CN117552972A - Intelligent plunger pump and method and system for monitoring internal and external leakage in real time - Google Patents
Intelligent plunger pump and method and system for monitoring internal and external leakage in real time Download PDFInfo
- Publication number
- CN117552972A CN117552972A CN202311815262.9A CN202311815262A CN117552972A CN 117552972 A CN117552972 A CN 117552972A CN 202311815262 A CN202311815262 A CN 202311815262A CN 117552972 A CN117552972 A CN 117552972A
- Authority
- CN
- China
- Prior art keywords
- plunger pump
- liquid level
- time domain
- signal
- pressure
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 36
- 238000012544 monitoring process Methods 0.000 title claims description 31
- 239000007788 liquid Substances 0.000 claims abstract description 56
- 238000003062 neural network model Methods 0.000 claims abstract description 33
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 239000003921 oil Substances 0.000 description 55
- 238000011176 pooling Methods 0.000 description 6
- 238000007789 sealing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012806 monitoring device Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000005299 abrasion Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005461 lubrication Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 239000010720 hydraulic oil Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B51/00—Testing machines, pumps, or pumping installations
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention relates to the technical field of pumps, in particular to an intelligent plunger pump. And an oil outlet flange of the plunger pump body is fixedly connected with a second pressure sensor and is used for detecting a second pressure time domain signal of the oil return pipeline in real time. The liquid level signal of the inner oil duct is detected through a liquid level sensor fixedly arranged at the bottom of the intelligent plunger pump. The signals are subjected to Fourier transformation after the mean value is subtracted by the A/D converter, and then working condition data corresponding to different rotating speed values are input into a trained neural network model, so that internal leakage and external leakage fault identification data are obtained and output. The multi-source state characteristics of the hydraulic plunger pump can be extracted, and the fault identification accuracy is high, so that the equipment can be monitored in real time and intelligently, and the equipment operation efficiency and the overhaul work efficiency are greatly improved.
Description
Technical Field
The invention relates to the technical field of pumps, in particular to an intelligent plunger pump and a method and a system for monitoring internal and external leakage in real time.
Background
The plunger Pump (Piston Pump) is a core power element in a hydraulic system and mainly comprises a cylinder body, a plunger and the like, the plunger of the cylinder body is driven to rotate through the rotation of a main shaft, and the plunger reciprocates in a plunger cavity to change the volume of a sealed cavity so as to realize oil suction and discharge. The swash plate type axial plunger pump has the advantages of compact structure, stable operation and the like, and is widely applied to the fields of transportation, aerospace and the like.
The axial plunger pump used in the field of engineering machinery at present mainly causes leakage to influence the reliability of the plunger pump because of lubrication and abrasion failure of three key friction pairs, and the equipment can finally cause sealing failure and cause faults after continuously maintaining high-strength operation for a long time under the condition of leakage. CN117006037a discloses a fault monitoring method of a double-screw pump based on deep learning, which comprises the following steps: s1: collecting vibration data of operation of the double-screw pump, forming a data set, preprocessing the data set, and inputting the data set as a noise reduction self-encoder;
s2: setting related parameters of the noise-reducing self-encoders, taking collected vibration data as input of a neural network, training a first noise-reducing self-encoder, taking output of the first noise-reducing self-encoder as input of a later noise-reducing self-encoder, and training a plurality of noise-reducing self-encoders according to the training results to form a stacked noise-reducing self-encoder; s3: testing the stacked noise reduction self-encoder by using a test set in the data set, calculating the accuracy, judging whether the calculation result meets the accuracy requirement of initial setting, if so, ending training and outputting a network for fault monitoring, otherwise, returning to the step S2, and adjusting various parameters of the stacked noise reduction self-encoder for training; s4: inputting a vibration signal of the double-screw pump to be tested into a stacking noise reduction self-encoder after training is completed, and calculating a reconstruction error; s5: according to the extremum theory, a superthreshold extremum model is adopted, and the self-adaptive threshold of the specific working condition of the double-screw pump is calculated; s6: and (3) comparing the reconstruction error calculated in the step (S4) with the self-adaptive threshold value calculated in the step (S5), and if the reconstruction error is larger than the self-adaptive threshold value, indicating that the double-screw pump is abnormal.
CN115898859B discloses a hydraulic plunger pump oil distributing cover, a hydraulic plunger pump and a power supply method, comprising: the oil distribution cover body is provided with an oil inlet flow passage and a mounting groove communicated with the oil inlet flow passage; the generator assembly is arranged in the mounting groove and comprises a generator and an impeller arranged on a rotating shaft of the generator, and the impeller is at least partially positioned in the oil inlet flow passage; the rectification circuit board is arranged in the mounting groove and is electrically connected with the generator and used for rectifying alternating current generated by the generator into direct current; the groove cover is arranged at the notch of the mounting groove and is provided with a power supply socket electrically connected with the rectifying circuit board; the peripheral wall of the oil inlet flow passage is provided with a mounting opening, and the oil inlet flow passage is communicated with the mounting groove through the mounting opening; and a part of the impeller penetrates through the mounting opening and stretches into the oil inlet flow passage, and the impeller, the generator and the rectifying circuit board are sequentially arranged along the extending direction of the oil inlet flow passage.
In the prior art, a common method for leakage monitoring of a plunger pump is to externally connect a pipeline and an oil discharge tank and install a sensor and an electromagnetic valve on the oil discharge pipeline; or the compound type multi-sensor is buried under the swash plate and on the surface of the cylinder body in a manner of embedding the sensor. Because the closed plunger pump often works in high-pressure high-rotation speed and severe environments for a long time, the internal leakage and the external leakage cannot be effectively monitored in real time.
Disclosure of Invention
Long-term practice shows that a plunger pump working under high-speed and high-pressure working conditions for a long time usually generates a certain amount of leakage, wherein internal leakage can flow back into an oil tank in a shell and can cause the increase of the pressure in the shell, so that the internal leakage monitoring requires the pressure in the inner cavity of the shell to be lower than a certain threshold value; the leakage can cause the oil to overflow and break the seal to cause faults, so that the leakage monitoring requires that the edge of the shell does not allow oil to overflow, and the existing method can not monitor the inner leakage and the outer leakage simultaneously. The plunger pump can influence the embedded sensor on the surfaces of the swash plate and the cylinder body when running at high speed and high pressure for a long time, so that the sensor monitoring precision is insufficient, and when the lubrication abrasion failure of the sliding shoe pair is serious, the leakage quantity is increased, and even the embedded sensor can be damaged, so that the whole control monitoring system cannot guarantee stable running for a long time. The monitoring device is simple, efficient and accurate in selection, and the technical problems that the real-time performance and the efficiency of the composite multi-sensor are low when the monitoring device is externally connected with a pipeline oil tank and is installed, and the pressure change can not be monitored in real time can be solved.
In view of the above, the invention provides an intelligent plunger pump, which comprises a plunger pump body, a first pressure sensor, a second pressure sensor, a liquid level sensor and an intelligent detection module, wherein the first pressure sensor is fixedly connected with the plunger pump body and can be used for detecting a first pressure time domain signal generated by leaked oil in a friction pair; the second pressure sensor is fixedly connected with the oil outlet flange of the plunger pump body and can be used for detecting a second pressure time domain signal of the oil return pipeline; the liquid level sensor can be fixedly arranged at the bottom of the intelligent plunger pump and can be used for detecting a liquid level signal of oil in the cavity;
the first pressure sensor, the second pressure sensor and the liquid level sensor are respectively and electrically connected with the intelligent detection module.
The invention avoids the external oil pipe oil tank and the electronic valve, and also changes the potential safety hazard caused by the direct embedding of the sensor. The sensor and other components are integrated with the plunger pump housing, internal leakage and external leakage are monitored simultaneously, accuracy and safety of monitoring the pressure in the cavity of the plunger pump housing and the liquid level in the edge groove of the plunger pump housing are improved, and the complexity of the plunger pump structure is greatly reduced.
The invention also provides a real-time monitoring method for the internal and external leakage of the intelligent plunger pump, which comprises the following steps,
step S1, collecting first pressure time domain signals of a normal state and an internal leakage state of a plunger pump through the first pressure sensor, inputting the first pressure time domain signals to an intelligent detection module through an analog input interface, and converting the first pressure time domain signals into first digital signals through an A/D converter;
s2, acquiring a second pressure time domain signal of an oil return pipeline through the second pressure sensor, wherein the second pressure time domain signal is input to an intelligent detection module through an analog input interface, and is converted into a second digital signal through an A/D converter;
s3, acquiring a liquid level signal of oil in the cavity channel through the liquid level sensor, inputting the liquid level signal to the intelligent detection module through the analog input interface, and converting the liquid level signal into a third digital signal through the A/D converter;
s4, collecting a rotating speed value in the working condition of the plunger pump, inputting the rotating speed value into the intelligent detection module, and forming a mapping relation between the working condition and the rotating speed value;
step S5, respectively subtracting the mean values of the first digital signal, the second digital signal and the third digital signal, and performing Fourier transformation to form digital data in a frequency domain;
and S6, inputting the digital data in the frequency domain and the working condition data corresponding to different rotation speed values into the trained neural network model, and identifying and outputting the internal leakage and external leakage identification data under the corresponding working conditions.
Preferably, the first pressure time domain signal, the second pressure time domain signal and the liquid level signal are respectively transmitted to the intelligent detection module through CAN communication.
Preferably, the neural network model comprises a convolutional neural network model.
Preferably, the neural network model is obtained through supervised learning training of historical data of internal leakage and external leakage of the plunger pump under different working conditions.
The invention also discloses a system for executing the method for monitoring the internal and external leakage in real time, which comprises,
the first acquisition module is used for acquiring first pressure time domain signals of a normal state and an internal leakage state of the plunger pump through the first pressure sensor, wherein the first pressure time domain signals are input to the intelligent detection module through an analog input interface, and the first pressure time domain signals are converted into first digital signals through an A/D converter;
the second acquisition module is used for acquiring a second pressure time domain signal of the oil return pipeline through the second pressure sensor, wherein the second pressure time domain signal is input to the intelligent detection module through an analog input interface and is converted into a second digital signal through an A/D converter;
the third acquisition module is used for acquiring a liquid level signal of the oil in the cavity channel through the liquid level sensor, inputting the liquid level signal into the intelligent detection module through the analog input interface, and converting the liquid level signal into a third digital signal through the A/D converter;
the fourth acquisition module is used for acquiring a rotating speed value in the working condition of the plunger pump and inputting the rotating speed value into the intelligent detection module to form a mapping relation between the working condition and the rotating speed value;
the data processing module is used for respectively subtracting the mean values of the first digital signal, the second digital signal and the third digital signal and performing Fourier transformation to form digital data in a frequency domain;
the fault recognition module is used for inputting the digital data in the frequency domain and the working condition data corresponding to different rotating speed values into the trained neural network model, and recognizing and outputting the internal leakage and external leakage recognition data under the corresponding working conditions.
Preferably, the system further comprises a training module, wherein the training module is used for supervised learning of the neural network model by inputting historical data of internal leakage and external leakage occurring under different working conditions.
Preferably, the data processing module further comprises a data preprocessing module, and the data preprocessing module is used for inputting the normalized digital data in the frequency domain into the trained neural network model.
The invention also provides electronic equipment, at least one processor; and a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.
The present invention also provides a machine-readable storage medium having stored thereon instructions for causing a machine to perform a method as described above.
Compared with the prior art, the intelligent plunger pump provided by the invention has the advantages that the first pressure sensor is fixedly connected to the plunger pump body, so that the first pressure time domain signal generated by oil leakage in the friction pair is obtained in real time. And an oil outlet flange of the plunger pump body is fixedly connected with a second pressure sensor and is used for detecting a second pressure time domain signal of the oil return pipeline in real time. The liquid level signal of the oil in the cavity is detected through a liquid level sensor fixedly arranged at the bottom of the intelligent plunger pump. The invention discloses a real-time monitoring method for internal and external leakage, which is characterized in that under different working conditions, a first pressure time domain signal, a second pressure time domain signal and a liquid level signal are respectively acquired, are input into an intelligent detection module through an analog input interface, are converted into digital signals through an A/D converter, respectively subtract the mean value of the digital signals and perform Fourier transformation to form digital data in a frequency domain, and the working condition data corresponding to different rotating speed values are input into a trained neural network model, so that internal leakage fault identification data and external leakage fault identification data are obtained and output. The invention also discloses a system for executing the internal and external leakage real-time monitoring method. Through neural network model and data preprocessing mode, realize extracting the multisource state characteristic of hydraulic plunger pump, it is high to interior leakage fault identification rate of accuracy to make equipment obtain real-time supervision, intelligent monitoring, promote equipment operating efficiency and maintenance work efficiency by a wide margin.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, illustrate and explain the invention and are not to be construed as limiting the invention. In the drawings:
FIG. 1 is a schematic diagram of the positions of a first pressure sensor and a second pressure sensor in an intelligent plunger pump according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the location of the liquid level sensor and the intelligent detection module in the intelligent plunger pump according to an embodiment of the present invention;
FIG. 3 is a cross-sectional view of a channel and seal arrangement in an intelligent plunger pump according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of the placement of the channels and level sensors in an intelligent plunger pump according to one embodiment of the present invention;
FIG. 5 is a graph of convergence results of neural network model training according to one embodiment of the present invention;
FIG. 6 is a graph of accuracy of neural network model predictive failure in accordance with one embodiment of the invention.
Reference numerals illustrate:
1 first pressure sensor 2 second pressure sensor
3 liquid level sensor 4 intelligent detection module
5 channel 6 sealing ring
7-cavity channel
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," "third," and the like in the description and the claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, a certain amount of leakage usually occurs in a plunger pump working under a high-speed high-pressure working condition for a long time, wherein the internal leakage can flow back into an oil tank in a shell and can cause the rising of the pressure in the shell, so that the internal leakage monitoring requires the pressure in the inner cavity of the shell to be lower than a certain threshold value; the leakage can cause the oil to overflow and break the seal to cause faults, so that the leakage monitoring requires that the edge of the shell does not allow oil to overflow, and the existing method can not monitor the inner leakage and the outer leakage simultaneously. The plunger pump can influence the embedded sensor on the surfaces of the swash plate and the cylinder body when running at high speed and high pressure for a long time, so that the sensor monitoring precision is insufficient, and when the lubrication abrasion failure of the sliding shoe pair is serious, the leakage quantity is increased, and even the embedded sensor can be damaged, so that the whole control monitoring system cannot guarantee stable running for a long time. The monitoring device is simple, efficient and accurate in selection, and the technical problems that the real-time performance and the efficiency of the composite multi-sensor are low when the monitoring device is externally connected with a pipeline oil tank and is installed, and the pressure change can not be monitored in real time can be solved. As shown in fig. 1-4, the invention provides an intelligent plunger pump, which comprises a plunger pump body, a first pressure sensor 1, a second pressure sensor 2, a liquid level sensor 3 and an intelligent detection module 4, wherein the first pressure sensor 1 is fixedly connected with the plunger pump body and can be used for detecting a first pressure time domain signal generated by leaked oil in a friction pair; the second pressure sensor 2 is fixedly connected with the oil outlet flange of the plunger pump body and can be used for detecting a second pressure time domain signal of the oil return pipeline; the liquid level sensor 3 can be fixedly arranged at the bottom of the intelligent plunger pump and can be used for detecting a liquid level signal of oil in the cavity 7;
the first pressure sensor 1, the second pressure sensor 2 and the liquid level sensor 3 are respectively and electrically connected with the intelligent detection module 4.
In the technical scheme of the invention, as shown in fig. 1-4, a first pressure sensor 1, a second pressure sensor 2 and a liquid level sensor 3 are fixedly connected with an intelligent plunger pump through threads. In order to detect whether the oil is not tightly sealed by the sealing ring 6, such as damage or aging of the sealing ring 6. The outside leakage appears in the fluid in the intelligent plunger pump, and processing out channel 5 in the outside that sealing washer 6 kept away from intelligent plunger pump cavity, channel 5 is used for gathering the hydraulic oil that leaks outward and leading-in cavity 7 in, and cavity 7 sets up in intelligent plunger pump bottom, with channel 5 intercommunication. When the hydraulic oil leaks outwards and is collected to the cavity 7 under the action of vibration and gravity, the liquid level sensor 3 detects the oil, and a signal is generated and sent to the intelligent detection module 4.
The plunger pump drives the cylinder body and the plunger in the plunger cavity to rotate through the rotation of the main shaft, and the plunger generates axial displacement when rotating due to the action of the inclined angle of the inclined plate, so that the volume of the plunger cavity can be changed by compression and expansion when the cylinder body rotates, and the compression and expansion of the volume of the plunger cavity alternately realize the pumping and oil discharge of the plunger pump. The plunger pump leaks in the working process, the oil leaked from the inside flows back to the oil tank through the oil return pipeline, and the first pressure sensor 1 detects pressure change generated by the oil leaked from the friction pair. The second pressure sensor 2 detects the pressure near the oil outlet, i.e. the pressure change of the return line. The leaked oil flows into a cavity 7 below the plunger pump through a channel 5, and the liquid level sensor 3 generates a feedback signal to the intelligent detection module 4 when encountering the oil.
The invention avoids the external oil pipe oil tank and the electronic valve, and also changes the potential safety hazard caused by the direct embedding of the sensor. The sensor and other components are integrated with the plunger pump housing, internal leakage and external leakage are monitored simultaneously, accuracy and safety of monitoring the pressure in the cavity of the plunger pump housing and the liquid level in the edge groove of the plunger pump housing are improved, and the complexity of the plunger pump structure is greatly reduced.
The invention also provides a real-time monitoring method for the internal and external leakage of the intelligent plunger pump,
step S1, collecting first pressure time domain signals of a normal state and an internal leakage state of a plunger pump through the first pressure sensor 1, inputting the first pressure time domain signals into the intelligent detection module 4 through an analog input interface, and converting the first pressure time domain signals into first digital signals through an A/D converter;
step S2, a second pressure time domain signal of an oil return pipeline is acquired through the second pressure sensor 2, the second pressure time domain signal is input to the intelligent detection module 4 through an analog input interface, and the second pressure time domain signal is converted into a second digital signal through an A/D converter;
step S3, liquid level signals in the external leakage state are collected through the liquid level sensor 3 and are input into the intelligent detection module 4 through an analog input interface, and the liquid level signals are converted into third digital signals through an A/D converter;
s4, collecting a rotating speed value in the working condition of the plunger pump, inputting the rotating speed value into the intelligent detection module 4, and forming a mapping relation between the working condition and the rotating speed value;
step S5, respectively subtracting the mean values of the first digital signal, the second digital signal and the third digital signal, and performing Fourier transformation to form digital data in a frequency domain; wherein the average value of the third digital signal is 0.
And S6, inputting the digital data in the frequency domain and the working condition data corresponding to different rotation speed values into the trained neural network model, and identifying and outputting the internal leakage and external leakage identification data under the corresponding working conditions.
The first pressure sensor 1 is selected and used, a positive side of the plunger pump housing is installed, pressure time domain signals reflecting the normal state and the internal leakage state of the plunger pump are collected, the time domain signals are input into the intelligent detection module through the analog input interface, and the analog signals are converted into digital signals through the A/D converter to be used as original data for diagnosing internal leakage. The liquid level sensor 3 is selected and installed near the joint sealing ring 6, signals reflecting whether the plunger pump is in an external leakage state or not are collected, and the signals are input into the intelligent detection module 4 through the CAN communication interface and used as original data for diagnosing the external leakage. The second pressure sensor 2 is arranged on an oil return pipeline, acquires pressure signals reflecting the working condition of the plunger pump, and inputs the signals into the intelligent detection module 4 through an analog input interface and converts the signals into digital signals through an A/D converter. The working condition rotating speed of the plunger pump is input into the intelligent detection module 4 through a digital IO interface.
The acquired signals are input into the processor through the A/D converter, and the amplitude of the pressure signal of the first pressure sensor 1 is acquired through fast Fourier transform in the central processor, so that implicit characteristic information is highlighted. To mitigate errors, the time domain signal is subtracted in advance by a fast fourier transform. And performing fast Fourier transform on the preprocessed pressure signals in the central processing unit, processing the input amplitude data, and inputting the processed amplitude data into a convolutional neural network model which has been learned according to the corresponding working conditions to perform comparison and identification results.
The internal and external leakage identification results are input into a display screen through a display screen interface, and the display screen displays the current working conditions and the internal leakage and external leakage identification results calculated through formulas.
The invention discloses a real-time monitoring method for internal and external leakage, which is characterized in that under different working conditions, a first pressure time domain signal, a second pressure time domain signal and a liquid level signal are respectively acquired, are input into an intelligent detection module through an analog input interface, are converted into digital signals through an A/D converter, respectively subtract the mean value of the digital signals and perform Fourier transformation to form digital data in a frequency domain, and the working condition data corresponding to different rotating speed values are input into a trained neural network model, so that internal leakage fault identification data and external leakage fault identification data are obtained and output. Through neural network model and data preprocessing mode, realize extracting the multisource state characteristic of hydraulic plunger pump, it is high to interior leakage fault identification rate of accuracy to make equipment obtain real-time supervision, intelligent monitoring, promote equipment operating efficiency and maintenance work efficiency by a wide margin.
In order to improve the anti-interference performance in the signal transmission process and reduce the interference of the outside on the signal, in the preferred case of the present invention, the first pressure time domain signal, the second pressure time domain signal and the liquid level signal are respectively transmitted to the intelligent detection module 4 through CAN communication. More preferably, the first pressure time domain signal, the second pressure time domain signal, and the liquid level signal may be edge calculated on the sensor side, and the data signal may be obtained and transmitted, so as to further reduce the data transmission amount of the signal.
In order to better identify and predict faults, the nonlinear correlation relationship among the collected first pressure time domain signal, the second pressure time domain signal, the liquid level signal and the faults of the plunger pump is better reflected, and in the preferred case of the invention, the neural network model comprises a convolutional neural network model. The convolutional neural network model comprises an input layer, a convolutional layer A, a maximum pooling layer A, a convolutional layer B, a convolutional layer C, a convolutional layer D, a maximum pooling layer B, a convolutional layer E, a convolutional layer F, a maximum pooling layer C, a full connection layer A, a full connection layer B and a classification layer. The pressure amplitude data obtained after the signal preprocessing is input from an input layer; and carrying out feature extraction on the input samples through the parts of the convolution layer A, the pooling layer A, the convolution layer B, the convolution layer C, the convolution layer D, the maximum pooling layer B, the convolution layer E, the convolution layer F and the pooling layer C. And the full connection layer A, the full connection layer B and the classification layer finish the identification of the internal leakage and external leakage faults.
In order to identify the fault results of internal leakage and external leakage under different working conditions, under the preferred condition of the invention, the neural network model is obtained by performing supervised learning training on historical data of the internal leakage and the external leakage of the plunger pump working under different working conditions. For example, rated rotation speeds are 2500r/min, 5000r/min and 7000r/min respectively, rated pressures are 3MPa and 9MPa, 2 pressure sensors are selected and respectively arranged on the positive side of the plunger pump housing and an oil return pipeline, and pressure time domain signals of 10 typical states of the plunger pump under different working conditions are collected through a first pressure sensor 1 arranged on the positive side of the plunger pump housing and are used as original state data for analysis, and the sampling frequency is 10kHz. The 10 typical states respectively comprise normal states of 2500r/min-3MPa, 2500r/min-9MPa, 5000r/min-3MPa, 5000r/min-9MPa and 7000r/min-3MPa of working conditions, and inner leakage state data and outer leakage state data corresponding to the working conditions. The liquid level sensor 3 at the joint is installed to collect the liquid level signal. And the working condition information of the plunger pump is acquired through a second pressure sensor 2 arranged on the oil return pipeline and a rotating speed signal output by the plunger pump.
The invention also discloses a system for executing the method for monitoring the internal and external leakage in real time, which comprises,
the first collecting module is used for collecting first pressure time domain signals of a normal state and an internal leakage state of the plunger pump through the first pressure sensor 1, wherein the first pressure time domain signals are input to the intelligent detecting module 4 through an analog input interface, and the first pressure time domain signals are converted into first digital signals through an A/D converter;
the second acquisition module is used for acquiring a second pressure time domain signal of the oil return pipeline through the second pressure sensor 2, wherein the second pressure time domain signal is input to the intelligent detection module 4 through an analog input interface, and is converted into a second digital signal through an A/D converter;
the third acquisition module is used for acquiring a liquid level signal in an external leakage state through the liquid level sensor 3, inputting the liquid level signal into the intelligent detection module 4 through an analog input interface, and converting the liquid level signal into a third digital signal through an A/D converter;
the fourth acquisition module is used for acquiring a rotating speed value in the working condition of the plunger pump and inputting the rotating speed value into the intelligent detection module 4 to form a mapping relation between the working condition and the rotating speed value;
the data processing module is used for respectively subtracting the mean values of the first digital signal, the second digital signal and the third digital signal and performing Fourier transformation to form digital data in a frequency domain;
the fault recognition module is used for inputting the digital data in the frequency domain and the working condition data corresponding to different rotating speed values into the trained neural network model, and recognizing and outputting the internal leakage and external leakage recognition data under the corresponding working conditions.
The invention discloses a system for executing the internal and external leakage real-time monitoring method, which is characterized in that under different working conditions, a first pressure time domain signal, a second pressure time domain signal and a liquid level signal are respectively acquired through a first acquisition module, a second acquisition module and a third acquisition module, are input into an intelligent detection module through an analog input interface, and are converted into digital signals through an A/D converter. And respectively subtracting the mean values from the digital signals of the data processing module, performing Fourier transform to form digital data in a frequency domain, and inputting the working condition data corresponding to different rotating speed values into the trained neural network model, so as to obtain and output the internal leakage and external leakage fault identification data. The fault recognition module is used for extracting the multi-source state characteristics of the hydraulic plunger pump through the neural network model and the data preprocessing mode, and is high in accuracy of identifying internal leakage and external leakage faults, so that the equipment can be monitored in real time and intelligently, and the running efficiency and the maintenance working efficiency of the equipment are greatly improved.
In order to better train the neural network model, so that the neural network model has higher recognition accuracy, as shown in fig. 5-6, in the preferred case of the present invention, the system further comprises a training module, wherein the training module is used for supervised learning of the neural network model by inputting history data of internal leakage and external leakage occurring under different working conditions. For example, after the accuracy of the neural network model after supervised learning reaches a certain threshold, the threshold may be preferably set to 98%, so as to output the neural network model. As shown in fig. 5, the process of performing supervised learning has fast convergence, high efficiency, and can output the neural network model more efficiently.
In order to better normalize the input signal, the neural network model is input in a standard format, and in the preferred case of the invention, the data processing module further comprises a data preprocessing module, which is used for normalizing the digital data in the frequency domain and inputting the normalized digital data into the trained neural network model. As shown in fig. 6, the prediction accuracy of the model is higher.
The invention also provides electronic equipment, at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.
The present invention also provides a machine-readable storage medium having stored thereon instructions for causing a machine to perform a method as described above.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present invention is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present invention. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a mobile terminal, a server or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-only memory (ROM), a random access memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The intelligent plunger pump is characterized by comprising a plunger pump body, a first pressure sensor (1), a second pressure sensor (2), a liquid level sensor (3) and an intelligent detection module (4), wherein the first pressure sensor (1) is fixedly connected with the plunger pump body and can be used for detecting a first pressure time domain signal generated by leaked oil in a friction pair; the second pressure sensor (2) is fixedly connected with the oil outlet flange of the plunger pump body and can be used for detecting a second pressure time domain signal of the oil return pipeline; the liquid level sensor (3) can be fixedly arranged at the bottom of the intelligent plunger pump and can be used for detecting a liquid level signal of oil in the cavity (7);
the first pressure sensor (1), the second pressure sensor (2) and the liquid level sensor (3) are respectively and electrically connected with the intelligent detection module (4).
2. A real-time monitoring method for internal and external leakage of an intelligent plunger pump according to claim 1, characterized in that,
step S1, collecting first pressure time domain signals of a normal state and an internal leakage state of a plunger pump through the first pressure sensor (1), inputting the first pressure time domain signals into an intelligent detection module (4) through an analog input interface, and converting the first pressure time domain signals into first digital signals through an A/D converter;
s2, acquiring a second pressure time domain signal of an oil return pipeline through the second pressure sensor (2), wherein the second pressure time domain signal is input to the intelligent detection module (4) through an analog input interface, and is converted into a second digital signal through an A/D converter;
s3, acquiring a liquid level signal of oil in the cavity (7) through the liquid level sensor (3), inputting the liquid level signal into the intelligent detection module (4) through an analog input interface, and converting the liquid level signal into a third digital signal through an A/D converter;
s4, collecting a rotating speed value in the working condition of the plunger pump, inputting the rotating speed value into an intelligent detection module (4), and forming a mapping relation between the working condition and the rotating speed value;
step S5, respectively subtracting the mean values of the first digital signal, the second digital signal and the third digital signal, and performing Fourier transformation to form digital data in a frequency domain;
and S6, inputting the digital data in the frequency domain and the working condition data corresponding to different rotation speed values into the trained neural network model, and identifying and outputting the internal leakage and external leakage identification data under the corresponding working conditions.
3. The method for monitoring internal and external leakage in real time according to claim 2, wherein the first pressure time domain signal, the second pressure time domain signal and the liquid level signal are respectively transmitted to the intelligent detection module (4) through CAN communication.
4. The method of real-time monitoring internal and external leakage according to claim 2, wherein the neural network model comprises a convolutional neural network model.
5. The method for monitoring internal and external leakage in real time according to claim 4, wherein the neural network model is obtained by performing supervised learning training on historical data of internal leakage and external leakage of the plunger pump under different working conditions.
6. A system for performing the method for monitoring internal and external leakage in real time according to any one of claims 2 to 5, characterized in that the system comprises,
the first acquisition module is used for acquiring first pressure time domain signals of a normal state and an internal leakage state of the plunger pump through the first pressure sensor (1), wherein the first pressure time domain signals are input to the intelligent detection module (4) through an analog input interface, and the first pressure time domain signals are converted into first digital signals through an A/D converter;
the second acquisition module is used for acquiring a second pressure time domain signal of the oil return pipeline through the second pressure sensor (2), wherein the second pressure time domain signal is input to the intelligent detection module (4) through an analog input interface and is converted into a second digital signal through an A/D converter;
the third acquisition module is used for inputting a liquid level signal of oil in a cavity (7) of the liquid level sensor (3) to the intelligent detection module (4) through an analog input interface and converting the liquid level signal into a third digital signal through an A/D converter;
the fourth acquisition module is used for acquiring a rotating speed value in the working condition of the plunger pump and inputting the rotating speed value into the intelligent detection module (4) to form a mapping relation between the working condition and the rotating speed value;
the data processing module is used for respectively subtracting the mean values of the first digital signal, the second digital signal and the third digital signal and performing Fourier transformation to form digital data in a frequency domain;
the fault recognition module is used for inputting the digital data in the frequency domain and the working condition data corresponding to different rotating speed values into the trained neural network model, and recognizing and outputting the internal leakage and external leakage recognition data under the corresponding working conditions.
7. The system of claim 6, further comprising a training module for supervised learning of the neural network model by inputting historical data of internal and external leaks occurring under different conditions.
8. The system according to claim 6 or 7, wherein the data processing module further comprises a data preprocessing module, configured to normalize the digital data in the frequency domain and input the normalized digital data to the trained neural network model.
9. An electronic device characterized by at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 2-5.
10. A machine-readable storage medium having stored thereon instructions for causing a machine to perform the method of any of claims 2-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311815262.9A CN117552972A (en) | 2023-12-26 | 2023-12-26 | Intelligent plunger pump and method and system for monitoring internal and external leakage in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311815262.9A CN117552972A (en) | 2023-12-26 | 2023-12-26 | Intelligent plunger pump and method and system for monitoring internal and external leakage in real time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117552972A true CN117552972A (en) | 2024-02-13 |
Family
ID=89811185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311815262.9A Pending CN117552972A (en) | 2023-12-26 | 2023-12-26 | Intelligent plunger pump and method and system for monitoring internal and external leakage in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117552972A (en) |
-
2023
- 2023-12-26 CN CN202311815262.9A patent/CN117552972A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11401927B2 (en) | Status monitoring and failure diagnosis system for plunger pump | |
| US11341836B2 (en) | Persistent monitoring and real time low latency local control of centrifugal hydraulic pump, remote monitoring and control, and collecting data to produce performance profiles | |
| Du et al. | Layered clustering multi-fault diagnosis for hydraulic piston pump | |
| CN106761681B (en) | Electric pump well fault real-time diagnosis system and method based on time sequence data analysis | |
| US20180087499A1 (en) | System for detecting faults in a pump | |
| CN111043023B (en) | Fracturing pump on-line monitoring and fault diagnosis system | |
| CN106949056B (en) | A kind of perception of pressure fan operating status and failure prediction system and method | |
| KR102206737B1 (en) | Method and system for fault diagnosis of pump-turbines based on machine learning | |
| CN114934898B (en) | Hydraulic pump fault diagnosis analysis system based on multi-mode parameters | |
| CN108956107A (en) | Couple the Fault tree diagnosis method of the reciprocating compressor typical fault of Triangular Fuzzy Number | |
| CA3130904A1 (en) | System and method for evaluating reciprocating downhole pump data using polar coordinate analytics | |
| CN113819045B (en) | Method and system for on-line monitoring vibration diagnosis of lubricating oil liquid of reciprocating compressor | |
| CN114861362A (en) | Pump health analysis method, device, equipment and medium based on knowledge graph | |
| CN112124229A (en) | Remote real-time fault diagnosis method for emergency pump truck | |
| CN114810572A (en) | Hydraulic pump fault diagnosis method and device | |
| CN117552972A (en) | Intelligent plunger pump and method and system for monitoring internal and external leakage in real time | |
| US10378537B2 (en) | System for detecting failure location in a pump | |
| CN109139443B (en) | piston rod fault diagnosis method based on displacement signals | |
| US20230296015A1 (en) | Advanced diagnostics and control system for artificial lift systems | |
| KR20240086258A (en) | System and method for detecting anomaly of motor by 2 step ai diagnosis | |
| CN115342101A (en) | Hydraulic system internal leakage detection method and system for hydraulic generator speed regulator | |
| CN114689248A (en) | Supercharger oil leakage detection equipment, method, device and medium | |
| KR102688082B1 (en) | An abnormal sensing system of pump equipment for three-phase motor electric power data and abnormal sensing method using the system | |
| CN112943639A (en) | Method for detecting cavitation failure of pump | |
| CN114326652B (en) | Marine water spray propeller fault diagnosis system |
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 |