CN208207843U - A kind of slush pump trouble-shooter - Google Patents
A kind of slush pump trouble-shooter Download PDFInfo
- Publication number
- CN208207843U CN208207843U CN201820496491.7U CN201820496491U CN208207843U CN 208207843 U CN208207843 U CN 208207843U CN 201820496491 U CN201820496491 U CN 201820496491U CN 208207843 U CN208207843 U CN 208207843U
- Authority
- CN
- China
- Prior art keywords
- slush pump
- sensor
- attached
- data processing
- center
- 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.)
- Expired - Fee Related
Links
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 16
- 238000013528 artificial neural network Methods 0.000 abstract description 6
- 230000015556 catabolic process Effects 0.000 abstract description 2
- 230000008859 change Effects 0.000 abstract description 2
- 230000002123 temporal effect Effects 0.000 abstract description 2
- 238000012549 training Methods 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 abstract 3
- 238000005553 drilling Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The utility model patent provides a kind of slush pump trouble-shooter, the vibration of slush pump is detected by vibrating sensor, it is transferred to dynamic signal testing module by data line, finally uploads data processing module, carries out signal processing and diagnosis using data processing module.The wavelet character value of slush pump vibration signal to be measured and the wavelet character value of fault-free slush pump are compared, this method is as main method;Using the temporal signatures in database as training sample, fault diagnosis is carried out to slush pump to be measured with the least square method of the multinomial fitting of formula, this method is as householder method;Fault diagnosis is carried out to slush pump to be measured using PNN neural network.Hardware mainly includes dynamic signal testing instrument, wireless aps, power switch, magnet base, vibrating sensor, explosion-proof tank, data processing module.The utility model can help expert to judge equipment running status, change traditional method listened, estimated by ear and carry out breakdown judge to slush pump, increase the accuracy of judgement.
Description
Technical field
The utility model relates to field of oil drilling, and in particular to arrive a kind of slush pump trouble-shooter.
Background technique
Slush pump is the important equipment in oil drilling circulation, because operating condition is severe in drilling process, often because failure causes
Construction is stagnated, to influence drilling process.At present in oil drilling, the mode listened, estimated generally by ear, to slush pump
Working condition assessed, judge mainly by engineer experience.Mud failure of pump cannot be promptly and accurately determined in this way, often
It is low to often result in slush pump working efficiency, more serious failure occurs, has seriously affected drilling course.
A kind of on-the-spot test of means of testing realization slush pump is badly in need of at scene, to meet the need of slush pump working state evaluation
It wants.Fault method is judged by vibration-testing although having now, the method primarily now applied is BP neural network to vibration
Signal is identified;Due to there are many slush pump itself vibration source, these methods cannot all apply to slush pump.Such as use BP
Neural network recognization, not only identification error is very high, while also calculation amount can be made very big, requires height to data processing module, cannot
Meet the requirement of on-the-spot test.The applicant is had found by many experiments first with brief method processing data, then with PNN mind
Through Network Recognition, this method identifies that the ability of failure is not only accurate but also efficient.
Summary of the invention
The utility model provides a kind of slush pump trouble-shooter, which is capable of the work of on-site test slush pump
State provides maintenance foundation, overhauls in standby time to slush pump, ensure that the fault-free in drilling process of slush pump
Operation carries out fault detection to slush pump in the event of a failure, it is ensured that fast and accurately diagnose fault, saved maintenance time.
The technical scheme adopted by the utility model to solve the technical problem is as follows: including power switch, magnet base, vibration biography
Sensor, wireless aps, dynamic signal testing system;Magnet base is fixed on vibrating sensor on slush pump, vibrating sensor detection
Slush pump vibration signal, signal of the dynamic signal testing system for acquisition realize dynamic signal testing system by wireless aps
With the connection of data processing module, the data processing module is placed in explosion-proof tank.
Sensor (b6, b5, b4) is attached to respectively at the 1/2 of left, center, right clack box inlet valve and end cap;By sensor
(b1, b2, b3) is attached to respectively on the clack box drain pressure cylinder of left, center, right;By sensor (d1, d2, d10, d11, d12, d13) point
It is not attached to above the cylinder sleeve shell of left, center, right;Sensor (d3, d4, d5, d6, d9) is attached to left, center, right crosshead shell respectively
Top;Sensor (c3, a4) is attached to the both ends transmission shaft bearing side of covering respectively, by sensor (c1, c2, c4, c5, a2, a6,
A7, a8) it is attached on the four direction of left crankshaft and right crankshaft respectively.
The beneficial effects of the utility model are: the utility model can be realized on-the-spot test, change tradition listened by ear,
The method of range estimation carries out breakdown judge to slush pump, increases the accuracy of judgement, can be good at the state for judging equipment, be
In time maintenance provide foundation, it is therefore prevented that equipment work when damage suddenly, there is more serious failure, seriously affected drilling well into
Journey.
Detailed description of the invention
Fig. 1 hardware plan design drawing;
Fig. 2 working principle diagram;
Fig. 3 Troubleshooting Flowchart;
The preferred sensor position figure of Fig. 4.
Specific embodiment
It should be noted that in the absence of conflict, feature in the embodiments of the present invention and embodiment can be with
It is combined with each other.Below with reference to the accompanying drawings the utility model is described in detail and in conjunction with the embodiments.
A kind of slush pump trouble-shooter, including power switch, explosion-proof tank, wireless aps, vibrating sensor, Dynamic Signal
Tester, magnet base.Magnet base is fixed on vibrating sensor the designated position of slush pump, and vibrating sensor and Dynamic Signal are surveyed
Test system is connected, and the data of dynamic signal testing system acquisition upload to data processing module by wireless aps, at the data
Reason module is placed in explosion-proof tank.
As shown, specified sensor test position, is attached to left, center, right clack box for sensor (b6, b5, b4) respectively
At the 1/2 of inlet valve and end cap;Sensor (b1, b2, b3) is attached to respectively on the clack box drain pressure cylinder of left, center, right;It will sensing
Device (d1, d2, d10, d11, d12, d13) is attached to respectively above the cylinder sleeve shell of left, center, right;By sensor (d3, d4, d5, d6,
D9 it) is attached to respectively above the crosshead shell of left, center, right;Sensor (c3, a4) is attached to both ends transmission shaft bearing respectively to cover
Side, sensor (c1, c2, c4, c5, a2, a6, a7, a8) is attached to respectively on the four direction of left crankshaft and right crankshaft.
The slush pump trouble-shooter carries out malfunction test under the operating condition of frequency acquisition 10Hz, 10Mpa, to failure
Slush pump carries out data acquisition, and establishes various slush pump Mishap Databases.Sensor arrangement is preferred sensor position, first
The vibration signal under slush pump unfaulty conditions is first acquired, then by the failure components of field overhaul, respectively single installation
On fault-free pump, continue to test slush pump vibration signal.The vibration signal of acquisition is subjected to data processing, passes through time-domain analysis
Obtain temporal signatures value;Wavelet character value is obtained by wavelet decomposition.
It should be noted that the extraction to slush pump fault vibration characteristic value, the utility model filter processing method is used
Then Threshold Denoising technical treatment carries out time-domain analysis, wavelet analysis, obtain fault vibration signal wavelet character value.
The foundation of 1 database of embodiment: the vibration signal first under acquisition slush pump unfaulty conditions, it then will be live big
It repairs that the n kind failed part of slush pump is single respectively to be mounted on fault-free slush pump, continues test vibration signal, gained is believed
Number wavelet filter processing removal interference signal is carried out, extracting vibration signal influences maximum time domain charactreristic parameter, calculates each
Fitted polynomial coefficients establish the fault mode of each failure;The vibration signal for acquiring multiple groups fault-free slush pump carries out small wavelength-division
Solution, obtains each wavelet character value;Various fitted polynomial coefficients and trouble-free wavelet character value to slush pump are based on
Rough set data reduction removes redundancy, is analyzed and processed to given information, finds out tacit knowledge and excavates potential rule;
Slush pump fault vibration signal characteristic value is associated with failure, establish digitized expert database.
2 fitting of a polynomial of embodiment determines failure: acquiring slush pump vibration signal to be measured, extracting vibration signal influences maximum
Time domain charactreristic parameter, digital simulation multinomial coefficient, the last system of polynomials of more each coefficient and each fault mode of database
Distance between several, if slush pump fitted polynomial coefficients to be measured between the multinomial coefficient of a certain fault mode at a distance from it is minimum,
It decides that and belongs to the failure.
The troubleshooting of 3 wavelet decomposition of embodiment: acquiring slush pump vibration signal to be measured, extracts small echo signal and is divided into four
Layer extracts wavelet character value, and the wavelet character value of extraction and the fault-free wavelet character value comparison in database are judged whether
It breaks down.
4 fault identification of embodiment: establishing PNN Simulation of Neural Network using data processing, and data in database are imported PNN
Training is repeated in neural network, until identification error is met the requirements.Slush pump vibration signal to be measured is acquired, vibration letter is extracted
Number influence maximum time domain charactreristic parameter, digital simulation multinomial coefficient, then using program to the small wavelength-division of vibration signal progress
Wavelet character value is extracted in analysis;The multinomial coefficient of gained time-domain value and wavelet character value are imported into PNN neural network, with small echo
It based on analysis, is judged supplemented by fitting of a polynomial, exports result.
The above, only specific embodiment of the utility model cannot limit the range that the utility model is implemented with it,
So its equivalent means is replaced, or according to equivalent variations made by the utility model patent protection scope and modification, it all should belong to this
Patent covers scope.
Claims (2)
1. a kind of slush pump trouble-shooter, it is characterised in that: including power switch, magnet base, vibrating sensor, wireless
AP, dynamic signal testing system;Magnet base is fixed on vibrating sensor on slush pump, and vibrating sensor detects slush pump vibration
Signal, signal of the dynamic signal testing system for acquisition realize dynamic signal testing system and data processing by wireless aps
The connection of module, the data processing module are placed in explosion-proof tank.
2. a kind of slush pump trouble-shooter according to claim 1, it is characterized in that: by sensor (b6, b5, b4) point
It is not attached at the 1/2 of left, center, right clack box inlet valve and end cap;Sensor (b1, b2, b3) is attached to left, center, right clack box respectively
On drain pressure cylinder;Sensor (d1, d2, d10, d11, d12, d13) is attached to respectively above the cylinder sleeve shell of left, center, right;It will pass
Sensor (d3, d4, d5, d6, d9) is attached to respectively above the crosshead shell of left, center, right;Sensor (c3, a4) is attached to two respectively
The transmission shaft bearing side of covering is held, sensor (c1, c2, c4, c5, a2, a6, a7, a8) is attached to left crankshaft and right crankshaft respectively
On four direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820496491.7U CN208207843U (en) | 2018-04-10 | 2018-04-10 | A kind of slush pump trouble-shooter |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820496491.7U CN208207843U (en) | 2018-04-10 | 2018-04-10 | A kind of slush pump trouble-shooter |
Publications (1)
Publication Number | Publication Date |
---|---|
CN208207843U true CN208207843U (en) | 2018-12-07 |
Family
ID=64526771
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201820496491.7U Expired - Fee Related CN208207843U (en) | 2018-04-10 | 2018-04-10 | A kind of slush pump trouble-shooter |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN208207843U (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978048A (en) * | 2019-03-22 | 2019-07-05 | 大唐环境产业集团股份有限公司 | A kind of Desulfurization tower slurry circulating pump malfunction analysis and problem shpoting method |
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 |
CN110307981A (en) * | 2019-06-17 | 2019-10-08 | 西安工程大学 | Method for Bearing Fault Diagnosis based on PNN-IFA |
WO2022216522A3 (en) * | 2021-04-06 | 2022-12-22 | Delaware Capital Formation, Inc. | Predictive maintenance of industrial equipment |
-
2018
- 2018-04-10 CN CN201820496491.7U patent/CN208207843U/en not_active Expired - Fee Related
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978048A (en) * | 2019-03-22 | 2019-07-05 | 大唐环境产业集团股份有限公司 | A kind of Desulfurization tower slurry circulating pump malfunction analysis and problem shpoting method |
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 |
CN110307981A (en) * | 2019-06-17 | 2019-10-08 | 西安工程大学 | Method for Bearing Fault Diagnosis based on PNN-IFA |
WO2022216522A3 (en) * | 2021-04-06 | 2022-12-22 | Delaware Capital Formation, Inc. | Predictive maintenance of industrial equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN208207843U (en) | A kind of slush pump trouble-shooter | |
WO2019080367A1 (en) | Method for evaluating health status of mechanical device | |
CN108399277B (en) | Bridge damage identification method based on temperature and strain correlation | |
CN202083555U (en) | System for extracting and diagnosing fault feature of gasoline engine | |
Zhang et al. | A new feature extraction approach using improved symbolic aggregate approximation for machinery intelligent diagnosis | |
CN109583386A (en) | A kind of intelligent rotating mechanical breakdown depth network characterization discrimination method | |
CN103499382B (en) | A kind ofly to merge and the Diagnosis Method of Transformer Faults of image recognition based on vibration data | |
CN108304348B (en) | Bearing residual life prediction method based on binary wiener process | |
CN110490024A (en) | A kind of slush pump method for diagnosing faults and its device | |
CN107831024B (en) | Fan vibration fault state diagnosis method based on multipoint vibration signal characteristic values | |
CN110398647A (en) | Transformer state monitoring method | |
CN113607415A (en) | Bearing fault diagnosis method based on short-time stochastic resonance under variable rotating speed | |
CN112233695A (en) | Oiling machine abnormal sound analysis and fault early warning system based on artificial intelligence and big data | |
CN111076809A (en) | Convolutional neural network-based equipment abnormal sound identification method and system | |
CN113567162A (en) | Fan fault intelligent diagnosis device and method based on acoustic sensor | |
CN110553789A (en) | state detection method and device of piezoresistive pressure sensor and brake system | |
CN108716463B (en) | Fault diagnosis method for annular air valve of reciprocating compressor | |
CN113887586A (en) | FFCNN-SVM transfer learning fault diagnosis method based on feature fusion under small sample | |
CN108871558B (en) | Power cable operation vibration health monitoring system based on big data | |
CN116699400A (en) | Generator rotor short-circuit fault monitoring system, method and readable storage medium | |
CN116335892A (en) | Wind turbine generator blade abnormality detection method and system | |
CN111456915A (en) | Fault diagnosis device and method for internal components of fan engine room | |
CN204253291U (en) | With the offshore wind generating of the collection of floor data real-time online and pre-treater | |
CN108287074B (en) | V-shaped machine combustion condition online monitoring and diagnosis method | |
CN105890740A (en) | Air conditioner six-dimensional vibration testing system and method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181207 |