CN111306142A - Hydraulic pump cavitation state detection system - Google Patents
Hydraulic pump cavitation state detection system Download PDFInfo
- Publication number
- CN111306142A CN111306142A CN202010116130.7A CN202010116130A CN111306142A CN 111306142 A CN111306142 A CN 111306142A CN 202010116130 A CN202010116130 A CN 202010116130A CN 111306142 A CN111306142 A CN 111306142A
- Authority
- CN
- China
- Prior art keywords
- hydraulic pump
- data
- oil
- oil inlet
- detected
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 12
- 239000003921 oil Substances 0.000 claims description 108
- 239000010720 hydraulic oil Substances 0.000 claims description 20
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims 1
- 238000012360 testing method Methods 0.000 description 6
- 238000000926 separation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F15—FLUID-PRESSURE ACTUATORS; HYDRAULICS OR PNEUMATICS IN GENERAL
- F15B—SYSTEMS ACTING BY MEANS OF FLUIDS IN GENERAL; FLUID-PRESSURE ACTUATORS, e.g. SERVOMOTORS; DETAILS OF FLUID-PRESSURE SYSTEMS, NOT OTHERWISE PROVIDED FOR
- F15B19/00—Testing; Calibrating; Fault detection or monitoring; Simulation or modelling of fluid-pressure systems or apparatus not otherwise provided for
- F15B19/007—Simulation or modelling
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F15—FLUID-PRESSURE ACTUATORS; HYDRAULICS OR PNEUMATICS IN GENERAL
- F15B—SYSTEMS ACTING BY MEANS OF FLUIDS IN GENERAL; FLUID-PRESSURE ACTUATORS, e.g. SERVOMOTORS; DETAILS OF FLUID-PRESSURE SYSTEMS, NOT OTHERWISE PROVIDED FOR
- F15B19/00—Testing; Calibrating; Fault detection or monitoring; Simulation or modelling of fluid-pressure systems or apparatus not otherwise provided for
- F15B19/005—Fault detection or monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention relates to a hydraulic pump cavitation state detection system, which comprises a signal acquisition module and a main control module; the signal acquisition module is used for acquiring current operation data of a hydraulic pump to be detected in the hydraulic circuit in the operation process; the current operation data comprises temperature data of an oil inlet of a hydraulic pump to be detected, pressure data of the oil inlet of the hydraulic pump to be detected, flow data of the oil inlet of the hydraulic pump to be detected, pressure data of an oil outlet of the hydraulic pump to be detected, flow data of the oil outlet of the hydraulic pump to be detected and vibration data of a pump shell of the hydraulic pump to be detected; the master control module is integrated with a trained over-limit learning machine model; the trained overrun learning machine model is obtained by training according to historical operation data of the hydraulic pump and hydraulic pump cavitation state images corresponding to the historical operation data. The cavitation state of the hydraulic pump to be detected is determined according to the current operation data of the hydraulic pump and the trained over-limit learning machine model, and the cavitation state of the hydraulic pump can be detected truly and comprehensively.
Description
Technical Field
The invention relates to the technical field of hydraulic pump detection, in particular to a hydraulic pump cavitation state detection system.
Background
As industrial applications and social development demands, hydraulic pumps are being developed toward low noise, low flow pulsation and high speed and high pressure, and the influence of cavitation phenomena on the performance of hydraulic pumps becomes more prominent. The cavitation phenomenon refers to a phenomenon in which air or steam is separated from oil liquid, which occurs when the pressure thereof is lowered to below the air separation pressure or the saturated vapor pressure at some point during the flow of the liquid. Hydraulic fluids typically contain some air suspended or dissolved therein, the amount of air in a hydraulic fluid is known as the air void fraction, which can reach 6-12% at standard atmospheric pressure. When the pressure is lower than the air separation pressure, air can be separated out from the liquid and gathered into bubbles to be free in the hydraulic oil, the smaller the pressure, the more the separated air is, the larger the diameter of the formed bubbles is, and even a cavity group is formed, and the separated air is called gas cavitation. In engineering application, the cavitation phenomenon is mainly gas cavitation.
In the operation process of the hydraulic system, the back pressure of the loop is limited, the inlet pressure is low, and the hydraulic pump is easy to generate cavitation. When the gas separated out during cavitation is condensed, local extreme high temperature (1900K-5000K) and high pressure (140 MPa-170 MPa) can generate adverse effect on the working characteristics of the hydraulic pump. The cavitation of the hydraulic pump is a direct cause of cavitation in the pump, which increases noise and impact of the hydraulic pump, reduces working efficiency, and even causes fatigue failure of parts in the pump, and thus the cavitation becomes one of the main factors affecting the performance of the hydraulic pump. Many scholars and researchers have studied the cavitation of the hydraulic pump, but basically all focus on the theory and simulation research of cavitation mechanism, and can not simulate the real cavitation, and there are many factors influencing the cavitation, and the simulation and theoretical research does not fully consider all influencing factors. Therefore, how to really and comprehensively detect the cavitation state of the hydraulic pump is an important problem to be faced currently.
Disclosure of Invention
The invention aims to provide a hydraulic pump cavitation state detection system which can truly and comprehensively detect the cavitation state of a hydraulic pump.
In order to achieve the purpose, the invention provides the following scheme:
a hydraulic pump cavitation condition detection system, comprising: the system comprises a signal acquisition module and a main control module; wherein,
the signal acquisition module is used for acquiring current operation data of a hydraulic pump to be detected in the hydraulic circuit in the operation process; the current operation data comprises temperature data of an oil inlet of a hydraulic pump to be detected, pressure data of the oil inlet of the hydraulic pump to be detected, pressure data of an oil outlet of the hydraulic pump to be detected, flow data of the oil outlet of the hydraulic pump to be detected and vibration data of a pump shell of the hydraulic pump to be detected;
the master control module is integrated with a trained over-limit learning machine model; the main control module is used for determining the cavitation state of the hydraulic pump to be tested according to the current operation data and the trained over-limit learning machine model; the trained overrun learning machine model is obtained by training according to historical operation data of the hydraulic pump and hydraulic pump cavitation state images corresponding to the historical operation data.
Optionally, the main control module is provided with a database, a data acquisition module, a model training module and a state determination module; wherein,
the database is used for storing the historical operation data and hydraulic pump cavitation state images corresponding to the historical operation data;
the data acquisition module is used for acquiring the current operation data;
the model training module is used for dividing the cavitation state of the hydraulic pump according to the cavitation state image of the hydraulic pump, and training an overrun learning machine model according to the historical operation data and the cavitation state of the hydraulic pump to obtain the trained overrun learning machine model; the input of the trained over-limit learning machine model is the current operation data, and the output of the trained over-limit learning machine model is the cavitation state of the hydraulic pump to be tested;
and the state determination module is used for determining the cavitation state of the hydraulic pump to be tested according to the current operation data and the trained over-limit learning machine model.
Optionally, the signal acquisition module is provided with an oil inlet temperature sensor, an oil inlet pressure sensor, an oil outlet flow sensor and a vibration sensor; wherein,
the oil inlet temperature sensor and the oil inlet pressure sensor are both arranged on one side of an oil inlet of the hydraulic pump; the oil outlet pressure sensor and the oil outlet flow sensor are both arranged on one side of the oil outlet of the hydraulic pump; the vibration sensor is arranged on the pump shell of the hydraulic pump.
Optionally, the vibration sensor is a three-axis acceleration sensor.
Optionally, the three-axis acceleration sensors are arranged in three numbers and are respectively installed on the side face of the pump body of the hydraulic pump, the lower end of the pump body of the hydraulic pump and the shaft end of the hydraulic pump.
Optionally, the signal acquisition module is further provided with an image acquisition device and a transparent pipeline; wherein,
the transparent pipeline is arranged on one side of an oil inlet of the hydraulic pump; the image acquisition device is arranged corresponding to the transparent pipeline and used for acquiring and storing hydraulic pump cavitation state images corresponding to hydraulic oil in the transparent pipeline.
Optionally, the image capturing device includes a camera and a light source.
Optionally, the hydraulic circuit is provided with a motor, a hydraulic pump to be tested, an oil inlet filter, an oil outlet filter, an overflow valve, a gate valve and an oil tank; wherein,
the motor is connected with the hydraulic pump; the oil tank is used for providing hydraulic oil; the oil tank is communicated with the hydraulic pump through a pipeline; the oil inlet filter and the gate valve are arranged on one side of an oil inlet of the hydraulic pump, and the oil outlet filter and the overflow valve are arranged on one side of an oil outlet of the hydraulic pump.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a hydraulic pump cavitation state detection system, which comprises: the system comprises a signal acquisition module and a main control module; the signal acquisition module is used for acquiring current operation data of a hydraulic pump to be detected in the hydraulic circuit in the operation process; the current operation data comprises temperature data of an oil inlet of a hydraulic pump to be detected, pressure data of the oil inlet of the hydraulic pump to be detected, flow data of the oil inlet of the hydraulic pump to be detected, pressure data of an oil outlet of the hydraulic pump to be detected, flow data of the oil outlet of the hydraulic pump to be detected and vibration data of a pump shell of the hydraulic pump to be detected; the master control module is integrated with a trained over-limit learning machine model; the main control module is used for determining the cavitation state of the hydraulic pump to be tested according to the current operation data and the trained overrun learning machine model; the trained overrun learning machine model is obtained by training according to historical operation data of the hydraulic pump and hydraulic pump cavitation state images corresponding to the historical operation data.
The cavitation state of the hydraulic pump to be tested is determined according to the current operation data of the hydraulic pump and the trained over-limit learning machine model, the current operation data of the hydraulic pump comprises hydraulic pump oil inlet temperature data, hydraulic pump oil inlet pressure data, hydraulic pump oil inlet flow data, hydraulic pump oil outlet pressure data, hydraulic pump oil outlet flow data and hydraulic pump shell vibration data, and the cavitation state of the hydraulic pump can be detected truly and comprehensively.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a system block diagram of a hydraulic pump cavitation detection system according to an embodiment of the present invention;
fig. 2 is a block diagram of a signal acquisition module according to an embodiment of the present invention;
FIG. 3 is a graph showing the results of an experiment in which the hydraulic oil is in a pure hydraulic state when the internal pressure of the hydraulic oil is greater than the air separation pressure;
FIG. 4 is a graph showing the results of an experiment in the initial cavitation;
FIG. 5 is a graph showing the results of experiments in which discrete cavitation bubbles gradually increase and the phenomenon of aggregation and fusion of the discrete bubbles occurs;
FIG. 6 is a graph showing the results of a test in which cavitation bubbles are present in large numbers to form cavitation groups when the cavitation level continues to increase;
FIG. 7 is a graph of hydraulic pump cavitation.
Description of the symbols:
1-oil tank, 2-filter, 3-gate valve, 4-light source, 5-transparent pipeline, 6-camera, 7-oil inlet temperature sensor, 8-oil inlet pressure sensor, 9-oil inlet flow sensor, 10-motor, 11-hydraulic pump, 12-vibration sensor, 13-oil outlet flow sensor, 14-oil outlet pressure sensor and 15-overflow valve.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a hydraulic pump cavitation state detection system which can truly and comprehensively detect the cavitation state of a hydraulic pump.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example (b):
fig. 1 is a system block diagram of a hydraulic pump cavitation state detection system according to an embodiment of the present invention, and as shown in fig. 1, the detection system includes a signal acquisition module and a main control module. The signal acquisition module is used for acquiring current operation data of the hydraulic pump to be detected in the hydraulic circuit in the operation process. The master control module is integrated with a trained overrun learning machine model. The main control module is used for determining the cavitation state of the hydraulic pump to be tested according to the current operation data of the hydraulic pump to be tested in the operation process and the trained over-limit learning machine model. The trained overrun learning machine model is obtained by training according to historical operation data of the hydraulic pump and hydraulic pump cavitation state images corresponding to the historical operation data.
The current operation data of the hydraulic pump comprises hydraulic pump oil inlet temperature data, hydraulic pump oil inlet pressure data, hydraulic pump oil inlet flow data, hydraulic pump oil outlet pressure data, hydraulic pump oil outlet flow data and hydraulic pump shell vibration data.
The historical operation data of the hydraulic pump comprises historical oil inlet temperature data of the hydraulic pump, historical oil inlet pressure data of the hydraulic pump, historical oil inlet flow data of the hydraulic pump, historical oil outlet pressure data of the hydraulic pump, historical oil outlet flow data of the hydraulic pump and historical pump shell vibration data of the hydraulic pump.
Fig. 2 is a block diagram of a signal acquisition module according to an embodiment of the present invention, and as shown in fig. 2, the signal acquisition module includes an oil tank 1, a filter 2, a gate valve 3, an oil inlet temperature sensor 7, an oil inlet pressure sensor 8, an oil inlet flow sensor 9, a motor 10, a hydraulic pump 11, a vibration sensor 12, an oil outlet flow sensor 13, an oil outlet pressure sensor 14, and an overflow valve 15. Wherein oil tank 1 passes through the pipeline and is connected with hydraulic pump 11, and filter 2 locates the oil inlet department of pipeline, and filter 2 is used for filtering hydraulic oil. The side of the filter 2 which is immediately adjacent to the filter 2 and remote from the tank 1 is provided with a gate valve 3. The transparent pipeline 5 is arranged on one side of an oil inlet of the hydraulic pump 11. An oil inlet temperature sensor 7, an oil inlet pressure sensor 8 and an oil inlet flow sensor 9 are arranged on one side of an oil inlet of a hydraulic pump 11. The motor 10 is used to power the hydraulic pump 11. The vibration sensors 12 are three-axis acceleration sensors, and are respectively installed on the side surface of the pump body of the hydraulic pump 11, the lower end of the pump body of the hydraulic pump 11, and the shaft end of the hydraulic pump 11. An oil outlet flow sensor 13, an oil outlet pressure sensor 14 and an overflow valve 15 are arranged at the oil outlet of the hydraulic pump 11. The oil tank 1 is connected with an oil outlet of the hydraulic pump 11 through a pipeline, and the oil tank 1 is used for loading hydraulic oil flowing out of the hydraulic pump 11. The overflow valve 15 is arranged at the oil outlet of the pipeline.
In the present embodiment, the hydraulic pump 11 is a plunger pump of type a10VS045, the motor 10 is of type Y225S-4, and the vibration sensor 12 is of type 8795a 50.
In this embodiment, the signal acquisition module further includes a light source 4, a transparent pipe 5, and a camera 6. The camera 6 is used for acquiring and storing hydraulic pump cavitation state images corresponding to the hydraulic oil in the transparent pipeline 5 under the irradiation of the light source 4.
In this embodiment, the historical operation data of the hydraulic pump and the hydraulic pump cavitation state image corresponding to the historical operation data may be acquired by the signal acquisition module, and the acquisition process of the signal acquisition module is as follows:
under a given working condition, the air content of the hydraulic oil entering the hydraulic pump 11 is controlled by controlling the opening degree of the gate valve 3, so that the pressure of the hydraulic oil at the oil inlet is reduced according to a certain gradient, the vacuum degree of the inlet of the hydraulic pump 11 is controlled, and the hydraulic pump 11 is subjected to a normal state to a severe cavitation state. The signal acquisition module acquires historical operation data of the hydraulic pump 11 from a normal state to a severe cavitation state and a hydraulic pump cavitation state image corresponding to the historical operation data of the hydraulic pump 11.
In this embodiment, the main control module further includes a database, a data acquisition module, a model training module, and a state determination module. The database stores therein historical operation data of the hydraulic pump 11 and hydraulic pump cavitation state images corresponding to the historical operation data of the hydraulic pump 11. The data acquisition module is used for acquiring current operation data of the hydraulic pump to be detected in the operation process. The model training module is used for dividing the cavitation state of the hydraulic pump according to the cavitation state image of the hydraulic pump, and training the ultralimit learning machine model according to the historical operation data of the hydraulic pump 11 and the cavitation state of the hydraulic pump to obtain the trained ultralimit learning machine model.
The specific working process of the model training module in this embodiment is as follows:
(1) the cavitation state of the hydraulic pump 11 is divided into three stages according to the flow of the hydraulic pump oil inlet, the pressure of the hydraulic pump oil inlet and the hydraulic pump cavitation state image:
1. and (4) a normal state. When the internal pressure of the hydraulic oil is higher than the air separation pressure, the air is completely dissolved in the hydraulic oil, and the hydraulic oil is in a pure oil state, and no air bubbles are generated, as shown in fig. 3. The outlet flow of the hydraulic pump 11 remains constant during this process.
2. A state of cavitation development. When the internal pressure of the hydraulic oil is reduced to the air separation pressure, air particles suspended in the hydraulic oil grow, air dissolved in the hydraulic oil begins to separate out, visible discrete bubbles can be observed to appear through the transparent pipeline 5 by the camera 6, and at the moment, the hydraulic pump 11 begins to cavitate, as shown in fig. 4. And the number of cavitation bubbles increases with continued decrease in pressure, increasing in volume. Cavitation affects the density of hydraulic oil so that the outlet flow of the hydraulic pump begins to decrease, but the decrease in flow is less than 1%.
3. Severe cavitation conditions. As the internal pressure of the hydraulic oil continues to decrease, the effect of cavitation on the performance of the hydraulic pump 11 is more pronounced. Fig. 5 is a graph showing the experimental results when discrete cavitation bubbles gradually increase and the phenomenon of aggregation and fusion of the discrete bubbles occurs. And then the outlet flow of the hydraulic pump 11 is sharply reduced, the reduction amplitude is more than or equal to 1%, violent vibration and obvious 'howling' occur, the camera 6 can be used for observing that cavitation bubbles are mutually aggregated to form cavitation bubble groups through the transparent pipeline 5, and the hydraulic pump 11 is cavitated and collapsed. FIG. 6 is a graph showing the results of experiments in which cavitation bubbles are generated in large numbers to form cavitation groups when the cavitation level is continuously increased.
A hydraulic pump cavitation state graph plotted according to historical operation data and cavitation state of the hydraulic pump 11 is shown in fig. 7.
(2) Training an overrun learning machine model according to historical operating data and a cavitation state of a hydraulic pump, and the specific process is as follows:
1. and respectively extracting the characteristics of the historical hydraulic pump shell vibration data and the historical hydraulic pump oil outlet flow data. Specifically, time domain characteristic vectors of pump shell vibration signals are obtained through time domain analysis of historical hydraulic pump shell vibration data, wherein the time domain characteristic vectors comprise peak values, mean values, variances, standard variances, mean square values, root mean square values, waveform indexes, peak value indexes, margin indexes, skewness indexes and kurtosis indexes. Time domain analysis is carried out on historical hydraulic pump shell vibration data to obtain 12-dimensional pump shell vibration time domain characteristics, EMD decomposition is carried out on the 12-dimensional pump shell vibration time domain characteristics, and sample entropy values of decomposition coefficients of each layer are calculated to obtain 9-dimensional sample entropy nonlinear characteristics of pump shell vibration. And performing time domain analysis on the historical hydraulic pump oil outlet flow data to obtain 12-dimensional pump outlet flow time domain characteristics.
2. And (3) performing feature simplification and dimension reduction on the features by using a parallel coordinate graph method and a correlation analysis method, and performing normalization processing on the fused features to obtain original data.
3. 300 samples of the original data were taken. Wherein, 100 samples are available in a normal state, 100 samples are available in a cavitation development state, and 100 samples are available in a cavitation severe state. According to the number of training samples and the number of testing samples 3: a ratio of 1 divides the three state samples into training sets and test sets (75 samples of 225 training samples containing three states each and 25 samples of 75 test samples containing three states each). And training the ultralimit learning machine model by using the training data and the cavitation state corresponding to the original data to obtain the trained ultralimit learning machine model.
4. And verifying the trained overrun learning machine model. Inputting the test data into the trained overrun learning machine model to obtain the cavitation degree identification result of the hydraulic pump, and comparing the identification result with the real cavitation degree of the hydraulic pump to obtain a table 1:
TABLE 1
| Time/s | Recognition rate/%) | |
| ELM | 0.26 | 98 |
The time consumption is the training time of the trained over-limit learning machine model, and the recognition rate is the test recognition rate of the trained over-limit learning machine model. As can be seen from Table 1, the training time required for a well-trained overrun learning model is very short and the accuracy is high.
The state determining module in the main control module of the detection system finally inputs the real-time operation data of the hydraulic pump into the trained ultralimit learning machine model, and the cavitation state of the hydraulic pump to be detected can be determined.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
1. the cavitation state of the hydraulic pump to be tested is determined according to the current operation data of the hydraulic pump and the trained over-limit learning machine model, and the trained over-limit learning machine model is obtained according to the historical operation data of the hydraulic pump and the corresponding hydraulic pump cavitation state image training. And the current operation data of the hydraulic pump comprises hydraulic pump oil inlet temperature data, hydraulic pump oil inlet pressure data, hydraulic pump oil inlet flow data, hydraulic pump oil outlet pressure data, hydraulic pump oil outlet flow data and hydraulic pump casing vibration data, and the cavitation state of the hydraulic pump can be detected truly and comprehensively.
2. The ultralimit learning machine model has the advantages of simple structure, strong robustness and fault tolerance and good generalization capability. And only a few parameters need to be set, repeated operation does not exist, the operation speed is high, and the accuracy is high.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to assist in understanding the core concepts of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A hydraulic pump cavitation state detection system, comprising: the system comprises a signal acquisition module and a main control module; wherein,
the signal acquisition module is used for acquiring current operation data of a hydraulic pump to be detected in the hydraulic circuit in the operation process; the current operation data comprises temperature data of an oil inlet of a hydraulic pump to be detected, pressure data of the oil inlet of the hydraulic pump to be detected, flow data of the oil inlet of the hydraulic pump to be detected, pressure data of an oil outlet of the hydraulic pump to be detected, flow data of the oil outlet of the hydraulic pump to be detected and vibration data of a pump shell of the hydraulic pump to be detected;
the master control module is integrated with a trained over-limit learning machine model; the main control module is used for determining the cavitation state of the hydraulic pump to be tested according to the current operation data and the trained over-limit learning machine model; the trained overrun learning machine model is obtained by training according to historical operation data of the hydraulic pump and hydraulic pump cavitation state images corresponding to the historical operation data.
2. The detection system according to claim 1, wherein the main control module is provided with a database, a data acquisition module, a model training module and a state determination module; wherein,
the database is used for storing the historical operation data and hydraulic pump cavitation state images corresponding to the historical operation data;
the data acquisition module is used for acquiring the current operation data;
the model training module is used for dividing the cavitation state of the hydraulic pump according to the cavitation state image of the hydraulic pump, and training an overrun learning machine model according to the historical operation data and the cavitation state of the hydraulic pump to obtain the trained overrun learning machine model; the input of the trained over-limit learning machine model is the current operation data, and the output of the trained over-limit learning machine model is the cavitation state of the hydraulic pump to be tested;
and the state determination module is used for determining the cavitation state of the hydraulic pump to be tested according to the current operation data and the trained over-limit learning machine model.
3. The detection system according to claim 1, wherein the signal acquisition module is provided with an oil inlet temperature sensor, an oil inlet pressure sensor, an oil inlet flow sensor, an oil outlet pressure sensor, an oil outlet flow sensor and a vibration sensor; wherein,
the oil inlet temperature sensor, the oil inlet pressure sensor and the oil inlet flow sensor are all arranged on one side of an oil inlet of the hydraulic pump; the oil outlet pressure sensor and the oil outlet flow sensor are both arranged on one side of the oil outlet of the hydraulic pump; the vibration sensor is arranged on the pump shell of the hydraulic pump.
4. A detection system according to claim 3, wherein the vibration sensor is a three-axis acceleration sensor.
5. The detection system according to claim 4, wherein three triaxial acceleration sensors are provided, respectively mounted on a side surface of the pump body of the hydraulic pump, a lower end of the pump body of the hydraulic pump, and a shaft end of the hydraulic pump.
6. The detection system according to claim 3, wherein the signal acquisition module is further provided with an image acquisition device and a transparent pipeline; wherein,
the transparent pipeline is arranged on one side of an oil inlet of the hydraulic pump; the image acquisition device is arranged corresponding to the transparent pipeline and used for acquiring and storing hydraulic pump cavitation state images corresponding to hydraulic oil in the transparent pipeline.
7. The inspection system of claim 6, wherein the image capture device comprises a camera and a light source.
8. The detection system according to claim 1, wherein the hydraulic circuit is provided with a motor, a hydraulic pump to be detected, an oil inlet filter, an oil outlet filter, an overflow valve, a gate valve and an oil tank; wherein,
the motor is connected with the hydraulic pump; the oil tank is used for providing hydraulic oil; the oil tank is communicated with the hydraulic pump through a pipeline; the oil inlet filter and the gate valve are arranged on one side of an oil inlet of the hydraulic pump, and the oil outlet filter and the overflow valve are arranged on one side of an oil outlet of the hydraulic pump.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116130.7A CN111306142B (en) | 2020-02-25 | 2020-02-25 | Hydraulic pump cavitation state detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116130.7A CN111306142B (en) | 2020-02-25 | 2020-02-25 | Hydraulic pump cavitation state detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111306142A true CN111306142A (en) | 2020-06-19 |
| CN111306142B CN111306142B (en) | 2022-04-08 |
Family
ID=71152974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010116130.7A Active CN111306142B (en) | 2020-02-25 | 2020-02-25 | Hydraulic pump cavitation state detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111306142B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113670790A (en) * | 2021-07-30 | 2021-11-19 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Method and device for determining working state of ceramic filter |
| CN114997246A (en) * | 2022-07-27 | 2022-09-02 | 浙江大学 | Cavitation state identification method driven by fluid mechanical vibration data |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6655922B1 (en) * | 2001-08-10 | 2003-12-02 | Rockwell Automation Technologies, Inc. | System and method for detecting and diagnosing pump cavitation |
-
2020
- 2020-02-25 CN CN202010116130.7A patent/CN111306142B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6655922B1 (en) * | 2001-08-10 | 2003-12-02 | Rockwell Automation Technologies, Inc. | System and method for detecting and diagnosing pump cavitation |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113670790A (en) * | 2021-07-30 | 2021-11-19 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Method and device for determining working state of ceramic filter |
| CN113670790B (en) * | 2021-07-30 | 2024-03-22 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Method and device for determining working state of ceramic filter |
| CN114997246A (en) * | 2022-07-27 | 2022-09-02 | 浙江大学 | Cavitation state identification method driven by fluid mechanical vibration data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111306142B (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111306142B (en) | Hydraulic pump cavitation state detection system | |
| CN109668723B (en) | Regulating valve cavitation diagnosis system and diagnosis method thereof | |
| CN114898126B (en) | Method for improving fault diagnosis precision of oil extraction machine under composite working condition | |
| CN111521388A (en) | Regulating valve cavitation diagnosis device and diagnosis method thereof | |
| CN101520379A (en) | Test board for flow rate pressure of pressure regulating valve | |
| CN108757426B (en) | Fault diagnosis method for water injection plunger pump in petroleum mine field | |
| Dai et al. | Cavitation state identification of centrifugal pump based on CEEMD-DRSN | |
| CN112727784A (en) | Axial flow pump blade top cavitation vortex dynamic characteristic identification test device and method | |
| CN108918103B (en) | Hydraulic control check valve dynamic characteristic test system and test method | |
| CN110991544A (en) | Axial plunger pump cavitation level identification method based on PICA-VMD and Hilbert marginal spectrum | |
| CN112067283A (en) | Regulating valve cavitation diagnosis system based on sound power spectrum and diagnosis method thereof | |
| Li et al. | A fault diagnosis approach for gears using multidimensional features and intelligent classifier | |
| Ye et al. | Multi-variable classification model for valve internal leakage based on acoustic emission time–frequency domain characteristics and random forest | |
| CN105928666B (en) | Leakage acoustic characteristic extracting method based on Hilbert-Huang transform and blind source separating | |
| CN207195361U (en) | Experimental provision for guiding valve oscillating flow field visual testing | |
| RU2008137214A (en) | METHOD OF TESTING GAS SEPARATORS OF SUBMERSIBLE ELECTRIC PUMP UNITS FOR OIL PRODUCTION AND AUTOMATED STAND FOR ITS IMPLEMENTATION | |
| McCloy et al. | Some cavitation effects in spool valve orifices | |
| Liu et al. | Similar or unknown fault mode detection of aircraft fuel pump using transfer learning with subdomain adaption | |
| Azizi et al. | Cavitation severity detection in centrifugal pumps | |
| CN108168612A (en) | Biphase gas and liquid flow volume void fraction measuring method based on differential pressure signal fluctuation | |
| Wang et al. | Fault diagnosis of reciprocating compressor using component estimating empirical mode decomposition and de-dimension template with double-loop correction algorithm | |
| CN104834829B (en) | Fluctuation pressure Numerical Predicting Method | |
| CN203189243U (en) | Air extracting device | |
| Xiaoxiao et al. | A self-evolution fault diagnosis method of sucker rod pump based on simulating dynamometer card | |
| CN201569574U (en) | Flow pressure test board of pressure regulating valve |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |