CN115270862A - Fault detection method and device for plunger pump and electronic equipment - Google Patents
Fault detection method and device for plunger pump and electronic equipment Download PDFInfo
- Publication number
- CN115270862A CN115270862A CN202210858243.3A CN202210858243A CN115270862A CN 115270862 A CN115270862 A CN 115270862A CN 202210858243 A CN202210858243 A CN 202210858243A CN 115270862 A CN115270862 A CN 115270862A
- Authority
- CN
- China
- Prior art keywords
- plunger pump
- state
- fault detection
- state data
- early warning
- 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)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The application discloses a fault detection method and device for a plunger pump and electronic equipment, wherein the method comprises the following steps: acquiring running state data of the plunger pump, wherein the running state data comprises vibration state data and rotation state data; performing characteristic extraction based on the operation state data to obtain the state characteristic of the plunger pump; establishing an abnormality judgment index according to the running state data and/or the state characteristics, and determining whether to generate an abnormality early warning according to the abnormality judgment index; responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model; and responding to the condition that no abnormal early warning is generated, and generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data. Based on the running state data of the plunger pump, abnormity early warning is carried out in advance, fault detection or health state detection is further carried out, and detection of faults which are difficult to trigger changes of parameters such as oil temperature, oil pressure and liquid level in time is achieved.
Description
Technical Field
The application relates to the technical field of plunger pumps, in particular to a fault detection method and device of a plunger pump and electronic equipment.
Background
The mining reciprocating plunger pump is a core device in a liquid supply system of a coal face, can provide hydraulic power for the action of a hydraulic support, can also be used for spraying dust fall of a coal mining machine, cooling of a power transmission system of the device and the like, and has important effects on high-efficiency coal mining due to safe and stable operation.
The sensor is arranged on the mining reciprocating plunger pump to acquire the state information of the equipment, and then fault detection is realized through data analysis, so that malignant faults are prevented, and economic loss is reduced.
In the related technology, the fault detection of the plunger pump is realized mainly by means of slowly-varying state data such as oil temperature, oil pressure and liquid level and by combining a threshold value alarm method. However, the detection method can only preliminarily judge some performance-degrading faults, and cannot detect faults which are difficult to trigger parameter changes such as oil temperature, oil pressure and liquid level in time when the faults occur.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, a first objective of the present application is to provide a fault detection method for a plunger pump, which is used to solve the problem of detecting a fault that it is difficult to trigger changes of parameters such as oil temperature, oil pressure, and liquid level in time in the related art.
In order to achieve the above object, a first embodiment of the present application provides a failure detection method for a plunger pump, where the method includes: acquiring running state data of the plunger pump, wherein the running state data comprises vibration state data and rotation state data; performing feature extraction based on the operation state data to obtain state features of the plunger pump; establishing an abnormality judgment index according to the running state data and/or the state characteristics, and determining whether to generate an abnormality early warning according to the abnormality judgment index; responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model; and responding to the condition that the abnormal early warning is not generated, and generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data.
In addition, the method for detecting the fault of the plunger pump according to the above embodiment of the present application may further have the following additional technical features:
according to an embodiment of the application, the vibration status data comprises a pump valve vibration signal of the plunger pump and a crankcase vibration signal of the plunger pump, and the rotation status data comprises a crank key phase signal of the plunger pump.
According to an embodiment of the present application, the performing feature extraction based on the operation status data to obtain the status feature of the plunger pump includes: respectively intercepting the whole-cycle signals of the pump valve vibration signal and the crankcase vibration signal according to the crankshaft key phase signal to obtain the whole-cycle pump valve vibration signal and the whole-cycle crankcase vibration signal; based on an order ratio tracking algorithm, resampling the pump valve vibration signal in the whole period and the crankcase vibration signal in the whole period respectively to obtain corresponding candidate vibration signals; and performing feature extraction on the candidate vibration signals to obtain the state features.
According to an embodiment of the application, the status feature comprises at least one of: time domain features, frequency domain features, angular domain features, and time-frequency domain features.
According to an embodiment of the present application, the constructing an abnormality determination index according to the operating state data and/or the state feature, and determining whether to generate an abnormality warning according to the abnormality determination index includes: performing signal reconstruction on the candidate vibration signal obtained based on the operation state data to obtain a signal reconstruction error, and taking the signal reconstruction error as the abnormality judgment index; and/or carrying out feature selection and dimension reduction fusion processing on the state features to obtain abnormal features, and taking the values of the abnormal features as the abnormal judgment indexes; and comparing the abnormality judgment index with an abnormality early warning threshold value currently corresponding to the abnormality judgment index, and determining whether to generate the abnormality early warning according to a comparison result.
According to one embodiment of the application, the anomaly early warning threshold is an initial threshold or an adaptive updating threshold.
According to an embodiment of the present application, the generating a fault detection result according to the state feature and a pre-trained fault detection model in response to the generating of the abnormal early warning includes: carrying out feature selection and dimension reduction fusion processing on the state features to obtain fault features of the plunger pump; and generating the fault detection result according to the fault characteristics and the fault detection model, wherein the fault detection model is a classification model.
According to an embodiment of the present application, the generating a health status detection result according to the status feature, the pre-trained performance degradation model and the historical health status data in response to not generating the abnormal early warning includes: carrying out feature selection and dimension reduction fusion processing on the state features to obtain health fusion features of the plunger pump; and generating a health state detection result according to the health fusion characteristics, the performance degradation model and the historical health state data.
In order to achieve the above object, an embodiment of a second aspect of the present application provides a failure detection apparatus for a plunger pump, including: the data acquisition module is used for acquiring running state data of the plunger pump, wherein the running state data comprises vibration state data and rotation state data; the preprocessing module is used for extracting features based on the running state data to obtain the state features of the plunger pump; the abnormality early warning module is used for constructing an abnormality judgment index according to the running state data and/or the state characteristics and determining whether to generate abnormality early warning according to the abnormality judgment index; the fault detection module is used for responding to the abnormal early warning and generating a fault detection result according to the state characteristics and a pre-trained fault detection model; and the health state detection module is used for responding to the condition that the abnormal early warning is not generated and generating a health state detection result according to the state characteristics, the pre-trained performance degradation model and historical health state data.
In addition, the failure detection device for the plunger pump according to the above embodiment of the present application may further have the following additional technical features:
according to an embodiment of the application, the vibration status data comprises a pump valve vibration signal of the plunger pump and a crankcase vibration signal of the plunger pump, and the rotation status data comprises a crank key phase signal of the plunger pump.
According to an embodiment of the present application, the preprocessing module is further configured to perform signal interception of a whole cycle on the pump valve vibration signal and the crankcase vibration signal according to the crank key phase signal, so as to obtain a whole cycle of the pump valve vibration signal and a whole cycle of the crankcase vibration signal; based on an order ratio tracking algorithm, resampling the pump valve vibration signal in the whole period and the crankcase vibration signal in the whole period respectively to obtain corresponding candidate vibration signals; and performing feature extraction on the candidate vibration signals to obtain the state features.
According to an embodiment of the application, the status feature comprises at least one of: time domain features, frequency domain features, angular domain features, and time-frequency domain features.
According to an embodiment of the present application, the abnormality warning module is further configured to: performing signal reconstruction on the candidate vibration signal obtained based on the operation state data to obtain a signal reconstruction error, and taking the signal reconstruction error as the abnormality judgment index; and/or carrying out feature selection and dimension reduction fusion processing on the state features to obtain abnormal features, and taking the values of the abnormal features as the abnormal judgment indexes; and comparing the abnormality judgment index with an abnormality early warning threshold value currently corresponding to the abnormality judgment index, and determining whether to generate the abnormality early warning according to a comparison result.
According to one embodiment of the application, the anomaly early warning threshold is an initial threshold or an adaptive updating threshold.
According to an embodiment of the present application, the fault detection module is further configured to: carrying out feature selection and dimension reduction fusion processing on the state features to obtain fault features of the plunger pump; and generating the fault detection result according to the fault characteristics and the fault detection model, wherein the fault detection model is a classification model.
According to an embodiment of the present application, the health status detection module is further configured to: carrying out feature selection and dimension reduction fusion processing on the state features to obtain health fusion features of the plunger pump; and generating a health state detection result according to the health fusion characteristics, the performance degradation model and the historical health state data.
In order to achieve the above object, an embodiment of a third aspect of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, when executing the program, implementing the method of fault detection of a plunger pump as described in any of the embodiments of the first aspect of the present application.
According to the fault detection method for the plunger pump, the running state data of the plunger pump are obtained, wherein the running state data comprise vibration state data and rotation state data; performing characteristic extraction based on the operation state data to obtain the state characteristic of the plunger pump; establishing an abnormality judgment index according to the running state data and/or the state characteristics, and determining whether to generate an abnormality early warning according to the abnormality judgment index; responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model; and responding to the condition that no abnormal early warning is generated, and generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data. The embodiment of the disclosure carries out abnormity early warning on the plunger pump in advance based on vibration state data and rotation state data of the plunger pump, and further carries out fault detection or health state detection according to an abnormity early warning result so as to analyze the working state of parts of the plunger pump, thereby realizing timely detection of faults which are difficult to trigger the change of parameters such as oil temperature, oil pressure and liquid level in time.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting a failure of a plunger pump according to an embodiment of the present disclosure.
Fig. 2 is a schematic flow chart illustrating a method for detecting a failure of a plunger pump according to another embodiment of the present disclosure.
Fig. 3 is a schematic flowchart of a method for detecting a failure of a plunger pump according to another embodiment of the present disclosure.
Fig. 4 is a schematic flowchart of a method for detecting a failure of a plunger pump according to another embodiment of the present disclosure.
Fig. 5 is a schematic flowchart of a method for detecting a failure of a plunger pump according to another embodiment of the present disclosure.
Fig. 6 is a block diagram of an application system of a fault detection method for a plunger pump according to an embodiment of the present application.
Fig. 7 is a schematic overall flow chart of a fault detection method for a plunger pump according to an embodiment of the present application.
Fig. 8 is a schematic structural diagram of a failure detection device for a plunger pump according to an embodiment of the present application.
Fig. 9 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.
Detailed Description
In order to better understand the above technical solutions, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.
A failure detection method, a failure detection device, and an electronic apparatus for a plunger pump according to an embodiment of the present application are described below with reference to the drawings.
Fig. 1 is a schematic flowchart of a failure detection method for a plunger pump according to an embodiment of the present disclosure.
As shown in fig. 1, the method for detecting a failure of a plunger pump provided in the embodiment of the present application specifically includes the following steps:
s101, acquiring running state data of the plunger pump, wherein the running state data comprises vibration state data and rotation state data.
The main executing body of the fault detection method for the plunger pump in the embodiment of the present application may be the fault detection device for the plunger pump provided in the embodiment of the present application, and the fault detection device for the plunger pump may be a hardware device having a data information processing capability and/or necessary software for driving the hardware device to operate.
In the embodiment of the present application, the operation state data of the plunger pump may include vibration state data and rotation state data, wherein the vibration state data may be a pump valve vibration signal of the plunger pump and a crankcase vibration signal of the plunger pump, and the rotation state data may be a crank key phase signal of the plunger pump.
In some embodiments, the vertical vibration acceleration of the pump valve can be monitored by a vibration sensor arranged on a plug board of the liquid discharge cavity of the plunger pump to obtain a pump valve vibration signal; the crank key phase signal is monitored by 3 signal sensors arranged on a crank shaft and a rotating speed sensor arranged on an end cover of a crank case, wherein the signal sensors are used for acquiring the rotating angle of the crank shaft so as to increase the signal fineness of the crank key phase signal, and in addition, the signal sensors can be replaced by a fluted disc; detecting vibration acceleration of the upper surface and the side surface of the crankcase by using vibration sensors arranged on the upper surface and the side surface of the crankcase body to obtain a crankcase vibration signal; in addition, the pump valve vibration signal, the crankshaft key phase signal and the crankcase key phase signal can be acquired through a data acquisition unit arranged on the plunger pump train, and the signals are sent to a database to be stored as the running state data of the plunger pump, so that required data can be acquired during fault detection.
And S102, extracting characteristics based on the running state data to obtain the state characteristics of the plunger pump.
In the embodiment of the present application, the operating state data of the plunger pump is subjected to feature extraction to obtain the state features of the plunger pump, which may specifically include the state features of zero devices in the plunger pump.
S103, establishing an abnormity judgment index according to the running state data and/or the state characteristics, and determining whether to generate abnormity early warning according to the abnormity judgment index.
In the embodiment of the application, the abnormality judgment index corresponding to the plunger pump can be constructed according to the running state data of the plunger pump, and the abnormality judgment index corresponding to the plunger pump can also be constructed according to the state characteristics of the plunger pump. And carrying out abnormity early warning judgment on the plunger pump according to the abnormity judgment indexes, and determining whether to generate abnormity early warning.
And S104, responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and the pre-trained fault detection model.
And under the condition of generating the abnormal early warning, carrying out fault detection on the plunger pump according to the state characteristics of the plunger pump and a pre-trained fault detection model, and outputting a fault detection result by the model.
And S105, responding to the condition that no abnormal early warning is generated, and generating a health state detection result according to the state characteristics, the pre-trained performance degradation model and the historical health state data.
Under the condition that no abnormal early warning is generated, a health state detection result can be further obtained according to the state characteristics of the plunger pump, a pre-trained performance degradation model and historical health state data of the plunger pump in different health states, wherein the health state detection result can comprise a health state grade.
In summary, the method for detecting the fault of the plunger pump in the embodiment of the present application obtains the operation state data of the plunger pump, where the operation state data includes vibration state data and rotation state data; performing characteristic extraction based on the operation state data to obtain the state characteristic of the plunger pump; establishing an abnormality judgment index according to the running state data and/or the state characteristics, and determining whether to generate an abnormality early warning according to the abnormality judgment index; responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model; and responding to the condition that no abnormal early warning is generated, and generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data. The embodiment of the application carries out the abnormal early warning to the plunger pump in advance based on the vibration state data and the rotation state data of the plunger pump, and further carries out fault detection or health state detection according to whether the abnormal early warning is generated or not to analyze the working state of the parts of the plunger pump, thereby realizing timely detection of the fault which is difficult to trigger the change of parameters such as oil temperature, oil pressure and liquid level in time.
On the basis of the above embodiment, as shown in fig. 2, the step S102 of "performing feature extraction based on the operation state data to obtain the state feature of the plunger pump" may include the following steps:
and S201, respectively carrying out whole-cycle signal interception on the pump valve vibration signal and the crankcase vibration signal according to the crank shaft key phase signal to obtain a whole-cycle pump valve vibration signal and a whole-cycle crankcase vibration signal.
In some embodiments, based on continuously and synchronously acquired vibration signals (such as a pump valve vibration signal and a crankcase vibration signal) of each measuring point of the plunger pump and a crankshaft key phase signal, periodic signal interception is performed: and intercepting vibration signals of each measuring point corresponding to 360 degrees or multiples of 360 degrees of crankshaft rotation according to the rising edge of the periodic pulse signal of the key phase signal, so as to obtain vibration signals of a whole period (such as a pump valve vibration signal of the whole period and a crankcase vibration signal of the whole period) corresponding to each measuring point.
S202, based on the order ratio tracking algorithm, resampling is respectively carried out on the pump valve vibration signal in the whole period and the crankcase vibration signal in the whole period, and obtaining corresponding candidate vibration signals.
In some embodiments, angular domain resampling of the vibration signal is performed based on an order ratio tracking algorithm, constant angular interval sampling is used for replacing constant time interval sampling, the sampling frequency of the vibration signal can be changed synchronously with the rotation speed of the crankshaft, and the length of the sample of the vibration signal in the whole period is adjusted in a self-adaptive mode.
Wherein the following formula can be described for the cumulative crank angle:
θ(t)＝a0+a1t+a2t2
according to the three signal inductors during key phase signal monitoring, the corresponding rotation angles of the crankshaft at 3 moments can be obtained, and the rotation angles are as follows:
in the formula, Δ Φ is a crank angle variation value obtained from the crank key phase signal. From this system of equations, the coefficient a can be calculated0、a1And a2An expression for an arbitrary angle θ and time t is obtained, i.e., time is expressed as a function of accumulated rotation angle, as shown in the following equation:
and S203, extracting the characteristics of the candidate vibration signals to obtain state characteristics.
In the embodiment of the present application, the full-cycle pump valve vibration signal and the full-cycle crankcase vibration signal (i.e., the candidate vibration signals) obtained after resampling are subjected to feature extraction. For example, the time domain, the frequency domain, the angular domain and the time-frequency domain feature extraction are performed on the whole-period vibration signals to obtain state features including time domain features, frequency domain features, angular domain features and time-frequency domain features. Of course, one or more of the time-domain feature, the frequency-domain feature, the angular-domain feature and the time-frequency-domain feature may be extracted as needed, which is not limited in this application.
On the basis of the above embodiment, as shown in fig. 3, the step S103 of "constructing an abnormality determination index according to the operation state data and/or the state feature, and determining whether to generate an abnormality warning according to the abnormality determination index" includes the following steps:
s301, performing signal reconstruction on the candidate vibration signals obtained based on the running state data to obtain signal reconstruction errors, and taking the signal reconstruction errors as abnormal judgment indexes.
In the embodiment of the application, an abnormality judgment index representing a zero device in the plunger pump is constructed on the basis of the signal reconstruction errors of the pump valve vibration signal of the whole period and the crankcase vibration signal of the whole period, which are obtained after resampling.
S302, carrying out feature selection and dimension reduction fusion processing on the state features to obtain abnormal features, and taking the values of the abnormal features as abnormal judgment indexes.
In some embodiments, an abnormality judgment index representing a zero device in the plunger pump can be constructed according to the obtained state characteristics and by combining with a characteristic selection and dimension reduction processing technology.
And S303, comparing the abnormality judgment index with an abnormality early warning threshold value corresponding to the abnormality judgment index at present, and determining whether to generate abnormality early warning according to a comparison result.
In the embodiment of the application, the abnormality judgment indexes of all parts and components calculated in real time are compared with the current corresponding abnormality early warning threshold value of the index, and the abnormality early warning is generated according to the comparison result.
The abnormal early warning threshold value is an initial threshold value or a self-adaptive updating threshold value, wherein the initial threshold value can be an average value of abnormal evaluation state indexes obtained by combining the abnormal early warning model with delivery test state data of the plunger pump, and the self-adaptive updating threshold value can be an average value of the abnormal evaluation state indexes obtained by combining the abnormal early warning model with operation state data of a whole day before 6 days.
On the basis of the foregoing embodiment, as shown in fig. 4, the step S104 of "generating a fault detection result according to the state feature and the pre-trained fault detection model in response to generating the abnormality warning" may include the following steps:
s401, performing feature selection and dimension reduction fusion processing on the state features to obtain fault features of the plunger pump.
In the embodiment of the application, fault detection is started after abnormal early warning occurs, and fault characteristics representing parts in the plunger pump are constructed on the basis of state characteristics and by combining characteristic selection and a characteristic dimension reduction fusion technology.
S402, generating a fault detection result according to the fault characteristics and the fault detection model, wherein the fault detection model is a classification model.
On the basis of the embodiment, the fault characteristics calculated in real time are used as model input based on the pre-trained fault detection models of the parts, and whether the parts of the plunger pump have faults or not and the type of the faults are judged according to the output of the model. If the fault occurs, a fault alarm is sent out, and if the fault does not occur, the current running state of the plunger pump is kept.
On the basis of the foregoing embodiment, as shown in fig. 5, the step S105 of "generating a health status detection result according to the status feature, the pre-trained performance degradation model and the historical health status data in response to no generation of the abnormal early warning" includes the following steps:
s501, performing feature selection and dimension reduction fusion processing on the state features to obtain the health fusion features of the plunger pump.
And starting health state detection under the condition that no abnormal early warning occurs, and constructing health fusion characteristics representing parts in the plunger pump based on state characteristics by combining characteristic selection and a characteristic dimension reduction fusion technology.
And S502, generating a health state detection result according to the health fusion characteristics, the performance degradation model and the historical health state data.
In some embodiments, the health state of the plunger pump is detected by using the health fusion characteristics and combining a performance degradation model and a fault symptom trend change rule of the parts, and the health state grade of the plunger pump is further obtained by combining an analytic hierarchy process. Wherein the trend change rule of the fault symptom can be obtained based on historical data (namely historical health state data) of the plunger pump under different health states.
In some embodiments, the running state data, the state characteristics, the health detection results, the fault early warning and fault detection results and the like of the plunger pump can be displayed on an interface in the display device, so that related personnel can conveniently perform operation management and maintenance decision of the plunger pump. When the plunger pump fails, information related to the failure is further output, including the location of the failure, the type of the failure, and the troubleshooting method.
In some embodiments, parameter configuration may also be performed in advance before fault detection, where the parameters to be configured may be technical parameters of the plunger pump (including flow rate, pressure, motor speed, reduction gearbox gear ratio, movement sequence of the plunger during liquid suction and discharge processes, and the like), state monitoring parameters (including sensor arrangement information, sampling frequency, number of sampling points, and the like), and parameters of the fault early warning model and the fault detection model (including model number, model method principle, model structure, data used for model training, and model frame used).
In some embodiments, the online acquired operational status data, extracted status features, and data analysis results (such as fault warning, fault detection, and health detection results) may also be stored in a database, for example: for data such as vibration signals, key phase signals and the like acquired in real time, data are stored densely at regular time, and data coverage time intervals are set to be 7 days; for the state characteristics and the data analysis results, the data can be stored every 0.1s, and a data coverage strategy is not set.
In summary, the method for detecting the fault of the plunger pump in the embodiment of the present application obtains the operation state data of the plunger pump, where the operation state data includes vibration state data and rotation state data; performing characteristic extraction based on the operation state data to obtain the state characteristic of the plunger pump; establishing an abnormality judgment index according to the running state data and/or the state characteristics, and determining whether to generate an abnormality early warning according to the abnormality judgment index; responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model; and responding to the condition that the abnormal early warning is not generated, and generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data. According to the plunger pump state detection method and device, more comprehensive plunger pump state information is obtained by adding the plurality of sensor measuring points, based on vibration state data and rotation state data of the plunger pump, abnormal early warning is carried out on the plunger pump in advance, fault detection or health state detection is further carried out according to whether the abnormal early warning is generated or not, and therefore the working states of parts of the plunger pump are analyzed.
For clarity of description of the failure detection method of the plunger pump according to the embodiment of the present application, which will be described in detail with reference to fig. 6 and 7, the failure detection method of the plunger pump according to the embodiment of the present application can be applied to the failure detection system shown in fig. 6, as shown in fig. 6, the fault detection system includes a state monitoring device, a system parameter setting module, a data storage module, a data preprocessing module, an abnormality pre-warning module, a health detection module, a fault detection module and an interface display module, in which the state monitoring device including a vibration sensor, a key phase sensor (or a signal sensor) and a key phase sensor is installed in each component of the plunger pump, for example, a vibration sensor is arranged on a liquid discharge cavity plugging plate at the hydraulic end of the plunger pump to obtain a pump valve vibration signal, a key phase sensor is arranged on a crankshaft at the power end of the plunger pump to obtain the rotation angle of the crankshaft, a key phase sensor arranged on a crankcase body is combined to obtain a crankshaft key phase signal with higher precision, and a vibration sensor is arranged on the surface of the crankcase body to obtain a crankcase vibration signal, the data acquisition unit stores the collected running state data of the crankcase vibration signal, the pump valve vibration signal and the crankshaft key phase signal into a data storage module, the data preprocessing module obtains the running state data from the data storage module, and extracting state characteristics according to the running state data, determining whether an abnormal early warning is generated or not by the abnormal early warning module according to the state characteristics, starting the fault detection module if the abnormal early warning is generated, generating a fault detection result by the fault detection module according to the state characteristics obtained by the data preprocessing module, starting the health detection module if the abnormal early warning is not generated, and generating a health state detection result by the health detection module according to the state characteristics obtained by the data preprocessing module. In the process, the state characteristics, the abnormal early warning, the fault detection result and the health state detection result can be displayed on the interface display module, in addition, the interface display module and the data acquisition unit can be subjected to related parameter setting according to the system parameter setting module, and other modules which do not display the connection relation with the system parameter setting module in the figure 6 can be subjected to related parameter setting.
Fig. 7 is a schematic overall flow chart of a method for detecting a failure of a plunger pump according to an embodiment of the present application, which may include the following steps:
and S701, acquiring a crankcase vibration signal, a crankshaft key phase signal and a pump valve vibration signal.
And S702, respectively carrying out whole-period signal interception on the pump valve vibration signal and the crankcase vibration signal according to the crank shaft key phase signal to obtain a whole-period pump valve vibration signal and a whole-period crankcase vibration signal.
And S703, resampling the pump valve vibration signal in the whole period and the crankcase vibration signal in the whole period respectively based on a step ratio tracking algorithm to obtain corresponding candidate vibration signals.
And S704, performing feature extraction on the candidate vibration signals to obtain state features.
S705, performing signal reconstruction on the candidate vibration signals obtained based on the running state data to obtain signal reconstruction errors, and taking the signal reconstruction errors as the abnormal judgment indexes; and/or performing feature selection and dimension reduction fusion processing on the state features to obtain abnormal features, and taking the values of the abnormal features as abnormal judgment indexes.
S706, comparing the abnormality judgment index with an abnormality early warning threshold value corresponding to the abnormality judgment index at present, and determining whether to generate the abnormality early warning according to the comparison result. If yes, executing step S707 and step S708; if not, go to step S712.
And S707, displaying an abnormity early warning.
And S708, responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and the pre-trained fault detection model.
And S709, judging whether a fault occurs according to the fault detection result. If yes, go to step S710; if not, step S711 is executed.
And S710, sending out a fault alarm.
S711, the current operation state of the plunger pump is maintained.
And S712, responding to the condition that no abnormal early warning is generated, generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data.
And S713, displaying the health state detection result.
Fig. 8 is a schematic structural diagram of a failure detection device for a plunger pump according to an embodiment of the present application.
As shown in fig. 8, the failure detection device 800 for a plunger pump includes: a data acquisition module 801, a preprocessing module 802, an abnormality warning module 803, a fault detection module 804 and a health status detection module 805. Wherein the content of the first and second substances,
the data acquisition module 801 is configured to acquire operation state data of the plunger pump, where the operation state data includes vibration state data and rotation state data.
And the preprocessing module 802 is configured to perform feature extraction based on the operation state data to obtain state features of the plunger pump.
And an anomaly early warning module 803, configured to construct an anomaly judgment index according to the operating state data and/or the state characteristics, and determine whether to generate an anomaly early warning according to the anomaly judgment index.
And the fault detection module 804 is used for responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model.
And the health state detection module 805 is configured to generate a health state detection result according to the state feature, the pre-trained performance degradation model, and the historical health state data in response to that no abnormal early warning is generated.
According to an embodiment of the application, the vibration status data comprises a pump valve vibration signal of the plunger pump and a crankcase vibration signal of the plunger pump, and the rotation status data comprises a crank key phase signal of the plunger pump.
According to an embodiment of the present application, the preprocessing module 802 is further configured to perform signal interception of a whole period on the pump valve vibration signal and the crankcase vibration signal according to the crank key phase signal, respectively, to obtain a pump valve vibration signal of the whole period and a crankcase vibration signal of the whole period; based on an order ratio tracking algorithm, resampling the pump valve vibration signal of the whole period and the crankcase vibration signal of the whole period respectively to obtain corresponding candidate vibration signals; and performing feature extraction on the candidate vibration signals to obtain state features.
According to one embodiment of the application, the status features include at least one of: time domain features, frequency domain features, angular domain features, and time-frequency domain features.
According to an embodiment of the present application, the anomaly early warning module 803 is further configured to: performing signal reconstruction on candidate vibration signals obtained based on the running state data to obtain signal reconstruction errors, and taking the signal reconstruction errors as abnormal judgment indexes; and/or performing feature selection and dimension reduction fusion processing on the state features to obtain abnormal features, and taking the values of the abnormal features as abnormal judgment indexes; and comparing the abnormality judgment index with an abnormality early warning threshold value currently corresponding to the abnormality judgment index, and determining whether to generate abnormality early warning according to a comparison result.
According to one embodiment of the application, the anomaly early warning threshold is an initial threshold or an adaptive updating threshold.
According to an embodiment of the present application, the failure detection module 804 is further configured to: performing feature selection and dimensionality reduction fusion processing on the state features to obtain fault features of the plunger pump; and generating a fault detection result according to the fault characteristics and the fault detection model, wherein the fault detection model is a classification model.
According to an embodiment of the application, the health status detection module 805 is further configured to: performing feature selection and dimension reduction fusion processing on the state features to obtain health fusion features of the plunger pump; and generating a health state detection result according to the health fusion characteristics, the performance degradation model and the historical health state data.
It should be noted that the above explanation of the embodiment of the method for detecting a failure of a plunger pump is also applicable to the device for detecting a failure of a plunger pump of this embodiment, and is not repeated herein.
In summary, according to the fault detection device for the plunger pump provided by the embodiment of the application, the operation state data of the plunger pump is obtained, and the operation state data comprises vibration state data and rotation state data; performing characteristic extraction based on the operation state data to obtain the state characteristic of the plunger pump; constructing an abnormality judgment index according to the running state data and/or the state characteristics, and determining whether to generate an abnormality early warning according to the abnormality judgment index; responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model; and responding to the condition that no abnormal early warning is generated, and generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data. According to the plunger pump state detection method and device, more comprehensive plunger pump state information is obtained by adding the plurality of sensor measuring points, based on vibration state data and rotation state data of the plunger pump, abnormal early warning is carried out on the plunger pump in advance, fault detection or health state detection is further carried out according to whether the abnormal early warning is generated or not, and therefore the working states of parts of the plunger pump are analyzed.
In order to implement the above embodiments, the present application further proposes an electronic device 900, as shown in fig. 9, which includes a memory 901, a processor 902, and a computer program stored on the memory 903 and operable on the processor 903, and when the processor executes the computer program, the processor implements the foregoing failure detection method for the plunger pump.
In the description of the present application, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the present application and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the present application.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
In this application, unless expressly stated or limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly and encompass, for example, both fixed and removable connections or integral parts thereof; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as the case may be.
In this application, unless expressly stated or limited otherwise, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through intervening media. Also, a first feature "on," "above," and "over" a second feature may be directly on or obliquely above the second feature, or simply mean that the first feature is at a higher level than the second feature. A first feature "under," "beneath," and "under" a second feature may be directly under or obliquely under the second feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method of fault detection for a plunger pump, comprising:
acquiring running state data of the plunger pump, wherein the running state data comprises vibration state data and rotation state data;
performing feature extraction based on the operation state data to obtain state features of the plunger pump;
establishing an abnormality judgment index according to the running state data and/or the state characteristics, and determining whether to generate an abnormality early warning according to the abnormality judgment index;
responding to the abnormal early warning, and generating a fault detection result according to the state characteristics and a pre-trained fault detection model;
and responding to the condition that the abnormal early warning is not generated, and generating a health condition detection result according to the condition characteristics, the pre-trained performance degradation model and the historical health condition data.
2. The fault detection method of claim 1, wherein the vibration status data includes a pump valve vibration signal of the plunger pump and a crankcase vibration signal of the plunger pump, and the rotational status data includes a crank key phase signal of the plunger pump.
3. The fault detection method according to claim 2, wherein the performing feature extraction based on the operating state data to obtain the state feature of the plunger pump comprises:
respectively intercepting the pump valve vibration signal and the crankcase vibration signal in a whole period according to the crankshaft key phase signal to obtain the pump valve vibration signal in the whole period and the crankcase vibration signal in the whole period;
based on an order ratio tracking algorithm, resampling the pump valve vibration signal in the whole period and the crankcase vibration signal in the whole period respectively to obtain corresponding candidate vibration signals;
and performing feature extraction on the candidate vibration signals to obtain the state features.
4. The fault detection method according to claim 3, wherein the status signature comprises at least one of: time domain features, frequency domain features, angular domain features, and time-frequency domain features.
5. The fault detection method according to claim 3, wherein the constructing an abnormality determination index according to the operating state data and/or the state feature, and determining whether to generate an abnormality warning according to the abnormality determination index includes:
performing signal reconstruction on the candidate vibration signal obtained based on the running state data to obtain a signal reconstruction error, and taking the signal reconstruction error as the abnormality judgment index; and/or
Performing feature selection and dimension reduction fusion processing on the state features to obtain abnormal features, and taking the values of the abnormal features as the abnormal judgment indexes;
and comparing the abnormality judgment index with an abnormality early warning threshold value currently corresponding to the abnormality judgment index, and determining whether to generate the abnormality early warning according to a comparison result.
6. The fault detection method of claim 5, wherein the anomaly early warning threshold is an initial threshold or an adaptively updated threshold.
7. The method of claim 1, wherein the generating a fault detection result based on the state feature and a pre-trained fault detection model in response to generating the anomaly early warning comprises:
carrying out feature selection and dimension reduction fusion processing on the state features to obtain fault features of the plunger pump;
and generating the fault detection result according to the fault characteristics and the fault detection model, wherein the fault detection model is a classification model.
8. The method of claim 1, wherein the generating a health status detection result from the status signature, a pre-trained performance degradation model, and historical health status data in response to not generating the anomaly early warning comprises:
carrying out feature selection and dimension reduction fusion processing on the state features to obtain health fusion features of the plunger pump;
and generating a health state detection result according to the health fusion characteristics, the performance degradation model and the historical health state data.
9. A failure detection device for a plunger pump, comprising:
the data acquisition module is used for acquiring running state data of the plunger pump, wherein the running state data comprises vibration state data and rotation state data;
the preprocessing module is used for extracting features based on the running state data to obtain the state features of the plunger pump;
the abnormity early warning module is used for constructing an abnormity judgment index according to the running state data and/or the state characteristics and determining whether to generate abnormity early warning according to the abnormity judgment index;
the fault detection module is used for responding to the abnormal early warning and generating a fault detection result according to the state characteristics and a pre-trained fault detection model;
and the health state detection module is used for responding to the condition that the abnormal early warning is not generated, and generating a health state detection result according to the state characteristic, the pre-trained performance degradation model and the historical health state data.
10. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, which when executed by the processor implements the method of fault detection of a plunger pump according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210858243.3A CN115270862A (en) | 2022-07-20 | 2022-07-20 | Fault detection method and device for plunger pump and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210858243.3A CN115270862A (en) | 2022-07-20 | 2022-07-20 | Fault detection method and device for plunger pump and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115270862A true CN115270862A (en) | 2022-11-01 |
Family
ID=83767199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210858243.3A Pending CN115270862A (en) | 2022-07-20 | 2022-07-20 | Fault detection method and device for plunger pump and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115270862A (en) |
-
2022
- 2022-07-20 CN CN202210858243.3A patent/CN115270862A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6556939B1 (en) | Inferential signal generator for instrumented equipment and processes | |
| EP3271583B1 (en) | Pump monitoring apparatus and method | |
| CN112763908B (en) | Motor health index evaluation system based on multi-fault feature combination | |
| US10113552B2 (en) | System, method, and apparatus to monitor compressor health | |
| CN107247230B (en) | Rotary motor state monitoring method based on support vector machine and data driving | |
| CN103180793B (en) | Apparatus for diagnosis of abnormality and industrial machinery | |
| CA2875071C (en) | Method and system for testing operational integrity of a drilling rig | |
| US20130030765A1 (en) | System and method for use in monitoring machines | |
| AU2002236463A1 (en) | Inferential signal generator for instrumented equipment and processes | |
| MX2014014577A (en) | Methods apparatuses for defect diagnosis in a mechanical system. | |
| CN114576152B (en) | Water pump state monitoring system, monitoring method and device, electronic equipment and medium | |
| CN109405889A (en) | System and method for for the prediction of development machine working arm decelerator trouble | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN114036656A (en) | Fault diagnosis method and device for wind turbine generator gearbox | |
| CN112014094B (en) | Shield tunneling machine main driving performance monitoring and repairing method | |
| CN115270862A (en) | Fault detection method and device for plunger pump and electronic equipment | |
| CN116383750A (en) | Rolling bearing early-stage abnormality detection method based on windowed differential health index | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN115962100A (en) | Wind turbine generator system state monitoring system | |
| CN113516023A (en) | Equipment vibration abnormality diagnosis method and system | |
| CN103617350A (en) | Rotary mechanical equipment fault diagnosing method based on diagnosing evidence smooth updating | |
| CN117113172A (en) | Vibration analysis state index threshold value determining method, system, device and medium | |
| CN117825947A (en) | Driving motor fault detection method, driving motor fault detection device, computer equipment and storage medium | |
| CN116166938A (en) | Fault prediction and health management method for steering system | |
| Fu et al. | Development of the remote monitoring and warning system for operation condition of the main drainage pump in mine |
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 |