposed in a control box of the high-voltage circuit breaker and connected to the central processing circuit, the first switching power supply is connected to the central processing circuit, the central processing circuit is wirelessly connected to the upper computer, and the second switching power supply is connected to the upper computer. According to the technical scheme, the loop circuit in the high-voltage circuit breaker is detected in real time under the condition that power equipment is electrified, and electric parameters in the opening or closing process of the high-voltage circuit breaker are obtained. However, it cannot solve the technical problem of how to analyze the detection data of the high-voltage circuit breaker and obtain the state of the high-voltage circuit breaker.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the technical problems of low efficiency and poor accuracy of analyzing and evaluating the detection data of the high-voltage circuit breaker at present are solved. A rapid and accurate high-voltage circuit breaker state evaluation method based on big data technology is provided.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a high-voltage circuit breaker state evaluation method based on big data technology comprises the following steps: A) acquiring detection data of historical maintenance time of high-voltage circuit breakers of the same type; B) the method comprises the steps of obtaining a plurality of high-voltage circuit breakers with faults and the same model, detecting to obtain detection data under corresponding faults, and establishing a fault evaluation model of the high-voltage circuit breakers; C) establishing a correlation model of mechanical characteristics of the high-voltage circuit breakers of the same type and a life cycle of mechanical parts; D) obtaining an association model of the electrified switching-on and switching-off times and contact resistance of the high-voltage circuit breakers of the same type; E) acquiring detection data of a high-voltage circuit breaker to be evaluated, inputting the detection data into a fault evaluation model, and taking an output result of the fault evaluation model as a fault evaluation result of the high-voltage circuit breaker; F) inputting the mechanical characteristic detection data of the high-voltage circuit breaker to be evaluated into the correlation model of the mechanical characteristic and the mechanical part life cycle to obtain the mechanical part life cycle evaluation result of the high-voltage circuit breaker to be evaluated; G) and obtaining the number of times of electrified switching-on and switching-off of the high-voltage circuit breaker to be evaluated, and comparing the number of times of electrified switching-on and switching-off of the high-voltage circuit breaker with the correlation model of the contact resistance to obtain the evaluation result of the contact resistance. The fault evaluation model is established by acquiring historical detection data of the high-voltage circuit breaker and detection data under the fault, so that the fault existing in the high-voltage circuit breaker can be quickly judged, and for the high-voltage circuit breaker which does not have the fault, a life cycle evaluation result of a mechanical part is given and used as a result of state evaluation of the high-voltage circuit breaker.
Preferably, the detection data includes closing time, opening time, closing speed just, opening speed just, three-phase different degrees of synchronism, in-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 in 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 method for acquiring the same type of high-voltage circuit breaker with the fault comprises: B11) acquiring a high-voltage circuit breaker retired due to faults, wherein the high-voltage circuit breaker retired due to faults is a high-voltage circuit breaker which has damaged parts and cannot be reused; B12) the method comprises the steps of obtaining a running high-voltage circuit breaker with a bad state, decommissioning the high-voltage circuit breaker, and detecting the high-voltage circuit breaker for a plurality of times to obtain detection data under the bad state, wherein the detection data is used as bad detection data, and the high-voltage circuit breaker with the bad state is a high-voltage circuit breaker which has the bad state and can still be used continuously; B13) and acquiring a normal high-voltage circuit breaker, manually setting a bad state or fault, and detecting to acquire bad detection data or fault detection data. The high-voltage circuit breaker with the retired faults can be recycled, the cost is saved, meanwhile, fault data under the real environment can be obtained, the high-voltage circuit breaker running under the bad state is detected, the characteristics of the detection data under the bad state can be obtained, the detection data are used for analyzing the states of other high-voltage circuit breakers, and the characteristics of the detection data and the corresponding bad state or fault relevance can be stronger through artificially setting the bad state or fault.
Preferably, in step B13), the method for detecting the failure state or the malfunction by manually setting the failure state or the malfunction includes: B131) detecting the high-voltage circuit breaker for a plurality of times; B132) according to the maintenance requirement 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 after the electrified opening and closing action is carried out for a plurality of times, the detection is carried out for a plurality of times; B133) two maintenance requirements are sequentially selected to enable the maintenance requirements not to reach the standard, and after the electrified opening and closing actions are carried out for a plurality of times, the detection is carried out for a plurality of times; B134) and (3) rapidly cooling the high-voltage circuit breaker by using liquid nitrogen or dry ice, and performing mechanical characteristic tests for a plurality of times to obtain detection data of the mechanical characteristic tests. 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 establishing the fault evaluation model of the high-voltage circuit breaker comprises: B21) acquiring all detection data, and associating the detection data with the corresponding fault type to be used as sample data; B22) and preprocessing the sample data, normalizing, training a neural network model, and taking the trained neural network model as a fault evaluation model. By carrying out normalization processing on the sample data, the convergence speed of the fault evaluation model can be increased, the establishment efficiency of the fault evaluation model is increased, and the accuracy of the fault evaluation model is improved.
Preferably, in step B21), the method for associating the detection data with the corresponding fault type includes: B211) obtaining the detection data in the step B131) as historical detection data; B212) comparing a plurality of groups of detection data obtained by a plurality of times of detection in the steps B132) and B133) with historical detection data in sequence, and associating the group of detection data with the maintenance requirement which does not reach the standard if the difference between the detection data and the historical detection data is greater than a preset threshold value; B213) comparing a plurality of groups of detection data obtained by a plurality of times of mechanical characteristic tests in the step B134) with historical detection data, and if the difference between the detection data and the historical detection data is larger than a preset threshold value, associating the group of detection data with the jamming fault of the mechanical part. When a fault source exists, the detection data of the high-voltage circuit breaker do not always present the fault data characteristics immediately, and the method can screen out the detection data presenting the fault characteristics.
Preferably, the method for judging whether the difference between the detection data and the historical detection data is greater than a preset threshold comprises the following steps: B31) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B32) normalizing the detection data and numerical values in the historical detection data, averaging all items of the normalized historical detection data, arranging the processed Boolean quantities and the numerical values according to a set sequence, forming detection vectors after the detection data are sequenced, and forming the historical detection vectors after all the average values of the historical detection data are sequenced; B33) and calculating the distance between the detection vector and the historical detection vector, comparing the distance with a preset distance threshold, if the distance is greater than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is greater than the preset threshold, otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not greater than the preset threshold. The calculation of the spacing between vectors is common in the art. For the setting of the preset threshold value, a plurality of known vector distances between fault data and normal data are adopted, and the preset threshold value is set to be slightly lower than the minimum value of the vector distances.
Alternatively, the method for determining whether the difference between the detection data and the historical detection data is greater than a preset threshold value includes: B41) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B42) normalizing the detection data and the numerical values in the historical detection data to respectively obtain the minimum value and the maximum value of each item of the normalized historical detection data, arranging the Boolean quantity and the numerical values after processing according to a set sequence, forming a detection vector after sequencing the detection data, forming a historical detection left vector after sequencing each minimum value of the historical detection data, and forming a historical detection right vector after sequencing each maximum value of the historical detection data; B43) and respectively calculating the distances between the detection vector and the historical detection left vector as well as between the detection vector and the historical detection right vector, comparing the distances with a preset distance threshold, if the distances between the detection vector and the historical detection left vector as well as between the detection vector and the historical detection right vector are larger than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is larger than the preset threshold, and otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not larger than the preset threshold. The judgment is more accurate through the history detection left vector and the history detection right vector.
Alternatively, the method for determining whether the difference between the detection data and the historical detection data is greater than a preset threshold value includes: B51) carrying out segmentation processing on the numerical quantity in the detection data and the historical detection data, and converting the numerical quantity into a state quantity by taking a segmentation interval as a name; B52) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B52) taking the Boolean quantity of the processed historical detection data as a numerical value to calculate a mean value, rounding the mean value to an integer, taking the obtained integer as the Boolean quantity again, and sequencing the processed detection data and the historical detection data according to setting to respectively form a detection vector and a historical detection vector; B53) and calculating the distance between the detection vector and the historical detection vector, comparing the distance with a preset distance threshold, if the distance is greater than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is greater than the preset threshold, otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not greater than the preset threshold. The boolean vector can eliminate the bias associated with the numeric data.
Preferably, in step B51), the method for performing segmentation processing on the numerical values in the detection data and the historical detection data includes: B511) selecting a numerical value, obtaining all numeric values of the numerical value in the historical detection data, sequentially arranging the numeric values according to the numerical values, and recording the numeric values as a set Ki, wherein the minimum value in the set Ki is kminAnd maximum value of kmax(ii) a B512) Starting a partition by ksGiving an initial value of kminPartition end point keGiving an initial value of kmaxInvestigation of value km＝ks+ n × Δ k, Δ k being a step length set manually, n being a positive integer, and the initial value of n being 1; B513) n is continuously added with 1, if the value k is examinedmThe following conditions are satisfied:
Figure BDA0002194263670000041
where the function N (x, y) represents the set Ki, and the number of data values in the numerical interval (x, y) would be (2 k)m-ks) As interval divisionPoint and add partition set Km, will (2 k)m-ks) Is assigned to ksContinuing to make n continuously self-add 1 until km＞kmax(ii) a B514) Will kminAnd kmaxAdding a set Km, using a value in the Km as a dividing point, and dividing numerical value data into numerical value intervals; B515) selecting the next numerical value, and repeating the steps B511) to B514) until all the numerical values are divided into subarea segments; B516) the detection data is divided into intervals by numerical values corresponding to the historical detection data. According to the aggregation characteristics of the numerical values, segmentation is carried out, and the segmentation can be closer to different states of the numerical values.
Preferably, in step B51), the method for converting a numerical value into a state quantity with a segment interval as a name includes the steps of: B511) dividing the numerical data into a number of compartments, [ n ]m(1)，nm(2)]，[nm(2)，nm(3)]...[nm(k-1)，nm(k)]Wherein n ism(1)And nm(k)Respectively the start and end of the interval of values, nm(2)～nm(k-1)For the intermediate division point of the value interval, will
Figure BDA0002194263670000051
Respectively as the state names of the corresponding value intervals; B512) if the data of the historical detection numerical quantity falls into the interval [ n ]m(d)，nm(d+1)]，d∈[1，k-1]Then the status name
Figure BDA0002194263670000052
And as the value of the numerical quantity, finishing the conversion of the numerical quantity data into the state quantity data. The conversion of numerical quantities into state quantities can be completed quickly.
Preferably, in step B52), the method of converting the state quantities in the detection data and the history detection data into boolean quantities includes the steps of: B521) obtaining all state values of the state quantity data; B522) splitting the state quantity field into a plurality of fields by taking the state value as a field name; B523) and setting the field with the same field name and state quantity data value as 1 and setting the rest splitting fields as 0 to finish splitting the state quantity data into Boolean quantity data. The state quantity is divided into Boolean quantities, and the training efficiency of the neural network can be accelerated.
Preferably, in step B512), the setting method of the step Δ k includes: and calculating pairwise difference values of numerical quantity data in the set Ki, eliminating the difference values which are zero, performing absolute value calculation on the residual difference values, and taking the minimum value as the step length delta k to participate in calculation. Segmentation can be made more reasonable.
Preferably, in step B521), the method for obtaining all state values of the state quantity data includes: if the state quantity data is the state of the circuit breaker, all the state values comprise all possible values of the state; if the state quantity data is converted from the numerical quantity data, all the state values only comprise the values appearing in the historical state. The state value is more reasonable.
Preferably, in step B, the method for establishing the fault evaluation model of the high-voltage circuit breaker comprises: B61) acquiring all detection data and acquiring fault types corresponding to the detection data; B62) preprocessing the detection data, performing binarization processing on the detection data, and arranging sample data after binarization processing into a matrix; B63) constructing an image, wherein the size of an image pixel is the same as the number of rows and columns of a matrix, the value of a matrix element corresponding to the position of the image pixel is 1, the pixel is set to be black, the value of the matrix element corresponding to the position of the image pixel is 0, the pixel is set to be white, a sample portrait is obtained, and the sample portrait is associated with a fault type corresponding to detection data; B64) and constructing a convolutional neural network model, training by using the sample portrait associated with the fault type, using the trained convolutional neural network model as a fault evaluation model, processing the detection data of the high-voltage circuit breaker to be evaluated through the steps B62) to B63), inputting the processed detection data into the convolutional neural network model obtained in the step, and outputting the convolutional neural network model as a fault evaluation result of the high-voltage circuit breaker to be evaluated. The data characteristics of the high-voltage circuit breaker are reflected by constructing images, and different fault types can be well identified through the convolutional neural network.
Preferably, in step B62), the method of binarizing the detected data includes the steps of: B621) carrying out segmentation processing on the numerical value in all the detection data, and converting the numerical value into a state quantity by taking a segmentation interval as a name; B622) converting state quantities in all detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B623) taking the Boolean quantity of all the processed detection data as a numerical value, calculating an average value, rounding the obtained average value into an integer, and taking the obtained integer as the Boolean quantity again; B624) the boolean quantity result obtained in step B623) is taken as a binarization processing result of the detection data. The efficiency of neural network training can be improved by carrying out binarization on the detection data.
Preferably, in step B61), the detection data includes detection data of the high-voltage circuit breaker in a normal operating state, and the detection data of the high-voltage circuit breaker in the normal operating state corresponds to a fault type being no fault.
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 F), a non-contact displacement sensor is arranged on each mechanical motion part of the high-voltage circuit breaker to be evaluated, the high-voltage circuit breaker to be evaluated is subjected to one-time switching on and off, displacement data measured by the non-contact displacement sensors are obtained and compared with historical displacement data, the switching on and off test times N corresponding to the closest historical displacement data are obtained, and the (N-N) is used as the residual service life of the high-voltage circuit breaker to be evaluated.
Preferably, in the step B), a non-contact type 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 F), a non-contact displacement sensor is arranged on each mechanical motion part of the high-voltage circuit breaker to be evaluated, the high-voltage circuit breaker to be evaluated is subjected to one-time switching on and off to obtain displacement data measured by the non-contact displacement sensor, the displacement data measured by the non-contact displacement sensor of the high-voltage circuit breaker to be evaluated is compared with historical displacement data to obtain the switching on and off test times N corresponding to the closest historical displacement data, and the (N-N) is used as the residual service life of the high-voltage circuit breaker to be evaluated.
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 low reflection area, and the diameter of a light spot of the laser transmitter is equal to the integral multiple of the interval width, 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.
Preferably, in the step G, comparing the number of times of switching on and off the high-voltage circuit breaker with the same model with a correlation model of the contact resistance, and taking a quotient of the contact resistance of the high-voltage circuit breaker to be evaluated and the contact resistance output by the correlation model as an evaluation result of the contact resistance of the high-voltage circuit breaker to be evaluated.
Preferably, in the step G, the method for establishing the correlation model between the electrified switching-on and switching-off times and the contact resistance of the high-voltage circuit breakers of the same model comprises the following steps: G1) acquiring the electrified switching-on and switching-off times in all historical detection data of the high-voltage circuit breakers of the same type and the contact resistance measured when the times correspond to the electrified switching-on and switching-off times; G2) grouping the contact resistors according to the corresponding electrified switching-on and switching-off times to obtain all the contact resistors under each electrified switching-on and switching-off time, and calculating an average value; G3) and taking the electrified switching-on and switching-off times as an independent variable, taking the mean value of the contact resistance corresponding to the electrified switching-on and switching-off times as a function value, fitting, and taking the fitting function as a correlation model of the electrified switching-on and switching-off times and the contact resistance of the high-voltage circuit breaker of the same type.
The substantial effects of the invention are as follows: the fault evaluation model is established by acquiring historical detection data of the high-voltage circuit breaker and detection data under the fault, the fault existing in the high-voltage circuit breaker can be quickly judged, for the high-voltage circuit breaker which does not have the fault, a life cycle evaluation result of a mechanical part is given and serves as a result of state evaluation of the high-voltage circuit breaker, and a fault source is actively set, so that the technical problem that the number of detection data samples under the fault is small can be solved, the detection data and the fault are more relevant, the improvement of the accuracy of fault analysis is facilitated, the convergence rate of the fault evaluation model can be accelerated by carrying out normalization processing on the sample data, the establishment efficiency of the fault evaluation model is improved, and the accuracy of the fault evaluation model is improved.
Drawings
Fig. 1 is a block diagram of a method for evaluating a state of a high-voltage circuit breaker according to an embodiment.
Fig. 2 is a flow chart of a method for acquiring a failed high-voltage circuit breaker according to an embodiment.
Fig. 3 is a flowchart illustrating a method for setting a bad status or fault and detecting the bad status or fault according to an embodiment.
Fig. 4 is a schematic structural diagram of a non-contact displacement sensor according to an embodiment.
Fig. 5 and 6 are schematic diagrams illustrating a non-contact displacement sensor according to an embodiment of the present invention.
Fig. 7 is a flowchart of a method for establishing a fault evaluation model of a high-voltage circuit breaker according to the second embodiment.
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 method for evaluating the state of a high-voltage circuit breaker based on big data technology is disclosed, as shown in figure 1, and comprises the following steps: A) and acquiring detection data of historical maintenance of the high-voltage circuit breakers of the same type. The detection data 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 the moving contact, average speed of the moving contact, action time of the moving contact, bounce time, bounce times, maximum bounce amplitude, opening and closing stroke, current waveform curve of the opening and closing process, dynamic curve of time speed stroke 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.
B) The method comprises the steps of obtaining a plurality of high-voltage circuit breakers with faults and the same model, detecting to obtain detection data under the corresponding faults, and establishing a fault evaluation model of the high-voltage circuit breakers. As shown in fig. 2, the method for acquiring the same type of high-voltage circuit breaker with a fault comprises the following steps: B11) acquiring a high-voltage circuit breaker retired due to faults, wherein the high-voltage circuit breaker retired due to faults is a high-voltage circuit breaker which has damaged parts and cannot be reused; B12) the method comprises the steps of obtaining a running high-voltage circuit breaker with a bad state, decommissioning the high-voltage circuit breaker, detecting the high-voltage circuit breaker for a plurality of times, obtaining detection data under the bad state, using the detection data as bad detection data, and enabling the high-voltage circuit breaker with the bad state to be a high-voltage circuit breaker which has the bad state and can still be used continuously; B13) and acquiring a normal high-voltage circuit breaker, manually setting a bad state or fault, and detecting to acquire bad detection data or fault detection data. The high-voltage circuit breaker with the retired faults can be recycled, the cost is saved, meanwhile, fault data under the real environment can be obtained, the high-voltage circuit breaker running under the bad state is detected, the characteristics of the detection data under the bad state can be obtained, the detection data are used for analyzing the states of other high-voltage circuit breakers, and the characteristics of the detection data and the corresponding bad state or fault relevance can be stronger through artificially setting the bad state or fault. As shown in fig. 3, the method for detecting a failure state or a failure by manually setting the failure state or the failure in step B13) includes: B131) detecting the high-voltage circuit breaker for a plurality of times; B132) according to the maintenance requirement 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 after the electrified opening and closing action is carried out for a plurality of times, the detection is carried out for a plurality of times; B133) two maintenance requirements are sequentially selected to enable the maintenance requirements not to reach the standard, and after the electrified opening and closing actions are carried out for a plurality of times, the detection is carried out for a plurality of times; B134) and (3) rapidly cooling the high-voltage circuit breaker by using liquid nitrogen or dry ice, and performing mechanical characteristic tests for a plurality of times to obtain detection data of the mechanical characteristic tests. 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.
In the step B, the method for establishing the fault evaluation model of the high-voltage circuit breaker comprises the following steps: B21) acquiring all detection data, and associating the detection data with the corresponding fault type to be used as sample data; B22) and preprocessing the sample data, normalizing, training a neural network model, and taking the trained neural network model as a fault evaluation model. By carrying out normalization processing on the sample data, the convergence speed of the fault evaluation model can be increased, the establishment efficiency of the fault evaluation model is increased, and the accuracy of the fault evaluation model is improved. In step B21), the method for associating the detection data with the corresponding fault type includes: B211) obtaining the detection data in the step B131) as historical detection data; B212) comparing a plurality of groups of detection data obtained by a plurality of times of detection in the steps B132) and B133) with historical detection data in sequence, and associating the group of detection data with the maintenance requirement which does not reach the standard if the difference between the detection data and the historical detection data is greater than a preset threshold value; B213) comparing a plurality of groups of detection data obtained by a plurality of times of mechanical characteristic tests in the step B134) with historical detection data, and if the difference between the detection data and the historical detection data is larger than a preset threshold value, associating the group of detection data with the jamming fault of the mechanical part. When a fault source exists, the detection data of the high-voltage circuit breaker do not always present the fault data characteristics immediately, and the method can screen out the detection data presenting the fault characteristics. The method for judging whether the difference between the detection data and the historical detection data is greater than the preset threshold value comprises the following steps: B31) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B32) normalizing the detection data and numerical values in the historical detection data, averaging all items of the normalized historical detection data, arranging the processed Boolean quantities and the numerical values according to a set sequence, forming detection vectors after the detection data are sequenced, and forming the historical detection vectors after all the average values of the historical detection data are sequenced; B33) and calculating the distance between the detection vector and the historical detection vector, comparing the distance with a preset distance threshold, if the distance is greater than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is greater than the preset threshold, otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not greater than the preset threshold. The calculation of the spacing between vectors is common in the art. For the setting of the preset threshold value, a plurality of known vector distances between fault data and normal data are adopted, and the preset threshold value is set to be slightly lower than the minimum value of the vector distances.
The method comprises the steps that a non-contact displacement sensor is arranged on each mechanical motion part of a normal high-voltage circuit breaker, the high-voltage circuit breaker is subjected to opening and closing tests continuously and repeatedly 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 are recorded, and displacement data of each mechanical motion part in the opening and closing process are used as historical displacement data.
Each mechanical motion part of the normal high-voltage circuit breaker is provided with a non-contact displacement sensor; 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; and 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 the next test with the maintenance requirements which do not reach the standard.
As shown in fig. 4, 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 width of the high reflection area is equal to the width of the low reflection area, 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 module 200. Fig. 4 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. 5, when the non-contact displacement detection of the displacement is performed on the rotating member, 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. 6, 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.
C) And establishing a correlation model of the mechanical characteristics of the high-voltage circuit breakers of the same model and the life cycle of mechanical parts.
D) And obtaining a correlation model of the electrified switching-on and switching-off times and the contact resistance of the high-voltage circuit breakers of the same model.
E) And obtaining detection data of the high-voltage circuit breaker to be evaluated, inputting the detection data into a fault evaluation model, and taking an output result of the fault evaluation model as a fault evaluation result of the high-voltage circuit breaker.
F) And (2) mounting a non-contact displacement sensor on each mechanical motion part of the high-voltage circuit breaker to be evaluated, performing one-time switching on and switching off on the high-voltage circuit breaker to be evaluated to obtain displacement data measured by the non-contact displacement sensors, comparing the displacement data with historical displacement data to obtain the switching on and switching off test times 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 evaluated. And inputting the mechanical characteristic detection data of the high-voltage circuit breaker to be evaluated into the correlation model of the mechanical characteristic and the mechanical part life cycle to obtain the mechanical part life cycle evaluation result of the high-voltage circuit breaker to be evaluated.
G) And obtaining the number of times of electrified switching-on and switching-off of the high-voltage circuit breaker to be evaluated, and comparing the number of times of electrified switching-on and switching-off of the high-voltage circuit breaker with the correlation model of the contact resistance to obtain the evaluation result of the contact resistance. The fault evaluation model is established by acquiring historical detection data of the high-voltage circuit breaker and detection data under the fault, so that the fault existing in the high-voltage circuit breaker can be quickly judged, and for the high-voltage circuit breaker which does not have the fault, a life cycle evaluation result of a mechanical part is given and used as a result of state evaluation of the high-voltage circuit breaker. And comparing the number of times of switching on and switching off the electrified high-voltage circuit breaker with the correlation model of the contact resistance of the high-voltage circuit breaker of the same model, and taking the quotient of the contact resistance of the high-voltage circuit breaker to be evaluated and the contact resistance output by the correlation model as the evaluation result of the contact resistance of the high-voltage circuit breaker to be evaluated.
The method for establishing the association model of the electrified switching-on and switching-off times and the contact resistance of the high-voltage circuit breakers of the same type comprises the following steps of: G1) acquiring the electrified switching-on and switching-off times in all historical detection data of the high-voltage circuit breakers of the same type and the contact resistance measured when the times correspond to the electrified switching-on and switching-off times; G2) grouping the contact resistors according to the corresponding electrified switching-on and switching-off times to obtain all the contact resistors under each electrified switching-on and switching-off time, and calculating an average value; G3) and taking the electrified switching-on and switching-off times as an independent variable, taking the mean value of the contact resistance corresponding to the electrified switching-on and switching-off times as a function value, fitting, and taking the fitting function as a correlation model of the electrified switching-on and switching-off times and the contact resistance of the high-voltage circuit breaker of the same type.
Example two:
in this embodiment, on the basis of the first embodiment, an alternative is provided for the method for establishing the fault evaluation model of the high-voltage circuit breaker in step B, as shown in fig. 7, the method includes: B61) acquiring all detection data and acquiring fault types corresponding to the detection data; B62) preprocessing the detection data, performing binarization processing on the detection data, and arranging sample data after binarization processing into a matrix; B63) constructing an image, wherein the size of an image pixel is the same as the number of rows and columns of a matrix, the value of a matrix element corresponding to the position of the image pixel is 1, the pixel is set to be black, the value of the matrix element corresponding to the position of the image pixel is 0, the pixel is set to be white, a sample portrait is obtained, and the sample portrait is associated with a fault type corresponding to detection data; B64) and constructing a convolutional neural network model, training by using the sample portrait associated with the fault type, using the trained convolutional neural network model as a fault evaluation model, processing the detection data of the high-voltage circuit breaker to be evaluated through the steps B62) to B63), inputting the processed detection data into the convolutional neural network model obtained in the step, and outputting the convolutional neural network model as a fault evaluation result of the high-voltage circuit breaker to be evaluated. The data characteristics of the high-voltage circuit breaker are reflected by constructing images, and different fault types can be well identified through the convolutional neural network.
In step B62), the method of binarizing the detected data includes the steps of: B621) carrying out segmentation processing on the numerical value in all the detection data, and converting the numerical value into a state quantity by taking a segmentation interval as a name; B622) converting state quantities in all detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B623) taking the Boolean quantity of all the processed detection data as a numerical value, calculating an average value, rounding the obtained average value into an integer, and taking the obtained integer as the Boolean quantity again; B624) the boolean quantity result obtained in step B623) is taken as a binarization processing result of the detection data. The efficiency of neural network training can be improved by carrying out binarization on the detection data. In the step B61), the detection data includes detection data of the high-voltage circuit breaker in the normal operating state, and the detection data of the high-voltage circuit breaker in the normal operating state corresponds to a fault type being no fault. The rest steps are the same as the first embodiment.
Example three:
the method for judging whether the difference between the detection data and the historical detection data is greater than the preset threshold value comprises the following steps: B41) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B42) normalizing the detection data and the numerical values in the historical detection data to respectively obtain the minimum value and the maximum value of each item of the normalized historical detection data, arranging the Boolean quantity and the numerical values after processing according to a set sequence, forming a detection vector after sequencing the detection data, forming a historical detection left vector after sequencing each minimum value of the historical detection data, and forming a historical detection right vector after sequencing each maximum value of the historical detection data; B43) and respectively calculating the distances between the detection vector and the historical detection left vector as well as between the detection vector and the historical detection right vector, comparing the distances with a preset distance threshold, if the distances between the detection vector and the historical detection left vector as well as between the detection vector and the historical detection right vector are larger than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is larger than the preset threshold, and otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not larger than the preset threshold. The judgment is more accurate through the history detection left vector and the history detection right vector. The rest steps are the same as the first embodiment.
Example four:
the method for judging whether the difference between the detection data and the historical detection data is greater than the preset threshold value comprises the following steps: B51) carrying out segmentation processing on the numerical quantity in the detection data and the historical detection data, and converting the numerical quantity into a state quantity by taking a segmentation interval as a name; B52) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 }; B52) taking the Boolean quantity of the processed historical detection data as a numerical value to calculate a mean value, rounding the mean value to an integer, taking the obtained integer as the Boolean quantity again, and sequencing the processed detection data and the historical detection data according to setting to respectively form a detection vector and a historical detection vector; B53) and calculating the distance between the detection vector and the historical detection vector, comparing the distance with a preset distance threshold, if the distance is greater than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is greater than the preset threshold, otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not greater than the preset threshold. The boolean vector can eliminate the bias associated with the numeric data.
In step B51), the method for performing segmentation processing on the numerical values in the detection data and the historical detection data includes: B511) selecting a numerical value to obtain historical examinationAll numeric values of the numeric value in the measured data are sequentially arranged according to the numeric value and are recorded as a set Ki, and the minimum value in the set Ki is kminAnd maximum value of kmax(ii) a B512) Starting a partition by ksGiving an initial value of kminPartition end point keGiving an initial value of kmaxInvestigation of value km＝ks+ n × Δ k, Δ k being a step length set manually, n being a positive integer, and the initial value of n being 1; the setting method of the step length delta k comprises the following steps: and calculating pairwise difference values of numerical quantity data in the set Ki, eliminating the difference values which are zero, performing absolute value calculation on the residual difference values, and taking the minimum value as the step length delta k to participate in calculation. The segmentation can be more reasonable; B513) n is continuously added with 1, if the value k is examinedmThe following conditions are satisfied:
Figure BDA0002194263670000121
where the function N (x, y) represents the set Ki, and the number of data values in the numerical interval (x, y) would be (2 k)m-ks) As interval division points and adding division point set Km, (2 k)m-ks) Is assigned to ksContinuing to make n continuously self-add 1 until km＞kmax(ii) a B514) Will kminAnd kmaxAdding a set Km, using a value in the Km as a dividing point, and dividing numerical value data into numerical value intervals; B515) selecting the next numerical value, and repeating the steps B511) to B514) until all the numerical values are divided into subarea segments; B516) the detection data is divided into intervals by numerical values corresponding to the historical detection data. According to the aggregation characteristics of the numerical values, segmentation is carried out, and the segmentation can be closer to different states of the numerical values.
In step B51), the method for converting a numerical value into a state quantity with a segment interval as a name includes the following steps: B511) dividing the numerical data into a number of compartments, [ n ]m(1)，nm(2)]，[nm(2)，nm(3)]...[nm(k-1)，nm(k)]Wherein n ism(1)And nm(k)Respectively, the start of the interval andend point, nm(2)～nm(k-1)For the intermediate division point of the value interval, will
Figure BDA0002194263670000131
Respectively as the state names of the corresponding value intervals; B512) if the data of the historical detection numerical quantity falls into the interval [ n ]m(d)，nm(d+1)]，d∈[1，k-1]Then the status name
Figure BDA0002194263670000132
And as the value of the numerical quantity, finishing the conversion of the numerical quantity data into the state quantity data. The conversion of numerical quantities into state quantities can be completed quickly.
In step B52), the method of converting the state quantities in the detection data and the history detection data into boolean quantities includes the steps of: B521) all state values of the state quantity data are obtained, and the method for obtaining all state values of the state quantity data comprises the following steps: if the state quantity data is the state of the circuit breaker, all the state values comprise all possible values of the state; if the state quantity data is converted from the numerical quantity data, all the state values only comprise the values appearing in the historical state. (ii) a B522) Splitting the state quantity field into a plurality of fields by taking the state value as a field name; B523) and setting the field with the same field name and state quantity data value as 1 and setting the rest splitting fields as 0 to finish splitting the state quantity data into Boolean quantity data. The state quantity is divided into Boolean quantities, and the training efficiency of the neural network can be accelerated. The rest steps are the same as the first embodiment.
The third embodiment and the fourth embodiment can be implemented simultaneously with the second embodiment, respectively, to form a new implementation. 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 (17)

1. A state evaluation method of a high-voltage circuit breaker based on big data technology is characterized in that,
the method comprises the following steps:
A) acquiring detection data of historical maintenance time of high-voltage circuit breakers of the same type;
B) the method comprises the steps of obtaining a plurality of high-voltage circuit breakers with faults and the same model, detecting to obtain detection data under corresponding faults, and establishing a fault evaluation model of the high-voltage circuit breakers;
the method for establishing the fault evaluation model of the high-voltage circuit breaker comprises the following steps:
B61) acquiring all detection data and acquiring fault types corresponding to the detection data;
B62) preprocessing the detection data, performing binarization processing on the detection data, and arranging sample data after binarization processing into a matrix;
B63) constructing an image, wherein the size of an image pixel is the same as the number of rows and columns of a matrix, the value of a matrix element corresponding to the position of the image pixel is 1, the pixel is set to be black, the value of the matrix element corresponding to the position of the image pixel is 0, the pixel is set to be white, a sample portrait is obtained, and the sample portrait is associated with a fault type corresponding to detection data;
B64) constructing a convolutional neural network model, training by using a sample portrait associated with a fault type, using the trained convolutional neural network model as a fault evaluation model, processing detection data of the high-voltage circuit breaker to be evaluated through steps B62) to B63), inputting the detection data into the convolutional neural network model obtained in the step, and outputting the convolutional neural network model as a fault evaluation result of the high-voltage circuit breaker to be evaluated;
C) establishing a correlation model of mechanical characteristics of the high-voltage circuit breakers of the same type and a life cycle of mechanical parts;
D) obtaining an association model of the electrified switching-on and switching-off times and contact resistance of the high-voltage circuit breakers of the same type;
E) acquiring detection data of a high-voltage circuit breaker to be evaluated, inputting the detection data into a fault evaluation model, and taking an output result of the fault evaluation model as a fault evaluation result of the high-voltage circuit breaker;
F) inputting the mechanical characteristic detection data of the high-voltage circuit breaker to be evaluated into the correlation model of the mechanical characteristic and the mechanical part life cycle to obtain the mechanical part life cycle evaluation result of the high-voltage circuit breaker to be evaluated;
G) and obtaining the number of times of electrified switching-on and switching-off of the high-voltage circuit breaker to be evaluated, and comparing the number of times of electrified switching-on and switching-off of the high-voltage circuit breaker with the correlation model of the contact resistance to obtain the evaluation result of the contact resistance.
2. The method for evaluating the state of a high-voltage circuit breaker based on big data technology as claimed in claim 1,
the detection data comprises closing time, opening time, closing speed, opening speed, three-phase different degrees, in-phase different degrees, golden short time, no-current time, maximum speed of the moving contact, average speed of the moving contact, action time of the moving contact, bounce time, bounce times, maximum bounce amplitude, opening and closing stroke, current waveform curve of the opening and closing process, dynamic curve of time speed stroke in the opening and closing stroke of the moving contact, opening distance and contact resistance.
3. A high voltage circuit breaker state evaluation method based on big data technology according to claim 1 or 2,
in the step B, the method for acquiring the high-voltage circuit breakers with the same type and faults comprises the following steps:
B11) acquiring a high-voltage circuit breaker retired due to faults, wherein the high-voltage circuit breaker retired due to faults is a high-voltage circuit breaker which has damaged parts and cannot be reused;
B12) the method comprises the steps of obtaining a running high-voltage circuit breaker with a bad state, decommissioning the high-voltage circuit breaker, and detecting the high-voltage circuit breaker for a plurality of times to obtain detection data under the bad state, wherein the detection data is used as bad detection data, and the high-voltage circuit breaker with the bad state is a high-voltage circuit breaker which has the bad state and can still be used continuously;
B13) and acquiring a normal high-voltage circuit breaker, manually setting a bad state or fault, and detecting to acquire bad detection data or fault detection data.
4. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 3,
in step B13), the method for manually setting a failure state or a failure and detecting the failure state or the failure includes:
B131) detecting the high-voltage circuit breaker for a plurality of times;
B132) according to the maintenance requirement 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 after the electrified opening and closing action is carried out for a plurality of times, the detection is carried out for a plurality of times;
B133) two maintenance requirements are sequentially selected to enable the maintenance requirements not to reach the standard, and after the electrified opening and closing actions are carried out for a plurality of times, the detection is carried out for a plurality of times;
B134) and (3) rapidly cooling the high-voltage circuit breaker by using liquid nitrogen or dry ice, and performing mechanical characteristic tests for a plurality of times to obtain detection data of the mechanical characteristic tests.
5. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 4,
in step B61), the method for associating the detection data with the corresponding fault type includes:
B211) obtaining the detection data in the step B131) as historical detection data;
B212) comparing a plurality of groups of detection data obtained by a plurality of times of detection in the steps B132) and B133) with historical detection data in sequence, and associating the group of detection data with the maintenance requirement which does not reach the standard if the difference between the detection data and the historical detection data is greater than a preset threshold value;
B213) comparing a plurality of groups of detection data obtained by a plurality of times of mechanical characteristic tests in the step B134) with historical detection data, and if the difference between the detection data and the historical detection data is larger than a preset threshold value, associating the group of detection data with the jamming fault of the mechanical part.
6. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 5,
the method for judging whether the difference between the detection data and the historical detection data is greater than the preset threshold value comprises the following steps:
B31) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 };
B32) normalizing the detection data and numerical values in the historical detection data, averaging all items of the normalized historical detection data, arranging the processed Boolean quantities and the numerical values according to a set sequence, forming detection vectors after the detection data are sequenced, and forming the historical detection vectors after all the average values of the historical detection data are sequenced;
B33) and calculating the distance between the detection vector and the historical detection vector, comparing the distance with a preset distance threshold, if the distance is greater than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is greater than the preset threshold, otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not greater than the preset threshold.
7. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 5,
the method for judging whether the difference between the detection data and the historical detection data is greater than the preset threshold value comprises the following steps:
B41) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 };
B42) normalizing the detection data and the numerical values in the historical detection data to respectively obtain the minimum value and the maximum value of each item of the normalized historical detection data, arranging the Boolean quantity and the numerical values after processing according to a set sequence, forming a detection vector after sequencing the detection data, forming a historical detection left vector after sequencing each minimum value of the historical detection data, and forming a historical detection right vector after sequencing each maximum value of the historical detection data;
B43) and respectively calculating the distances between the detection vector and the historical detection left vector as well as between the detection vector and the historical detection right vector, comparing the distances with a preset distance threshold, if the distances between the detection vector and the historical detection left vector as well as between the detection vector and the historical detection right vector are larger than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is larger than the preset threshold, and otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not larger than the preset threshold.
8. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 5,
the method for judging whether the difference between the detection data and the historical detection data is greater than the preset threshold value comprises the following steps:
B51) carrying out segmentation processing on the numerical quantity in the detection data and the historical detection data, and converting the numerical quantity into a state quantity by taking a segmentation interval as a name;
B52) converting state quantities in the detection data and the historical detection data into Boolean quantities, and respectively representing false and true by using {0,1 };
B52) taking the Boolean quantity of the processed historical detection data as a numerical value to calculate a mean value, rounding the mean value to an integer, taking the obtained integer as the Boolean quantity again, and sequencing the processed detection data and the historical detection data according to setting to respectively form a detection vector and a historical detection vector;
B53) and calculating the distance between the detection vector and the historical detection vector, comparing the distance with a preset distance threshold, if the distance is greater than the preset distance threshold, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is greater than the preset threshold, otherwise, judging that the distance between the detection data corresponding to the detection vector and the historical detection data is not greater than the preset threshold.
9. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 8,
in step B51), the method for performing segmentation processing on the numerical values in the detection data and the historical detection data includes:
B511) selecting a numerical value to obtain all the numerical values of the numerical value in the historical detection data, arranging the numerical values in sequence according to the numerical value, and recording the numerical valuesIs set Ki, the minimum value in the set Ki is
Figure DEST_PATH_IMAGE001
And a maximum value of
Figure 998543DEST_PATH_IMAGE002
；
B512) Starting a partition
Figure DEST_PATH_IMAGE003
Giving an initial value of
Figure 80768DEST_PATH_IMAGE001
End of zone division
Figure 270310DEST_PATH_IMAGE004
Giving an initial value of
Figure 449488DEST_PATH_IMAGE002
Investigation value
Figure DEST_PATH_IMAGE005
，
Figure 20277DEST_PATH_IMAGE006
For the step length to be set manually,
Figure DEST_PATH_IMAGE007
is a positive integer and is a non-zero integer,
Figure 514100DEST_PATH_IMAGE007
the initial value is 1;
B513）
Figure 710595DEST_PATH_IMAGE007
continuously adding 1 by itself, if the value is inspected
Figure 275438DEST_PATH_IMAGE008
The following conditions are satisfied:
Figure 282708DEST_PATH_IMAGE010
wherein the function
Figure DEST_PATH_IMAGE011
Representing a set Ki of data values in a range of values
Figure 580004DEST_PATH_IMAGE012
Will be the number of data
Figure DEST_PATH_IMAGE013
As interval division points and adding division point set Km, will
Figure 65343DEST_PATH_IMAGE013
Is assigned to
Figure 15850DEST_PATH_IMAGE003
Continue to order
Figure 725181DEST_PATH_IMAGE007
Continuously adding 1 to the final product
Figure 128349DEST_PATH_IMAGE014
；
B514) Will be provided with
Figure 403997DEST_PATH_IMAGE001
And
Figure 959743DEST_PATH_IMAGE002
adding a set Km, using a value in the Km as a dividing point, and dividing numerical value data into numerical value intervals;
B515) selecting the next numerical value, and repeating the steps B511) to B514) until all the numerical values are divided into subarea segments;
B516) the detection data is divided into intervals by numerical values corresponding to the historical detection data.
10. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 8,
in step B51), the method for converting a numerical value into a state quantity with a segment interval as a name includes the following steps:
B511) the numerical value data is divided into a number of compartments,
Figure DEST_PATH_IMAGE015
wherein
Figure 292504DEST_PATH_IMAGE016
And
Figure DEST_PATH_IMAGE017
respectively the start and end of the interval of values,
Figure 323914DEST_PATH_IMAGE018
for the intermediate division point of the value interval, will
Figure DEST_PATH_IMAGE019
Respectively as the state names of the corresponding value intervals;
B512) if the data of the historical detection numerical quantity falls into the interval
Figure 869165DEST_PATH_IMAGE020
Then the status name
Figure DEST_PATH_IMAGE021
And as the value of the numerical quantity, finishing the conversion of the numerical quantity data into the state quantity data.
11. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 8,
in step B52), the method of converting the state quantities in the detection data and the history detection data into boolean quantities includes the steps of:
B521) obtaining all state values of the state quantity data;
B522) splitting the state quantity field into a plurality of fields by taking the state value as a field name;
B523) and setting the field with the same field name and state quantity data value as 1 and setting the rest splitting fields as 0 to finish splitting the state quantity data into Boolean quantity data.
12. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 4,
in step B62), the method of binarizing the detected data includes the steps of:
B621) carrying out segmentation processing on the numerical value in all the detection data, and converting the numerical value into a state quantity by taking a segmentation interval as a name;
B622) converting state quantities in all detection data into Boolean quantities, and respectively representing false and true by using {0,1 };
B623) taking the Boolean quantity of all the processed detection data as a numerical value, calculating an average value, rounding the obtained average value into an integer, and taking the obtained integer as the Boolean quantity again;
B624) the boolean quantity result obtained in step B623) is taken as a binarization processing result of the detection data.
13. The big data technology-based high-voltage circuit breaker state evaluation method according to claim 4,
in the step B61), the detection data includes detection data of the high-voltage circuit breaker in the normal operating state, and the detection data of the high-voltage circuit breaker in the normal operating state corresponds to a fault type being no fault.
14. The big data technology-based high voltage circuit breaker state evaluation method according to claim 13,
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 F), a non-contact displacement sensor is arranged on each mechanical motion part of the high-voltage circuit breaker to be evaluated, the high-voltage circuit breaker to be evaluated is subjected to one-time switching on and off, displacement data measured by the non-contact displacement sensors are obtained and compared with historical displacement data, the switching on and off test times N corresponding to the closest historical displacement data are obtained, and the (N-N) is used as the residual service life of the high-voltage circuit breaker to be evaluated.
15. The big data technology-based high voltage circuit breaker state evaluation method according to claim 13,
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 F), a non-contact displacement sensor is arranged on each mechanical motion part of the high-voltage circuit breaker to be evaluated, the high-voltage circuit breaker to be evaluated is subjected to one-time switching on and off to obtain displacement data measured by the non-contact displacement sensor, the displacement data measured by the non-contact displacement sensor of the high-voltage circuit breaker to be evaluated is compared with historical displacement data to obtain the switching on and off test times N corresponding to the closest historical displacement data, and the (N-N) is used as the residual service life of the high-voltage circuit breaker to be evaluated.
16. A high voltage circuit breaker state evaluation method based on big data technology according to claim 1 or 2,
and G, comparing the number of times of electrified switching-on and switching-off of the high-voltage circuit breakers of the same model with the correlation model of the contact resistance, and taking the quotient of the contact resistance of the high-voltage circuit breaker to be evaluated and the contact resistance output by the correlation model as the evaluation result of the contact resistance of the high-voltage circuit breaker to be evaluated.
17. A high voltage circuit breaker state evaluation method based on big data technology according to claim 1 or 2,
in the step G, the method for establishing the association model of the electrified switching-on and switching-off times and the contact resistance of the high-voltage circuit breakers of the same model comprises the following steps:
G1) acquiring the electrified switching-on and switching-off times in all historical detection data of the high-voltage circuit breakers of the same type and the contact resistance measured when the times correspond to the electrified switching-on and switching-off times;
G2) grouping the contact resistors according to the corresponding electrified switching-on and switching-off times to obtain all the contact resistors under each electrified switching-on and switching-off time, and calculating an average value;
G3) and taking the electrified switching-on and switching-off times as an independent variable, taking the mean value of the contact resistance corresponding to the electrified switching-on and switching-off times as a function value, fitting, and taking the fitting function as a correlation model of the electrified switching-on and switching-off times and the contact resistance of the high-voltage circuit breaker of the same type.
CN201910842869.3A 2019-09-06 2019-09-06 High-voltage circuit breaker state evaluation method based on big data technology Active CN110648315B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910842869.3A CN110648315B (en) 2019-09-06 2019-09-06 High-voltage circuit breaker state evaluation method based on big data technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910842869.3A CN110648315B (en) 2019-09-06 2019-09-06 High-voltage circuit breaker state evaluation method based on big data technology

Publications (2)

Publication Number Publication Date
CN110648315A CN110648315A (en) 2020-01-03
CN110648315B true CN110648315B (en) 2022-04-26

Family

ID=68991681

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910842869.3A Active CN110648315B (en) 2019-09-06 2019-09-06 High-voltage circuit breaker state evaluation method based on big data technology

Country Status (1)

Country Link
CN (1) CN110648315B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112129967A (en) * 2020-09-24 2020-12-25 国网河南省电力公司检修公司 Laser speed measuring device for testing rigid-separation speed and rigid-combination speed of high-voltage switch
CN113567845A (en) * 2021-06-11 2021-10-29 国网浙江省电力有限公司嘉兴供电公司 High-voltage circuit breaker life cycle intelligent evaluation method based on deep belief network
CN113567844A (en) * 2021-06-11 2021-10-29 国网浙江省电力有限公司嘉兴供电公司 High-voltage circuit breaker state diagnosis method and vacuum arc-extinguishing chamber structure
CN113533950B (en) * 2021-06-11 2023-12-26 国网浙江省电力有限公司嘉兴供电公司 BiLSTM-based high-voltage circuit breaker operation voltage sampling method
CN114184368B (en) * 2021-12-03 2023-10-17 国家电网有限公司 Built-in hydraulic transmission infrared distance and speed measuring device and evaluation method
CN114936141B (en) * 2022-07-22 2022-11-04 浙江中控技术股份有限公司 Performance evaluation method and system for control loop of distributed control system
CN117114422B (en) * 2023-10-19 2023-12-26 福建逢兴机电设备有限公司 Fusion monitoring system of high-voltage switch equipment
CN117872122A (en) * 2024-01-24 2024-04-12 广东电网有限责任公司江门供电局 Mechanical fault diagnosis method based on high-voltage circuit breaker

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101592559A (en) * 2009-06-30 2009-12-02 河南省电力公司商丘供电公司 System for testing mechanical properties of integral circuit breaker
CN102289590A (en) * 2011-08-18 2011-12-21 沈阳工业大学 Method for estimating operating state of SF6 high-voltage circuit breaker and intelligent system
CN103245911A (en) * 2013-05-03 2013-08-14 云南电力试验研究院（集团）有限公司电力研究院 Breaker fault diagnosis method based on Bayesian network
CN104266827A (en) * 2014-08-01 2015-01-07 云南电力试验研究院（集团）有限公司电力研究院 Circuit breaker state evaluation system and method based on mechanical performance parameters
CN105353301A (en) * 2015-10-23 2016-02-24 华北电力大学（保定） Circuit breaker state assessment parameter obtaining method
CN105867236A (en) * 2016-04-22 2016-08-17 南彦勃 Intelligent control system of high-voltage circuit-breaker with self-diagnostic function
CN107728509A (en) * 2017-09-04 2018-02-23 厦门斯玛特思智能电气股份有限公司 A kind of breaker mechanic property on-line expert diagnostic system based on Multidimensional Data Model
CN108734202A (en) * 2018-04-27 2018-11-02 西安工程大学 A kind of Fault Diagnosis for HV Circuit Breakers method based on improved BP

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101592559A (en) * 2009-06-30 2009-12-02 河南省电力公司商丘供电公司 System for testing mechanical properties of integral circuit breaker
CN102289590A (en) * 2011-08-18 2011-12-21 沈阳工业大学 Method for estimating operating state of SF6 high-voltage circuit breaker and intelligent system
CN103245911A (en) * 2013-05-03 2013-08-14 云南电力试验研究院（集团）有限公司电力研究院 Breaker fault diagnosis method based on Bayesian network
CN104266827A (en) * 2014-08-01 2015-01-07 云南电力试验研究院（集团）有限公司电力研究院 Circuit breaker state evaluation system and method based on mechanical performance parameters
CN105353301A (en) * 2015-10-23 2016-02-24 华北电力大学（保定） Circuit breaker state assessment parameter obtaining method
CN105867236A (en) * 2016-04-22 2016-08-17 南彦勃 Intelligent control system of high-voltage circuit-breaker with self-diagnostic function
CN107728509A (en) * 2017-09-04 2018-02-23 厦门斯玛特思智能电气股份有限公司 A kind of breaker mechanic property on-line expert diagnostic system based on Multidimensional Data Model
CN108734202A (en) * 2018-04-27 2018-11-02 西安工程大学 A kind of Fault Diagnosis for HV Circuit Breakers method based on improved BP

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"高压断路器在线监测与状态评估系统的研究";任双利;《万方数据》;20170517;第2-4章 *

Also Published As

Publication number Publication date
CN110648315A (en) 2020-01-03

Similar Documents

Publication Publication Date Title
CN110648315B (en) High-voltage circuit breaker state evaluation method based on big data technology
CN103886610B (en) A kind of insulator image defect detection method
CN110376522B (en) Motor fault diagnosis method of data fusion deep learning network
CN106646096A (en) Transformer fault classification and identification method based on vibration analysis method
CN109787979B (en) Method for detecting electric power network event and invasion
CN110673024B (en) High-voltage circuit breaker fault early warning method based on power Internet of things
Pal et al. Real‐time condition monitoring of substation equipment using thermal cameras
Martins et al. Induction motor fault detection and diagnosis using a current state space pattern recognition
Silva et al. Wavelet-based information filtering for fault diagnosis of electric drive systems in electric ships
KR101797400B1 (en) Method and apparatus for diagnosing fault based on probabilistic density
CN110705038B (en) High-voltage circuit breaker life cycle assessment and fault early warning method
Arabaci et al. A knowledge-based diagnosis algorithm for broken rotor bar fault classification using FFT, principal component analysis and support vector machines
CN109936113B (en) Protection action intelligent diagnosis method and system based on random forest algorithm
CN113379252A (en) Bayesian network high-voltage switch cabinet health system evaluation method based on multi-scale arrangement entropy
CN110703075B (en) High-voltage circuit breaker quick overhaul method based on big data technology
CN110716133B (en) High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology
Breuneval et al. Identification of a roller screw for diagnosis of flight control actuator
CN112613494A (en) Power line monitoring abnormity identification method and system based on deep countermeasure network
Gitzel et al. Towards robust ML-algorithms for the condition monitoring of Switchgear
Gitzel et al. Automatic Analysis Of Thermograms–Challenge In Thermal Monitoring Of Switchgears Using Infrared Cameras
CN115575863A (en) OLTC (on-line test) voiceprint signal identification method based on phase space trajectory diagram principle
Yang et al. An intelligent identification algorithm for obtaining the state of power equipment in SIFT-based environments
Hussain et al. Early fault identification for operating circuit breaker based on classifier model system
de Oliveira et al. Development and experimental evaluation of a vision system for detecting defects of stator windings in induction motor assembly lines
Shan et al. Research on Efficient Detection Method of Foreign Objects on Transmission Lines Based on Improved YOLOv4 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
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20200103

Assignee: JIAXING HENGCHUANG ELECTRIC EQUIPMENT Co.,Ltd.

Assignor: JIAXING POWER SUPPLY COMPANY OF STATE GRID ZHEJIANG ELECTRIC POWER Co.,Ltd.

Contract record no.: X2023330000033

Denomination of invention: A method of high-voltage circuit breaker condition evaluation based on big data technology

Granted publication date: 20220426

License type: Common License

Record date: 20230131

EE01 Entry into force of recordation of patent licensing contract