CN117109800A - Air pressure monitoring method of additional air chamber - Google Patents
Air pressure monitoring method of additional air chamber Download PDFInfo
- Publication number
- CN117109800A CN117109800A CN202311079844.5A CN202311079844A CN117109800A CN 117109800 A CN117109800 A CN 117109800A CN 202311079844 A CN202311079844 A CN 202311079844A CN 117109800 A CN117109800 A CN 117109800A
- Authority
- CN
- China
- Prior art keywords
- target
- air chamber
- air pressure
- additional air
- self
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 238000012512 characterization method Methods 0.000 claims description 91
- 238000012549 training Methods 0.000 claims description 73
- 238000013528 artificial neural network Methods 0.000 claims description 25
- 238000013507 mapping Methods 0.000 claims description 23
- 238000000418 atomic force spectrum Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 16
- 239000002184 metal Substances 0.000 abstract description 4
- 230000033001 locomotion Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 7
- 238000012806 monitoring device Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000009422 external insulation Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L9/00—Measuring steady of quasi-steady pressure of fluid or fluent solid material by electric or magnetic pressure-sensitive elements; Transmitting or indicating the displacement of mechanical pressure-sensitive elements, used to measure the steady or quasi-steady pressure of a fluid or fluent solid material, by electric or magnetic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
- G01M3/32—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators
- G01M3/3236—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators by monitoring the interior space of the containers
- G01M3/3272—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for containers, e.g. radiators by monitoring the interior space of the containers for verifying the internal pressure of closed containers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Measuring Fluid Pressure (AREA)
Abstract
The application discloses a method for monitoring air pressure of an additional air chamber, which can acquire driving time sequence current when a motor control contact moves; the motor is positioned at the atmospheric pressure and outside the tank body, so that the acquisition of the driving time sequence current does not need to process an additional air chamber, and a signal containing the driving time sequence current does not need to pass through thicker metal when the driving time sequence current is transmitted; extracting the characteristics of the driving time sequence current to obtain a target characteristic quantity of the driving time sequence current; and determining the target air pressure of the additional air chamber according to the target characteristic quantity, wherein the target air pressure is used for judging whether the additional air chamber leaks air or not. Therefore, the application can monitor the air leakage of the additional air chamber by utilizing the current of the motor which is easy to obtain, has stronger practicability and is simple to operate.
Description
Technical Field
The application relates to the technical field of power grids, in particular to a method for monitoring air pressure of an additional air chamber.
Background
The vacuum arc-extinguishing chamber, also called vacuum switch tube, is a device for realizing the connection and disconnection of a circuit by controlling the switch-on and switch-off of a pair of contacts sealed in vacuum through a motor. In an environment-friendly tank vacuum circuit breaker or a vacuum breaking GIS of a power transmission grade, in order to ensure the external insulation performance of a vacuum arc-extinguishing chamber, gas with the gas pressure of more than 0.6MPa is filled outside the vacuum arc-extinguishing chamber. The high air pressure causes huge pressure to the corrugated pipe of the vacuum arc-extinguishing chamber, so that the air pressure born by the corrugated pipe is reduced in a mode of installing an additional air chamber on the movable side of the vacuum arc-extinguishing chamber at present, and as shown in fig. 1, one end of the corrugated pipe is connected with the vacuum arc-extinguishing chamber, and the other end is connected with the additional air chamber; simultaneously, vacuum interrupter and additional air chamber all are located jar internal portion, and the motor is located jar external portion. In the use process of the vacuum arc-extinguishing chamber, once the additional air chamber leaks air, the corrugated pipe of the vacuum arc-extinguishing chamber is easy to damage, so that the breaking failure is caused. Therefore, how to determine whether the additional air chamber leaks or not is an important concern for those skilled in the art.
In the prior art, the air pressure of the additional air chamber is collected through an air pressure meter, and whether the additional air chamber leaks air is judged according to the air pressure. The data that the barometer gathered can be outside to the vacuum interrupter through wired transmission, also can be outside to the vacuum interrupter through wireless transmission, but wired transmission needs to process additional air chamber, can influence the gas tightness of additional air chamber, and when adopting wireless transmission, the signal that contains data need pass thicker metal, is difficult to realize the receipt of signal.
Disclosure of Invention
In view of the above, the present application provides a method for monitoring the air pressure of an additional air chamber, for monitoring whether the additional air chamber leaks air.
In order to achieve the above object, the following solutions have been proposed:
a method of monitoring air pressure in an additional air chamber, comprising:
acquiring a driving time sequence current when a motor control contact moves;
extracting the characteristics of the driving time sequence current to obtain a target characteristic quantity of the driving time sequence current;
and determining the target air pressure of the additional air chamber according to the target characteristic quantity, wherein the target air pressure is used for judging whether the additional air chamber leaks air or not.
Optionally, the performing feature extraction on the driving time sequence current to obtain a target feature quantity of the driving time sequence current includes:
performing fast Fourier transform or wavelet transform on the driving time sequence current to obtain a plurality of types of current characteristic quantities;
and selecting a plurality of target feature quantities matched with a preset target type from the current feature quantities.
Optionally, the determining the target air pressure of the additional air chamber according to the target feature quantity includes:
acquiring a first characterization model for representing the mapping relation between the air pressures of different values of the additional air chamber and the characteristic quantities of different driving time sequence currents;
and determining the target air pressure of the additional air chamber by using the first characterization model and the target characteristic quantity.
Optionally, obtaining the first characterization model includes:
acquiring training air pressures of a plurality of different values of the additional air chamber, and training characteristic values corresponding to each training air pressure;
establishing a first characterization neural network;
and training the first characterization neural network by sequentially utilizing each training air pressure and the corresponding training characteristic value until the first characterization neural network meets a preset stopping condition, and taking the finally obtained first characterization neural network as a first characterization model.
Optionally, the determining the air pressure of the additional air chamber according to the target feature quantity includes:
obtaining a second characterization model for representing the mapping relation between the self-closing force corresponding to the air pressures with different values of the additional air chamber and the characteristic quantities of different driving time sequence currents;
and determining the target air pressure of the additional air chamber by using the second characterization model and the target characteristic quantity.
Optionally, the determining, using the second characterization model and the target feature quantity, the target air pressure of the additional air chamber includes:
determining a target self-closing force corresponding to the target feature quantity by using the second characterization model;
and determining the target air pressure of the additional air chamber according to the target self-closing force.
Optionally, determining the target air pressure of the additional air chamber according to the target self-closing force includes:
acquiring the outer wall air pressure of a vacuum arc-extinguishing chamber provided with the additional air chamber, the first stress area of a corrugated pipe corresponding to the additional air chamber, and the second stress area of the additional air chamber;
and determining the target air pressure of the additional air chamber according to the target self-closing force, the outer wall air pressure, the first stressed area and the second stressed area.
Optionally, the acquiring the first stress area of the bellows corresponding to the additional air chamber, and the second stress area of the additional air chamber includes:
and analyzing and obtaining a first stressed area of the bellows corresponding to the additional air chamber and a second stressed area of the additional air chamber by adopting a finite element modeling method.
Optionally, determining the target air pressure of the additional air chamber according to the target self-closing force includes:
acquiring a self-closing force curve representing the corresponding relation between the self-closing forces with different values and the air pressures with different values;
and selecting the air pressure matched with the target self-closing force from the self-closing force curve as target air pressure.
Optionally, obtaining the second characterization model includes:
acquiring training self-closing forces with a plurality of different values, and characteristic training amounts corresponding to each training self-closing force;
constructing an initial vector machine;
and training the initial vector machine by sequentially utilizing each training self-closing force and the corresponding characteristic training quantity until the initial vector machine accords with preset training conditions, and taking the finally obtained initial vector machine as a second characterization model.
According to the technical scheme, the method for monitoring the air pressure of the additional air chamber can acquire the driving time sequence current when the motor control contact moves; the motor is positioned at the atmospheric pressure and outside the tank body, so that the acquisition of the driving time sequence current can be directly completed under the atmospheric pressure, the acquisition of the driving time sequence current does not need to process an additional air chamber, and a signal containing the driving time sequence current does not need to pass through thicker metal when the driving time sequence current is transmitted; extracting the characteristics of the driving time sequence current to obtain a target characteristic quantity of the driving time sequence current; thus, the current characteristics of the motor when controlling the movement of the contact can be analyzed; according to the target characteristic quantity, the target air pressure of the additional air chamber is determined, and the target air pressure is used for judging whether the additional air chamber leaks air or not. Therefore, the application can monitor the air leakage of the additional air chamber by utilizing the current of the motor which is easy to obtain, has stronger practicability and is simple to operate.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a vacuum interrupter according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for monitoring the air pressure of an additional air chamber according to an embodiment of the present application;
FIG. 3 is a block diagram of an air pressure monitoring device with an additional air chamber according to an embodiment of the present application;
fig. 4 is a block diagram of a hardware structure of an air pressure monitoring device with an additional air chamber according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides a method for monitoring the air pressure of an additional air chamber, which can be applied to various computing systems or monitoring systems, and also can be applied to various computer terminals or intelligent terminals, wherein an execution subject of the method can be a processor or a server of the computer terminal or the intelligent terminal, and a flow chart of the method is shown in fig. 2, and specifically comprises the following steps:
and S1, acquiring a driving time sequence current when the motor control contact moves.
Specifically, the driving time sequence current of the motor control contact during switching on and switching off can be obtained, the driving time sequence current of the motor control contact during movement can be obtained by receiving wireless signals, and the driving time sequence current of the motor control contact during movement can also be obtained by a wired technology.
And S2, carrying out feature extraction on the driving time sequence current to obtain a target feature quantity of the driving time sequence current.
Specifically, the characteristics of the driving time sequence current can be extracted through a plurality of modes such as windowing Fourier transform, fast Fourier transform or wavelet transform, and the target characteristic quantity of the driving time sequence current can be obtained after extraction.
And S3, determining the target air pressure of the additional air chamber according to the target characteristic quantity, wherein the target air pressure is used for judging whether the additional air chamber leaks air or not.
Specifically, the air pressure matching the target feature amount may be selected as the target air pressure of the additional air chamber.
Whether the target air pressure is within a preset threshold range or not can be compared, if so, the additional air chamber is not leaked, and if not, the additional air chamber is leaked, and an alarm is needed.
According to the technical scheme, the method for monitoring the air pressure of the additional air chamber can acquire the driving time sequence current when the motor control contact moves; the motor is positioned at the atmospheric pressure and outside the tank body, so that the acquisition of the driving time sequence current can be directly completed under the atmospheric pressure, the acquisition of the driving time sequence current does not need to process an additional air chamber, and a signal containing the driving time sequence current does not need to pass through thicker metal when the driving time sequence current is transmitted; extracting the characteristics of the driving time sequence current to obtain a target characteristic quantity of the driving time sequence current; thus, the current characteristics of the motor when controlling the movement of the contact can be analyzed; according to the target characteristic quantity, the target air pressure of the additional air chamber is determined, and the target air pressure is used for judging whether the additional air chamber leaks air or not. Therefore, the application can monitor the air leakage of the additional air chamber by utilizing the current of the motor which is easy to obtain, has stronger practicability and is simple to operate.
In some embodiments of the present application, the process of extracting the characteristics of the driving time-series current in step S2 to obtain the target characteristic quantity of the driving time-series current is described in detail, and the steps are as follows:
s20, performing fast Fourier transform or wavelet transform on the driving time sequence current to obtain a plurality of types of current characteristic quantities.
Specifically, the driving time sequence current may be subjected to fast fourier transform to obtain a plurality of types of current feature values, or may be subjected to wavelet transform to obtain a plurality of types of current feature values.
The current feature amounts of the plurality of types may include a plurality of values reflecting the driving timing current feature information, such as a driving timing current maximum value, a driving timing current minimum value, a driving timing current effective value, a driving timing current average value, a driving timing current spectrum maximum value, a driving timing current spectrum effective value, a driving timing current spectrum minimum value, a driving timing current spectrum average value, a driving timing current slope maximum value, and a driving timing current slope minimum value.
S21, selecting a plurality of target feature quantities matched with a preset target type from the current feature quantities.
Specifically, a plurality of driving currents under different voltages can be obtained in advance, and feature extraction is performed on each driving current to obtain a plurality of types of driving feature values under each driving current;
determining the variation percentage of the driving characteristic quantity of each type under the same air pressure variation;
sequencing the change percentages according to the sequence from big to small, sequencing the change percentages of all types, and selecting the type corresponding to the first N change percentages as a target type;
from the respective current feature amounts, a plurality of current feature amounts matching the target type may be selected as target feature amounts, respectively.
The driving current under different voltages can be obtained by analyzing a classical formula of the motor, experimental measurement or finite element calculation and the like.
The classical formula of the motor may comprise a driving circuit topology related formula, a motor structure related formula and the like related to driving time sequence current.
Obtaining the drive currents at a plurality of different voltages by analyzing the classical formula of the motor may include: analyzing driving operation work according to a classical formula to estimate peak values and effective values of driving currents under a plurality of air pressures so as to form driving currents under a plurality of different air pressures;
obtaining drive currents at a plurality of different voltages by way of experimental determination may include: simulating driving currents under different driving loads through an experimental platform;
obtaining drive currents at a plurality of different voltages by means of finite element calculations may include: according to a driving circuit of the motor, a motor model is established, and mesh subdivision is carried out on the motor model;
according to the actual motion condition of the motor, the effective motion quality of the motion of the control contact and the friction force when the control contact moves, excitation and boundary conditions are set to obtain driving currents under different air pressures. Wherein the effective moving mass controlling the movement of the contact may comprise the sum of the effective masses of all moving parts related to the movement of the contact during the movement of the contact; the friction force when driving the movement of the contact may comprise the sum of the friction forces that need to be overcome during the movement of the contact.
As can be seen from the above technical solution, the present embodiment provides an alternative way of extracting the target feature, by which the target feature that is greatly affected by the air pressure can be further extracted, so that the target air pressure is better determined by the target feature, and the accuracy of the present application is further improved.
Referring to fig. 1, it can be found that the vacuum interrupter and the additional air chamber are located in the tank body, one side of the bellows is the additional air chamber, and the other side is the vacuum interrupter, so the air pressure difference between the tank body and the additional air chamber, and the air pressure difference between the additional air chamber and the vacuum interrupter can generate self-closing force when the motor drives the contact to move, which affects the control of the motor on the contact, and further affects the driving time sequence current of the motor, namely, the air pressure difference between the tank body and the additional air chamber, and the air pressure difference between the additional air chamber and the vacuum interrupter can generate self-closing force when the motor drives the contact to move, which affects the driving time sequence current of the motor. The air pressure of the additional air chamber, the air pressure of the vacuum arc-extinguishing chamber and the air pressure in the tank body can influence the self-closing force, and in general, the numerical variation of the air pressure of the vacuum arc-extinguishing chamber and the air pressure in the tank body can not be great. On the basis, the air pressure of the additional air chamber and the driving time sequence current of the motor have a certain mapping relation, the air pressure of the additional air chamber and the self-closing force have a certain mapping relation, and meanwhile, the self-closing force and the driving time sequence current have a certain mapping relation.
According to the above three mapping relationships, in some embodiments of the present application, two ways of implementing step S3 to determine the target air pressure of the additional air chamber according to the target feature quantity are provided, and the two ways will be described in detail below, specifically as follows:
a first kind of,
S30, acquiring a first characterization model representing the mapping relation between the air pressures of different values of the additional air chamber and the characteristic quantities of different driving time sequence currents.
Specifically, the target air pressure may be determined directly using the mapping relationship between the air pressure and the driving timing current. At this time, a first characterization model may be trained, which may be a characterization model that characterizes a mapping relationship between the air pressures of different values of the additional air chamber and the characteristic quantities of the respective different driving time-series currents.
The first characterization model may be in various different forms, may be a fitting formula, may be a neural network, or may be a vector machine.
S31, determining the target air pressure of the additional air chamber by using the first characterization model and the target characteristic quantity.
Specifically, the target feature quantity may be directly input into the first characterization model, so as to obtain the target air pressure predicted by the first characterization model based on the target feature quantity.
A second kind of,
S32, obtaining a second characterization model representing the mapping relation between the self-closing force corresponding to the air pressures with different values of the additional air chamber and the characteristic quantities of the currents with different driving time sequences.
Specifically, the mapping relation between different driving time sequence currents and the self-closing forces with different values can be utilized, the target self-closing force matched with the target characteristic quantity is determined through the target characteristic quantity of the driving time sequence currents, and then the target air pressure is determined through the target self-closing force.
At this time, a second characterization model may be obtained, where the second characterization model may be a characterization model that characterizes a mapping relationship between the self-closing forces corresponding to the air pressures of different values of the additional air chamber and the feature quantities of the different driving time-series currents.
The second characterization model may be in various different forms, may be a fitting formula, may be a neural network, or may be a vector machine.
S33, determining the target air pressure of the additional air chamber by using the second characterization model and the target characteristic quantity.
Specifically, the target feature quantity may be input into the second characterization model, a target self-closing force predicted by the second characterization model based on the target feature quantity may be obtained, and then, an air pressure matching the target self-closing force may be determined as the target air pressure.
As can be seen from the above technical solutions, the present embodiment provides two alternative ways of determining the target air pressure, and by using the above embodiment, the air pressure of the additional air chamber can be monitored by using the mapping relationship between the self-closing force and the driving time sequence current, and the air pressure of the additional air chamber can also be monitored by directly using the mapping relationship between the air pressure and the driving time sequence current, so that the reliability and pertinence of the present application are further improved.
In some embodiments of the present application, a process of obtaining a first characterization model that characterizes a mapping relationship between the air pressures of different values of the additional air chamber and the characteristic quantities of the different driving time-series currents in step S30 is described in detail, and the steps are as follows:
s300, obtaining training air pressures of a plurality of different values of the additional air chamber, and training characteristic values corresponding to each training air pressure.
Specifically, the air pressure of the additional air chambers under different air leakage degrees can be determined to be respectively used as training air pressure, the driving current of the motor driving contact for switching on and switching off under each training air pressure is monitored, and the characteristic value of the driving current corresponding to each training air pressure is extracted to be used as a training characteristic value.
S301, a first characterization neural network is established.
In particular, the first characterization neural network may be formed by pre-training.
And S302, training the first characterization neural network by sequentially utilizing each training air pressure and the corresponding training characteristic value until the first characterization neural network meets a preset stopping condition, and taking the finally obtained first characterization neural network as a first characterization model.
Specifically, the number of iterations may be initialized;
inputting each training air pressure and a training characteristic value corresponding to the training air pressure into a first characterization neural network in sequence to obtain predicted air pressure output by the first characterization neural network;
updating the iteration times, adopting a random gradient descent method, adjusting parameters of the first characterization neural network according to the predicted air pressure and the input training air pressure until the predicted air pressure is consistent with the input training air pressure or the iteration times are smaller than an iteration threshold value, and taking the finally obtained first characterization neural network as a first characterization model.
From the above technical solution, it can be seen that this embodiment provides a manner of obtaining the first characterization model, by which the trained first characterization model may be obtained, so as to further improve the reliability of the present application, and after obtaining the trained first characterization model, the first characterization model may be stored for later recall.
In some embodiments of the present application, a process of obtaining a second characterization model that characterizes a mapping relationship between the self-closing forces corresponding to the air pressures of different values of the additional air chamber and the characteristic quantities of different driving time-series currents in step S32 is described in detail, and the steps are as follows:
s320, obtaining training self-closing forces with a plurality of different values and characteristic training amounts corresponding to the training self-closing forces.
Specifically, the self-closing force generated by the additional air chambers with different air leakage degrees when the motor driving contact is switched on and off can be respectively used as the training self-closing force, and the characteristic value of the driving time sequence current corresponding to each training self-closing force is determined to be used as the characteristic training quantity.
S321, constructing an initial vector machine.
Specifically, the initial vector machine may be pre-trained to be obtained.
S322, training the initial vector machine by sequentially utilizing each training self-closing force and the corresponding characteristic training quantity until the initial vector machine meets preset training conditions, and taking the finally obtained initial vector machine as a second characterization model.
Specifically, the number of iterations may be recorded;
inputting each training self-closing force and the corresponding characteristic training quantity thereof into an initial vector machine in sequence to obtain a predicted self-closing force predicted by the initial vector machine;
updating the iteration times;
and adjusting parameters of the initial vector machine according to the Euclidean distance between the predicted self-closing force and the input training self-closing force until the iteration times exceed a preset iteration threshold or the initial vector machine converges, and taking the finally obtained initial vector machine as a second characterization model.
From the above technical solution, it can be seen that this embodiment provides an optional way of training the second characterization model, by which the accuracy of the second characterization model of the present application can be further improved, and at the same time, when the second characterization model needs to be acquired later, the trained second characterization model can be directly invoked.
In some embodiments of the present application, the process of determining the target air pressure of the additional air chamber in step S33 by using the second characterization model and the target feature quantity is described in detail as follows:
s330, determining the target self-closing force corresponding to the target characteristic quantity by using the second characterization model.
Specifically, target feature quantity can be subjected to pretreatment such as normalization and cleaning to obtain pretreated target feature quantity;
and inputting the preprocessed target characteristic quantity into a second characterization model, and predicting the target self-closing force based on the target characteristic quantity by using the second characterization model.
S331, determining the target air pressure of the additional air chamber according to the target self-closing force.
Specifically, the air pressure matching the target self-closing force may be determined as the target air pressure according to the mapping relationship between the self-closing force and the air pressure.
From the above technical solution, it can be seen that this embodiment provides an optional manner of determining the target air pressure by using the second characterization model, which further improves the reliability of the present application.
In some embodiments of the present application, considering that the mapping relationship between the air pressures of different values and the self-closing forces of different values may be stored in a plurality of ways, and determining the target air pressure corresponding to the target self-closing force by using the mapping relationship of different storage ways, the present embodiment provides two storage ways, and a process of determining the target air pressure by using the two storage ways. Next, the two processes, that is, the process of determining the target air pressure of the additional air chamber according to the target self-closing force in step S331 will be described in detail, specifically as follows:
a first kind of,
S3310, acquiring the outer wall air pressure of the vacuum arc extinguishing chamber provided with the additional air chamber, the first stress area of the corrugated pipe corresponding to the additional air chamber, and the second stress area of the additional air chamber.
Specifically, the first stress area may be an area of the bellows that receives a pressure difference between the vacuum interrupter and the additional air chamber, and the second stress area may be an area of the additional air chamber that receives a pressure difference between the additional air chamber and the tank outside the vacuum interrupter.
The outer wall air pressure can be the air pressure of the vacuum interrupter outer tank body, namely, the air pressure of the vacuum interrupter outer wall.
The outer wall air pressure of the vacuum arc-extinguishing chamber provided with the additional air chamber, the first stress area of the corrugated pipe corresponding to the additional air chamber and the second stress area of the additional air chamber can be obtained in various modes, for example, a vacuum arc-extinguishing chamber formula can be formed through the structure and the shape of the vacuum arc-extinguishing chamber, and the outer wall air pressure, the first stress area and the second stress area can be obtained through analyzing the structure and the shape of the vacuum arc-extinguishing chamber; the vacuum arc-extinguishing chamber can be constructed in a finite element calculation mode, mesh division is carried out on the vacuum arc-extinguishing chamber, and the outer wall air pressure of the vacuum arc-extinguishing chamber provided with the additional air chamber, the first stress area of the corrugated pipe corresponding to the additional air chamber and the second stress area of the additional air chamber are calculated; different air pressures can be directly introduced into the additional air chamber, then the pressure caused by the different air pressures is measured, an air pressure-pressure relation curve is drawn, and the slope of the air pressure-pressure relation curve is calculated as the stressed area.
S3311, determining the target air pressure of the additional air chamber according to the target self-closing force, the outer wall air pressure, the first stressed area and the second stressed area.
Specifically, the target self-closing force, the outer wall air pressure, the first stressed area and the second stressed area are substituted into an air pressure calculation function, and the target air pressure is calculated.
The barometric pressure calculation function is as follows:
wherein P is 1 Is the target air pressure, F is the target self-closing force, P 2 Is the outer wall air pressure, S 1 Is the first stress area S 2 Is the second force bearing area.
A second kind of,
S3312, obtaining a self-closing force curve representing the corresponding relation between the self-closing forces with different values and the air pressures with different values.
Specifically, the values of the self-closing force and the values of the air pressure of the additional air chamber under different air leakage degrees can be collected in advance, and the self-closing force curve is drawn according to the self-closing forces and the air pressures of the corresponding additional air chambers.
Specifically, the value of the self-closing force and the value of the air pressure of the additional air chamber under a plurality of different air leakage degrees can be acquired through various modes such as simulation model construction or finite element calculation.
S3313, selecting the air pressure matched with the target self-closing force from the self-closing force curve as target air pressure.
Specifically, a coordinate point that coincides with the target self-closing force value may be determined in the self-closing force curve, and the air pressure corresponding to the coordinate point may be taken as the target air pressure.
From the above technical solution, it can be seen that the present embodiment provides two alternative ways of determining the target air pressure corresponding to the target self-closing force, and by using the above way, the pertinence and the feasibility of the present application can be improved.
In some embodiments of the present application, the process of obtaining the first stress area of the bellows corresponding to the additional air chamber in step S3310 and the second stress area of the additional air chamber is described in detail, and the steps are as follows:
s33100, analyzing and obtaining a first stress area of the bellows corresponding to the additional air chamber and a second stress area of the additional air chamber by adopting a finite element modeling method.
Specifically, finite element modeling can be performed on the vacuum arc-extinguishing chamber, modeling can be performed through a plurality of types of finite element commercial software, and then the modeled vacuum arc-extinguishing chamber is calculated to obtain a first stress area and a second stress area.
From the above technical solution, it can be seen that this embodiment provides an optional method for obtaining the first stress area and the second stress area, and by using the above method, the air pressure monitoring of the additional air chamber can be better achieved.
The air pressure monitoring device for the additional air chamber provided by the application will be described in detail with reference to fig. 3, and the air pressure monitoring device for the additional air chamber provided below can be compared with the air pressure monitoring method for the additional air chamber provided above.
Referring to fig. 3, it can be seen that the air pressure monitoring device of the additional air chamber may include:
the acquisition module 10 is used for acquiring driving time sequence current when the motor control contact moves;
an extracting module 20, configured to perform feature extraction on the driving time-sequence current to obtain a target feature quantity of the driving time-sequence current;
and the determining module 30 is configured to determine a target air pressure of the additional air chamber according to the target feature quantity, where the target air pressure is used to determine whether the additional air chamber leaks air.
Further, the extraction module may include:
the current characteristic quantity acquisition unit is used for carrying out fast Fourier transform or wavelet transform on the driving time sequence current to obtain a plurality of types of current characteristic quantities;
and the target feature quantity selecting unit is used for selecting a plurality of target feature quantities matched with a preset target type from the current feature quantities.
Further, the determining module may include:
the first characterization model acquisition unit is used for acquiring a first characterization model for representing the mapping relationship between the air pressures of different values of the additional air chamber and the characteristic quantities of different driving time sequence currents;
and the first characterization model utilization unit is used for determining the target air pressure of the additional air chamber by utilizing the first characterization model and the target characteristic quantity.
Further, the first characterization model acquisition unit may include:
the training air pressure acquisition subunit is used for acquiring training air pressures of a plurality of different values of the additional air chamber and training characteristic values corresponding to each training air pressure;
a first characterization neural network building subunit configured to build a first characterization neural network;
the first characterization neural network training subunit is configured to train the first characterization neural network by sequentially using each training air pressure and a training feature value corresponding to the training air pressure until the first characterization neural network meets a preset stopping condition, and take the finally obtained first characterization neural network as a first characterization model.
Further, the determining module may further include:
the second characterization model acquisition unit is used for acquiring a second characterization model for representing the mapping relationship between the self-closing force corresponding to the air pressure of different values of the additional air chamber and the characteristic quantities of different driving time sequence currents;
and the second characterization model utilization unit is used for determining the target air pressure of the additional air chamber by utilizing the second characterization model and the target characteristic quantity.
Further, the second characterization model utilization unit may include:
a target self-closing force determining subunit, configured to determine a target self-closing force corresponding to the target feature quantity by using the second characterization model;
and the target self-closing force utilization subunit is used for determining the target air pressure of the additional air chamber according to the target self-closing force.
Further, the target self-closing force utilization subunit may include:
the first stress area acquisition subunit is used for acquiring the outer wall air pressure of the vacuum arc extinguishing chamber provided with the additional air chamber, the first stress area of the corrugated pipe corresponding to the additional air chamber and the second stress area of the additional air chamber;
the first stressed area utilization subunit is used for determining the target air pressure of the additional air chamber according to the target self-closing force, the outer wall air pressure, the first stressed area and the second stressed area.
Further, the first stress area acquiring subunit may include:
and the additional air chamber modeling subunit is used for analyzing and obtaining the first stressed area of the corrugated pipe corresponding to the additional air chamber and the second stressed area of the additional air chamber by adopting a finite element modeling method.
Further, the target self-closing force utilization subunit may include:
the self-closing force curve acquisition subunit is used for acquiring self-closing force curves representing the corresponding relation between the self-closing forces with different values and the air pressures with different values;
and the self-closing force curve utilization subunit is used for selecting the air pressure matched with the target self-closing force from the self-closing force curve as target air pressure.
Further, the second characterization model acquisition unit may include:
the training self-closing force acquisition subunit is used for acquiring training self-closing forces with a plurality of different values and characteristic training amounts corresponding to each training self-closing force;
an initial vector machine constructing subunit, configured to construct an initial vector machine;
and the initial vector machine training subunit is used for training the initial vector machine by sequentially utilizing each training self-closing force and the corresponding characteristic training quantity until the initial vector machine accords with a preset training condition, and taking the finally obtained initial vector machine as a second characterization model.
The air pressure monitoring equipment, such as a PC terminal, a cloud platform, a server cluster and the like, which can be applied to the additional air chamber. Optionally, fig. 4 shows a block diagram of a hardware structure of the air pressure monitoring device of the additional air chamber, and referring to fig. 4, the hardware structure of the air pressure monitoring device of the additional air chamber may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
in the embodiment of the application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete the communication with each other through the communication bus 4;
processor 1 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present application, etc.;
the memory 3 may comprise a high-speed RAM memory, and may further comprise a non-volatile memory (non-volatile memory) or the like, such as at least one magnetic disk memory;
wherein the memory stores a program, the processor is operable to invoke the program stored in the memory, the program operable to:
acquiring a driving time sequence current when a motor control contact moves;
extracting the characteristics of the driving time sequence current to obtain a target characteristic quantity of the driving time sequence current;
and determining the target air pressure of the additional air chamber according to the target characteristic quantity, wherein the target air pressure is used for judging whether the additional air chamber leaks air or not.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The embodiment of the present application also provides a readable storage medium storing a program adapted to be executed by a processor, the program being configured to:
acquiring a driving time sequence current when a motor control contact moves;
extracting the characteristics of the driving time sequence current to obtain a target characteristic quantity of the driving time sequence current;
and determining the target air pressure of the additional air chamber according to the target characteristic quantity, wherein the target air pressure is used for judging whether the additional air chamber leaks air or not.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Various embodiments of the present application may be combined with each other. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of monitoring the air pressure of an additional air chamber, comprising:
acquiring a driving time sequence current when a motor control contact moves;
extracting the characteristics of the driving time sequence current to obtain a target characteristic quantity of the driving time sequence current;
and determining the target air pressure of the additional air chamber according to the target characteristic quantity, wherein the target air pressure is used for judging whether the additional air chamber leaks air or not.
2. The method of claim 1, wherein the performing feature extraction on the driving time-series current to obtain the target feature quantity of the driving time-series current comprises:
performing fast Fourier transform or wavelet transform on the driving time sequence current to obtain a plurality of types of current characteristic quantities;
and selecting a plurality of target feature quantities matched with a preset target type from the current feature quantities.
3. The method according to claim 1, wherein the determining the target air pressure of the additional air chamber based on the target feature quantity includes:
acquiring a first characterization model for representing the mapping relation between the air pressures of different values of the additional air chamber and the characteristic quantities of different driving time sequence currents;
and determining the target air pressure of the additional air chamber by using the first characterization model and the target characteristic quantity.
4. A method of monitoring air pressure in an additional air chamber according to claim 3, wherein obtaining the first characterization model comprises:
acquiring training air pressures of a plurality of different values of the additional air chamber, and training characteristic values corresponding to each training air pressure;
establishing a first characterization neural network;
and training the first characterization neural network by sequentially utilizing each training air pressure and the corresponding training characteristic value until the first characterization neural network meets a preset stopping condition, and taking the finally obtained first characterization neural network as a first characterization model.
5. The method of monitoring the air pressure of the additional air chamber according to claim 1, wherein the determining the air pressure of the additional air chamber based on the target feature quantity includes:
obtaining a second characterization model for representing the mapping relation between the self-closing force corresponding to the air pressures with different values of the additional air chamber and the characteristic quantities of different driving time sequence currents;
and determining the target air pressure of the additional air chamber by using the second characterization model and the target characteristic quantity.
6. The method of claim 5, wherein determining the target air pressure of the additional air chamber using the second characterization model and the target feature quantity comprises:
determining a target self-closing force corresponding to the target feature quantity by using the second characterization model;
and determining the target air pressure of the additional air chamber according to the target self-closing force.
7. The method of air pressure monitoring of an additional air chamber according to claim 6, wherein determining a target air pressure of the additional air chamber based on the target self-closing force comprises:
acquiring the outer wall air pressure of a vacuum arc-extinguishing chamber provided with the additional air chamber, the first stress area of a corrugated pipe corresponding to the additional air chamber, and the second stress area of the additional air chamber;
and determining the target air pressure of the additional air chamber according to the target self-closing force, the outer wall air pressure, the first stressed area and the second stressed area.
8. The method for monitoring the air pressure of the additional air chamber according to claim 7, wherein the step of obtaining the first stress area of the bellows corresponding to the additional air chamber and the second stress area of the additional air chamber includes:
and analyzing and obtaining a first stressed area of the bellows corresponding to the additional air chamber and a second stressed area of the additional air chamber by adopting a finite element modeling method.
9. The method of air pressure monitoring of an additional air chamber according to claim 6, wherein determining a target air pressure of the additional air chamber based on the target self-closing force comprises:
acquiring a self-closing force curve representing the corresponding relation between the self-closing forces with different values and the air pressures with different values;
and selecting the air pressure matched with the target self-closing force from the self-closing force curve as target air pressure.
10. The method of claim 5, wherein obtaining the second characterization model comprises:
acquiring training self-closing forces with a plurality of different values, and characteristic training amounts corresponding to each training self-closing force;
constructing an initial vector machine;
and training the initial vector machine by sequentially utilizing each training self-closing force and the corresponding characteristic training quantity until the initial vector machine accords with preset training conditions, and taking the finally obtained initial vector machine as a second characterization model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311079844.5A CN117109800A (en) | 2023-08-25 | 2023-08-25 | Air pressure monitoring method of additional air chamber |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311079844.5A CN117109800A (en) | 2023-08-25 | 2023-08-25 | Air pressure monitoring method of additional air chamber |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117109800A true CN117109800A (en) | 2023-11-24 |
Family
ID=88799611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311079844.5A Pending CN117109800A (en) | 2023-08-25 | 2023-08-25 | Air pressure monitoring method of additional air chamber |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117109800A (en) |
-
2023
- 2023-08-25 CN CN202311079844.5A patent/CN117109800A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9026855B2 (en) | Fault localization in distributed systems using invariant relationships | |
| CN114818515A (en) | Multidimensional time sequence prediction method based on self-attention mechanism and graph convolution network | |
| CN110926782A (en) | Circuit breaker fault type judgment method and device, electronic equipment and storage medium | |
| CN115422696B (en) | Module digital twin model building method, system, terminal and medium | |
| CN103339702B (en) | The prediction unit and method operate time of electric power switch unit | |
| CN113852432A (en) | RCS-GRU model-based spectrum prediction sensing method | |
| CN112671585B (en) | Exception handling method and device of intelligent household equipment, processor and electronic equipment | |
| CN116432542B (en) | Switch cabinet busbar temperature rise early warning method and system based on error sequence correction | |
| CN115114878A (en) | Method and device for online prediction of battery life of energy storage power station and storage medium | |
| CN113009077A (en) | Gas detection method, gas detection device, electronic apparatus, and storage medium | |
| CN112784961A (en) | Training method and device for hyper network, electronic equipment and storage medium | |
| CN113671401A (en) | Lithium battery health state assessment method based on optimization algorithm and data driving | |
| CN111458629B (en) | Inversion method and device for mechanical fault of high-voltage switch | |
| CN115204491A (en) | Production line working condition prediction method and system based on digital twinning and LSTM | |
| CN116609651A (en) | Detection method of multifunctional circuit breaker for photovoltaic | |
| CN117109800A (en) | Air pressure monitoring method of additional air chamber | |
| CN112595537B (en) | Equipment health state monitoring method and system based on signal analysis and storage medium | |
| JP6615892B2 (en) | Time-varying profiling engine for physical systems | |
| CN115269928B (en) | Transformer fault prediction method, device, equipment and medium based on digital twin | |
| CN111258863B (en) | Data anomaly detection method, device, server and computer readable storage medium | |
| CN115389812A (en) | Artificial neural network short-circuit current zero prediction method and prediction terminal | |
| CN116070153A (en) | Method, device, equipment and medium for predicting fault parameters of phased array T/R assembly | |
| CN116522594A (en) | Time self-adaptive transient stability prediction method and device based on convolutional neural network | |
| CN112731150B (en) | Voltage sag state estimation method, device, computer equipment and storage medium | |
| CN114239254A (en) | SF6 electrical equipment sound field digital twin model construction method, device and equipment |
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 |