CN116717461A - Intelligent monitoring method and system for operating state of vacuum pump - Google Patents
Intelligent monitoring method and system for operating state of vacuum pump Download PDFInfo
- Publication number
- CN116717461A CN116717461A CN202310959057.3A CN202310959057A CN116717461A CN 116717461 A CN116717461 A CN 116717461A CN 202310959057 A CN202310959057 A CN 202310959057A CN 116717461 A CN116717461 A CN 116717461A
- Authority
- CN
- China
- Prior art keywords
- signal
- vacuum pump
- state
- intelligent
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000010586 diagram Methods 0.000 claims abstract description 40
- 238000001228 spectrum Methods 0.000 claims abstract description 29
- 230000009467 reduction Effects 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000003321 amplification Effects 0.000 claims description 10
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000005299 abrasion Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B51/00—Testing machines, pumps, or pumping installations
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B37/00—Pumps having pertinent characteristics not provided for in, or of interest apart from, groups F04B25/00 - F04B35/00
- F04B37/10—Pumps having pertinent characteristics not provided for in, or of interest apart from, groups F04B25/00 - F04B35/00 for special use
- F04B37/14—Pumps having pertinent characteristics not provided for in, or of interest apart from, groups F04B25/00 - F04B35/00 for special use to obtain high vacuum
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Compressors, Vaccum Pumps And Other Relevant Systems (AREA)
Abstract
The application relates to the technical field of intelligent monitoring, and provides an intelligent monitoring method and system for the running state of a vacuum pump, wherein the method comprises the following steps: receiving a vacuum pump signal sent by a monitoring terminal; generating a signal time domain diagram and a signal frequency spectrum diagram based on M signal voltages and M time identifiers respectively, analyzing the signal time domain diagram and the signal frequency spectrum diagram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result; if the preliminary judgment result accords with the preset state fault, generating a tracking and monitoring instruction, and analyzing M signal voltages and M time identifiers to obtain signal characteristic parameters; the intelligent state recognition model is used for analyzing the signal characteristic parameters to obtain a state recognition result, so that the technical problem of low fault monitoring efficiency of the vacuum pump is solved, the operation state of the vacuum pump is automatically detected, and the technical effect of improving the fault monitoring efficiency of the vacuum pump is achieved.
Description
Technical Field
The application relates to the technical field of intelligent monitoring, in particular to an intelligent monitoring method and system for the running state of a vacuum pump.
Background
The vacuum pump is a device for removing gas in a container and reducing pressure in the container, and is generally composed of a motor, a rotor, an oiling system and a group of airtight connectors, and is mainly applied to the fields of semiconductor manufacturing, vacuum tubes, high-energy physics, optical instruments, aerospace and the like.
In the operation process of the vacuum pump, overload and abrasion faults of parts such as a rotor, a bearing and a seal exist, the operation state monitoring is required to be carried out regularly, faults are found timely, sudden shutdown or other mechanical faults are prevented during the use of the vacuum pump, however, before any maintenance and overhaul operation is carried out, the vacuum pump is closed first, necessary safety precautions are taken, the operation state monitoring operation of the vacuum pump is complex, and the fault monitoring efficiency is low.
In summary, the prior art has the technical problem of low failure monitoring efficiency of the vacuum pump.
Disclosure of Invention
The application provides an intelligent monitoring method and system for the running state of a vacuum pump, and aims to solve the technical problem of low fault monitoring efficiency of the vacuum pump in the prior art.
In view of the above problems, the embodiment of the application provides an intelligent monitoring method and system for the running state of a vacuum pump.
The first aspect of the present disclosure provides an intelligent monitoring method for a vacuum pump running state, which is applied to a monitoring platform end, wherein the method includes: receiving a vacuum pump signal sent by a monitoring terminal, wherein the vacuum pump signal comprises M signal voltages of a target vacuum pump, the M signal voltages are provided with M time marks, and M is an integer greater than 1; generating a signal time domain graph and a signal spectrogram respectively based on the M signal voltages and the M time identifiers, analyzing the signal time domain graph and the signal spectrogram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result; if the preliminary judgment result accords with a preset state fault, generating a tracking monitoring instruction, and analyzing the M signal voltages and the M time identifiers based on the tracking monitoring instruction to obtain signal characteristic parameters; and analyzing the signal characteristic parameters through an intelligent state identification model to obtain a state identification result, wherein the state identification result is an intelligent monitoring result of the running state of the target vacuum pump.
In another aspect of the present disclosure, an intelligent monitoring system for an operating state of a vacuum pump is provided, wherein the system includes: the vacuum pump signal receiving module is used for receiving the vacuum pump signal sent by the monitoring terminal, wherein the vacuum pump signal comprises M signal voltages of the target vacuum pump, the M signal voltages are provided with M time marks, and M is an integer larger than 1; the preliminary judgment result obtaining module is used for respectively generating a signal time domain diagram and a signal spectrogram based on the M signal voltages and the M time identifiers, analyzing the signal time domain diagram and the signal spectrogram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result; the signal characteristic parameter obtaining module is used for generating a tracking monitoring instruction if the preliminary judging result accords with a preset state fault, and analyzing the M signal voltages and the M time identifiers based on the tracking monitoring instruction to obtain signal characteristic parameters; the state recognition result obtaining module is used for analyzing the signal characteristic parameters through the intelligent state recognition model to obtain a state recognition result, wherein the state recognition result is an intelligent monitoring result of the running state of the target vacuum pump.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the vacuum pump signal sent by the receiving monitoring terminal is adopted; generating a signal time domain diagram and a signal frequency spectrum diagram based on M signal voltages and M time identifiers respectively, analyzing the signal time domain diagram and the signal frequency spectrum diagram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result; if the preliminary judgment result accords with the preset state fault, generating a tracking and monitoring instruction, and analyzing M signal voltages and M time identifiers to obtain signal characteristic parameters; the intelligent state recognition model is used for analyzing the signal characteristic parameters to obtain a state recognition result, so that the technical effects of automatically detecting the running state of the vacuum pump and improving the fault monitoring efficiency of the vacuum pump in the running state of the vacuum pump are realized.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Fig. 1 is a schematic diagram of a possible flow chart of an intelligent monitoring method for a vacuum pump operation state according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a possible process for obtaining signal characteristic parameters in an intelligent monitoring method for a vacuum pump running state according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a possible flow for obtaining an intelligent state recognition model in an intelligent monitoring method for a vacuum pump operation state according to an embodiment of the present application;
fig. 4 is a schematic diagram of a possible structure of an intelligent monitoring system for a vacuum pump operating state according to an embodiment of the present application.
Reference numerals illustrate: the vacuum pump signal receiving module 100, the preliminary judgment result obtaining module 200, the signal characteristic parameter obtaining module 300 and the state recognition result obtaining module 400.
Detailed Description
The embodiment of the application provides an intelligent monitoring method and system for the running state of a vacuum pump, solves the technical problem of low fault monitoring efficiency of the vacuum pump, and achieves the technical effects of automatically detecting the running state of the vacuum pump and improving the fault monitoring efficiency of the vacuum pump in the running state of the vacuum pump.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent monitoring method for a vacuum pump running state, which is applied to a monitoring platform end, where the method includes:
s10: receiving a vacuum pump signal sent by a monitoring terminal, wherein the vacuum pump signal comprises M signal voltages of a target vacuum pump, the M signal voltages are provided with M time marks, and M is an integer greater than 1;
the step S10 further includes the steps of:
s11: acquiring an original signal of the target vacuum pump through an acoustic emission sensor;
s12: preprocessing and analyzing the original signal through a pre-amplifier to obtain the vacuum pump signal;
s13: and sending the vacuum pump signal to the monitoring platform end.
Specifically, the intelligent monitoring method of the air pump running state is applied to an intelligent monitoring system of the vacuum pump running state, the intelligent monitoring system of the vacuum pump running state is in communication and interconnection with a monitoring platform end, the communication and interconnection are simply through signal transmission and interaction, a communication network is formed between the intelligent monitoring system of the vacuum pump running state and the monitoring platform end, the intelligent monitoring system based on the vacuum pump running state is in communication and interconnection with the monitoring platform end, vacuum pump signals sent by a monitoring terminal are received, the vacuum pump signals comprise M signal voltages of a target vacuum pump, the M signal voltages have M time marks, M is an integer larger than 1, and the target vacuum pump is an object monitored in the running state;
the method comprises the steps that abnormal sounds or noises are generated by irregular vibration, if the vacuum pump emits abnormal sounds or noises, the vibration exceeds a normal range, faults or problems can be indicated, based on the abnormal sounds or noises, an acoustic emission sensor is arranged, the acoustic emission sensor can convert collected vacuum pump vibration into an electric signal, a vibration meter is arranged in the acoustic emission sensor, the vibration meter is used for collecting vibration corresponding to the abnormal sounds or noises emitted by the vacuum pump, and an original signal of the target vacuum pump is collected through the acoustic emission sensor;
the pre-amplifier is generally a signal amplifier, and the signal amplifier is used for amplifying and adjusting an electric signal, and preprocessing and analyzing the original signal through the pre-amplifier to obtain the vacuum pump signal; and the intelligent monitoring system based on the running state of the vacuum pump is communicated with the monitoring platform end, the vacuum pump signal is sent to the monitoring platform end, and the vibration corresponding to abnormal sound or noise emitted by the vacuum pump is collected, so that a basis is provided for judging the running state according to the vibration of the working process of the vacuum pump.
Step S12 includes the steps of:
s121: acquiring a preset monitoring working condition;
s122: the acoustic emission sensor converts the vibration signal of the target vacuum pump under the preset monitoring working condition to obtain an electric signal, and the electric signal is used as the original signal;
s123: and the pre-amplifier processes the original signal based on a preset signal amplification constraint to obtain the vacuum pump signal.
Specifically, the original signal is preprocessed and analyzed through a preamplifier to obtain the vacuum pump signal, wherein the preset monitoring working conditions comprise a normal operation working condition, an overload fault working condition, vacuum pump operation working conditions under different wear degrees and the like, the different wear degrees can be subdivided into slight wear, moderate wear and severe wear, the preset monitoring working conditions are obtained, and the preset monitoring working conditions can be custom set by a person skilled in the relevant field;
the upper limit of the sampling frequency of the selected data acquisition equipment is as high as possible so as to ensure the integrity of the acquired signals, the acoustic emission sensor needs to have good frequency response to the main frequency range of the vacuum pump signals, and the acquisition of vibration corresponding to environmental noise is avoided to a certain extent;
the pre-set signal amplification constraint comprises the minimum amplification factor of the pre-amplifier and the maximum amplification factor of the pre-amplifier, the pre-amplifier can adjust the amplification factor of the signal to different degrees, the signal is ensured not to be submerged in background noise due to overlarge and not to exceed the range of the acquisition equipment due to overlarge, then signal acquisition under the condition of different amplitudes is met, the pre-amplifier processes the original signal based on the pre-set signal amplification constraint, preferentially amplifies and acquires vibration corresponding to abnormal noise or noise emitted by the vacuum pump, amplifies the background noise without amplification or with small amplification factor, marks the amplified signal as the vacuum pump signal, pre-processes the obtained original signal to obtain the vacuum pump signal, and improves the signal quality to a certain extent.
S20: generating a signal time domain graph and a signal spectrogram respectively based on the M signal voltages and the M time identifiers, analyzing the signal time domain graph and the signal spectrogram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result;
before the analyzing the signal time domain diagram and the signal frequency spectrum diagram by the intelligent state judgment model to judge the operation state of the target vacuum pump, the step S20 further includes the steps of:
s21: collecting a history signal record of a vacuum pump, wherein the history signal record of the vacuum pump refers to a history signal record under the preset monitoring working condition;
s22: extracting a first history record in the history signal records of the vacuum pump, wherein the first history record comprises N history signal voltages with time marks, and N is an integer greater than 1;
s23: based on the N historical signal voltages with the time marks, a first historical signal time domain diagram and a first historical signal spectrogram are respectively obtained;
s24: performing feature acquisition on the first historical signal time domain graph to obtain a first time domain feature, wherein the first time domain feature comprises a first voltage amplitude, a first impact component and a first period length;
s25: analyzing the first historical signal spectrogram to obtain a first frequency spectrum range;
s26: the first voltage amplitude, the first impact component, the first period length, and the first spectral range comprise a first historical signal characteristic;
s27: and constructing a vacuum pump signal characteristic database based on the first historical signal characteristic, and storing the vacuum pump signal characteristic database into the intelligent state judgment model.
Specifically, generating a signal time domain graph and a signal frequency spectrum graph based on the M signal voltages and the M time identifiers, respectively, includes: the abscissa and the ordinate of the first coordinate system are M time marks and M signal changes (amplitudes), the M time marks and the M signal changes are input into the first coordinate system for data statistics, and curve fitting is carried out on data points after statistics is finished to generate a signal time domain diagram; the abscissa and the ordinate of the second coordinate system are the frequency and the amplitude (amplitude) corresponding to the frequency in the M signals respectively, and the signal time domain diagram is subjected to Fourier transformation and drawn in the second coordinate system to obtain a signal spectrogram;
according to a time domain diagram of a vacuum pump under a preset monitoring working condition, signals under the preset monitoring working condition show a certain periodic characteristic in the time domain, meanwhile, signals have differences in the morphology of the time domain and are generally represented in the aspects of voltage amplitude, impact components, period length and the like, based on the time domain diagram, experience data retrieval of the vacuum pump is carried out through an intelligent monitoring system of the vacuum pump running state, and a history signal record of the vacuum pump is acquired, wherein the history signal record of the vacuum pump refers to a history signal record under the preset monitoring working condition;
taking the signal voltage as a constraint condition, extracting data in an intelligent monitoring system of the running state of the vacuum pump, and extracting a first history record in the history signal records of the vacuum pump, wherein the first history record comprises N history signal voltages with time marks, and N is an integer larger than 1; the step of generating the first historical signal time domain diagram and the first historical signal spectrogram is consistent with the step of generating the signal time domain diagram and the signal spectrogram, and repeated explanation is not performed;
the signals are different in morphology of time domains and generally show the aspects of voltage amplitude, impact components, period length and the like, based on the differences, the voltage amplitude is used as a first acquisition characteristic, the impact components are used as a second acquisition characteristic, the period length is used as a third acquisition characteristic, the first historical signal time domain diagram is subjected to characteristic acquisition to obtain a first time domain characteristic, and the first time domain characteristic comprises a first voltage amplitude, a first impact component and a first period length;
the frequency spectrum analysis can reflect the frequency composition of signals under different working conditions, the first historical signal spectrogram is analyzed to obtain a first frequency spectrum range, and the first frequency spectrum range is verified: the frequency ranges of normal operation and overload faults are mainly concentrated below 10kHz, peaks exist near 7kHz and 4kHz respectively, the loss frequency ranges of slight abrasion and moderate abrasion are similar, and the peak frequency of severe abrasion is far greater than the peak frequency of any other working condition; the first voltage amplitude, the first impact component, the first period length, and the first spectral range comprise a first historical signal characteristic;
based on the first historical signal characteristics, the first historical record is any one of a plurality of historical records corresponding to the historical signal records of the vacuum pump, the plurality of historical records corresponding to the historical signal records of the vacuum pump are traversed, a plurality of historical signal characteristics are determined, the plurality of historical records are in one-to-one correspondence with the plurality of historical signal characteristics, new combined characteristics are constructed based on the plurality of historical records and the plurality of historical signal characteristics, a vacuum pump signal characteristic database is constructed according to the combined characteristics, the plurality of historical records and the plurality of historical signal characteristics, and the vacuum pump signal characteristic database is stored as a knowledge base to the intelligent state judgment model;
after the vacuum pump signal characteristic database is stored in the intelligent state judgment model, analyzing the signal time domain diagram and the signal frequency spectrum diagram through the intelligent state judgment model, determining the signal time domain diagram and the signal frequency spectrum diagram, judging that the current operation state of the target vacuum pump belongs to the normal operation working condition or the overload fault working condition or the vacuum pump operation working condition under different wear degrees, obtaining a preliminary judgment result, carrying out quantitative characterization on different operation working condition states of the vacuum pump, and further rapidly determining the current vacuum pump operation working condition of the target vacuum pump.
After said storing to said intelligent state judgment model, step S27 further comprises the steps of:
s271: performing characteristic acquisition on the signal time domain graph to obtain time domain characteristics, wherein the time domain characteristics comprise voltage amplitude, impact components and cycle length;
s272: analyzing the signal spectrogram to obtain a frequency spectrum range;
s273: the voltage amplitude, the impact component, the period length and the frequency spectrum range form signal characteristics of the target vacuum pump;
s274: inputting the signal characteristics into the intelligent state judgment model, and traversing and matching in the vacuum pump signal characteristic database to obtain target matching characteristics;
s275: and reversely acquiring a target history state of the target matching feature, and taking the target history state as the preliminary judgment result.
Specifically, analyzing the signal time domain graph and the signal spectrogram through an intelligent state judgment model to judge the running state of the target vacuum pump to obtain a preliminary judgment result, wherein after the signal time domain graph and the signal spectrogram are stored in the intelligent state judgment model, the signal time domain graph is subjected to characteristic acquisition to obtain a time domain characteristic, and the time domain characteristic comprises a voltage amplitude, an impact component and a period length; analyzing the signal spectrogram to obtain a frequency spectrum range, wherein the frequency spectrum range comprises main concentrated frequencies and frequency peaks; the voltage amplitude, the impact component, the period length and the frequency spectrum range form signal characteristics of the target vacuum pump;
inputting the signal characteristics of the target vacuum pump as input data, inputting the intelligent state judgment model, traversing and matching in the vacuum pump signal characteristic database to obtain target matching characteristics, and carrying out similarity analysis on the signal characteristics of the current target vacuum pump and the history signal characteristics, wherein the target matching characteristics are the vacuum pump states corresponding to the most similar history signals, the similarity analysis comprises voltage amplitude comparison analysis, impact component comparison analysis, cycle length comparison analysis and frequency spectrum range comparison analysis, comparing the history signals with the least comprehensive deviation, namely the most similar history signals, and the vacuum pump states corresponding to the most similar history signals are used as the states of the current target vacuum pump;
setting a state extraction tag by taking the target matching feature as an extraction tag, and reversely acquiring a target historical state of the target matching feature through the state extraction tag, wherein the state extraction tag is used for reversely extracting the historical state; and the target historical state is used as the preliminary judgment result, and the running state judgment is carried out according to the similarity analysis, so that the objectivity and the accuracy of the vacuum pump state judgment are ensured.
S30: if the preliminary judgment result accords with a preset state fault, generating a tracking monitoring instruction, and analyzing the M signal voltages and the M time identifiers based on the tracking monitoring instruction to obtain signal characteristic parameters;
as shown in fig. 2, step S30 includes the steps of:
s31: carrying out noise reduction on the M signal voltages and the M time identifiers to obtain noise reduction signals;
s32: acquiring preset characteristic indexes, wherein the preset characteristic indexes comprise preset dimensional characteristic indexes and preset dimensionless characteristic indexes;
s33: the preset dimensionless characteristic indexes comprise a peak value, a mean value, a root mean square value and a square root amplitude value, and the preset dimensionless characteristic indexes comprise a waveform index, a peak value index, a pulse index, a margin index and a kurtosis index;
s34: and carrying out feature extraction on the noise reduction processing signal based on the preset feature index to obtain the signal feature parameter.
Specifically, the preset state fault comprises an overload fault working condition and a serious abrasion state, the preset state fault can be set by a person skilled in the relevant field in a self-defined way, if the preliminary judgment result accords with the preset state fault, the preliminary judgment of the target vacuum pump is proved to have the fault, so that the target vacuum pump needs to be continuously focused on, the state is analyzed in time, and a tracking and monitoring instruction is generated based on the continuous focus, and the tracking and monitoring instruction is used for tracking and monitoring the target vacuum pump which accords with the preset state fault;
analyzing the M signal voltages and the M time marks based on the tracking monitoring instruction to obtain signal characteristic parameters, wherein the original signals comprise environmental noise in the acquisition process, so that vibration impact signals in the working process of a vacuum pump are covered, the obtained original signals are preprocessed based on the environmental noise to obtain the vacuum pump signals, the signal quality can be improved to a certain extent, further, the M signal voltages and the M time marks are subjected to noise reduction processing through EMD (Empirical Mode Decomposition) wavelet packet threshold noise reduction processing, the signal components lower than the fixed threshold are determined to be baseline drift signals through setting the fixed threshold, the baseline drift signals are extracted, noise components in the impact signals are eliminated as much as possible, and the signal quality is further improved;
generally, dimensional time domain parameters are generally easy to be influenced by external conditions, for example, when a vacuum pump performs extraction of different vacuum degrees according to requirements, the rotating speed of the vacuum pump can be correspondingly changed, even if the vacuum pump is in the same vacuum pump operating condition, due to different parameter conditions such as rotating speed, load and the like, the obtained time domain dimensional parameters can be obviously changed, and based on the obtained time domain dimensional parameters, preset characteristic indexes are obtained, wherein the preset characteristic indexes comprise preset dimensional characteristic indexes and preset dimensionless characteristic indexes, the preset dimensional characteristic indexes comprise peak values, average values, root mean square values and square root amplitudes, and the preset dimensionless characteristic indexes comprise waveform indexes, peak value indexes, pulse indexes, margin indexes and kurtosis indexes;
and introducing dimensionless characteristic indexes, and jointly carrying out characteristic extraction on the noise reduction processing signals by combining the dimensionless characteristic indexes, wherein the characteristic extraction is characteristic clustering extraction, and the noise reduction processing signals are subjected to bottom-up condensation hierarchical clustering extraction according to the preset characteristic indexes to obtain signal characteristic parameters, so that the influence caused by external factors such as mechanical size, rotating speed and the like is reduced as much as possible.
S40: and analyzing the signal characteristic parameters through an intelligent state identification model to obtain a state identification result, wherein the state identification result is an intelligent monitoring result of the running state of the target vacuum pump.
As shown in fig. 3, before the analysis of the signal characteristic parameters by the intelligent state recognition model, step S40 further includes the steps of:
s41: extracting the characteristic parameters of the N historical signal voltages with the time marks based on the preset characteristic indexes, and recording the characteristic parameters as first historical signal characteristic parameters;
s42: the first history record comprises a first history running state and a training data set is built by combining the characteristic parameters of the first history signals;
s43: and performing supervised learning on the training data set to obtain the intelligent state recognition model.
Specifically, referring to the process of obtaining the noise reduction processing signal, noise reduction processing is performed on the N historical signal voltages with the time identifiers, so as to obtain a historical noise reduction processing signal; referring to the process of obtaining the signal characteristic parameters, introducing dimensionless characteristic indexes, and performing bottom-up aggregation hierarchical clustering extraction on the historical noise reduction processing signals according to the preset characteristic indexes to obtain the first historical signal characteristic parameters, wherein the first historical signal characteristic parameters are the same in processing process and are not subjected to repeated explanation;
the first history record comprises a first history running state, the first history signal characteristic parameter corresponds to the first history running state, the first history running state can be any one of normal running working condition, overload fault working condition and vacuum pump running working condition under different wear degrees, a plurality of history records corresponding to the vacuum pump history signal record are traversed, a plurality of history signal characteristic parameters are determined, the plurality of history records and the plurality of history signal characteristic parameters correspond to each other one by one, and the plurality of history records comprise a plurality of history running states;
based on the feedforward neural network, a training data set is built based on the plurality of historical records and the plurality of historical signal characteristic parameters, the preset monitoring working conditions are used as identification results and are transmitted into the feedforward neural network to perform model convergence learning, a plurality of historical operation states in the plurality of historical records are used as supervision contents, the training data set is subjected to supervised learning, the intelligent state identification model is built and trained, the intelligent state identification model is determined, and a model basis is provided for carrying out state identification of the vacuum pump;
and taking the signal characteristic parameters as input data, inputting the signal characteristic parameters into the intelligent state recognition model, carrying out state recognition of the vacuum pump according to the signal characteristic parameters, outputting a state recognition result by the intelligent state recognition model, wherein the state recognition result is an intelligent monitoring result of the running state of the target vacuum pump, and automatically detecting the running state of the vacuum pump in the running state of the vacuum pump to emphasize the fault of the running state of the vacuum pump, thereby providing a basis for ensuring the efficient and stable running of the vacuum pump.
In summary, the intelligent monitoring method and system for the operation state of the vacuum pump provided by the embodiment of the application have the following technical effects:
1. the vacuum pump signal sent by the receiving monitoring terminal is adopted; generating a signal time domain diagram and a signal frequency spectrum diagram based on M signal voltages and M time identifiers respectively, analyzing the signal time domain diagram and the signal frequency spectrum diagram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result; if the preliminary judgment result accords with the preset state fault, generating a tracking and monitoring instruction, and analyzing M signal voltages and M time identifiers to obtain signal characteristic parameters; the intelligent monitoring method and the system for the operation state of the vacuum pump realize the technical effects of automatically detecting the operation state of the vacuum pump in the operation state of the vacuum pump and improving the fault monitoring efficiency of the vacuum pump by analyzing the signal characteristic parameters through the intelligent state identification model to obtain a state identification result.
2. Because the noise reduction processing is carried out on the M signal voltages and the M time marks, noise reduction processing signals are obtained; acquiring a preset characteristic index; and extracting the characteristics of the noise reduction processing signals to obtain signal characteristic parameters, and reducing the influence caused by external factors such as mechanical size, rotating speed and the like as much as possible.
Example 2
Based on the same inventive concept as the intelligent monitoring method of the operation state of the vacuum pump in the foregoing embodiment, as shown in fig. 4, an embodiment of the present application provides an intelligent monitoring system of the operation state of the vacuum pump, where the system includes:
the vacuum pump signal receiving module 100 is configured to receive a vacuum pump signal sent by the monitoring terminal, where the vacuum pump signal includes M signal voltages of the target vacuum pump, the M signal voltages have M time identifiers, and M is an integer greater than 1;
the preliminary judgment result obtaining module 200 is configured to generate a signal time domain diagram and a signal spectrogram based on the M signal voltages and the M time identifiers, and analyze the signal time domain diagram and the signal spectrogram through an intelligent state judgment model to perform operation state judgment on the target vacuum pump, so as to obtain a preliminary judgment result;
the signal characteristic parameter obtaining module 300 is configured to generate a tracking and monitoring instruction if the preliminary determination result accords with a preset state fault, and analyze the M signal voltages and the M time identifiers based on the tracking and monitoring instruction to obtain a signal characteristic parameter;
the state recognition result obtaining module 400 is configured to analyze the signal characteristic parameter through an intelligent state recognition model to obtain a state recognition result, where the state recognition result is an intelligent monitoring result of the operation state of the target vacuum pump.
Further, the system includes:
the original signal acquisition module is used for acquiring original signals of the target vacuum pump through the acoustic emission sensor;
the preprocessing analysis module is used for preprocessing and analyzing the original signal through a preamplifier to obtain the vacuum pump signal;
and the vacuum pump signal sending module is used for sending the vacuum pump signal to the monitoring platform end.
Further, the system includes:
the preset monitoring working condition acquisition module is used for acquiring preset monitoring working conditions;
the signal conversion module is used for converting the vibration signal of the target vacuum pump under the preset monitoring working condition by the acoustic emission sensor to obtain an electric signal, and taking the electric signal as the original signal;
the vacuum pump signal obtaining module is used for processing the original signal by the pre-amplifier based on preset signal amplification constraint to obtain the vacuum pump signal.
Further, the system includes:
the vacuum pump history signal record acquisition module is used for acquiring a vacuum pump history signal record, wherein the vacuum pump history signal record refers to a history signal record under the preset monitoring working condition;
the first history extraction module is used for extracting a first history record in the history signal records of the vacuum pump, wherein the first history record comprises N history signal voltages with time marks, and N is an integer greater than 1;
the time domain diagram and spectrogram obtaining module is used for respectively obtaining a first historical signal time domain diagram and a first historical signal spectrogram based on the N historical signal voltages with the time identifiers;
the first time domain feature acquisition module is used for carrying out feature acquisition on the first historical signal time domain graph to acquire first time domain features, wherein the first time domain features comprise a first voltage amplitude, a first impact component and a first period length;
the first frequency spectrum range obtaining module is used for analyzing the first historical signal spectrogram to obtain a first frequency spectrum range;
the first historical signal characteristic determining module is used for forming a first historical signal characteristic by the first voltage amplitude, the first impact component, the first period length and the first frequency spectrum range;
and the vacuum pump signal characteristic database building module is used for building a vacuum pump signal characteristic database based on the first historical signal characteristic and storing the vacuum pump signal characteristic database into the intelligent state judgment model.
Further, the system includes:
the time domain feature acquisition module is used for carrying out feature acquisition on the signal time domain graph to obtain time domain features, wherein the time domain features comprise voltage amplitude values, impact components and cycle lengths;
the frequency spectrum range analysis module is used for analyzing the signal spectrogram to obtain a frequency spectrum range;
the signal characteristic determining module is used for forming signal characteristics of the target vacuum pump by the voltage amplitude, the impact component, the period length and the frequency spectrum range;
the traversal matching module is used for inputting the signal characteristics into the intelligent state judgment model, and traversing and matching in the vacuum pump signal characteristic database to obtain target matching characteristics;
and the preliminary judgment result determining module is used for reversely acquiring the target history state of the target matching feature and taking the target history state as the preliminary judgment result.
Further, the system includes:
the noise reduction processing module is used for carrying out noise reduction processing on the M signal voltages and the M time identifiers to obtain noise reduction processing signals;
the device comprises a preset characteristic index acquisition module, a preset characteristic index generation module and a preset characteristic index generation module, wherein the preset characteristic index comprises a preset dimensional characteristic index and a preset dimensionless characteristic index;
the dimension characteristic index determining module is used for presetting dimension characteristic indexes including peak value, average value, root mean square value and square root amplitude, wherein the preset dimensionless characteristic indexes include waveform indexes, peak value indexes, pulse indexes, margin indexes and kurtosis indexes;
and the feature extraction module is used for carrying out feature extraction on the noise reduction processing signal based on the preset feature index to obtain the signal feature parameter.
Further, the system includes:
the first historical signal characteristic parameter determining module is used for extracting characteristic parameters of the N historical signal voltages with the time marks based on the preset characteristic indexes and recording the characteristic parameters as first historical signal characteristic parameters;
the training data set building module is used for building a training data set by combining the first historical signal characteristic parameters, wherein the first historical record comprises a first historical running state;
and the intelligent state recognition model construction module is used for performing supervised learning on the training data set to obtain the intelligent state recognition model.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. An intelligent monitoring method for the running state of a vacuum pump, which is applied to a monitoring platform end, is characterized by comprising the following steps:
receiving a vacuum pump signal sent by a monitoring terminal, wherein the vacuum pump signal comprises M signal voltages of a target vacuum pump, the M signal voltages are provided with M time marks, and M is an integer greater than 1;
generating a signal time domain graph and a signal spectrogram respectively based on the M signal voltages and the M time identifiers, analyzing the signal time domain graph and the signal spectrogram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result;
if the preliminary judgment result accords with a preset state fault, generating a tracking monitoring instruction, and analyzing the M signal voltages and the M time identifiers based on the tracking monitoring instruction to obtain signal characteristic parameters;
and analyzing the signal characteristic parameters through an intelligent state identification model to obtain a state identification result, wherein the state identification result is an intelligent monitoring result of the running state of the target vacuum pump.
2. The intelligent monitoring method according to claim 1, applied to the monitoring terminal, comprising:
acquiring an original signal of the target vacuum pump through an acoustic emission sensor;
preprocessing and analyzing the original signal through a pre-amplifier to obtain the vacuum pump signal; and is also provided with
And sending the vacuum pump signal to the monitoring platform end.
3. The intelligent monitoring method according to claim 2, wherein the preprocessing analysis is performed on the original signal by a preamplifier to obtain the vacuum pump signal, comprising:
acquiring a preset monitoring working condition;
the acoustic emission sensor converts the vibration signal of the target vacuum pump under the preset monitoring working condition to obtain an electric signal, and the electric signal is used as the original signal;
and the pre-amplifier processes the original signal based on a preset signal amplification constraint to obtain the vacuum pump signal.
4. The intelligent monitoring method according to claim 3, further comprising, before the analyzing the signal time-domain diagram and the signal frequency-spectrum diagram by the intelligent state judgment model to judge the operation state of the target vacuum pump:
collecting a history signal record of a vacuum pump, wherein the history signal record of the vacuum pump refers to a history signal record under the preset monitoring working condition;
extracting a first history record in the history signal records of the vacuum pump, wherein the first history record comprises N history signal voltages with time marks, and N is an integer greater than 1;
based on the N historical signal voltages with the time marks, a first historical signal time domain diagram and a first historical signal spectrogram are respectively obtained;
performing feature acquisition on the first historical signal time domain graph to obtain a first time domain feature, wherein the first time domain feature comprises a first voltage amplitude, a first impact component and a first period length;
analyzing the first historical signal spectrogram to obtain a first frequency spectrum range;
the first voltage amplitude, the first impact component, the first period length, and the first spectral range comprise a first historical signal characteristic;
and constructing a vacuum pump signal characteristic database based on the first historical signal characteristic, and storing the vacuum pump signal characteristic database into the intelligent state judgment model.
5. The intelligent monitoring method according to claim 4, comprising, after said storing to said intelligent state judgment model:
performing characteristic acquisition on the signal time domain graph to obtain time domain characteristics, wherein the time domain characteristics comprise voltage amplitude, impact components and cycle length;
analyzing the signal spectrogram to obtain a frequency spectrum range;
the voltage amplitude, the impact component, the period length and the frequency spectrum range form signal characteristics of the target vacuum pump;
inputting the signal characteristics into the intelligent state judgment model, and traversing and matching in the vacuum pump signal characteristic database to obtain target matching characteristics; and is also provided with
And reversely acquiring a target history state of the target matching feature, and taking the target history state as the preliminary judgment result.
6. The intelligent monitoring method according to claim 5, wherein the analyzing the M signal voltages and the M time identifiers based on the tracking and monitoring command to obtain signal characteristic parameters includes:
carrying out noise reduction on the M signal voltages and the M time identifiers to obtain noise reduction signals;
acquiring preset characteristic indexes, wherein the preset characteristic indexes comprise preset dimensional characteristic indexes and preset dimensionless characteristic indexes; and is also provided with
The preset dimensionless characteristic indexes comprise a peak value, a mean value, a root mean square value and a square root amplitude value, and the preset dimensionless characteristic indexes comprise a waveform index, a peak value index, a pulse index, a margin index and a kurtosis index;
and carrying out feature extraction on the noise reduction processing signal based on the preset feature index to obtain the signal feature parameter.
7. The intelligent monitoring method according to claim 6, comprising, before said analyzing said signal characteristic parameters by intelligent state recognition model:
extracting the characteristic parameters of the N historical signal voltages with the time marks based on the preset characteristic indexes, and recording the characteristic parameters as first historical signal characteristic parameters;
the first history record comprises a first history running state and a training data set is built by combining the characteristic parameters of the first history signals;
and performing supervised learning on the training data set to obtain the intelligent state recognition model.
8. An intelligent monitoring system for the operation state of a vacuum pump, characterized in that it is used for implementing an intelligent monitoring method for the operation state of a vacuum pump according to any one of claims 1 to 7, comprising:
the vacuum pump signal receiving module is used for receiving the vacuum pump signal sent by the monitoring terminal, wherein the vacuum pump signal comprises M signal voltages of the target vacuum pump, the M signal voltages are provided with M time marks, and M is an integer larger than 1;
the preliminary judgment result obtaining module is used for respectively generating a signal time domain diagram and a signal spectrogram based on the M signal voltages and the M time identifiers, analyzing the signal time domain diagram and the signal spectrogram through an intelligent state judgment model, and judging the running state of the target vacuum pump to obtain a preliminary judgment result;
the signal characteristic parameter obtaining module is used for generating a tracking monitoring instruction if the preliminary judging result accords with a preset state fault, and analyzing the M signal voltages and the M time identifiers based on the tracking monitoring instruction to obtain signal characteristic parameters;
the state recognition result obtaining module is used for analyzing the signal characteristic parameters through the intelligent state recognition model to obtain a state recognition result, wherein the state recognition result is an intelligent monitoring result of the running state of the target vacuum pump.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310959057.3A CN116717461B (en) | 2023-08-01 | 2023-08-01 | Intelligent monitoring method and system for operating state of vacuum pump |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310959057.3A CN116717461B (en) | 2023-08-01 | 2023-08-01 | Intelligent monitoring method and system for operating state of vacuum pump |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116717461A true CN116717461A (en) | 2023-09-08 |
| CN116717461B CN116717461B (en) | 2023-11-28 |
Family
ID=87866363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310959057.3A Active CN116717461B (en) | 2023-08-01 | 2023-08-01 | Intelligent monitoring method and system for operating state of vacuum pump |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116717461B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118244266A (en) * | 2024-05-20 | 2024-06-25 | 湖南云箭智能科技有限公司 | High-precision measurement method and system for special tool |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006161677A (en) * | 2004-12-07 | 2006-06-22 | Mitsubishi Electric Corp | Compressor inspection device |
| CN104879294A (en) * | 2015-04-14 | 2015-09-02 | 中国农业大学 | Device and method for analyzing transient signals of water pump |
| CN110837045A (en) * | 2019-10-28 | 2020-02-25 | 江苏大学 | Method for diagnosing potential fault of pump system and detection system |
| CN112431750A (en) * | 2020-11-10 | 2021-03-02 | 北京昊鹏智能技术有限公司 | System state detection method, device, equipment, system and storage medium |
| CN114576152A (en) * | 2020-12-01 | 2022-06-03 | 格兰富控股联合股份公司 | Water pump state monitoring system, monitoring method, device, electronic equipment and medium |
| CN116292246A (en) * | 2023-03-02 | 2023-06-23 | 苏州科瑞达智能科技有限公司 | Fault monitoring method and system for vacuum pump |
-
2023
- 2023-08-01 CN CN202310959057.3A patent/CN116717461B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006161677A (en) * | 2004-12-07 | 2006-06-22 | Mitsubishi Electric Corp | Compressor inspection device |
| CN104879294A (en) * | 2015-04-14 | 2015-09-02 | 中国农业大学 | Device and method for analyzing transient signals of water pump |
| CN110837045A (en) * | 2019-10-28 | 2020-02-25 | 江苏大学 | Method for diagnosing potential fault of pump system and detection system |
| CN112431750A (en) * | 2020-11-10 | 2021-03-02 | 北京昊鹏智能技术有限公司 | System state detection method, device, equipment, system and storage medium |
| CN114576152A (en) * | 2020-12-01 | 2022-06-03 | 格兰富控股联合股份公司 | Water pump state monitoring system, monitoring method, device, electronic equipment and medium |
| CN116292246A (en) * | 2023-03-02 | 2023-06-23 | 苏州科瑞达智能科技有限公司 | Fault monitoring method and system for vacuum pump |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118244266A (en) * | 2024-05-20 | 2024-06-25 | 湖南云箭智能科技有限公司 | High-precision measurement method and system for special tool |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116717461B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiang et al. | Fault diagnosis of rolling bearing under fluctuating speed and variable load based on TCO spectrum and stacking auto-encoder | |
| JP7199608B2 (en) | Methods and apparatus for inspecting wind turbine blades, and equipment and storage media therefor | |
| CN116717461B (en) | Intelligent monitoring method and system for operating state of vacuum pump | |
| CN112179691A (en) | Mechanical equipment running state abnormity detection system and method based on counterstudy strategy | |
| CN113551765A (en) | Sound spectrum analysis and diagnosis method for equipment fault | |
| CN111209934A (en) | Fan fault prediction and alarm method and system | |
| CN107545228B (en) | Electrified railway operation condition identification method based on wavelet transformation | |
| CN111879514A (en) | Brushless direct current motor bearing fault diagnosis method based on ELM model | |
| CN110632484A (en) | ELM-based GIS partial discharge defect diagnosis and classification system and method | |
| CN112098088A (en) | Rolling bearing fault diagnosis method based on KICA-fractal theory | |
| CN116230013A (en) | Transformer fault voiceprint detection method based on x-vector | |
| CN106546918A (en) | A kind of method for diagnosing faults of Hydropower Unit | |
| CN112666430B (en) | Intelligent fault detection method and system for voiceprint of transformer | |
| CN117932358A (en) | Intelligent remote electric field fault diagnosis method and system | |
| CN117782198B (en) | Highway electromechanical equipment operation monitoring method and system based on cloud edge architecture | |
| CN117093938A (en) | Fan bearing fault detection method and system based on deep learning | |
| CN116884432A (en) | VMD-JS divergence-based power transformer fault voiceprint diagnosis method | |
| CN113822565B (en) | Method for graded and refined analysis of time-frequency characteristics of fan monitoring data | |
| CN115310497A (en) | Abnormity identification method for bearing of numerical control machine tool | |
| Zhao et al. | A fault diagnosis approach for rolling element bearing based on S-transform and artificial neural network | |
| Istiaque et al. | Classification of Bearing Fault Using Radial Basis Neural Network and Genetic Algorithm | |
| CN117406046B (en) | Partial discharge detection device | |
| CN117672255B (en) | Abnormal equipment identification method and system based on artificial intelligence and equipment operation sound | |
| CN116520143B (en) | Voiceprint data-based rotating equipment monitoring method, device, equipment and medium | |
| CN114460466B (en) | Virtual sensor equipment for transmission monitoring and monitoring method thereof |
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 |