CN212272574U - Medium pump predictability maintenance system based on data analysis - Google Patents
Medium pump predictability maintenance system based on data analysis Download PDFInfo
- Publication number
- CN212272574U CN212272574U CN202020109986.7U CN202020109986U CN212272574U CN 212272574 U CN212272574 U CN 212272574U CN 202020109986 U CN202020109986 U CN 202020109986U CN 212272574 U CN212272574 U CN 212272574U
- Authority
- CN
- China
- Prior art keywords
- pump
- display
- medium pump
- medium
- data analysis
- 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
Images
Landscapes
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The utility model discloses a medium pump predictability maintenance system based on data analysis, including the medium pump, be equipped with the vibration record appearance on the lateral wall of medium pump and outside the impeller of medium pump, the medium exit position of medium pump is equipped with the pump efficiency tachymeter, the vibration record appearance with the pump efficiency tachymeter is connected with the master control platform through the serial port line, the master control platform includes the casing, the inside of casing is equipped with the host computer, the upper surface of casing is equipped with the display, the middle part of display is equipped with the display screen, one side of display is equipped with the speaker, be equipped with the warning light on the display, the system can replace artifical periodic detection, liberate the labour, can also carry out the early warning to the trouble that will probably take place when guaranteeing timely effectual detection proruption trouble, the risk is avoidd to the false detection hourglass that this system can effectively subjective factor leads to, the accuracy of fault detection is improved, the purpose of predictive maintenance is achieved, and normal operation of equipment is guaranteed.
Description
Technical Field
The utility model relates to a mineral processing technology field, specific field is medium pump predictability maintenance system based on data analysis.
Background
The working condition of the medium pump as a key device for dense medium coal separation is very important. In practical application, the working condition of the pump is extremely poor due to high specific gravity, high concentration and high lift of the medium, so that the abrasion of equipment is increased, and the maintenance amount is increased. The problems of pump body mechanical seal damage, bearing damage, impeller damage and the like can occur for many times during operation. Particularly, the heavy medium suspension comprises water, magnetite powder, coal slime and a small amount of impurities, so that the impeller is extremely easy to be damaged to cause equipment failure, and the heavy medium suspension can be divided into four types of failures: corrosion and wear, mechanical failure, performance failure, shaft seal failure, which tend to interact. If the faults of the equipment can be detected and repaired in time, and even the faults to be generated can be predicted in advance, the influence on normal production can be greatly reduced. At present, the traditional detection method is that the detection period is one day, and the manpower and financial resources are consumed. Moreover, due to manual inspection, detection errors may be caused by subjective factors such as personnel quality and management level, or faults occur after the inspection is correct, so that normal operation of equipment is affected, and economic losses are caused.
For most mechanical equipment, equipment failure often has a certain time dependency. In the case of a media pump, a significant portion of its failure is not abrupt, but rather undergoes a time-course of device aging, which tends to be dynamically nonlinear. Based on the device, a novel device is provided, and a certain scientific method can be adopted to model the equipment aging process, so that the fault prediction of the equipment is realized.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to provide a medium pump predictability maintenance system based on data analysis to solve and to propose in the above-mentioned background art because the manual work is examined, probably lead to the detection error because subjective factors such as personnel's quality and management level, perhaps break down after the inspection is errorless, and then influence equipment normal operating, cause economic loss's problem.
In order to achieve the above object, the utility model provides a following technical scheme: medium pump predictability maintenance system based on data analysis, including the medium pump, just be equipped with the vibration record appearance in the impeller outside of medium pump on the lateral wall of medium pump, the medium exit position of medium pump is equipped with the pump effect tachymeter, the vibration record appearance with the pump effect tachymeter is connected with the master control platform through the serial port line, the master control platform includes the casing, the inside of casing is equipped with the host computer, the upper surface of casing is equipped with the display, the middle part of display is equipped with the display screen, one side of display is equipped with the speaker, be equipped with the warning light on the display.
Preferably, the display screen is a touch screen, so that the operation of a user is facilitated.
Preferably, the lateral wall of the medium pump is provided with a slide rail, the slide rail is provided with a locking groove, the outside of the rear lateral wall of the pump efficiency tachymeter is provided with a slide bar, the upper part of the slide bar is provided with a limiting block, the slide bar is provided with a spring cavity, the bottom surface of the spring cavity is provided with one end of a compression spring, the other end of the compression spring is provided with a steel ball, and the steel ball is matched with the locking groove.
Preferably, the number of the sliding rails and the number of the sliding strips are both 2.
Preferably, the vibration recorder is connected to the medium pump by a bolt.
Preferably, the side wall of the shell is provided with a plurality of heat dissipation through grooves.
Compared with the prior art, the beneficial effects of the utility model are that: the medium pump predictive maintenance system based on data analysis can replace manual periodic detection, liberate labor force, guarantee timely and effective detection of sudden faults, and meanwhile can give early warning to the faults which possibly occur, avoid risks, effectively avoid false detection and missed detection caused by subjective factors, improve the accuracy of fault detection, achieve the purpose of predictive maintenance, and guarantee normal operation of equipment.
Drawings
Fig. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic structural view of the slide bar and the slide rail of the present invention;
FIG. 3 is a right schematic view of the pump efficiency tacheometer of the present invention;
FIG. 4 is an enlarged view of the point A in FIG. 2 according to the present invention;
fig. 5 is a system block diagram of the present invention.
In the figure: 1-medium pump, 2-vibration recorder, 3-pump efficiency tachymeter, 4-serial port line, 5-main console, 501-shell, 502-display, 503-display screen, 504-loudspeaker, 505-warning light, 506-heat dissipation through groove, 6-slide rail, 7-slide bar, 8-limiting block, 9-spring cavity, 10-compression spring and 11-steel ball.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative work belong to the protection scope of the present invention.
Referring to fig. 1-5, the present invention provides a technical solution: medium pump predictability maintenance system based on data analysis, including medium pump 1, be equipped with vibration record appearance 2 on medium pump 1's the lateral wall and in medium pump 1's impeller outside, medium pump 1's medium exit position is equipped with pump efficiency tachymeter 3, vibration record appearance 2 and pump efficiency tachymeter 3 are connected with master control platform 5 through serial port line 4, master control platform 5 includes casing 501, the inside of casing 501 is equipped with the host computer, the upper surface of casing 501 is equipped with display 502, the middle part of display 502 is equipped with display screen 503, one side of display 502 is equipped with speaker 504, be equipped with warning light 505 on the display 502, utilize vibration record appearance 2 to record the amplitude frequency of vibration and the temperature of medium pump 1, utilize pump efficiency tachymeter 3 to pump outlet pressure, instantaneous flow, cumulative flow and velocity of flow measurement record, will pump the pump efficiency tachymeter 3 to pump outlet pressure, instantaneous flow, cumulative flow and velocity of flow measurement recordThe data are transmitted to a main console 5 through a serial port line, stored in a database, cleaned, removed of repeated data in sample data, repaired and filled of missing data, integrity of the data is guaranteed, normalization processing is carried out on the data, consistency of a data structure is guaranteed, model convergence speed is accelerated, feature selection is carried out through a Relief algorithm, a neural network is further built, in the forward transmission process, the sample data such as amplitude flow and the like are transmitted into the whole network from an input layer, and after data processing of a hidden layer, the sample data are transmitted to an output layer to obtain actual output. At this time, once the error precision between the actual output of the whole network and the expected output of the sample data cannot be met, the connection strength and the threshold value of the neurons in the whole network are required to be updated, and the process is turned to the back propagation link of the error. And in the back propagation link, the error is used as an input signal, back propagation is carried out on the input layer through the hidden layer, and the error of the whole network is distributed to all the neurons in each layer according to the weight to obtain the respective error signal of each neuron. The error signal is used as a basis for the neuron to modify the connection weight and the threshold according to the following formula. The forward propagation of the input signal and the backward propagation of the error are continuously carried out along with the iteration of the connection weight and the threshold value, the iterative optimization process of the whole network is stopped along with the iteration until the output error of the whole network reaches the expected precision, when training, all the characteristic weights are reset to be 0 at first, the ith sample and the bottom j characteristics of the sample are selected, and the weight is applied to iterate and iterate
Screening is carried out, if j is less than or equal to jmaxReturning j to j +1 to the step of selecting the ith sample and the bottom j characteristics of the sample for data processing; if j > jmaxThen determine i and imaxIf i is less than or equal to imaxIf so, bringing i to i +1 back to the step of selecting the ith sample for data processing; if i > imaxAnd outputting the weight value of each characteristic parameter until the training is finished. After training is completed, the model is evaluated through data, and the model is judged through comparison between real data and predicted dataGood or bad. After the evaluation is completed, the process of training and evaluation can be repeated by adjusting the parameters of the model, the system can monitor various data of the equipment in real time during the operation of the equipment, the warning lamp 505 and the loudspeaker 502 give an alarm when a set threshold value is reached, and the display screen 503 is provided to prompt the maintenance of the part which is likely to have a fault.
Particularly, the display screen 503 is a touch screen, which is convenient for an operator to operate.
Specifically, the outer side wall of the medium pump 1 is provided with a slide rail 6 which is fixedly connected and can be welded, the cross section of the slide rail 6 is in a dovetail shape, the slide rail 6 is provided with a locking groove which is in an inwards concave arc shape, the outside of the rear side wall of the pump efficiency tachymeter 3 is provided with a slide bar 7 which is fixedly connected and can be integrally formed, the upper part of the slide bar 7 is provided with a limit block 8 which can be welded and can also be integrally formed, the slide bar 7 is provided with a spring cavity 9, the spring cavity 9 is a cylindrical cavity, the spring cavity 9 is in a non-penetrating structure, the bottom surface of the spring cavity 9 is provided with one end of a compression spring 10 which is fixedly connected and can be bonded together through strong glue, the other end of the compression spring 10 is provided with a steel ball 11 which is fixedly connected, the steel ball 11 is matched with the locking groove, the outer diameters of the steel ball 11 and the compression spring 10 are smaller than the inner diameter, the curvature of the steel ball 11 is slightly equal to the concave curvature of the locking groove, and the diameter of the steel ball 11 is slightly smaller than the concave diameter of the locking groove.
Specifically, the quantity of slide rail 6 and draw runner 7 is 2, so can guarantee medium pump 1 and the quick measuring apparatu 3 fixed connection's of pump efficiency reliability, manufacturing cost is also lower simultaneously.
Specifically, the vibration recorder 2 is connected to the medium pump 1 by a bolt, which is a fine-thread anti-loosening bolt, to prevent the vibration recorder 2 from dropping due to vibration, and the reason why the connection is not made in a sliding manner is to avoid affecting the accuracy of the vibration recorder 2.
Specifically, the side wall of the housing 501 is provided with a plurality of heat dissipation through grooves 506, so that the heat dissipation performance of the housing 501 is improved, and the control of the working temperature of the host is facilitated.
The working principle is as follows: the utility model discloses utilize vibration recorder 2 recording medium pump 1's amplitude vibration frequency and temperature, utilize pump efficiency tachymeter 3 to pump outlet pressure, instantaneous flow, cumulative flow and velocity of flow measurement record, with data with the transmission of serial port line to main control platform 5, output result at display screen 503 after 5 handles these data of main control platform department that have the good host computer of training, when main control platform 1 judges that medium pump 1 has latent trouble or has the trend of damage, main control platform 1 controls warning light 505 scintillation, the speaker is put outward "medium pump has damage risk" and the like audio frequency reminds the user to pay attention to this risk; the pump efficiency tachymeter 3 is fixed on the pump body of the medium pump 1 in a sliding mode, the disassembly is convenient, during the installation, the pump efficiency tachymeter 3 slides downwards, the sliding strip 7 slides in the sliding rail 6 at the moment, when the steel ball 11 on the sliding strip 7 is matched with the locking groove under the action of the compression spring 10, the locking of the pump efficiency tachymeter 3 is realized, the locking fails when the pump efficiency tachymeter 3 slides downwards continuously, because the steel ball 11 and the locking groove are arranged, along with the sliding, the steel ball 11 and the locking groove are separated from the longitudinal force required by the locking, the lower end face of the limiting block 8 is contacted with the upper end face of the sliding rail 6, at the moment, all the steel balls 11 are locked with the locking groove, the longitudinal force required by the separation of the locking state reaches the maximum value, and the reliable connection relation between the pump efficiency tachymeter 3 and the medium pump 1 is ensured.
In the description of the present invention, unless expressly stated or limited otherwise, the terms "mounted," "connected," and "fixed" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral part; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meaning of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The utility model discloses the standard part that uses all can purchase from the market, and dysmorphism piece all can be customized according to the description with the record of drawing of description, and the concrete connection mode of each part all adopts conventional means such as ripe bolt, rivet, welding among the prior art, and machinery, part and equipment all adopt prior art, and conventional model, including circuit connection adopts conventional connection mode among the prior art, does not detailed here again.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. Media pump predictive maintenance system based on data analysis, comprising a media pump (1), characterized in that: the utility model discloses a pump, including medium pump (1), vibration recorder (2), main control platform (5) are connected with through string mouthful line (4) with vibration recorder (2) on the impeller outside of medium pump (1) and at medium pump (1) on the lateral wall of medium pump (1), the medium exit position of medium pump (1) is equipped with pump effect tachymeter (3), vibration recorder (2) with pump effect tachymeter (3), main control platform (5) are including casing (501), the inside of casing (501) is equipped with the host computer, the upper surface of casing (501) is equipped with display (502), the middle part of display (502) is equipped with display screen (503), one side of display (502) is equipped with speaker (504), be equipped with warning light (505) on display (502).
2. The data analysis-based media pump predictive maintenance system of claim 1, wherein: the display screen (503) is a touch screen.
3. The data analysis-based media pump predictive maintenance system of claim 1, wherein: be equipped with on the lateral wall of dielectric pump (1) slide rail (6), be equipped with the locking groove on slide rail (6), the back lateral wall outside of pump efficiency tachymeter (3) is equipped with draw runner (7), the upper portion of draw runner (7) is equipped with stopper (8), spring chamber (9) have been seted up on draw runner (7), the bottom surface of spring chamber (9) is equipped with the one end of compression spring (10), the other end of compression spring (10) is equipped with steel ball (11), steel ball (11) with the locking groove cooperatees.
4. The data analysis-based media pump predictive maintenance system of claim 3, wherein: the number of the sliding rails (6) and the number of the sliding strips (7) are both 2.
5. The data analysis-based media pump predictive maintenance system of claim 1, wherein: the vibration recorder (2) is connected with the medium pump (1) through a bolt.
6. The data analysis-based media pump predictive maintenance system of claim 1, wherein: the side wall of the shell (501) is provided with a plurality of heat dissipation through grooves (506).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020109986.7U CN212272574U (en) | 2020-01-18 | 2020-01-18 | Medium pump predictability maintenance system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020109986.7U CN212272574U (en) | 2020-01-18 | 2020-01-18 | Medium pump predictability maintenance system based on data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212272574U true CN212272574U (en) | 2021-01-01 |
Family
ID=73872992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202020109986.7U Active CN212272574U (en) | 2020-01-18 | 2020-01-18 | Medium pump predictability maintenance system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212272574U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11643908B1 (en) | 2021-11-04 | 2023-05-09 | Halliburton Energy Services, Inc. | Automated configuration of pumping equipment |
| US11852134B2 (en) | 2021-11-04 | 2023-12-26 | Halliburton Energy Services, Inc. | Automated mix water test |
| US11939862B2 (en) | 2021-09-27 | 2024-03-26 | Halliburton Energy Services, Inc. | Cementing unit power on self test |
-
2020
- 2020-01-18 CN CN202020109986.7U patent/CN212272574U/en active Active
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11939862B2 (en) | 2021-09-27 | 2024-03-26 | Halliburton Energy Services, Inc. | Cementing unit power on self test |
| US11643908B1 (en) | 2021-11-04 | 2023-05-09 | Halliburton Energy Services, Inc. | Automated configuration of pumping equipment |
| US11852134B2 (en) | 2021-11-04 | 2023-12-26 | Halliburton Energy Services, Inc. | Automated mix water test |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN212272574U (en) | Medium pump predictability maintenance system based on data analysis | |
| CN105866638B (en) | A kind of city net cable connector state of insulation on-line monitoring prior-warning device and method | |
| CN112145151B (en) | Dynamic impact risk detection and evaluation method based on response parameters while drilling | |
| CN112327191B (en) | Battery diving probability evaluation method based on geometric feature fusion decision | |
| CN110455517B (en) | Tower barrel health monitoring method of wind generating set | |
| CN116734750B (en) | Intelligent detection method and system for thickness of ice layer of ice rink based on optical fiber sensor | |
| CN113361208A (en) | Solid state disk residual life evaluation method based on comprehensive health index | |
| CN113432857B (en) | Method and system for predicting residual service life of underwater Christmas tree system based on digital twins | |
| CN110363404A (en) | A kind of dry-type air-core reactor status data analysis method | |
| CN113987908A (en) | Natural gas pipe network leakage early warning method based on machine learning method | |
| KR102510060B1 (en) | An obtaining method abnormality data through deep learning pump simulation and an abnormality detection model establishment method based on auto-encoder and a system thereof | |
| CN111340284A (en) | Intelligent waterwheel room water level prediction method based on long-time memory network | |
| CN114444823A (en) | Method and system for predicting lost circulation risk in drilling operation process | |
| CN107403279A (en) | A kind of adaptive status early warning system and method for oil transportation pump condition | |
| CN115689114A (en) | Submarine cable running state prediction method based on combined neural network | |
| CN114810213A (en) | Multi-source information fusion intelligent early warning method and device for coal and gas outburst | |
| CN110987396A (en) | Intelligent fault diagnosis and service life prediction method for coal mining machine rocker arm | |
| CN117142009B (en) | Scraper conveyor health state assessment method based on graph rolling network | |
| CN104598705A (en) | Method and device for recognizing underground material layer | |
| CN109872511B (en) | Self-adaptive two-stage alarm method for monitoring axial displacement sudden change | |
| CN116122799A (en) | Real-time intelligent monitoring and alarming device and method for overflow leakage of drilling fluid | |
| CN115905869A (en) | Ultrasonic water meter fault early warning method | |
| CN117287188A (en) | Drilling well leakage monitoring method based on downhole pressure data stream | |
| CN114004059A (en) | Health portrait method for hydroelectric generating set | |
| CN114913302B (en) | Rotary joint service life prediction system and method based on multi-sensor fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |