CN112943595A - Hydraulic pump fault prediction method, hydraulic pump fault prediction device, electronic equipment and storage medium - Google Patents
Hydraulic pump fault prediction method, hydraulic pump fault prediction device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112943595A CN112943595A CN202110172016.0A CN202110172016A CN112943595A CN 112943595 A CN112943595 A CN 112943595A CN 202110172016 A CN202110172016 A CN 202110172016A CN 112943595 A CN112943595 A CN 112943595A
- Authority
- CN
- China
- Prior art keywords
- hydraulic pump
- fault prediction
- fault
- sound
- prediction model
- 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
Images
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)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a hydraulic pump fault prediction method, a hydraulic pump fault prediction device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring sound information of a hydraulic pump; inputting the sound information into a fault prediction model to obtain a fault prediction result output by the fault prediction model; the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump. The method, the device, the electronic equipment and the storage medium provided by the invention enable engineering technicians to know the use state of the hydraulic pump and the type of possible faults in advance, reasonably arrange the working period of the hydraulic pump, facilitate the timely overhaul and maintenance of the hydraulic pump and prolong the service life of the hydraulic pump.
Description
Technical Field
The invention relates to the technical field of mechanical engineering, in particular to a hydraulic pump fault prediction method and device, electronic equipment and a storage medium.
Background
The hydraulic pump is a power element of a hydraulic system, and is an element which is driven by an engine or an electric motor, sucks oil from a hydraulic oil tank, forms pressure oil, discharges the pressure oil and sends the pressure oil to an execution element.
In the prior art, temperature, pressure or vibration signals are usually adopted to detect faults of the hydraulic pump, and the signals represent state parameters after the hydraulic pump has faults, can only be used for subsequent maintenance and cannot realize early warning in advance, so that favorable opportunity for fault removal is missed.
Disclosure of Invention
The invention provides a hydraulic pump fault prediction method, a hydraulic pump fault prediction device, electronic equipment and a storage medium, which are used for solving the technical problems that the existing fault detection method can only be used for after-the-fact maintenance and can not realize early warning in advance.
The invention provides a hydraulic pump fault prediction method, which comprises the following steps:
acquiring sound information of a hydraulic pump;
inputting the sound information into a fault prediction model to obtain a fault prediction result output by the fault prediction model;
the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump.
According to the method for predicting the fault of the hydraulic pump provided by the invention, the step of acquiring the sound information of the hydraulic pump comprises the following steps:
collecting an original sound signal when a hydraulic pump runs;
and performing time domain analysis and/or frequency domain analysis on the original sound signal to obtain the sound information.
According to the method for predicting the fault of the hydraulic pump, the original sound signal when the hydraulic pump runs is collected, and then the method comprises the following steps:
pre-emphasis, framing and windowing the original sound signal.
According to the method for predicting the fault of the hydraulic pump provided by the invention, the time domain analysis is carried out on the original sound signal to obtain the sound information, and the method comprises the following steps:
determining sound time domain information of the original sound signal in each time interval based on a preset time interval;
the sound information is determined based on sound time domain information for each time interval.
According to the method for predicting the fault of the hydraulic pump provided by the invention, the frequency domain analysis is carried out on the original sound signal to obtain the sound information, and the method comprises the following steps:
determining sound frequency domain information of the original sound signal;
dividing the sound frequency domain information into a plurality of frequency sections, and respectively determining the energy of each frequency section;
the sound information is determined based on the energy of each frequency bin.
According to the method for predicting the fault of the hydraulic pump, provided by the invention, the sound information is input into a fault prediction model to obtain a fault prediction result output by the fault prediction model, and the method comprises the following steps:
inputting sound information of a plurality of continuous periods into a fault prediction model to obtain a plurality of fault prediction results output by the fault prediction model;
and if the plurality of fault prediction results are consistent, determining that the plurality of fault prediction results are valid.
According to the hydraulic pump fault prediction method provided by the invention, the fault prediction models correspond to the types of the hydraulic pumps one by one.
The present invention also provides a hydraulic pump failure prediction device, including:
an acquisition unit for acquiring sound information of the hydraulic pump;
the prediction unit is used for inputting the sound information into a fault prediction model to obtain a fault prediction result output by the fault prediction model;
the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the hydraulic pump failure prediction method as described in any one of the above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the hydraulic pump failure prediction method as described in any one of the above.
According to the hydraulic pump fault prediction method, the hydraulic pump fault prediction device, the electronic equipment and the storage medium, the fault prediction model is obtained through training according to the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump, and the fault prediction model can predict according to the sound information of the hydraulic pump to obtain the fault prediction result, so that engineering technicians can know the use state of the hydraulic pump and the type of possible fault in advance, the working period of the hydraulic pump is reasonably arranged, the hydraulic pump is convenient to overhaul and maintain in time, and the service life of the hydraulic pump is prolonged.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a hydraulic pump failure prediction method provided by the present invention;
FIG. 2 is a schematic flow chart illustrating a method for predicting a fault of a hydraulic pump of an excavator according to the present invention;
FIG. 3 is a schematic structural diagram of a hydraulic pump failure prediction device provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. 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 hydraulic pump is a power element of a hydraulic system, and is an element which is driven by an engine or an electric motor, sucks oil from a hydraulic oil tank, forms pressure oil, discharges the pressure oil and sends the pressure oil to an execution element. The hydraulic pump is divided into a gear pump, a plunger pump, a vane pump and a screw pump according to the structure. For work machines, hydraulic pumps are an important source of power. Its function is to convert the mechanical energy of power machine into the pressure energy of liquid. There are many factors that affect the service life of a hydraulic pump, including the operating state of the work machine, in addition to the design and manufacture of the pump itself.
In the operation process, common faults of the hydraulic pump include oil pipe blockage, overlarge noise, hydraulic oil leakage, heating of the hydraulic pump and the like.
The hydraulic system of the excavator is a combination body which organically connects various hydraulic components by pipelines according to the transmission requirements of the excavator working device and various mechanisms. The hydraulic control system mainly comprises a hydraulic oil tank, a hydraulic pump, a multi-way valve, pipelines, oil cylinders for executing various actions, a motor and other components. The hydraulic excavator has the functions that oil is used as a working medium, the mechanical energy of an engine is converted into hydraulic energy by using a hydraulic pump and is transmitted, and then the hydraulic energy is converted back into the mechanical energy by using a hydraulic cylinder, a hydraulic motor and the like, so that various actions of the excavator are realized. Therefore, the hydraulic pump is a core device of the excavator. The embodiment of the invention takes an excavator hydraulic pump as an example to explain a hydraulic pump fault prediction method.
Fig. 1 is a schematic flow chart of a hydraulic pump failure prediction method provided by the present invention, as shown in fig. 1, the method includes:
Specifically, for the detection of the hydraulic pump, a vibration sensor, a temperature sensor, a pressure sensor and the like are usually installed on the hydraulic pump to perform fault diagnosis on the hydraulic pump, and these signals are usually abnormal after the occurrence of a fault, so that fault prediction cannot be performed in advance, and a potential or sudden abnormal fault cannot be processed, which results in unnecessary disassembly and installation of the hydraulic pump, and causes excessive equipment maintenance cost and additional break-in loss.
The sound information of the hydraulic pump can be acquired in the running process of the excavator to predict and monitor the fault of the hydraulic pump.
The sound information may be the frequency, loudness, energy and other characteristics of the sound, and may also be divided into sound time domain information and sound frequency domain information. And acquiring sound time domain information and/or sound frequency domain information after sound signals are acquired and processed.
Specifically, the failure prediction result refers to the type of failure that the hydraulic pump may have, such as oil inlet pipe blockage, oil outlet pipe blockage, oil leakage, insufficient oil quantity, too low oil pressure, gear friction, and the like. Generally, the characteristics of the sound information corresponding to each fault type are completely different. For example, when gear friction occurs in a hydraulic pump, the loudness of the collected sound information may increase significantly.
The sound information can be input into the fault prediction model, and the fault type of the hydraulic pump can be predicted to obtain a fault prediction result. The fault prediction result is used for indicating the type of the possible fault of the hydraulic pump, and can provide reference for the maintenance of the hydraulic pump.
The fault prediction model can be obtained by pre-training, and specifically can be obtained by the following training modes: first, sound information of a large number of sample hydraulic pumps is collected. And secondly, detecting the use state of each sample hydraulic pump in a manual mode, and determining the fault detection result of each sample hydraulic pump. The fault detection result is a real fault type obtained by detecting the hydraulic pump. And then, training the initial model according to the sound information of a large number of sample hydraulic pumps and the fault detection result of each sample hydraulic pump so as to improve the prediction capability of the initial model on the fault type of the hydraulic pump and obtain a fault prediction model.
The initial model may be selected from a Convolutional Neural Network (CNN), a full Convolutional Neural Network (FCN), a cyclic Neural Network (RNN), and the like, and the selection of the initial model is not specifically limited in the embodiment of the present invention.
The method can also adopt a statistical method to count the sound information of a large number of sample hydraulic pumps and the fault detection result of each sample hydraulic pump to obtain a fault prediction model, wherein the statistical method comprises a perception machine, a k-nearest neighbor method, a naive Bayes method, a decision tree, a support vector machine and the like.
And a fault prediction model can be obtained by adopting a model fusion method. The method can be used for classifying the sample hydraulic pumps according to the fault detection results of the sample hydraulic pumps, classifying the sample hydraulic pumps with the same fault detection results into the same class, and training the initial model to obtain the fault prediction submodel corresponding to the fault detection results. According to the method, the fault prediction submodels corresponding to a plurality of fault detection results can be trained. And then fusing the plurality of failure prediction submodels to obtain a failure prediction model.
The model fusion is to train a plurality of models, and fuse the plurality of models into one model according to a certain method. The model fusion method comprises a linear weighted fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method, a prediction fusion method and the like.
The fused fault prediction model can fully utilize the advantages of each fault prediction submodel, improve the analysis capability of the fault prediction model on the sound information of different fault types, and improve the overall performance and the applicability of the fault prediction model.
According to the hydraulic pump fault prediction method provided by the embodiment of the invention, the fault prediction model is obtained by training according to the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump, and the fault prediction model can predict according to the sound information of the hydraulic pump to obtain the fault prediction result, so that engineering technicians can know the use state of the hydraulic pump and the type of the fault which possibly occurs in advance, the operation period of the hydraulic pump is reasonably arranged, the hydraulic pump can be overhauled and maintained in time, and the service life of the hydraulic pump is prolonged.
Based on the above embodiment, step 110 includes:
collecting an original sound signal when a hydraulic pump runs;
and carrying out time domain analysis and/or frequency domain analysis on the original sound signal to obtain sound information.
Specifically, the raw sound signal of the hydraulic pump when running can be collected by the sound sensor. The sound sensor may be at least one of a piezo ceramic type sound sensor, a capacitive type sound sensor, and a moving coil type sound sensor.
The sound sensor is arranged in the cabin of the hydraulic pump, and particularly can be arranged near an oil inlet of the hydraulic pump, can also be arranged near an oil outlet of the hydraulic pump, and can also be arranged near a transmission shaft of the hydraulic pump.
And carrying out time domain analysis and/or frequency domain analysis on the original sound signal to obtain sound information. For example, the time domain analysis may be performed on the original sound signal acquired within a preset time to obtain sound time domain information. The continuous signal length of the sound time domain information may be determined according to a preset time. The preset time may be set to 1 minute or 1 hour, etc. For another example, the original audio signal may be subjected to frequency domain transformation to obtain audio frequency domain information. The sound frequency domain information is analyzed, each frequency point of sound can be obtained, the frequency distribution of each frequency point is compared with the frequency spectrum of the hydraulic pump in normal operation, the abnormal frequency point of the hydraulic pump in the current working state can be determined, and therefore fault diagnosis and early warning are conducted on the hydraulic pump.
Based on any embodiment, the method for acquiring the original sound signal when the hydraulic pump operates comprises the following steps:
the original sound signal is pre-emphasized, framed and windowed.
Specifically, pre-emphasis refers to passing the original sound signal through a high-pass filter to emphasize the high frequency part of the original sound signal, thereby enhancing the high frequency resolution of the original sound signal. Framing refers to sampling a sound signal, and collecting a plurality of sampling points to form a frame signal. Windowing introduces each frame signal into the window function to eliminate possible signal discontinuities at the two ends of each frame, resulting in a signal with short-term stationarity.
According to the hydraulic pump fault prediction method provided by the embodiment of the invention, the original sound signal is preprocessed by pre-emphasis, framing and windowing, so that the original sound signal can be compressed, the representative characteristics of the original sound signal are extracted for fault prediction, the data volume processed by a fault prediction model is reduced, and the fault prediction efficiency is improved.
Based on any of the above embodiments, performing time domain analysis on an original sound signal to obtain sound information includes:
determining sound time domain information of the original sound signal in each time interval based on a preset time interval;
based on the sound time domain information for each time interval, sound information is determined.
Specifically, time domain analysis is performed on the original sound signal, a preset time interval can be set, and the collected original sound signal is divided to obtain sound time domain information of a plurality of time intervals. And analyzing the sound time domain information of each time interval to determine the pitch, amplitude and other data of the sound.
For example, the pitch of a sound is frequency dependent, with higher frequencies and higher pitches representing denser waveforms in the same time interval; the lower the frequency, the lower the pitch, and the more sparse the waveform appears to be in the same time interval. The loudness of sound is related to amplitude, the greater the loudness; the smaller the amplitude and the smaller the loudness, the amplitude can be derived from the sound time domain information.
Based on any of the above embodiments, performing frequency domain analysis on the original sound signal to obtain sound information includes:
determining sound frequency domain information of an original sound signal;
dividing the sound frequency domain information into a plurality of frequency sections, and respectively determining the energy of each frequency section;
based on the energy of each frequency bin, sound information is determined.
In particular, fourier transform transforms represent a certain function that satisfies a certain condition as a trigonometric function (sine and/or cosine function) or a linear combination of their integrals. In different fields of research, fourier transforms have many different variant forms, such as continuous fourier transforms and discrete fourier transforms.
Fast Fourier Transform (FFT) is a general name for an efficient and fast calculation method for calculating Discrete Fourier Transform (DFT) using a computer, and is abbreviated as FFT. The multiplication times required by a computer for calculating the discrete Fourier transform can be greatly reduced by adopting the algorithm, and particularly, the more the number of the converted sampling points is, the more remarkable the calculation amount of the FFT algorithm is saved. The time-frequency conversion can be performed on the original sound signal by adopting fast Fourier transform to obtain the sound frequency domain information of the original sound signal.
The sound frequency domain information may be divided into a plurality of frequency bins, and the energy of each frequency bin may be calculated separately. The energy may be expressed as the sum of the squared amplitudes of the respective frequencies of the sound signal in the frequency bin. After the energy of each frequency range is obtained, the energy sum and the energy distribution rule of the sound can be obtained.
Based on any of the above embodiments, step 120 includes:
inputting sound information of a plurality of continuous periods into a fault prediction model to obtain a plurality of fault prediction results output by the fault prediction model;
and if the multiple fault prediction results are consistent, determining that the multiple fault prediction results are effective.
Specifically, to prevent false alarm of fault information, collecting sound information of multiple periods may be linked. The period can be set according to actual conditions.
And inputting sound information of a plurality of continuous periods into the fault prediction model to obtain a plurality of fault prediction results output by the fault prediction model. And comparing the multiple fault prediction results, and if the comparison results are consistent and are of the same fault type, considering that the multiple fault prediction results are effective and sending a fault alarm signal. And if the comparison result shows that the results are inconsistent, the multiple fault prediction results are considered to be invalid, and a fault alarm signal is not sent out.
Based on any of the above embodiments, the failure prediction model corresponds to the type of the hydraulic pump one to one.
Specifically, the hydraulic pump can be divided into: variable displacement pumps and fixed displacement pumps. The output flow can be adjusted according to the requirements and is called variable pump, and the flow which can not be adjusted is called fixed pump. The hydraulic pump is divided into: gear pumps, vane pumps, plunger pumps, and the like. The gear pump has small volume, simple structure and low requirement on the cleanliness of oil; however, the pump shaft is subjected to unbalanced force, the abrasion is serious, and the leakage is large. Vane pumps are classified into double-acting vane pumps and single-acting vane pumps. The pump has the advantages of uniform flow, stable operation, low noise, higher working pressure and volume efficiency than a gear pump and more complex structure than the gear pump. The plunger pump has high volumetric efficiency and small leakage, can work under high pressure and is mostly used for a high-power hydraulic system; but the structure is complex, the requirements on material and processing precision are high, the price is high, and the requirement on the cleanliness of oil is high.
Therefore, when the fault prediction model of the hydraulic pump is established, the fault prediction model can be in one-to-one correspondence with the type of the hydraulic pump, the fault prediction model is trained by using sample data of the same type as the hydraulic pump, and the accuracy of the fault prediction model can be improved.
Based on the above embodiment, fig. 2 is a schematic flow chart of the method for predicting the fault of the hydraulic pump of the excavator, as shown in fig. 2, the method includes:
collecting an original sound signal of a hydraulic pump of an excavator;
selecting a certain length of an original sound signal of the hydraulic pump of the excavator to perform fast Fourier transform to obtain sound information;
inputting the sound information into a model, and performing fault prediction to obtain a fault prediction result, wherein the model is determined according to the sound information and the fault detection results of a large number of sample excavator hydraulic pumps;
inputting sound information of a plurality of continuous periods into the model to obtain a plurality of fault prediction results output by the model, and if the fault prediction results are consistent, determining that the fault prediction results are effective and sending out a fault early warning signal of the hydraulic pump of the excavator;
and fifthly, judging the fault prediction result by combining the actual situation, and performing parameter optimization on the model according to the judgment result.
According to the method for predicting the fault of the hydraulic pump of the excavator, the state of the hydraulic pump is evaluated through the sound information of the hydraulic pump of the excavator, and then fault early warning is carried out.
Based on any of the above embodiments, fig. 3 is a schematic structural diagram of a hydraulic pump failure prediction apparatus provided by the present invention, as shown in fig. 3, the apparatus includes:
an acquisition unit 310 for acquiring sound information of the hydraulic pump;
the prediction unit 320 is configured to input the sound information to the fault prediction model to obtain a fault prediction result output by the fault prediction model;
the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump.
Specifically, the acquisition unit 310 is used to acquire sound information of the hydraulic pump. The prediction unit 320 is configured to input the sound information to the fault prediction model, and obtain a fault prediction result output by the fault prediction model.
According to the hydraulic pump fault prediction method provided by the embodiment of the invention, the fault prediction model is obtained by training according to the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump, and the fault prediction model can predict according to the sound information of the hydraulic pump to obtain the fault prediction result, so that engineering technicians can know the use state of the hydraulic pump and the type of the fault which possibly occurs in advance, the operation period of the hydraulic pump is reasonably arranged, the hydraulic pump can be overhauled and maintained in time, and the service life of the hydraulic pump is prolonged.
Based on any of the above embodiments, the obtaining unit 310 includes:
the acquisition subunit is used for acquiring an original sound signal when the hydraulic pump operates;
and the analysis subunit is used for carrying out time domain analysis and/or frequency domain analysis on the original sound signal to obtain sound information.
Based on any of the above embodiments, the obtaining unit 310 further includes:
and the preprocessing subunit is used for performing pre-emphasis, framing and windowing on the original sound signal.
Based on any of the above embodiments, the analysis subunit includes a time domain analysis module, and the time domain analysis module is specifically configured to:
determining sound time domain information of the original sound signal in each time interval based on a preset time interval;
based on the sound time domain information for each time interval, sound information is determined.
Based on any of the above embodiments, the analysis subunit includes a frequency domain analysis module, and the frequency domain analysis module is specifically configured to:
determining sound frequency domain information of an original sound signal;
dividing the sound frequency domain information into a plurality of frequency sections, and respectively determining the energy of each frequency section;
based on the energy of each frequency bin, sound information is determined.
Based on any of the above embodiments, the prediction unit 320 is specifically configured to:
inputting sound information of a plurality of continuous periods into a fault prediction model to obtain a plurality of fault prediction results output by the fault prediction model;
and if the multiple fault prediction results are consistent, determining that the multiple fault prediction results are effective.
Based on any of the above embodiments, the failure prediction model corresponds to the type of the hydraulic pump one to one.
Based on any of the above embodiments, fig. 4 is a schematic structural diagram of an electronic device provided by the present invention, and as shown in fig. 4, the electronic device may include: a Processor (Processor)410, a communication Interface (communication Interface)420, a Memory (Memory)430 and a communication Bus (communication Bus)440, wherein the Processor 410, the communication Interface 420 and the Memory 430 are communicated with each other via the communication Bus 440. The processor 410 may call logical commands in the memory 430 to perform the following method:
acquiring sound information of a hydraulic pump; inputting the sound information into a fault prediction model to obtain a fault prediction result output by the fault prediction model; the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump.
In addition, the logic commands in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic commands are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of commands for enabling a computer device (which may be a personal computer, a server, or a network device) to execute 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 removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The processor in the electronic device provided in the embodiment of the present invention may call a logic instruction in the memory to implement the method, and the specific implementation manner of the method is consistent with the implementation manner of the method, and the same beneficial effects may be achieved, which is not described herein again.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method provided in the foregoing embodiments when executed by a processor, and the method includes:
acquiring sound information of a hydraulic pump; inputting the sound information into a fault prediction model to obtain a fault prediction result output by the fault prediction model; the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump.
When the computer program stored on the non-transitory computer readable storage medium provided in the embodiments of the present invention is executed, the method is implemented, and the specific implementation manner of the method is consistent with the implementation manner of the method, and the same beneficial effects can be achieved, which is not described herein again.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes commands for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A hydraulic pump fault prediction method is characterized by comprising the following steps:
acquiring sound information of a hydraulic pump;
inputting the sound information into a fault prediction model to obtain a fault prediction result output by the fault prediction model;
the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump.
2. The hydraulic pump failure prediction method of claim 1, wherein the obtaining acoustic information of the hydraulic pump comprises:
collecting an original sound signal when a hydraulic pump runs;
and performing time domain analysis and/or frequency domain analysis on the original sound signal to obtain the sound information.
3. The method of claim 2, wherein the collecting the raw sound signal of the operation of the hydraulic pump is followed by:
pre-emphasis, framing and windowing the original sound signal.
4. The method for predicting the failure of the hydraulic pump according to claim 2, wherein the time-domain analyzing the original sound signal to obtain the sound information comprises:
determining sound time domain information of the original sound signal in each time interval based on a preset time interval;
the sound information is determined based on sound time domain information for each time interval.
5. The method for predicting the failure of the hydraulic pump according to claim 2, wherein the performing the frequency domain analysis on the original sound signal to obtain the sound information comprises:
determining sound frequency domain information of the original sound signal;
dividing the sound frequency domain information into a plurality of frequency sections, and respectively determining the energy of each frequency section;
the sound information is determined based on the energy of each frequency bin.
6. The hydraulic pump failure prediction method according to any one of claims 1 to 5, wherein the inputting the sound information into a failure prediction model to obtain a failure prediction result output by the failure prediction model comprises:
inputting sound information of a plurality of continuous periods into a fault prediction model to obtain a plurality of fault prediction results output by the fault prediction model;
and if the plurality of fault prediction results are consistent, determining that the plurality of fault prediction results are valid.
7. The hydraulic pump failure prediction method according to any one of claims 1 to 5, characterized in that the failure prediction model corresponds one-to-one to the type of the hydraulic pump.
8. A hydraulic pump failure prediction apparatus characterized by comprising:
an acquisition unit for acquiring sound information of the hydraulic pump;
the prediction unit is used for inputting the sound information into a fault prediction model to obtain a fault prediction result output by the fault prediction model;
the fault prediction model is trained on the sound information of the sample hydraulic pump and the fault detection result of the sample hydraulic pump.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the hydraulic pump failure prediction method according to any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the steps of the hydraulic pump failure prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110172016.0A CN112943595A (en) | 2021-02-07 | 2021-02-07 | Hydraulic pump fault prediction method, hydraulic pump fault prediction device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110172016.0A CN112943595A (en) | 2021-02-07 | 2021-02-07 | Hydraulic pump fault prediction method, hydraulic pump fault prediction device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112943595A true CN112943595A (en) | 2021-06-11 |
Family
ID=76244137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110172016.0A Pending CN112943595A (en) | 2021-02-07 | 2021-02-07 | Hydraulic pump fault prediction method, hydraulic pump fault prediction device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112943595A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113624493A (en) * | 2021-08-04 | 2021-11-09 | 蝴蝶供应链有限公司 | Hydraulic system abnormity monitoring method, equipment, system and storage medium |
| CN113641562A (en) * | 2021-08-10 | 2021-11-12 | 中国工商银行股份有限公司 | Fault alarm method and device for noise reduction cabinet, computer equipment and storage medium |
| CN114109800A (en) * | 2021-12-03 | 2022-03-01 | 河南省高远公路养护技术有限公司 | Hydraulic plunger pump fault diagnosis device and method based on sound recognition technology |
| CN114962248A (en) * | 2022-07-27 | 2022-08-30 | 北京华夏圣远能源科技有限公司 | Artificial intelligence-based monitoring method and device for small-molecule recyclable fracturing fluid delivery pump and medium |
| CN115907104A (en) * | 2022-11-03 | 2023-04-04 | 重庆忽米网络科技有限公司 | Hydraulic pump fault prediction method based on Internet of things big data and machine learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103038508A (en) * | 2010-02-23 | 2013-04-10 | 阿尔特弥斯智能动力有限公司 | Fluid-working machine and method of operating a fluid-working machine |
| US20150377745A1 (en) * | 2013-02-19 | 2015-12-31 | Basim Al-Najjar | A method and an apparatus for predicting the condition of a machine or a component of the machine |
| CN105889052A (en) * | 2016-03-29 | 2016-08-24 | 中海石油(中国)有限公司深圳分公司 | Noise separation method for fault diagnosis of slurry pump |
| CN110135492A (en) * | 2019-05-13 | 2019-08-16 | 山东大学 | Equipment fault diagnosis and method for detecting abnormality and system based on more Gauss models |
| US20190339162A1 (en) * | 2016-12-30 | 2019-11-07 | Grundfos Holding A/S | Sensor assembly and method for fault detection in pumps and pump assembly with sensor assembly |
| CN112049787A (en) * | 2019-10-25 | 2020-12-08 | 华北电力大学（保定） | Non-contact water pump fault detection method and system |
-
2021
- 2021-02-07 CN CN202110172016.0A patent/CN112943595A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103038508A (en) * | 2010-02-23 | 2013-04-10 | 阿尔特弥斯智能动力有限公司 | Fluid-working machine and method of operating a fluid-working machine |
| US20150377745A1 (en) * | 2013-02-19 | 2015-12-31 | Basim Al-Najjar | A method and an apparatus for predicting the condition of a machine or a component of the machine |
| CN105889052A (en) * | 2016-03-29 | 2016-08-24 | 中海石油(中国)有限公司深圳分公司 | Noise separation method for fault diagnosis of slurry pump |
| US20190339162A1 (en) * | 2016-12-30 | 2019-11-07 | Grundfos Holding A/S | Sensor assembly and method for fault detection in pumps and pump assembly with sensor assembly |
| CN110135492A (en) * | 2019-05-13 | 2019-08-16 | 山东大学 | Equipment fault diagnosis and method for detecting abnormality and system based on more Gauss models |
| CN112049787A (en) * | 2019-10-25 | 2020-12-08 | 华北电力大学（保定） | Non-contact water pump fault detection method and system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113624493A (en) * | 2021-08-04 | 2021-11-09 | 蝴蝶供应链有限公司 | Hydraulic system abnormity monitoring method, equipment, system and storage medium |
| CN113641562A (en) * | 2021-08-10 | 2021-11-12 | 中国工商银行股份有限公司 | Fault alarm method and device for noise reduction cabinet, computer equipment and storage medium |
| CN114109800A (en) * | 2021-12-03 | 2022-03-01 | 河南省高远公路养护技术有限公司 | Hydraulic plunger pump fault diagnosis device and method based on sound recognition technology |
| CN114962248A (en) * | 2022-07-27 | 2022-08-30 | 北京华夏圣远能源科技有限公司 | Artificial intelligence-based monitoring method and device for small-molecule recyclable fracturing fluid delivery pump and medium |
| CN115907104A (en) * | 2022-11-03 | 2023-04-04 | 重庆忽米网络科技有限公司 | Hydraulic pump fault prediction method based on Internet of things big data and machine learning |
| CN115907104B (en) * | 2022-11-03 | 2023-12-26 | 重庆忽米网络科技有限公司 | Hydraulic pump fault prediction method based on big data of Internet of things and machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112943595A (en) | Hydraulic pump fault prediction method, hydraulic pump fault prediction device, electronic equipment and storage medium | |
| CN103810374B (en) | A kind of mechanical disorder Forecasting Methodology based on MFCC feature extractions | |
| CN110674842A (en) | Wind turbine generator main shaft bearing fault prediction method | |
| CN102023100A (en) | Equipment failure early-warning system and method | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| CN112686110A (en) | Method, device and equipment for diagnosing faults of centrifugal pump and storage medium | |
| CN105003453A (en) | Online monitoring and fault diagnosis system of mine fan | |
| CN103969069A (en) | Working condition monitoring and fault diagnosis method for mechanical equipment | |
| CN104713728A (en) | On-line large slewing bearing residual life prediction method based on multi-dimensional data drive | |
| CN111896254A (en) | Fault prediction system and method for variable-speed variable-load large rolling bearing | |
| JP2019067197A (en) | Method for detecting trouble sign | |
| CN105487530A (en) | Diesel low-exhaust-temperature fault prediction system and method | |
| CN103822786A (en) | Wind turbine generator set mechanical equipment state diagnosis method based on multivariate statistical analysis | |
| WO2023279382A1 (en) | Motor bearing running state fault detection method and system | |
| CN103149276A (en) | Method for determining cavitation erosion initial point of runner blade of model water turbine | |
| CN113125135A (en) | Fault diagnosis method for rotary machine, storage medium, and electronic device | |
| CN102393303B (en) | Method for detecting abnormal sequencing of gas turbine engine | |
| CN117171657A (en) | Wind power generation equipment fault diagnosis method and device, electronic equipment and storage medium | |
| Feng et al. | Gas turbine blade fracturing fault diagnosis based on broadband casing vibration | |
| CN110334562B (en) | Bearing vibration operation state prediction model training method, prediction method and prediction device | |
| Dutta et al. | PROAD (Process Advisor): A health monitoring framework for centrifugal pumps | |
| Pino et al. | Bearing diagnostics of hydro power plants using wavelet packet transform and a hidden Markov model with orbit curves | |
| CN116877452B (en) | Non-positive-displacement water pump running state monitoring system based on Internet of things data | |
| CN2771505Y (en) | Hydroelectric generating set monitoring and expert fuzzy diagnostic apparatus | |
| CN109165396A (en) | A kind of equipment remaining life prediction technique of failure evolution trend |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210611 |
|
| RJ01 | Rejection of invention patent application after publication |