CN209783910U - Intelligent fault diagnosis system for nuclear power pump bearing - Google Patents
Intelligent fault diagnosis system for nuclear power pump bearing Download PDFInfo
- Publication number
- CN209783910U CN209783910U CN201920637485.3U CN201920637485U CN209783910U CN 209783910 U CN209783910 U CN 209783910U CN 201920637485 U CN201920637485 U CN 201920637485U CN 209783910 U CN209783910 U CN 209783910U
- Authority
- CN
- China
- Prior art keywords
- nuclear power
- pump bearing
- fault diagnosis
- diagnosis system
- low
- 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
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Monitoring And Testing Of Nuclear Reactors (AREA)
Abstract
The utility model discloses a pump bearing intelligence fault diagnosis system for nuclear power, including the vibration sensor, data acquisition unit and the upper computer system that connect gradually, the vibration sensor sets up on pump bearing for the nuclear power, and the data acquisition unit is connected with the AD converter including parallelly connected low pass branch road and high pass branch road, the output of low pass branch road and high pass branch road, and the AD converter passes through network data transmission line and upper computer system connection, and the upper computer system includes data acquisition system and WEB end. The utility model discloses a nuclear power pump bearing intelligence fault diagnosis system can carry out trend analysis, tracking to the application operating mode of nuclear power pump, and then alleviates maintenance personal a large amount of loaded down with trivial details, complicated data analysis, comparison, statistics and comprehensive work, reduces human error, improves the efficiency and the performance of state monitoring system greatly; the equipment state information can be timely, fully and comprehensively provided; the fault type and the fault degree can be accurately identified, and the fault component can be determined.
Description
Technical Field
The utility model belongs to the technical field of bearing fault detection, concretely relates to pump bearing intelligence fault diagnosis system for nuclear power.
Background
in modern industrial production, electricity is an indispensable energy source. Because the modern industrial power demand is large, the nuclear power station is the power station with the largest generation capacity at the present time, and the nuclear power station has less pollution to the environment, so that the construction of the nuclear power station becomes a key project in China.
The current fault diagnosis system monitors in a monitoring center, and if the fault diagnosis system is operated remotely, the operation is difficult to carry out, and the convenience is lacked; the fault identification of the current fault diagnosis system is not detailed enough, and the system is more general, for example, the current system can only detect the outer ring fault, and whether the outer ring fault is worn or pitting or other faults cannot be judged.
SUMMERY OF THE UTILITY MODEL
The purpose of the invention is as follows: the utility model aims at providing a realize not enough of accurate nuclear power pump bearing intelligent fault diagnosis system who judges of trouble.
The technical scheme is as follows: in order to achieve the above purpose, the technical solution adopted by the present invention is as follows:
The utility model provides a nuclear power is with pump bearing intelligence fault diagnosis system which characterized in that: including vibration sensor, data acquisition unit and the host computer system that connects gradually, vibration sensor sets up on nuclear power is with pump bearing, the data acquisition unit is including parallelly connected low pass branch road and high pass branch road, the output and the AD converter of low pass branch road and high pass branch road are connected, the AD converter passes through network data transmission line and host computer system connection, the host computer system includes data acquisition system and WEB end.
Preferably, the high-pass branch comprises a band-pass filter, a low-noise amplifier and a detector which are sequentially connected, the low-pass branch comprises a low-pass filter, the output end of the vibration sensor is respectively connected with the input ends of the band-pass filter and the low-pass filter, and the output end of the low-pass filter and the output end of the detector are connected with the AD converter.
Preferably, the vibration sensor is connected with and collects vibration signals of an inner ring, an outer ring and a rolling body of the nuclear power pump bearing.
Preferably, the AD converter is a parallel-comparison type, a serial-parallel type, or a sigma-delta modulation type AD converter.
Preferably, the low noise amplifier is AD8032, and the detector is an operational amplifier configured as a detector circuit.
Preferably, the upper computer unit comprises a data acquisition system and a WEB terminal.
Has the advantages that: compared with the prior art, the utility model has the advantages of it is following:
The utility model discloses a nuclear power pump bearing intelligence fault diagnosis system can carry out trend analysis, tracking to the application operating mode of nuclear power pump, and then alleviates maintenance personal a large amount of loaded down with trivial details, complicated data analysis, comparison, statistics and comprehensive work, reduces human error, improves the efficiency and the performance of state monitoring system greatly; the equipment state information can be timely, fully and comprehensively provided; the fault type and the fault degree can be accurately identified, the fault component can be determined, the maintenance efficiency is improved, and the maintenance loss is reduced; the early warning of the fault, the advance maintenance decision and the maintenance preparation, the application loss reduction, the major fault alarm and the safety protection of personnel and equipment are provided with practical and reliable technical support.
Drawings
FIG. 1 is a schematic diagram of a hardware structure of an intelligent fault diagnosis system for a nuclear power pump bearing;
FIG. 2 is a block diagram of a nuclear power pump bearing intelligent fault diagnosis system;
FIG. 3 is a flow chart of a nuclear power pump bearing intelligent fault diagnosis method;
FIG. 4 is a fault classification recognition diagram of an intelligent fault diagnosis method for a nuclear power pump bearing.
Detailed Description
The present invention will be further illustrated by the following specific examples, which are carried out on the premise of the technical scheme of the present invention, and it should be understood that these examples are only for illustrating the present invention and are not intended to limit the scope of the present invention.
the utility model provides a pump bearing intelligence fault diagnosis system for nuclear power, including vibration sensor 2 that connects gradually, data acquisition unit 3 and upper computer system 4, vibration sensor 2 sets up on pump bearing 1 for nuclear power, data acquisition unit 3 is including parallelly connected low pass branch road and high pass branch road, the output and the AD converter of low pass branch road and high pass branch road are connected, the AD converter passes through the network data transmission line and is connected with upper computer system 4, upper computer system 4 includes data acquisition system and WEB end.
The high-pass branch comprises a band-pass filter, a low-noise amplifier and a detector which are sequentially connected, the low-pass branch comprises a low-pass filter, the output end of the vibration sensor is respectively connected with the input ends of the band-pass filter and the low-pass filter, and the output end of the low-pass filter and the output end of the detector are connected with the AD converter.
The vibration sensor is connected with and collects vibration signals on an inner ring, an outer ring and a rolling body of the nuclear power pump bearing.
The AD converter is a parallel-comparison type, a serial-parallel type, or a sigma-delta modulation type AD converter. The low noise amplifier adopts AD8032, and the detector adopts an operational amplifier to form a detection circuit. The upper computer unit comprises a data acquisition system and a WEB terminal, in particular data acquisition software and WEB terminal software.
The vibration sensor 2 measures vibration signals of the nuclear power pump bearing 1 and transmits the vibration signals to the data acquisition unit 3, the data acquisition unit 3 performs low-pass filtering and band-pass filtering on the vibration signals, and low-frequency components are directly transmitted to the high-precision AD converter to be converted into digital signals; the high-frequency component after the band-pass filtering is subjected to noise amplification through a noise amplifier, low-pass filtering is carried out on the high-frequency component to obtain a low-frequency signal in the high-frequency component, and the low-frequency signal is transmitted to a high-precision AD converter to convert an analog signal into a digital signal. And the digital signals are transmitted to a data acquisition system of the upper computer unit through a network for processing, and finally, the data are transmitted to a WEB end system.
The intelligent nuclear power pump bearing fault diagnosis method adopting the intelligent nuclear power pump bearing fault diagnosis system comprises the following steps:
1) Measuring vibration signal data of a pump bearing for nuclear power under a normal state and three fault states;
2) Performing VMD (variational modal decomposition) on the vibration signals in each state to obtain IMF components;
3) Performing singular value decomposition on the IMF in each state, extracting a bearing characteristic value, and establishing an expert database;
4) Calculating the bearing vibration signal speed effective value and the kurtosis of vibration acceleration, and judging whether the bearing breaks down; when the effective speed value is more than 4.5mm/s and the kurtosis of the vibration acceleration is more than 3, the bearing may be in failure; when the effective value of the speed is more than 7.1mm/s and the kurtosis of the vibration acceleration is more than 8, the bearing has serious faults.
5) and decomposing the bearing vibration signal with the fault through VMD, extracting singular values of each IMF, and comparing the singular values with data in an expert database through a support vector machine to identify the fault.
In the step 1), the three fault states are respectively an inner ring fault, an outer ring fault and a rolling body fault. The vibration sensor is connected with and collects vibration signals on an inner ring, an outer ring and a rolling body of the nuclear power pump bearing.
The vibration sensor is arranged on the bearing, the input end of the data acquisition unit is connected with the output end of the vibration sensor, the output end of the data acquisition unit is connected with the upper computer system, and the data acquisition unit is transmitted to the upper computer system through a network data transmission line; the invention uses the vibration sensor to measure the vibration signal data of the bearing, and then uses the data acquisition unit to extract and process the vibration signal measured by the vibration sensor and transmit the vibration signal to the upper computer system for fault diagnosis.
and 3) randomly selecting and dividing the extracted fault characteristic values into training samples and testing samples, wherein the training samples and the testing samples respectively correspond to four states of normal, inner ring, outer ring and rolling body. And storing the training samples into an expert database, and continuously supplementing fault characteristic values into the expert database to gradually improve the expert database.
as an embodiment, 7 groups of bearings are selected to respectively extract vibration signals measured by the acceleration sensors in four states of normal bearing, inner ring fault, outer ring fault and rolling element fault, VMD decomposition and singular value analysis are performed on the vibration signals, and characteristic values are extracted, as shown in table 1.
TABLE 1 eigenvalues
| Status of state | k1 | k2 | k3 | k4 | k5 | k6 | k7 |
| Is normal | 53.6011 | 53.0605 | 53.5382 | 53.2316 | 54.2462 | 53.3709 | 53.6049 |
| Inner ring | 47.7117 | 47.4350 | 47.4800 | 47.6933 | 47.7414 | 47.7849 | 47.5824 |
| Outer ring | 61.7429 | 60.6159 | 64.4058 | 65.3770 | 64.0580 | 63.5723 | 63.7192 |
| Rolling body | 136.6660 | 141.2309 | 138.6591 | 139.7922 | 141.2684 | 140.0772 | 136.8400 |
and respectively carrying out support vector machine tests on 28 groups of extracted VMD decomposed samples of the normal, inner ring, outer ring and rolling body. Wherein 16 groups are randomly selected for training, and the other 12 groups are used for testing and respectively correspond to four states of normal, inner ring, outer ring and rolling body. When training samples, the selected normal sample is regarded as +1, the inner circle sample is regarded as +2, the outer circle sample is regarded as +3, and the rolling body sample is regarded as + 4. The actual classification and the predicted classification of the test set are shown in fig. 4.
As can be seen from the test results of fig. 4, the bearing state recognition rate reaches 100%. And storing the training samples in an expert database.
The invention establishes the expert database based on the WEB terminal, and can establish a perfect expert database as long as the fault characteristic value of the nuclear power pump is continuously supplemented, thereby facilitating the rapid comparison and identification of the specific fault type in the follow-up process.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, a plurality of modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (7)
1. The utility model provides a nuclear power is with pump bearing intelligence fault diagnosis system which characterized in that: including vibration sensor, data acquisition unit and the host computer system that connects gradually, vibration sensor sets up on nuclear power is with pump bearing, the data acquisition unit is including parallelly connected low pass branch road and high pass branch road, the output and the AD converter of low pass branch road and high pass branch road are connected, the AD converter passes through network data transmission line and is connected with the host computer unit.
2. The intelligent fault diagnosis system for the nuclear power pump bearing, according to claim 1, is characterized in that: the high-pass branch comprises a band-pass filter, a low-noise amplifier and a detector which are sequentially connected, the low-pass branch comprises a low-pass filter, the output end of the vibration sensor is respectively connected with the input ends of the band-pass filter and the low-pass filter, and the output end of the low-pass filter and the output end of the detector are connected with the AD converter.
3. the intelligent fault diagnosis system for the nuclear power pump bearing, according to claim 1, is characterized in that: the vibration sensor is connected with and collects vibration signals on an inner ring, an outer ring and a rolling body of the pump bearing for nuclear power.
4. The intelligent fault diagnosis system for the nuclear power pump bearing, according to claim 1, is characterized in that: the AD converter is a parallel-comparison type, a serial-parallel type, or a sigma-delta modulation type AD converter.
5. The intelligent fault diagnosis system for the nuclear power pump bearing, according to claim 2, is characterized in that: the low noise amplifier adopts AD8032, and the detector adopts the fortune to put up into detection circuit.
6. The intelligent fault diagnosis system for the nuclear power pump bearing, according to claim 1, is characterized in that: the upper computer unit comprises a data acquisition system and a WEB end.
7. the intelligent fault diagnosis system for the nuclear power pump bearing, according to claim 1, is characterized in that: the vibration sensor is an acceleration sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920637485.3U CN209783910U (en) | 2019-05-06 | 2019-05-06 | Intelligent fault diagnosis system for nuclear power pump bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920637485.3U CN209783910U (en) | 2019-05-06 | 2019-05-06 | Intelligent fault diagnosis system for nuclear power pump bearing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN209783910U true CN209783910U (en) | 2019-12-13 |
Family
ID=68804871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920637485.3U Active CN209783910U (en) | 2019-05-06 | 2019-05-06 | Intelligent fault diagnosis system for nuclear power pump bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN209783910U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057587A (en) * | 2019-05-06 | 2019-07-26 | 江苏联能电子技术有限公司 | A kind of nuclear power pump bearing intelligent failure diagnosis method and system |
| CN114738389A (en) * | 2022-03-29 | 2022-07-12 | 南京航空航天大学 | Intelligent bearing system for slip diagnosis and slip diagnosis prediction method |
-
2019
- 2019-05-06 CN CN201920637485.3U patent/CN209783910U/en active Active
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057587A (en) * | 2019-05-06 | 2019-07-26 | 江苏联能电子技术有限公司 | A kind of nuclear power pump bearing intelligent failure diagnosis method and system |
| CN114738389A (en) * | 2022-03-29 | 2022-07-12 | 南京航空航天大学 | Intelligent bearing system for slip diagnosis and slip diagnosis prediction method |
| CN114738389B (en) * | 2022-03-29 | 2023-03-28 | 南京航空航天大学 | Intelligent bearing system for slip diagnosis and slip diagnosis prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102053016B (en) | System for monitoring vibration of rotating machinery rolling bearing in wireless mode | |
| CN209783910U (en) | Intelligent fault diagnosis system for nuclear power pump bearing | |
| CN105241680A (en) | Health state assessment method for rotary machine based on probability density function | |
| CN102182671A (en) | State analysis monitoring system and method of gas compressor | |
| CN102183951A (en) | Device for monitoring state of rotary bearing and diagnosing fault based on laboratory virtual instrument engineering workbench (Lab VIEW) | |
| CN110056640B (en) | Speed reducer wireless fault diagnosis method based on acceleration signal and edge calculation | |
| CN102607641A (en) | Cluster anomaly detection method of combustion gas turbine | |
| CN111307455B (en) | Train bogie bearing fault monitoring method and system based on dictionary learning | |
| CN110553789A (en) | state detection method and device of piezoresistive pressure sensor and brake system | |
| CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
| CN111046790A (en) | Pump bearing fault diagnosis method | |
| CN116295948A (en) | Abnormality detection method, system and storage medium of industrial temperature sensor in large temperature difference environment | |
| CN110057587A (en) | A kind of nuclear power pump bearing intelligent failure diagnosis method and system | |
| CN114280383A (en) | Health detection device and health detection method for large ground station antenna | |
| CN114519382A (en) | Nuclear power plant key operation parameter extraction and abnormity monitoring method | |
| CN108957299A (en) | A kind of multiple-level serially connected inversion detection tester for electronic circuit fault based on output signal acquisition | |
| CN110160781B (en) | Test set reconstruction and prediction method for rotary machine fault classification | |
| CN211452846U (en) | Fan fault remote monitoring system based on current signal | |
| CN112113766A (en) | Characteristic extraction method for early damage state of rolling bearing | |
| CN115081491B (en) | Running state fault diagnosis method for sanitary towel production equipment | |
| CN105424387A (en) | Steering gear real-time remote intelligent monitoring system | |
| CN214409216U (en) | Fault monitoring device of industrial equipment | |
| CN113098132A (en) | Improved machine learning fault diagnosis system based on group intelligent optimization | |
| CN115356627A (en) | Motor fault diagnosis method and system based on stray magnetic flux detection | |
| CN112381130A (en) | Cluster analysis-based power distribution room multivariate data anomaly detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |