CN116538092B - Compressor on-line monitoring and diagnosing method, device, equipment and storage medium - Google Patents
Compressor on-line monitoring and diagnosing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116538092B CN116538092B CN202310823240.0A CN202310823240A CN116538092B CN 116538092 B CN116538092 B CN 116538092B CN 202310823240 A CN202310823240 A CN 202310823240A CN 116538092 B CN116538092 B CN 116538092B
- Authority
- CN
- China
- Prior art keywords
- fault
- compressor
- characteristic information
- equipment
- compressor equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000003745 diagnosis Methods 0.000 claims abstract description 82
- 238000004458 analytical method Methods 0.000 claims abstract description 48
- 238000013135 deep learning Methods 0.000 claims abstract description 17
- 238000007405 data analysis Methods 0.000 claims abstract description 14
- 230000036541 health Effects 0.000 claims abstract description 13
- 238000013178 mathematical model Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 8
- 238000002405 diagnostic procedure Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 238000003909 pattern recognition Methods 0.000 claims description 5
- 230000010349 pulsation Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000013461 design Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000005299 abrasion Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013433 optimization analysis Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000003872 anastomosis Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000000368 destabilizing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity 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
- F04C—ROTARY-PISTON, OR OSCILLATING-PISTON, POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; ROTARY-PISTON, OR OSCILLATING-PISTON, POSITIVE-DISPLACEMENT PUMPS
- F04C28/00—Control of, monitoring of, or safety arrangements for, pumps or pumping installations specially adapted for elastic fluids
- F04C28/28—Safety arrangements; Monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The application relates to a compressor on-line monitoring and diagnosing method, a device, equipment and a storage medium. The method comprises the following steps: collecting vibration signals and operation data of compressor equipment; extracting characteristic information of the compressor equipment from the vibration signals and the operation data by adopting a fault identification analysis model; comparing the extracted characteristic information with a fault mode database, carrying out fault mode analysis on the compressor equipment according to the comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system; and the expert diagnosis system performs fault diagnosis and health state prediction on the compressor equipment by using the deep learning data analysis model based on the characteristic information and the fault mode classification result, and generates a fault diagnosis conclusion of the compressor equipment. The embodiment of the application can more comprehensively and accurately monitor the vibration and diagnose the faults of the screw compressor, and improve the fault prediction precision and the stability and reliability of compressor equipment.
Description
Technical Field
The application belongs to the technical field of energy power, and particularly relates to a compressor on-line monitoring and diagnosing method, device, equipment and storage medium.
Background
Compressors are a common type of equipment in industrial production, the stability and reliability of which are critical to the continuous performance of the production. The reliability problem in the use process not only can influence the normal operation of equipment, but also can lead to equipment damage. In particular to the application of a screw compressor to large scientific devices such as a superconducting accelerator, and if the compressor fails, serious accidents of paralysis of the whole scientific device are usually caused.
At present, some solutions for monitoring vibration of a screw compressor exist, but the traditional vibration monitoring solutions neglect the influence of high-frequency vibration impact on equipment wear and fatigue, and do not consider characteristic factors such as aerodynamics, rotor dynamics and the like. Meanwhile, the national standard vibration intensity value does not correspond to the vibration frequency, and is not suitable for the screw compressor with the energy impact of high-frequency signals. In addition, the existing vibration monitoring scheme usually only focuses on data acquisition and simple model analysis, has single functions and models, cannot meet actual requirements, has the problems of low accuracy, inaccurate and timely diagnosis and the like, is less in application in actual engineering, and cannot effectively guide the optimized development of screw rotor technology and improve the reliability of the screw compressor.
Disclosure of Invention
The application provides a compressor on-line monitoring, diagnosis and diagnosis analysis method, device, equipment and storage medium, which aim to solve at least one of the technical problems in the prior art to a certain extent.
In order to solve the problems, the application provides the following technical scheme:
an on-line monitoring and diagnosing method for a compressor, comprising:
collecting vibration signals and operation data of compressor equipment;
extracting characteristic information of the compressor equipment from the vibration signals and the operation data by adopting a fault identification analysis model, wherein the characteristic information comprises aerodynamic characteristics and rotor dynamic characteristics;
comparing the extracted characteristic information with a fault mode database, carrying out fault mode analysis on the compressor equipment according to a comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system;
and the expert diagnosis system performs fault diagnosis and health state prediction on the compressor equipment by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, predicts a fault cause and a fault evolution trend by combining a fatigue failure mathematical model, and generates a fault diagnosis conclusion of the compressor equipment.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the vibration signals and the operation data of the compressor equipment are collected specifically as follows:
the vibration signal of the compressor equipment is acquired in real time through a data acquisition device, and operation data of the compressor equipment are acquired in real time, wherein the data acquisition device is a vibration sensor, a speed sensor or a displacement sensor, and the operation data comprise pressure and temperature data of an air path and an oil path of the compressor equipment.
The technical scheme adopted by the embodiment of the application further comprises the following steps: after the vibration signals and the operation data of the compressor equipment are collected, the method further comprises the following steps:
and converting the vibration signal into a digital signal by adopting low-pass filtering and AD conversion, and uploading the digital signal and the operation data to a cloud service platform.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the characteristic information of the compressor equipment is extracted from the vibration signals and the operation data by adopting a fault identification analysis model specifically comprises the following steps:
receiving digital signals and operation data of compressor equipment through the cloud service platform, preprocessing the digital signals and the operation data, and then performing deep learning and pattern recognition on the digital signals and the operation data based on a large database fault analysis mode through the fault recognition analysis model to extract aerodynamic characteristics and rotor dynamic characteristics of the compressor equipment; the fault identification analysis model is obtained through training of a large database and a classification sample model base.
The technical scheme adopted by the embodiment of the application further comprises the following steps: comparing the extracted characteristic information with a fault mode database, analyzing the fault mode of the compressor equipment according to the comparison result, and after obtaining the fault mode classification result of the compressor equipment, further comprising:
and forming a log file and a parameter history curve according to the analysis result of the fault mode, and classifying the fault mode into a big data archive of the cloud service platform.
The technical scheme adopted by the embodiment of the application further comprises the following steps: based on characteristic information and a fault mode classification result, the expert diagnosis system utilizes a deep learning data analysis model to conduct fault diagnosis and health state prediction on the compressor equipment, and predicts a fault cause and a fault evolution trend by combining a fatigue failure mathematical model, wherein the generation of a fault diagnosis conclusion of the compressor equipment is specifically as follows:
the method comprises the steps of receiving characteristic information and fault mode classification results through an expert diagnosis system, analyzing intrinsic frequency identification, operation and regulation strategy analysis, factor decomposition inducing fault modes, formation and evolution processes of an oil film, rotor thermal state deformation and gap change, analyzing a gas working medium pulsation mechanism of compressor equipment by utilizing a large database fault mode, establishing a fatigue failure mathematical model, predicting fault reasons and fault evolution trend by utilizing the fatigue failure mathematical model according to a time domain waveform of a vibration signal, a frequency domain characteristic and a correlation analysis method of the fault modes and the factors, and generating a fault diagnosis conclusion of the compressor equipment; the fault diagnosis conclusion comprises a mechanical fault, an operation fault or a control fault.
The technical scheme adopted by the embodiment of the application further comprises the following steps: after the fault diagnosis conclusion of the compressor equipment is generated, the method further comprises the following steps:
and returning a fault solution strategy to the compressor equipment according to the fault diagnosis conclusion.
The embodiment of the application adopts another technical scheme that: an on-line monitoring and diagnostic device for a compressor, comprising:
and a data acquisition module: the vibration signal and the operation data of the compressor equipment are collected;
and the feature extraction module is used for: extracting characteristic information of the compressor device from the vibration signal and the operation data by using a fault identification analysis model, wherein the characteristic information comprises aerodynamic characteristics and rotor dynamics characteristics;
and a fault identification module: the fault mode analysis method comprises the steps of comparing the extracted characteristic information with a fault mode database, analyzing the fault mode of the compressor equipment according to a comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system;
and a fault diagnosis module: the expert diagnosis system is used for carrying out fault diagnosis and health state prediction on the compressor equipment by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, and generating a fault diagnosis conclusion of the compressor equipment by combining a fatigue failure mathematical model to predict fault reasons and fault evolution trend.
The embodiment of the application adopts the following technical scheme: an apparatus comprising a processor, a memory coupled to the processor, wherein,
the memory stores program instructions for realizing the compressor on-line monitoring and diagnosing method;
the processor is used for executing the program instructions stored in the memory to control the compressor on-line monitoring and diagnosis method.
The embodiment of the application adopts the following technical scheme: a storage medium storing program instructions executable by a processor for performing the compressor on-line monitoring and diagnostic method.
Compared with the prior art, the embodiment of the application has the beneficial effects that: the online monitoring and diagnosing method, device, equipment and storage medium of the compressor can perform deep learning and pattern recognition based on the fault pattern analysis of the large database, can more truly, comprehensively and accurately consider the characteristics of gas dynamics and rotor dynamics, improve rotor molded line design, rotor dynamics design and the like through database optimization analysis, realize more accurate, timely and efficient online monitoring and fault diagnosis of vibration signals of the screw compressor, and prolong maintenance-free period of the screw compressor while improving stability and reliability of the screw compressor. The embodiment of the application comprehensively considers the fault mode and the occurrence mechanism, working medium, rotor molded line, gas dynamics, rotor dynamics, and other factors, can more comprehensively and accurately monitor vibration and diagnose faults of the screw compressor, and improves the fault prediction precision and the stability and reliability of compressor equipment.
Drawings
FIG. 1 is a flow chart of a compressor on-line monitoring and diagnostic method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of the basic modules of an expert diagnostic system in accordance with an embodiment of the present application;
FIG. 3 is a schematic illustration of the results of an embodiment of the present application in an experiment;
FIG. 4 is a schematic diagram of peak clipping and quantitative analysis of vibration waveforms in experiments according to an embodiment of the present application;
FIG. 5 is a schematic diagram of an on-line monitoring and diagnosing apparatus for a compressor according to an embodiment of the present application;
FIG. 6 is a schematic diagram of an apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a storage medium 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 fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. 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 terms "first," "second," "third," and the like in this disclosure are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", and "a third" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise. All directional indications (such as up, down, left, right, front, back … …) in embodiments of the present application are merely used to explain the relative positional relationship, movement, etc. between the components in a particular gesture (as shown in the drawings), and if the particular gesture changes, the directional indication changes accordingly. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Referring to fig. 1, a flow chart of a compressor on-line monitoring and diagnosing method according to an embodiment of the application is shown. The compressor on-line monitoring and diagnosing method provided by the embodiment of the application comprises the following steps of:
s100: the method comprises the steps that vibration signals of compressor equipment are collected in real time through a data collection device, and operation data of the compressor equipment are obtained in real time;
in the step, the data acquisition device is a vibration sensor, a speed sensor or a displacement sensor, wherein the vibration sensor is a piezoelectric type, piezoresistive type or capacitive type vibration sensor, the speed sensor is an eddy current type or magneto-electric type speed sensor, and the displacement sensor is an eddy current type or laser type displacement sensor. Taking a vibration sensor as an example, the vibration sensor is composed of a high-precision 3-coordinate acceleration sensor, a filter, an analog-to-digital converter, a signal conditioner, a signal shielding device and the like and is used for estimating the vibration state of an object by detecting the vibration size and the vibration frequency of the object. Specifically, the vibration sensor needs to measure vibration signals of 3 coordinates at one measuring point, the acceleration range is plus or minus 5g (g is gravity acceleration), the signal frequency can be acquired within the range of 10 to 3000Hz, the sampling frequency is 5000 to 40000Hz, and the values can be optimized and improved specifically according to practical application scenes so as to improve the acquisition sensitivity and precision of the vibration signals. The operation data includes, but is not limited to, pressure and temperature of the gas and oil passages of the compressor device.
S110: converting the acquired vibration signals into digital signals by adopting low-pass filtering and AD conversion, and uploading the digital signals and operation data to a cloud service platform;
s120: the method comprises the steps of receiving digital signals and operation data of compressor equipment through a cloud service platform, preprocessing the digital signals and the operation data, and identifying and extracting characteristic information such as gas dynamics, rotor dynamics and the like of the compressor equipment from the digital signals and the operation data through a fault identification analysis model;
in the step, the fault identification analysis model is obtained through training of a large database and a classification sample model library. The fault recognition analysis model performs deep learning and pattern recognition on the digital signals and the operation data based on a large database fault analysis mode, and extracts aerodynamic characteristics and rotor dynamic characteristics of the compressor equipment. Wherein rotor dynamics refers to all dynamics related to the rotating machine rotor and its components and structures, including dynamic response, vibration, strength, fatigue, stability, reliability, etc.; aerodynamic characteristics refer to characteristics such as forces and motion states to which an object is subjected when moving in air. Data support for subsequent expert diagnostic systems may be provided by extracting aerodynamic and rotor dynamics characteristic information of the compressor rig.
S130: comparing the extracted characteristic information with a fault mode database, analyzing and classifying the fault mode of the compressor equipment according to the comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system;
in this step, the fault mode database is an actual physical machine or operation parameter characteristic fault mode database. The cloud service platform also has the functions of data statistics classification, formation of log files, parameter history curves and the like, performs full-element fault mode analysis after data preprocessing and feature information extraction on the cloud service platform, obtains a fault mode classification result of the compressor equipment, forms the log files and the parameter history curves according to the fault mode analysis result, and classifies the fault mode into a big data archive.
S140: the method comprises the steps of receiving characteristic information and a fault mode classification result through an expert diagnosis system, carrying out fault diagnosis and health state prediction on a screw compressor by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, and generating a fault diagnosis conclusion of compressor equipment by combining a fatigue failure mathematical model to predict a fault cause and a fault evolution trend;
in the step, the expert diagnosis system utilizes a large database fault mode to carry out comprehensive analysis on the characteristics frequency identification, operation and regulation strategy analysis, factor decomposition inducing the fault mode, formation and evolution process of an oil film, rotor thermal state deformation and gap change, gas working medium pulsation mechanism and the like of parts such as a bearing, a rotor, a shell, a pipe valve and the like of the compressor equipment, establishes a fatigue failure mathematical model, predicts fault reasons and fault evolution trend by utilizing the fatigue failure mathematical model according to a time domain waveform of a vibration signal, a frequency domain characteristic and a correlation analysis method of the fault mode and the factors, and carries out multi-level health state prediction on the compressor equipment such as dynamic analysis, a thermodynamic model, an airflow pulsation vibration model, natural frequency mode analysis of the parts and the like, thereby realizing more comprehensive and accurate online vibration monitoring and fault early warning of the compressor equipment.
Specifically, please refer to fig. 2 together, which is a schematic diagram of basic modules of an expert diagnosis system according to an embodiment of the present application, where the expert diagnosis system according to an embodiment of the present application includes a database module, an intelligent data analysis module, and a fault diagnosis analysis module, and the interaction between the modules is used to implement a fault diagnosis problem of a compressor device. Specifically, the database module comprises a compressor engineering database based on the primarily completed fault classification, a primarily fault sample database, a database of dynamic monitoring signals, a basic physical library of materials such as working media and the like; the intelligent data analysis module is used for introducing a fault mode recognition method to perform feature recognition, model training and classification prediction, so that fault diagnosis can be performed, prediction of instability and fatigue failure models can be realized, a deep learning data analysis model based on a multi-layer neural network model is established, and a reasonable fault solving strategy is provided. The fault diagnosis analysis module needs to combine the actual physical process to carry out multi-level health state prediction such as rotor dynamics analysis, thermodynamic model, airflow pulsation vibration model, natural frequency modal analysis of components and the like on a mechanical mechanism and characteristics thereof, wherein the most core part is the judgment on the engagement state of the rotor, including whether the rotor has poor engagement, friction between the rotor and a shell, abrasion, fatigue and bearing characteristic parameter identification, and the prediction of formation, evolution and lubrication performance attenuation of an oil film is carried out by combining an oil path model.
Further, the fault diagnosis conclusion is classified into a fault sample library, so that the accuracy of the expert diagnosis system can be improved. Meanwhile, the expert diagnosis system also has the function of guiding optimization of different working conditions and rotor specifications to improve the reliability scheme, and can help a user to quickly remove faults and perfect the system performance. The expert diagnosis system adopts an intelligent multi-layer analysis method to replace manual expert intervention, can avoid misjudgment or missed judgment of tendencies of experts with different professional degrees, and is beneficial to improving the accuracy of vibration monitoring and fault early warning. Characteristic parameters among different model layers can be transmitted, and when the characteristic parameters reach a set threshold value, an expert diagnosis system can reach a destabilizing state.
S150: returning a corresponding fault resolution strategy to the compressor equipment according to the fault diagnosis conclusion;
in this step, the fault diagnosis conclusion includes, but is not limited to, mechanical faults, operation faults, control faults (including faults caused by external environments), and the like, and the expert diagnosis system can provide specific operation suggestions according to different fault diagnosis conclusions. Specifically, for operation-type faults and control-type faults, the expert diagnostic system can feed back to the control system of the compressor equipment for automatic resolution. For mechanical faults, the expert diagnosis system returns fault solving strategies such as emergency stop, important fault maintenance or slight fault continuous operation observation according to different fault degrees. Mechanical faults can also provide basis for new rotor profiles and design adjustments of the rotor train.
Please refer to fig. 3, which is a schematic diagram of the experimental results of the embodiment of the present application. Experiments show that the expert diagnosis system of the embodiment of the application diagnoses the rotor meshing problem and the slight abrasion of the bearing by identifying the vibration signals with different components, and discovers the influence of high-frequency vibration impact on the stability, and the peak clipping and the quantitative analysis on the vibration waveform directly correspond to the rotor rubbing degree, as shown in fig. 4. Therefore, experiments show that the embodiment of the application can efficiently and accurately locate the cause of the fault. By comparing the disassembly of the equipment and judging the slight abrasion of the fault germination period, the high anastomosis is obtained. Experiments also prove that the practice of using the vibration intensity as the reliability value of the screw compressor by the national standard is unsuitable without considering frequency factors and the actual condition of screw rotor operation. These experimental results fully demonstrate the feasibility and practicality of the embodiments of the application.
It will be appreciated that embodiments of the present application may also be applied to fault diagnosis and health status monitoring of other types of rotary machinery such as centrifugal pumps, centrifugal compressors, screw vacuum pumps, roots pumps, and the like. The expert diagnosis system of the embodiment of the application can be connected with other intelligent industrial equipment to form a complete industrial Internet system, thereby realizing comprehensive intelligent management and maintenance of the equipment.
Based on the above, the online monitoring and diagnosing method for the compressor of the second embodiment of the application carries out deep learning and pattern recognition based on the fault pattern analysis of the large database, can more truly, comprehensively and accurately consider the characteristics of gas dynamics and rotor dynamics, improves rotor molded line design, rotor dynamics design and the like through database optimization analysis, realizes more accurate, timely and efficient online monitoring and fault diagnosis of vibration signals of the screw compressor, and prolongs maintenance-free period of the screw compressor while improving stability and reliability of the screw compressor. The embodiment of the application comprehensively considers the fault mode and the factors such as the occurrence mechanism, working medium, rotor molded line, gas dynamics, rotor dynamics and the like, can more comprehensively and accurately monitor the vibration and diagnose the fault of the screw compressor, improves the fault prediction precision and the stability and reliability of compressor equipment, provides a reasonable fault solving strategy for users, helps the users to quickly remove the fault and improves the system performance.
Fig. 5 is a schematic structural diagram of an on-line monitoring and diagnosing apparatus for a compressor according to an embodiment of the present application. The compressor on-line monitoring and diagnosing apparatus 40 of the embodiment of the present application includes:
data acquisition module 41: the vibration signal and the operation data of the compressor equipment are collected;
feature extraction module 42: extracting characteristic information of the compressor device from the vibration signal and the operation data by using a fault identification analysis model, wherein the characteristic information comprises aerodynamic characteristics and rotor dynamics characteristics;
fault identification module 43: the fault mode analysis method comprises the steps of comparing the extracted characteristic information with a fault mode database, analyzing the fault mode of the compressor equipment according to a comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system;
fault diagnosis module 44: the expert diagnosis system is used for carrying out fault diagnosis and health state prediction on the compressor equipment by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, and generating a fault diagnosis conclusion of the compressor equipment by combining a fatigue failure mathematical model to predict fault reasons and fault evolution trend.
Fig. 6 is a schematic diagram of an apparatus structure according to an embodiment of the application. The apparatus 50 comprises:
a memory 51 storing executable program instructions;
a processor 52 connected to the memory 51;
the processor 52 is configured to call the executable program instructions stored in the memory 51 and perform the steps of: collecting vibration signals and operation data of compressor equipment; extracting characteristic information of the compressor equipment from the vibration signals and the operation data by adopting a fault identification analysis model, wherein the characteristic information comprises aerodynamic characteristics and rotor dynamic characteristics; comparing the extracted characteristic information with a fault mode database, carrying out fault mode analysis on the compressor equipment according to a comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system; and the expert diagnosis system performs fault diagnosis and health state prediction on the compressor equipment by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, predicts a fault cause and a fault evolution trend by combining a fatigue failure mathematical model, and generates a fault diagnosis conclusion of the compressor equipment.
The processor 52 may also be referred to as a CPU (Central Processing Unit ). The processor 52 may be an integrated circuit chip having signal processing capabilities. Processor 52 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Fig. 7 is a schematic structural diagram of a storage medium according to an embodiment of the application. The storage medium of the embodiment of the present application stores program instructions 61 capable of implementing the steps of: collecting vibration signals and operation data of compressor equipment; extracting characteristic information of the compressor equipment from the vibration signals and the operation data by adopting a fault identification analysis model, wherein the characteristic information comprises aerodynamic characteristics and rotor dynamic characteristics; comparing the extracted characteristic information with a fault mode database, carrying out fault mode analysis on the compressor equipment according to a comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system; and the expert diagnosis system performs fault diagnosis and health state prediction on the compressor equipment by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, predicts a fault cause and a fault evolution trend by combining a fatigue failure mathematical model, and generates a fault diagnosis conclusion of the compressor equipment. The program instructions 61 may be stored in the storage medium as a software product, and include instructions for causing a device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program instructions, or a terminal device such as a computer, a server, a mobile phone, a tablet, or the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the partitioning of elements is merely a logical functional partitioning, and there may be additional partitioning in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not implemented. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units. The foregoing is only the embodiments of the present application, and therefore, the patent scope of the application is not limited thereto, and all equivalent structures or equivalent processes using the descriptions of the present application and the accompanying drawings, or direct or indirect application in other related technical fields, are included in the scope of the application.
Claims (8)
1. An on-line monitoring and diagnosing method for a compressor, comprising:
collecting vibration signals and operation data of compressor equipment;
extracting characteristic information of the compressor equipment from the vibration signals and the operation data by adopting a fault identification analysis model, wherein the characteristic information comprises aerodynamic characteristics and rotor dynamic characteristics;
comparing the extracted characteristic information with a fault mode database, carrying out fault mode analysis on the compressor equipment according to a comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system;
the expert diagnosis system performs fault diagnosis and health state prediction on the compressor equipment by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, predicts a fault cause and a fault evolution trend by combining a fatigue failure mathematical model, and generates a fault diagnosis conclusion of the compressor equipment;
the characteristic information of the compressor equipment is extracted from the vibration signals and the operation data by adopting a fault identification analysis model specifically comprises the following steps:
the method comprises the steps of receiving digital signals and operation data of compressor equipment through a cloud service platform, preprocessing the digital signals and the operation data, and carrying out deep learning and pattern recognition on the digital signals and the operation data based on a large database fault analysis mode through the fault recognition analysis model to extract aerodynamic characteristics and rotor dynamic characteristics of the compressor equipment; the fault identification analysis model is obtained through training of a large database and a classification sample model library;
based on characteristic information and a fault mode classification result, the expert diagnosis system utilizes a deep learning data analysis model to conduct fault diagnosis and health state prediction on the compressor equipment, and predicts a fault cause and a fault evolution trend by combining a fatigue failure mathematical model, wherein the generation of a fault diagnosis conclusion of the compressor equipment is specifically as follows:
the method comprises the steps of receiving characteristic information and fault mode classification results through an expert diagnosis system, analyzing intrinsic frequency identification, operation and regulation strategy analysis, factor decomposition inducing fault modes, formation and evolution processes of an oil film, rotor thermal state deformation and gap change, analyzing a gas working medium pulsation mechanism of compressor equipment by utilizing a large database fault mode, establishing a fatigue failure mathematical model, predicting fault reasons and fault evolution trend by utilizing the fatigue failure mathematical model according to a time domain waveform of a vibration signal, a frequency domain characteristic and a correlation analysis method of the fault modes and the factors, and generating a fault diagnosis conclusion of the compressor equipment; the fault diagnosis conclusion comprises a mechanical fault, an operation fault or a control fault.
2. The compressor on-line monitoring and diagnostic method of claim 1, wherein the collecting vibration signals and operation data of the compressor device is specifically as follows:
the vibration signal of the compressor equipment is acquired in real time through a data acquisition device, and operation data of the compressor equipment are acquired in real time, wherein the data acquisition device is a vibration sensor, a speed sensor or a displacement sensor, and the operation data comprise pressure and temperature data of an air path and an oil path of the compressor equipment.
3. The compressor on-line monitoring and diagnostic method of claim 2, further comprising, after the collecting the vibration signal and the operation data of the compressor device:
and converting the vibration signal into a digital signal by adopting low-pass filtering and AD conversion, and uploading the digital signal and the operation data to a cloud service platform.
4. The compressor on-line monitoring and diagnosing method as set forth in claim 3, wherein the comparing the extracted characteristic information with a fault mode database, performing fault mode analysis on the compressor device according to the comparison result, and after obtaining a fault mode classification result of the compressor device, further includes:
and forming a log file and a parameter history curve according to the analysis result of the fault mode, and classifying the fault mode into a big data archive of the cloud service platform.
5. The compressor on-line monitoring and diagnosing method as recited in claim 4, further comprising, after generating a fault diagnosis conclusion of the compressor apparatus:
and returning a fault solution strategy to the compressor equipment according to the fault diagnosis conclusion.
6. An on-line monitoring and diagnosing apparatus for a compressor using the on-line monitoring and diagnosing method for a compressor as set forth in claim 1, comprising:
and a data acquisition module: the vibration signal and the operation data of the compressor equipment are collected;
and the feature extraction module is used for: extracting characteristic information of the compressor device from the vibration signal and the operation data by using a fault identification analysis model, wherein the characteristic information comprises aerodynamic characteristics and rotor dynamics characteristics;
and a fault identification module: the fault mode analysis method comprises the steps of comparing the extracted characteristic information with a fault mode database, analyzing the fault mode of the compressor equipment according to a comparison result to obtain a fault mode classification result of the compressor equipment, and uploading the characteristic information and the fault mode classification result to an expert diagnosis system;
and a fault diagnosis module: the expert diagnosis system is used for carrying out fault diagnosis and health state prediction on the compressor equipment by utilizing a deep learning data analysis model based on the characteristic information and the fault mode classification result, and generating a fault diagnosis conclusion of the compressor equipment by combining a fatigue failure mathematical model to predict fault reasons and fault evolution trend.
7. An apparatus for implementing the compressor on-line monitoring and diagnostic method as set forth in any one of claims 1 to 5, wherein the apparatus comprises a processor, a memory coupled to the processor, wherein,
the memory stores program instructions for implementing the compressor on-line monitoring and diagnostic method of any one of claims 1-5;
the processor is used for executing the program instructions stored in the memory to control the compressor on-line monitoring and diagnosis method.
8. A storage medium having stored thereon program instructions executable by a processor for performing the compressor on-line monitoring and diagnostic method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310823240.0A CN116538092B (en) | 2023-07-06 | 2023-07-06 | Compressor on-line monitoring and diagnosing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310823240.0A CN116538092B (en) | 2023-07-06 | 2023-07-06 | Compressor on-line monitoring and diagnosing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116538092A CN116538092A (en) | 2023-08-04 |
| CN116538092B true CN116538092B (en) | 2023-11-14 |
Family
ID=87454600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310823240.0A Active CN116538092B (en) | 2023-07-06 | 2023-07-06 | Compressor on-line monitoring and diagnosing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116538092B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117649860A (en) * | 2024-01-30 | 2024-03-05 | 中密控股股份有限公司 | Method and device for identifying friction and wear state of key part of reciprocating compressor |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634605A (en) * | 2009-04-10 | 2010-01-27 | 北京工业大学 | Intelligent gearbox fault diagnosis method based on mixed inference and neural network |
| CN105372087A (en) * | 2015-11-30 | 2016-03-02 | 南通大学 | Fault diagnosis method based on multi-sensor signal analysis |
| CN206757009U (en) * | 2017-06-01 | 2017-12-15 | 北京华科同安监控技术有限公司 | A kind of unit vibration on-line monitoring analysis and fault diagnosis system |
| CN108008332A (en) * | 2017-11-29 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | A kind of new energy Remote testing device method for diagnosing faults based on data mining |
| CN109033930A (en) * | 2018-05-07 | 2018-12-18 | 北京化工大学 | Mechanical equipment fault diagnosis method based on fault mechanism and statistical model online learning |
| CN109779894A (en) * | 2018-12-29 | 2019-05-21 | 西安交通大学 | A kind of reciprocating compressor fault diagnosis system and method based on neural network algorithm |
| CN110412872A (en) * | 2019-07-11 | 2019-11-05 | 中国石油大学(北京) | Reciprocating compressor fault diagnosis optimization method and device |
| CN113962264A (en) * | 2021-10-22 | 2022-01-21 | 南京航空航天大学 | Aero-engine rotor system fault diagnosis algorithm based on deep learning |
-
2023
- 2023-07-06 CN CN202310823240.0A patent/CN116538092B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634605A (en) * | 2009-04-10 | 2010-01-27 | 北京工业大学 | Intelligent gearbox fault diagnosis method based on mixed inference and neural network |
| CN105372087A (en) * | 2015-11-30 | 2016-03-02 | 南通大学 | Fault diagnosis method based on multi-sensor signal analysis |
| CN206757009U (en) * | 2017-06-01 | 2017-12-15 | 北京华科同安监控技术有限公司 | A kind of unit vibration on-line monitoring analysis and fault diagnosis system |
| CN108008332A (en) * | 2017-11-29 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | A kind of new energy Remote testing device method for diagnosing faults based on data mining |
| CN109033930A (en) * | 2018-05-07 | 2018-12-18 | 北京化工大学 | Mechanical equipment fault diagnosis method based on fault mechanism and statistical model online learning |
| CN109779894A (en) * | 2018-12-29 | 2019-05-21 | 西安交通大学 | A kind of reciprocating compressor fault diagnosis system and method based on neural network algorithm |
| CN110412872A (en) * | 2019-07-11 | 2019-11-05 | 中国石油大学(北京) | Reciprocating compressor fault diagnosis optimization method and device |
| CN113962264A (en) * | 2021-10-22 | 2022-01-21 | 南京航空航天大学 | Aero-engine rotor system fault diagnosis algorithm based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116538092A (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | Intelligent fault diagnosis of rotating machinery using improved multiscale dispersion entropy and mRMR feature selection | |
| Kuncan et al. | A novel feature extraction method for bearing fault classification with one dimensional ternary patterns | |
| CN110849626B (en) | Self-adaptive sparse compression self-coding rolling bearing fault diagnosis system | |
| Zeng et al. | Gearbox oil temperature anomaly detection for wind turbine based on sparse Bayesian probability estimation | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN109460618A (en) | A kind of rolling bearing remaining life on-line prediction method and system | |
| Hu et al. | Dynamic degradation observer for bearing fault by MTS–SOM system | |
| CN116538092B (en) | Compressor on-line monitoring and diagnosing method, device, equipment and storage medium | |
| CN110008898B (en) | Industrial equipment data edge processing method based on symbol and convolutional neural network | |
| CN113076834B (en) | Rotating machine fault information processing method, processing system, processing terminal, and medium | |
| CN107473036A (en) | Elevator traction machine remote online detects and diagnostic system and its checkout and diagnosis method | |
| WO2023151488A1 (en) | Model training method, training device, electronic device and computer-readable medium | |
| CN114021932A (en) | Energy efficiency evaluation and diagnosis method, system and medium for wind turbine generator | |
| Atamuradov et al. | Feature selection and fault‐severity classification–based machine health assessment methodology for point machine sliding‐chair degradation | |
| Chalouli et al. | Intelligent health monitoring of machine bearings based on feature extraction | |
| CN115901263A (en) | Rolling bearing residual life online prediction method and system based on digital twinning | |
| Attoui | Novel fast and automatic condition monitoring strategy based on small amount of labeled data | |
| CN111881594A (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
| CN110160781B (en) | Test set reconstruction and prediction method for rotary machine fault classification | |
| CN116071053B (en) | Reciprocating compressor state early warning system based on digital twinning | |
| Song et al. | A fault feature extraction method for rolling bearings based on refined composite multi-scale amplitude-aware permutation entropy | |
| CN116226719A (en) | Bearing fault diagnosis method based on multidimensional steady-state vibration characteristics and related components | |
| CN114004059B (en) | Health portrait method for hydroelectric generating set | |
| CN113505639B (en) | Rotary machine multi-parameter health state assessment method based on TPE-XGBoost | |
| Nemani et al. | Health index construction with feature fusion optimization for predictive maintenance of physical systems |
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 |