CN110929677A - Vibration data on-line monitoring analysis system - Google Patents
Vibration data on-line monitoring analysis system Download PDFInfo
- Publication number
- CN110929677A CN110929677A CN201911229826.4A CN201911229826A CN110929677A CN 110929677 A CN110929677 A CN 110929677A CN 201911229826 A CN201911229826 A CN 201911229826A CN 110929677 A CN110929677 A CN 110929677A
- Authority
- CN
- China
- Prior art keywords
- vibration
- data
- module
- fault
- attitude information
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention discloses a vibration data on-line monitoring and analyzing system, which comprises: the target data acquisition module is used for acquiring vibration signals with attitude information; the data noise reduction module is used for carrying out noise reduction processing on the vibration signal by adopting a generalized morphological filter based on a mathematical morphology structure self-adaptive LMS algorithm; the data feature extraction module is used for acquiring attitude information, a vibration amplitude sequence, a frequency component sequence, energy distribution and box dimensions of the vibration signals; the fault identification module is used for giving different weights to the characteristic data according to the name of the target data source, realizing on-line training and detection and identifying and classifying the vibration fault signals; and the simulation analysis module is used for establishing a physical model of the target machine by using Simulink to realize simulation analysis of the vibration data. The false alarm rate is low, and can discern the vibration reason, realizes the visual of early warning result.
Description
Technical Field
The invention relates to the field of mechanical monitoring, in particular to a vibration data online monitoring and analyzing system.
Background
During the operation process of the mechanical equipment, the operation state of the mechanical equipment can be known and mastered through the detected mechanical vibration signal. The mechanical vibration signal can not only provide data information for improving the operation reliability, safety, effectiveness and management level of mechanical equipment, but also provide data information for the structure optimization, reasonable manufacturing and production processes of the mechanical equipment.
At present, most of existing vibration data analysis systems adopt a mode that vibration data exceed a threshold value to carry out trend early warning and state early warning, but not according to fault characteristics of vibration, the false alarm rate is high, vibration reasons cannot be identified, and the early warning result is invisible.
Disclosure of Invention
In order to solve the problems, the invention provides an on-line vibration data monitoring and analyzing system which is low in false alarm rate, can identify vibration reasons and realizes the visualization of an early warning result.
In order to achieve the purpose, the invention adopts the technical scheme that:
a vibration data online monitoring analysis system comprising:
the target data acquisition module is used for acquiring vibration signals with attitude information;
the data noise reduction module is used for carrying out noise reduction processing on the vibration signal by adopting a generalized morphological filter based on a mathematical morphology structure self-adaptive LMS algorithm;
the data characteristic extraction module is used for acquiring attitude information of the vibration signal, obtaining a vibration amplitude sequence and a frequency component sequence through Fourier transform, and extracting energy distribution of different frequency bands of the vibration signal through wavelet transform; extracting the box dimension of the vibration moment by adopting a fractal theory, and taking the obtained attitude information, vibration amplitude sequence, frequency component sequence, energy distribution and box dimension as the characteristic data of the vibration signal;
the fault identification module is used for giving different weights to the characteristic data according to the name of the target data source, realizing on-line training and detection and identifying and classifying the vibration fault signals;
and the simulation analysis module is used for establishing a physical model of the target machine by using Simulink to realize simulation analysis of the vibration data.
Furthermore, the target data acquisition module adopts a vibration sensor with a three-dimensional attitude sensor.
Further, it also includes a
And the fault summarizing module is used for summarizing fault identification results in an EXCEL table mode, wherein the fault identification results comprise target source names (corresponding target mechanical components), attitude information of target data, vibration amplitude sequences, frequency component sequences, energy distribution, box dimensions, corresponding acquisition time and fault identification results.
Furthermore, the attitude information, the vibration amplitude sequence, the frequency component sequence, the energy distribution and the box dimension of the target data are respectively related to the construction parameters of the physical model, and the physical model can be driven to generate corresponding changes through the input changes of the attitude information, the vibration amplitude sequence, the frequency component sequence, the energy distribution and the box dimension.
Further, still include:
and the fault evaluation module is used for giving different weights to the characteristic data according to the data classification result and the name of the target data source.
Furthermore, the fault identification result output by the fault identification module and the construction parameter of the physical model establish a relationship, and the physical model can be driven to generate corresponding change through the change of the input fault identification result.
Further, still include:
the curve generation module is used for generating various curve graphs according to the characteristic data;
the regression calculation module is used for carrying out regression calculation on the drawn curve graphs through different functions;
and the comparison analysis module is used for performing comparison analysis and prediction on the drawn curve and the original actual measurement curve and outputting an analysis prediction result.
And the early warning module is used for starting when the attitude information/fault recognition result/prediction result of the vibration signal falls into a preset threshold, and calling a corresponding template in the short message template to finish the automatic editing and sending of the corresponding early warning short message.
The invention has the following beneficial effects:
constructing a generalized morphological filter based on an adaptive LMS algorithm according to mathematical morphology, denoising the vibration signal, and simultaneously taking attitude information, vibration amplitude sequence, frequency component sequence, energy distribution and box dimension of target data as characteristic data of the vibration data, so that the speed and the precision of vibration signal identification can be improved, and the false alarm rate can be reduced; visualization and simulation analysis of the early warning result are achieved based on Simulink, and the system is provided with a prediction analysis function, so that potential safety hazards can be found in time.
Drawings
Fig. 1 is a system block diagram of an online vibration data monitoring and analyzing system according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides an online vibration data monitoring and analyzing system, including:
the target data acquisition module adopts a vibration sensor with a three-dimensional attitude sensor and is used for acquiring a vibration signal with attitude information;
the data noise reduction module is used for carrying out noise reduction processing on the vibration signal by adopting a generalized morphological filter based on a mathematical morphology structure self-adaptive LMS algorithm; .
The data characteristic extraction module is used for acquiring attitude information of the vibration signal through a Matlab program, performing Fourier transform on the vibration signal subjected to noise reduction through the Matlab program to obtain a vibration amplitude sequence and a frequency component sequence, and extracting energy distribution of different frequency bands of the vibration signal through wavelet transform; extracting the box dimension of the vibration moment by adopting a fractal theory, and taking the obtained attitude information, vibration amplitude sequence, frequency component sequence, energy distribution and box dimension as the characteristic data of the vibration signal;
the data classification module is used for realizing classification of target data according to the attitude information of the vibration signals;
and the fault identification module is used for giving different weights to the characteristic data according to the target data source name and the data classification result, realizing online training and detection, and identifying and classifying the vibration fault signals, wherein the fault identification result comprises the type and the similarity of the fault.
The simulation analysis module is used for establishing a physical model of the target machine by using Simulink to realize simulation analysis of vibration data; the attitude information, the vibration amplitude sequence, the frequency component sequence, the energy distribution, the box dimension of the target data and the fault identification result (fault type) output by the fault identification module are respectively in a relationship with the construction parameters of the physical model, and the physical model can be driven to generate corresponding change through the change of the input attitude information, the vibration amplitude sequence, the frequency component sequence, the energy distribution and the box dimension;
the fault summarizing module is used for summarizing fault recognition results in an EXCEL table mode, wherein the fault recognition results comprise target source names (corresponding target mechanical components), attitude information of target data, vibration amplitude sequences, frequency component sequences, energy distribution, box dimensions, corresponding acquisition time and fault recognition results;
the curve generation module is used for generating various curve graphs according to the characteristic data; the curve generation module generates a temporal curve and a spatial effect curve which change along with time and space according to the characteristic data, the temporal curve displays the change situation of the original data of each monitoring point along with time, and the spatial effect curve highlights the change rule of the monitoring results of different measuring points along with the position of the vibration sensor at the same time;
the regression calculation module is used for carrying out regression calculation on the drawn curve graphs through different functions;
the comparison analysis module is used for performing comparison analysis and prediction on the drawn curve and the original actual measurement curve and outputting an analysis prediction result;
the early warning module is used for starting when the attitude information/fault recognition result/prediction result of the vibration signal falls into a preset threshold, and calling a corresponding template in the short message template to finish the automatic editing and sending of the corresponding early warning short message; through the GRM530 wireless communication module and the configuration of short message alarm parameters, the remote short message and telephone alarm can be realized based on 4G, and the remote start-stop operation of equipment such as emergency measures and the like can be controlled in a short message form;
the central processing unit adopts a SIEMENS S7-1200 PLC controller and is used for coordinating the work of the modules; the target data acquisition module is connected with a SIEMENS S7-1200 PLC controller through an RS485 communication cable based on a Modbus protocol, and the early warning module is wirelessly connected with a cloud server through a wireless communication module GRM530 based on 4G/WIFI and further connected with a terminal device to be accessed; the wireless communication module GRM530 is connected to the controller via an ethernet cable.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (8)
1. The utility model provides a vibration data on-line monitoring analytic system which characterized in that: the method comprises the following steps:
the target data acquisition module is used for acquiring vibration signals with attitude information;
the data noise reduction module is used for carrying out noise reduction processing on the vibration signal by adopting a generalized morphological filter based on a mathematical morphology structure self-adaptive LMS algorithm;
the data characteristic extraction module is used for acquiring attitude information of the vibration signal, obtaining a vibration amplitude sequence and a frequency component sequence through Fourier transform, and extracting energy distribution of different frequency bands of the vibration signal through wavelet transform; extracting the box dimension of the vibration moment by adopting a fractal theory, and taking the obtained attitude information, vibration amplitude sequence, frequency component sequence, energy distribution and box dimension as the characteristic data of the vibration signal;
the fault identification module is used for giving different weights to the characteristic data according to the name of the target data source, realizing on-line training and detection and identifying and classifying the vibration fault signals;
and the simulation analysis module is used for establishing a physical model of the target machine by using Simulink to realize simulation analysis of the vibration data.
2. The vibration data online monitoring and analyzing system of claim 1, wherein: the target data acquisition module adopts a vibration sensor with a three-dimensional attitude sensor.
3. The vibration data online monitoring and analyzing system of claim 1, wherein: also comprises a
And the fault summarizing module is used for summarizing fault recognition results in an EXCEL table mode, wherein the fault recognition results comprise target source names, attitude information of target data, vibration amplitude sequences, frequency component sequences, energy distribution, box dimensions, corresponding acquisition time and fault recognition results.
4. The vibration data online monitoring and analyzing system of claim 1, wherein: the attitude information, the vibration amplitude sequence, the frequency component sequence, the energy distribution and the box dimension of the target data are respectively related to the construction parameters of the physical model, and the physical model can be driven to generate corresponding changes through the input changes of the attitude information, the vibration amplitude sequence, the frequency component sequence, the energy distribution and the box dimension.
5. The vibration data online monitoring and analyzing system of claim 1, wherein: further comprising:
and the fault evaluation module is used for giving different weights to the characteristic data according to the data classification result and the name of the target data source.
6. The vibration data online monitoring and analyzing system of claim 1, wherein: the fault recognition result output by the fault recognition module is in a relationship with the construction parameters of the physical model, and the physical model can be driven to generate corresponding changes through the changes of the input fault recognition result.
7. The vibration data online monitoring and analyzing system of claim 1, wherein: further comprising:
the curve generation module is used for generating various curve graphs according to the characteristic data;
the regression calculation module is used for carrying out regression calculation on the drawn curve graphs through different functions;
and the comparison analysis module is used for performing comparison analysis and prediction on the drawn curve and the original actual measurement curve and outputting an analysis prediction result.
8. The vibration data online monitoring and analyzing system of claim 1, wherein: the system also comprises an early warning module which is used for starting when the attitude information/fault recognition result/prediction result of the vibration signal falls into a preset threshold and calling a corresponding template in the short message template to finish the automatic editing and sending of the corresponding early warning short message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229826.4A CN110929677A (en) | 2019-12-04 | 2019-12-04 | Vibration data on-line monitoring analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229826.4A CN110929677A (en) | 2019-12-04 | 2019-12-04 | Vibration data on-line monitoring analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110929677A true CN110929677A (en) | 2020-03-27 |
Family
ID=69856773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911229826.4A Withdrawn CN110929677A (en) | 2019-12-04 | 2019-12-04 | Vibration data on-line monitoring analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929677A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669562A (en) * | 2021-01-22 | 2021-04-16 | 九江职业技术学院 | Computer internet of things fire early warning system |
| CN113095170A (en) * | 2021-03-29 | 2021-07-09 | 天地（常州）自动化股份有限公司 | Motor fault diagnosis method based on adjustable Q wavelet |
| CN117647392A (en) * | 2024-01-30 | 2024-03-05 | 成都三一能源环保技术有限公司 | Downhole drilling instrument scrapping monitoring and early warning system based on data analysis |
-
2019
- 2019-12-04 CN CN201911229826.4A patent/CN110929677A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669562A (en) * | 2021-01-22 | 2021-04-16 | 九江职业技术学院 | Computer internet of things fire early warning system |
| CN113095170A (en) * | 2021-03-29 | 2021-07-09 | 天地（常州）自动化股份有限公司 | Motor fault diagnosis method based on adjustable Q wavelet |
| CN113095170B (en) * | 2021-03-29 | 2024-04-02 | 天地（常州）自动化股份有限公司 | Fault diagnosis method based on adjustable Q wavelet motor |
| CN117647392A (en) * | 2024-01-30 | 2024-03-05 | 成都三一能源环保技术有限公司 | Downhole drilling instrument scrapping monitoring and early warning system based on data analysis |
| CN117647392B (en) * | 2024-01-30 | 2024-04-09 | 成都三一能源环保技术有限公司 | Downhole drilling instrument scrapping monitoring and early warning system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929677A (en) | Vibration data on-line monitoring analysis system | |
| CN107526329A (en) | Robot management system based on artificial intelligence design | |
| CN106656669B (en) | A kind of device parameter abnormality detection system and method based on threshold adaptive setting | |
| CN109443769B (en) | Motor bearing state detection method, system and device and readable storage medium | |
| CN116866095B (en) | Industrial router with touch panel and standby control method thereof | |
| CN108932581A (en) | The autonomous cognitive method and system of more physics domain information fusions | |
| CN115795401A (en) | Ocean pasture full-factor monitoring sensor multi-data fusion system | |
| CN114993640A (en) | Equipment state monitoring method, device, equipment and computer storage medium | |
| CN113670434A (en) | Transformer substation equipment sound abnormality identification method and device and computer equipment | |
| CN112002114A (en) | Electromechanical equipment wireless data acquisition system and method based on 5G-ZigBee communication | |
| CN114004996A (en) | Abnormal sound detection method, abnormal sound detection device, electronic equipment and medium | |
| Martin-del-Campo et al. | Towards zero-configuration condition monitoring based on dictionary learning | |
| CN208029012U (en) | A kind of identification device and monitoring device | |
| CN110763955A (en) | Cable fault detection system and method based on high-voltage pulse signal injection | |
| CN114741690A (en) | Network security monitoring method, device, equipment and computer storage medium | |
| CN204463412U (en) | A kind of supervising device based on internet | |
| CN114818813A (en) | Cutter wear value prediction algorithm based on self-attention convolution neural network | |
| EP3665895A1 (en) | Data processing device, data analyzing device, data processing system and method for processing data | |
| CN204154501U (en) | Sliding bearing monitoring system | |
| CN113985318A (en) | Multi-type partial discharge signal real-time extraction method for transformer operation state | |
| CN114430421A (en) | Method and system for automatically generating alarm rules based on function sets of various vehicle types | |
| Zhao et al. | Research on a vibration signal analysis method for motor bearing | |
| CN110220727B (en) | Abnormity detection method and device for motor equipment | |
| KR102217378B1 (en) | Smart Vibration Counting Device | |
| CN117455124B (en) | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200327 |
|
| WW01 | Invention patent application withdrawn after publication |