CN112857669B - Fault detection method, device and equipment of pressure sensor and storage medium - Google Patents
Fault detection method, device and equipment of pressure sensor and storage medium Download PDFInfo
- Publication number
- CN112857669B CN112857669B CN202110344469.7A CN202110344469A CN112857669B CN 112857669 B CN112857669 B CN 112857669B CN 202110344469 A CN202110344469 A CN 202110344469A CN 112857669 B CN112857669 B CN 112857669B
- Authority
- CN
- China
- Prior art keywords
- signal
- sensor
- target
- pressure sensor
- pressure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L25/00—Testing or calibrating of apparatus for measuring force, torque, work, mechanical power, or mechanical efficiency
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L27/00—Testing or calibrating of apparatus for measuring fluid pressure
- G01L27/007—Malfunction diagnosis, i.e. diagnosing a sensor defect
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Biomedical Technology (AREA)
- Measuring Fluid Pressure (AREA)
Abstract
The invention discloses a fault detection method, a fault detection device, fault detection equipment and a storage medium of a pressure sensor, and belongs to the technical field of sensors. The invention collects the sensor signal of the pressure sensor to be detected; preprocessing the sensor signal to obtain a target sensor signal; extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal; inputting the characteristic vector into a fault detection model, and acquiring a current pressure value output by the fault detection model; and fault detection is carried out on the pressure sensor to be detected according to the current pressure value, a characteristic vector is constructed through a sensor signal, then the fault of the pressure sensor is realized according to the pressure value output by the constructed fault detection model, and the fault detection accuracy of the pressure sensor is improved.
Description
Technical Field
The invention relates to the technical field of sensors, in particular to a method, a device, equipment and a storage medium for detecting faults of a pressure sensor.
Background
The pressure sensor is one of indispensable parts in all modern measurement and control devices as an important component of an automatic control and information system, and the acquired data can be used as an important reference for reference in many aspects such as subsequent data analysis, data processing, system operation and the like. The conventional pressure sensor fault detection is to regularly detect the pressure sensor in a manual mode, so that a large amount of manpower and material resources are wasted, and the efficiency is low. With the development of fault diagnosis technology, redundancy methods, data driving methods and the like are mostly adopted for the detection of a target on a pressure sensor, but the measurement processes of the methods are complicated, and the accuracy cannot be guaranteed.
The above is only for the purpose of assisting understanding of the technical solution of the present invention, and does not represent an admission that the above is the prior art.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for detecting faults of a pressure sensor, and aims to solve the technical problem that the pressure sensor in the prior art is inaccurate in detection.
In order to achieve the above object, the present invention provides a method, an apparatus, a device and a storage medium for detecting a failure of a pressure sensor, wherein the method for detecting a failure of a pressure sensor comprises the following steps:
collecting a sensor signal of a pressure sensor to be detected;
preprocessing the sensor signal to obtain a target sensor signal;
extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal;
inputting the characteristic vector into a fault detection model, and acquiring a current pressure value output by the fault detection model;
and carrying out fault detection on the pressure sensor to be detected according to the current pressure value.
Optionally, the preprocessing the sensor signal to obtain a target sensor signal includes:
acquiring a plurality of sensor signals according to a signal sampling window;
acquiring signal values corresponding to the signals of the sensors;
determining a target signal value from the signal value;
replacing the signal value corresponding to the first sensor signal in the signal sampling window with the target signal value;
and moving the signal sampling window according to the signal arrangement sequence corresponding to the sensor signals to finish the signal value replacement of each sensor signal so as to obtain the target sensor signal.
Optionally, before acquiring the plurality of sensor signals according to the signal sampling window, the method further includes:
acquiring the number of signals corresponding to the sensor signals;
determining the corresponding signal width according to the signal quantity;
determining the window size corresponding to the signal sampling window according to the signal width;
and setting a corresponding signal sampling window for the sensor signal according to the window size.
Optionally, the extracting, from the target sensor signal, a feature vector corresponding to the pressure sensor to be detected includes:
performing multi-scale decomposition on the target sensor signal to obtain sub-target sensor signals of a plurality of different frequency bands;
and reconstructing sub-target sensor signals in different frequency bands, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
Optionally, the reconstructing the sub-target sensor signals in each of the different frequency bands, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals includes:
acquiring the signal quantity of sub-target sensor signals in each frequency band;
respectively setting corresponding signal processing windows for the sub-target sensor signals in each frequency band according to the number of the signals;
and reconstructing sub-target sensor signals in each signal processing window, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
Optionally, the performing fault detection on the pressure sensor to be detected according to the current pressure value includes:
acquiring a target pressure value corresponding to the pressure sensor to be detected in normal operation;
acquiring a pressure difference value between the current pressure value and the target pressure value;
when the pressure difference value is smaller than or equal to a preset difference value threshold value, judging that the pressure sensor to be detected operates normally;
and when the pressure difference value is larger than the preset difference value threshold value, judging that the pressure sensor to be detected has an operation fault.
Optionally, after the fault detection is performed on the pressure sensor to be detected according to the current pressure value, the method further includes:
when the pressure sensor to be detected has operation faults, acquiring a signal identifier corresponding to a current sensor signal and a sensor fault index;
determining the corresponding sensor type according to the signal identification;
determining a corresponding fault type according to the sensor fault index;
and outputting and storing the sensor type and the corresponding fault type as fault information.
In order to achieve the above object, the present invention also provides a failure detection device for a pressure sensor, including:
the acquisition module is used for acquiring sensor signals of the pressure sensor to be detected;
the processing module is used for preprocessing the sensor signal to obtain a target sensor signal;
the extraction module is used for extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal;
the input module is used for inputting the characteristic vector into a fault detection model and acquiring a current pressure value output by the fault detection model;
and the detection module is used for carrying out fault detection on the pressure sensor to be detected according to the current pressure value.
Further, in order to achieve the above object, the present invention also proposes a failure detection apparatus of a pressure sensor, comprising: a memory, a processor and a fault detection program of a pressure sensor stored on said memory and operable on said processor, said fault detection program of a pressure sensor being configured to implement the steps of the fault detection method of a pressure sensor as described above.
Further, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a failure detection program of a pressure sensor, which when executed by a processor, implements the steps of the failure detection method of a pressure sensor as described above.
The invention collects the sensor signal of the pressure sensor to be detected; preprocessing the sensor signal to obtain a target sensor signal; extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal; inputting the characteristic vector into a fault detection model, and acquiring a current pressure value output by the fault detection model; and fault detection is carried out on the pressure sensor to be detected according to the current pressure value, a characteristic vector is constructed through a sensor signal, then the fault of the pressure sensor is realized according to the pressure value output by the constructed fault detection model, and the fault detection accuracy of the pressure sensor is improved.
Drawings
Fig. 1 is a schematic structural diagram of a fault detection device of a pressure sensor in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a method for detecting a failure of a pressure sensor in accordance with the present invention;
FIG. 3 is a schematic flow chart diagram of a second embodiment of a method for detecting a failure of a pressure sensor in accordance with the present invention;
FIG. 4 is a schematic flow chart diagram of a third embodiment of a method for detecting a failure of a pressure sensor in accordance with the present invention;
fig. 5 is a block diagram showing the configuration of a first embodiment of the failure detection device of the pressure sensor of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a fault detection device of a pressure sensor in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the failure detection apparatus of the pressure sensor may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the failure detection device of the pressure sensor, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a failure detection program of a pressure sensor.
In the failure detection device of the pressure sensor shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the failure detection device of the pressure sensor of the present invention may be provided in the failure detection device of the pressure sensor, which calls the failure detection program of the pressure sensor stored in the memory 1005 through the processor 1001 and executes the failure detection method of the pressure sensor provided by the embodiment of the present invention.
An embodiment of the present invention provides a method for detecting a fault of a pressure sensor, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the method for detecting a fault of a pressure sensor according to the present invention.
In this embodiment, the method for detecting a fault of a pressure sensor includes the following steps:
step S10: and acquiring a sensor signal of the pressure sensor to be detected.
It should be noted that the execution subject in this embodiment may be a fault detection device, and may also be other devices having the same or similar functions. In this embodiment, the fault detection device may collect a sensor signal of the pressure sensor, analyze the collected sensor signal, and determine whether the pressure sensor is in a normal operation state or a fault state by analyzing the sensor signal, where a fault detection model is stored in the fault detection device of this embodiment, and the fault detection model is used to process data such as the sensor signal, so as to determine an operation state of the pressure sensor according to a data analysis processing result.
In specific implementation, the fault detection device may trigger an operation of acquiring a sensor signal of the pressure sensor according to a detection instruction input by a user, or may set a preset time, and when the preset time is reached, the fault detection device automatically acquires the sensor signal of the pressure sensor, or may acquire the sensor signal of the pressure sensor in another manner, and may perform corresponding setting according to an actual situation, which is not limited in this embodiment. Further, it should be noted that, in this embodiment, signal transmission may be performed between the pressure sensor and the fault detection device through an optical fiber or in a wireless manner, where the wireless manner may adopt a communication Protocol such as IEEE 802.11, the optical fiber manner may adopt a communication Protocol such as an Internet fiber Channel Protocol (iFCP), and the specific communication manner and the corresponding communication Protocol may be set according to actual requirements, which is not limited in this embodiment.
Step S20: the sensor signal is preprocessed to obtain a target sensor signal.
It is easy to understand that, in the process of acquiring the sensor signal, due to accidental factors occurring in a system formed by the pressure sensor and the faulty equipment, there are usually some redundant signals and singular signals that do not conform to the random process rule, and these redundant signals and singular signals may have a large influence on fault detection of the pressure sensor.
Step S30: and extracting the characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal.
In a specific implementation, after a target sensor signal is obtained, a sensor parameter included in the target sensor signal is used as an eigenvalue of a matrix, and then a corresponding eigenvector is generated based on the eigenvalue, wherein the sensor parameter includes, but is not limited to, a rated load, a creep, a zero output, and a zero balance.
Step S40: and inputting the characteristic vector into a fault detection model, and acquiring a current pressure value output by the fault detection model.
It should be noted that, in this embodiment, the fault detection model is obtained by training according to historical operation information of the pressure sensor to be detected, the historical operation information is input into the neural network model as a training sample, the historical operation information is information when the pressure sensor to be detected normally operates, the neural network model may adopt a recurrent neural network model, a convolutional neural network model, a deep belief neural network model, and the like, selection of the training sample and the neural network model in this embodiment may be set according to an actual situation, which is not limited in this embodiment.
Step S50: and carrying out fault detection on the pressure sensor to be detected according to the current pressure value.
In a specific implementation, after obtaining the current pressure value, detecting whether the current pressure value is within a normal range, if so, determining that the pressure sensor to be detected has no operation fault, otherwise, determining that the pressure sensor to be detected operates normally, and specifically, step S50 specifically includes: acquiring a target pressure value corresponding to the pressure sensor to be detected in normal operation; acquiring a pressure difference value between the current pressure value and the target pressure value; when the pressure difference value is smaller than or equal to a preset difference threshold value, judging that the pressure sensor to be detected operates normally; and when the pressure difference value is larger than the preset difference value threshold value, judging that the pressure sensor to be detected has an operation fault.
It should be noted that the target pressure value is a pressure value when the pressure sensor to be detected normally operates, and the target pressure value of the pressure sensor to be detected can be obtained from historical information when the pressure sensor to be detected normally operates. Because the pressure value during detection has a certain error, in this embodiment, a preset difference threshold is set to detect whether the difference between the current pressure value and the target pressure value is too large, and it needs to be emphasized that the preset difference threshold in this embodiment is much smaller than the target pressure value, which is to detect a situation that the current pressure value is 0 due to a fault of the pressure sensor.
The embodiment collects the sensor signal of the pressure sensor to be detected; preprocessing the sensor signal to obtain a target sensor signal; extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal; inputting the characteristic vector into a fault detection model, and acquiring a current pressure value output by the fault detection model; and fault detection is carried out on the pressure sensor to be detected according to the current pressure value, a characteristic vector is constructed through a sensor signal, and then the fault of the pressure sensor is realized according to the pressure value output by the constructed fault detection model, so that the fault detection accuracy of the pressure sensor is improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a method for detecting a failure of a pressure sensor according to a second embodiment of the present invention.
Based on the first embodiment described above, the step S20 in the failure detection method of the pressure sensor of the present embodiment includes:
step S201: a number of sensor signals are acquired according to a signal sampling window.
It should be noted that the sensor signals are obtained in real time, and a corresponding sensor signal is obtained at each time, so that sensor signals of a plurality of different times and different frequency bands are collected.
It can be understood that, before acquiring a plurality of sensor signals, a signal sampling window is first established, and this embodiment further includes, before the step S201: acquiring the number of signals corresponding to the sensor signals; determining the corresponding signal width according to the signal quantity; determining the window size corresponding to the signal sampling window according to the signal width; and setting a corresponding signal sampling window for the sensor signal according to the window size.
It should be noted that too small a signal sampling window may increase the amount of calculation for signal processing, and decrease the detection efficiency, while too large a signal sampling window may decrease the detection accuracy, in this embodiment, the size of the signal sampling window is determined according to the number of sensor signals, for example, the acquired sensor signals are [ Q, W, E, R ], and the signal width may be 4, so that the window size may be determined to be 2, and if the acquired sensor signals are [ a, S, D, F, G, H ], the signal width may be 6, and thus the window size may be determined to be 4.
Step S202: and acquiring signal values corresponding to the sensor signals.
Step S203: a target signal value is determined from the signal value.
In a specific implementation, the acquired signal values are signal values corresponding to the sensor signals in the signal sampling window, in this embodiment, the target signal value may be determined according to the signal values corresponding to the sensor signals, specifically, the target signal value is determined by taking a median of the signal values, that is, the target signal value is a median of the signal values, for example, the signal value acquired through the signal sampling window is [20, 30, 60, 70, 70, 70], and then the target signal value may be determined to be 70.
Step S204: replacing the signal value corresponding to the first sensor signal in the signal sampling window with the target signal value.
In a specific implementation, after obtaining the target signal value, the signal value corresponding to the first sensor signal in the signal sampling window is replaced with the target signal value, for example, if the sensor signal obtained through the signal sampling window is [ X, Y, Z ], and the obtained target signal value is 80, the signal value of the first sensor signal X in the signal sampling window is replaced with 80.
Step S205: and moving the signal sampling window according to the signal arrangement sequence corresponding to the sensor signals to finish the signal value replacement of each sensor signal so as to obtain the target sensor signal.
It should be noted that the acquired sensor numbers have a corresponding arrangement order, for example, a time order, and after the signal value of the first sensor signal is replaced, the signal value of the second sensor signal acquired may be replaced according to the time order in the above manner, and after the signal values of all the sensor signals are replaced, the target sensor signal may be obtained.
Further, the step S30 further includes: carrying out multi-scale decomposition on the target sensor signal to obtain a plurality of sub-target sensor signals of different frequency bands; and reconstructing sub-target sensor signals in different frequency bands, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
It should be noted that, the acquired sensor signals have different frequency bands, and the target sensor signal may be divided according to different frequency bands to obtain sub-target sensor signals of multiple frequency bands, in this embodiment, an average value of the sub-target sensor signals in each frequency band is calculated to complete reconstruction of the sub-target sensor signals in each frequency band, and finally, a feature vector is generated according to parameters such as a rated load, a creep, a zero output, a zero balance, and the like in the sub-target sensor signals. Further, the step of reconstructing the sub-target sensor signals in each of the different frequency bands and generating the corresponding eigenvectors according to the reconstructed sub-target sensor signals specifically includes: acquiring the signal quantity of sub-target sensor signals in each frequency band; respectively setting corresponding signal processing windows for the sub-target sensor signals in each frequency band according to the number of the signals; and reconstructing sub-target sensor signals in each signal processing window, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
It should be noted that, in this embodiment, signal processing windows are respectively established for sub-target sensor signals of each frequency band, and the window size corresponding to each processing window is determined according to the number of sub-target sensor signals in the corresponding frequency band, for example, F 1 The number of sub-target sensors in a frequency band is 3, which can be at F 1 The window size of the signal processing window set by the frequency band is 2, and the reconstruction is to calculate the average value of the parameter values corresponding to the signal parameters in the frequency band.
In the embodiment, a plurality of sensor signals are acquired according to a signal sampling window; acquiring signal values corresponding to the signals of the sensors; determining a target signal value from the signal value; replacing a signal value corresponding to a first sensor signal in the signal sampling window with the target signal value; the signal sampling windows are moved according to the signal arrangement sequence corresponding to the sensor signals to complete signal value replacement of each sensor signal to obtain a target sensor signal, the signal sampling windows are used for sequentially replacing the signal values of the sensor signals, redundant signals and singular signals in the acquired sensor signals can be effectively removed, and meanwhile the target sensor signals are subjected to multi-scale decomposition to obtain a plurality of sub-target sensor signals of different frequency bands; and reconstructing sub-target sensor signals in different frequency bands, generating corresponding eigenvectors according to the reconstructed sub-target sensor signals, and decomposing and reconstructing the target sensor signals to improve the accuracy of the fault detection of the pressure sensor.
Referring to fig. 4, fig. 4 is a schematic flow chart of a method for detecting a failure of a pressure sensor according to a third embodiment of the present invention.
A third embodiment of a failure detection method of a pressure sensor of the present invention is proposed based on the first embodiment or the second embodiment described above.
Taking the first embodiment as an example for explanation, the step S50 in this embodiment further includes:
step S60: and when the pressure sensor to be detected has operation faults, acquiring a signal identifier corresponding to a current sensor signal and a sensor fault index.
In a specific implementation, when detecting that the pressure sensor has an operation failure, corresponding signal identifications, such as ID1, ID2, ID3, and the like, are extracted from the sensor signal with the sensor failure, and sensor failure indexes, such as 1.0, 2.0, 3.0, and the like, are also extracted from the sensor signal with the sensor failure.
Step S70: and determining the corresponding sensor type according to the signal identification.
Step S80: and determining the corresponding fault type according to the sensor fault index.
It should be noted that the identifiers of the sensor signals sent by different sensors are different, and the type of the corresponding sensor can be obtained according to the different sensor identifiers, for example, the type of the corresponding sensor can be determined to be the pressure sensor P according to the sensor identifier ID1 1 According toThe sensor identification ID2 may determine that the corresponding sensor type is a pressure sensor P 2 . Further, a specific fault type can be determined according to the sensor fault index, for example, the corresponding fault type is determined to be a hard fault according to the sensor fault index 1.0, and the corresponding fault type is determined to be a soft fault according to the sensor fault index 2.0.
Step S90: and outputting and storing the sensor type and the corresponding fault type as fault information.
In specific implementation, the detected sensor type and the corresponding fault type are used as fault information, and meanwhile, the fault information is output and stored in order to facilitate user management.
In the embodiment, when the pressure sensor to be detected has an operation fault, a signal identifier corresponding to a current sensor signal and a sensor fault index are obtained; determining the corresponding sensor type according to the signal identification; determining a corresponding fault type according to the sensor fault index; and outputting and storing the sensor type and the corresponding fault type as fault information, so that a user can conveniently identify the fault type of the pressure sensor and quickly position the pressure sensor with the operation fault.
Furthermore, an embodiment of the present invention further provides a storage medium, where a failure detection program of a pressure sensor is stored, and the failure detection program of the pressure sensor is executed by a processor to implement the steps of the failure detection method of the pressure sensor as described above.
Referring to fig. 5, fig. 5 is a block diagram showing a configuration of a failure detection device of a pressure sensor according to a first embodiment of the present invention.
As shown in fig. 5, a failure detection apparatus for a pressure sensor according to an embodiment of the present invention includes:
and the acquisition module 10 is used for acquiring sensor signals of the pressure sensor to be detected.
A processing module 20, configured to pre-process the sensor signal to obtain a target sensor signal.
And the extraction module 30 is configured to extract a feature vector corresponding to the pressure sensor to be detected from the target sensor signal.
And the input module 40 is configured to input the feature vector into a fault detection model, and acquire a current pressure value output by the fault detection model.
And the detection module 50 is used for carrying out fault detection on the pressure sensor to be detected according to the current pressure value.
The embodiment collects the sensor signal of the pressure sensor to be detected; preprocessing the sensor signal to obtain a target sensor signal; extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal; inputting the characteristic vector into a fault detection model, and acquiring a current pressure value output by the fault detection model; and fault detection is carried out on the pressure sensor to be detected according to the current pressure value, a characteristic vector is constructed through a sensor signal, and then the fault of the pressure sensor is realized according to the pressure value output by the constructed fault detection model, so that the fault detection accuracy of the pressure sensor is improved.
In an embodiment, the processing module 20 is further configured to obtain a plurality of sensor signals according to a signal sampling window; acquiring signal values corresponding to the signals of the sensors; determining a target signal value from the signal value; replacing the signal value corresponding to the first sensor signal in the signal sampling window with the target signal value; and moving the signal sampling window according to the signal arrangement sequence corresponding to the sensor signals to finish the signal value replacement of each sensor signal to obtain a target sensor signal.
In an embodiment, the processing module 20 is further configured to obtain a signal quantity corresponding to the sensor signal; determining a corresponding signal width according to the signal quantity; determining the window size corresponding to the signal sampling window according to the signal width; and setting a corresponding signal sampling window for the sensor signal according to the window size.
In an embodiment, the extracting module 30 is further configured to perform multi-scale decomposition on the target sensor signal to obtain sub-target sensor signals of a plurality of different frequency bands; and reconstructing sub-target sensor signals in different frequency bands, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
In an embodiment, the extracting module 30 is further configured to obtain the number of sub-target sensor signals in each frequency band; respectively setting corresponding signal processing windows for the sub-target sensor signals in each frequency band according to the number of the signals; and reconstructing sub-target sensor signals in each signal processing window, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
In an embodiment, the detecting module 50 is further configured to obtain a target pressure value corresponding to the pressure sensor to be detected in normal operation; acquiring a pressure difference value between the current pressure value and the target pressure value; when the pressure difference value is smaller than or equal to a preset difference value threshold value, judging that the pressure sensor to be detected operates normally; and when the pressure difference value is larger than the preset difference value threshold value, judging that the pressure sensor to be detected has an operation fault.
In one embodiment, the failure detection device of the pressure sensor further includes: an output module;
the output module is further used for acquiring a signal identifier corresponding to a current sensor signal and a sensor fault index when the pressure sensor to be detected has an operation fault; determining a corresponding sensor type according to the signal identification; determining a corresponding fault type according to the sensor fault index; and outputting and storing the sensor type and the corresponding fault type as fault information.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not elaborated in this embodiment may refer to the method for detecting a failure of a pressure sensor provided in any embodiment of the present invention, and are not described herein again.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A method of detecting a failure of a pressure sensor, comprising:
collecting a sensor signal of a pressure sensor to be detected;
preprocessing the sensor signal to obtain a target sensor signal;
extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal;
inputting the characteristic vector into a fault detection model, and acquiring a current pressure value output by the fault detection model;
carrying out fault detection on the pressure sensor to be detected according to the current pressure value;
the pre-processing the sensor signal to obtain a target sensor signal comprises:
acquiring a plurality of sensor signals according to a signal sampling window;
acquiring signal values corresponding to the signals of the sensors;
determining a target signal value from the signal value;
replacing the signal value corresponding to the first sensor signal in the signal sampling window with the target signal value;
and moving the signal sampling window according to the signal arrangement sequence corresponding to the sensor signals to finish the signal value replacement of each sensor signal to obtain a target sensor signal.
2. The method of pressure sensor fault detection according to claim 1, wherein prior to acquiring a plurality of sensor signals according to a signal sampling window, further comprising:
acquiring the number of signals corresponding to the sensor signals;
determining the corresponding signal width according to the signal quantity;
determining the window size corresponding to the signal sampling window according to the signal width;
and setting a corresponding signal sampling window for the sensor signal according to the window size.
3. The method for detecting the failure of the pressure sensor according to claim 1, wherein the extracting the feature vector corresponding to the pressure sensor to be detected from the target sensor signal comprises:
performing multi-scale decomposition on the target sensor signal to obtain sub-target sensor signals of a plurality of different frequency bands;
and reconstructing sub-target sensor signals in different frequency bands, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
4. The method for detecting a fault in a pressure sensor according to claim 3, wherein the reconstructing sub-target sensor signals in each of the different frequency bands and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals comprises:
acquiring the signal quantity of sub-target sensor signals in each frequency band;
respectively setting corresponding signal processing windows for the sub-target sensor signals in each frequency band according to the number of the signals;
and reconstructing sub-target sensor signals in each signal processing window, and generating corresponding eigenvectors according to the reconstructed sub-target sensor signals.
5. The method for detecting a failure of a pressure sensor according to claim 1, wherein said detecting a failure of the pressure sensor to be detected based on the current pressure value comprises:
acquiring a target pressure value corresponding to the pressure sensor to be detected in normal operation;
acquiring a pressure difference value between the current pressure value and the target pressure value;
when the pressure difference value is smaller than or equal to a preset difference value threshold value, judging that the pressure sensor to be detected operates normally;
and when the pressure difference value is larger than the preset difference value threshold value, judging that the pressure sensor to be detected has an operation fault.
6. The method for detecting a failure of a pressure sensor according to any one of claims 1 to 5, wherein after the detecting a failure of the pressure sensor to be detected based on the current pressure value, the method further comprises:
when the pressure sensor to be detected has operation faults, acquiring a signal identifier corresponding to a current sensor signal and a sensor fault index;
determining the corresponding sensor type according to the signal identification;
determining a corresponding fault type according to the sensor fault index;
and outputting and storing the sensor type and the corresponding fault type as fault information.
7. A failure detection device of a pressure sensor, characterized by comprising:
the acquisition module is used for acquiring sensor signals of the pressure sensor to be detected;
the processing module is used for preprocessing the sensor signal to obtain a target sensor signal;
the extraction module is used for extracting a characteristic vector corresponding to the pressure sensor to be detected from the target sensor signal;
the input module is used for inputting the characteristic vector into a fault detection model and acquiring a current pressure value output by the fault detection model;
the detection module is used for carrying out fault detection on the pressure sensor to be detected according to the current pressure value;
the processing module is also used for acquiring a plurality of sensor signals according to the signal sampling window; acquiring signal values corresponding to the signals of the sensors; determining a target signal value from the signal value; replacing the signal value corresponding to the first sensor signal in the signal sampling window with the target signal value; and moving the signal sampling window according to the signal arrangement sequence corresponding to the sensor signals to finish the signal value replacement of each sensor signal so as to obtain the target sensor signal.
8. A failure detection device of a pressure sensor, characterized by comprising: memory, a processor and a fault detection program of a pressure sensor stored on the memory and executable on the processor, the fault detection program of a pressure sensor being configured to implement the steps of the fault detection method of a pressure sensor according to any of claims 1 to 6.
9. A storage medium, characterized in that a failure detection program of a pressure sensor is stored thereon, which when executed by a processor implements the steps of the failure detection method of a pressure sensor according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110344469.7A CN112857669B (en) | 2021-03-30 | 2021-03-30 | Fault detection method, device and equipment of pressure sensor and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110344469.7A CN112857669B (en) | 2021-03-30 | 2021-03-30 | Fault detection method, device and equipment of pressure sensor and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112857669A CN112857669A (en) | 2021-05-28 |
| CN112857669B true CN112857669B (en) | 2022-12-06 |
Family
ID=75991813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110344469.7A Active CN112857669B (en) | 2021-03-30 | 2021-03-30 | Fault detection method, device and equipment of pressure sensor and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112857669B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255546B (en) * | 2021-06-03 | 2021-11-09 | 成都卡莱博尔信息技术股份有限公司 | Diagnosis method for aircraft system sensor fault |
| CN113252699B (en) * | 2021-06-28 | 2021-11-30 | 武汉飞恩微电子有限公司 | Fault diagnosis method, device and equipment for pressure sensor and storage medium |
| CN114264315B (en) * | 2021-11-24 | 2024-05-24 | 青岛迈金智能科技股份有限公司 | Parking judgment method based on barometer meter |
| CN113899393B (en) * | 2021-11-29 | 2024-03-19 | 武汉飞恩微电子有限公司 | Detection method, device, equipment and medium of MEMS sensor based on neural network |
| CN114295283B (en) * | 2021-12-13 | 2024-08-09 | 深圳数联天下智能科技有限公司 | Piezoelectric sensor fault detection method, device, equipment and medium |
| CN114944151A (en) * | 2022-05-12 | 2022-08-26 | 安徽理工大学 | Tunnel wall drilling robot fault detection method based on audio |
| CN116878728B (en) * | 2023-07-14 | 2024-02-27 | 浙江中电自控科技有限公司 | Pressure sensor fault detection analysis processing system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6598195B1 (en) * | 2000-08-21 | 2003-07-22 | General Electric Company | Sensor fault detection, isolation and accommodation |
| CN105094118A (en) * | 2015-08-12 | 2015-11-25 | 中国人民解放军空军勤务学院 | Airplane engine air compressor stall detection method |
| CN106447040A (en) * | 2016-09-30 | 2017-02-22 | 湖南科技大学 | Method for evaluating the health state of mechanical equipment based on heterogeneous multi-sensor data fusion |
| CN109997025A (en) * | 2016-11-29 | 2019-07-09 | Sts国防有限公司 | Engine Gernral Check-up device and method |
| CN110261109A (en) * | 2019-04-28 | 2019-09-20 | 洛阳中科晶上智能装备科技有限公司 | A kind of Fault Diagnosis of Roller Bearings based on bidirectional memory Recognition with Recurrent Neural Network |
| CN111982194A (en) * | 2020-08-18 | 2020-11-24 | 成都一通密封股份有限公司 | Wireless pressure and temperature integrated sensor |
| CN112232948A (en) * | 2020-11-02 | 2021-01-15 | 广东工业大学 | Method and device for detecting abnormality of flow data |
-
2021
- 2021-03-30 CN CN202110344469.7A patent/CN112857669B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6598195B1 (en) * | 2000-08-21 | 2003-07-22 | General Electric Company | Sensor fault detection, isolation and accommodation |
| CN105094118A (en) * | 2015-08-12 | 2015-11-25 | 中国人民解放军空军勤务学院 | Airplane engine air compressor stall detection method |
| CN106447040A (en) * | 2016-09-30 | 2017-02-22 | 湖南科技大学 | Method for evaluating the health state of mechanical equipment based on heterogeneous multi-sensor data fusion |
| CN109997025A (en) * | 2016-11-29 | 2019-07-09 | Sts国防有限公司 | Engine Gernral Check-up device and method |
| CN110261109A (en) * | 2019-04-28 | 2019-09-20 | 洛阳中科晶上智能装备科技有限公司 | A kind of Fault Diagnosis of Roller Bearings based on bidirectional memory Recognition with Recurrent Neural Network |
| CN111982194A (en) * | 2020-08-18 | 2020-11-24 | 成都一通密封股份有限公司 | Wireless pressure and temperature integrated sensor |
| CN112232948A (en) * | 2020-11-02 | 2021-01-15 | 广东工业大学 | Method and device for detecting abnormality of flow data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112857669A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112857669B (en) | Fault detection method, device and equipment of pressure sensor and storage medium | |
| US20190333296A1 (en) | Vehicle diagnostic method and device, and computer readable storage medium | |
| CN110141220B (en) | Myocardial infarction automatic detection system based on multi-mode fusion neural network | |
| CN109086876B (en) | Method and device for detecting running state of equipment, computer equipment and storage medium | |
| CN111008643B (en) | Picture classification method and device based on semi-supervised learning and computer equipment | |
| CN116520068B (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
| CN115576293B (en) | Pressure-sensitive adhesive on-line production analysis method and system based on data monitoring | |
| CN116304909A (en) | Abnormality detection model training method, fault scene positioning method and device | |
| CN111459796A (en) | Automatic testing method and device, computer equipment and storage medium | |
| CN110232130B (en) | Metadata management pedigree generation method, apparatus, computer device and storage medium | |
| CN112991343A (en) | Method, device and equipment for identifying and detecting macular region of fundus image | |
| CN115184674A (en) | Insulation test method and device, electronic terminal and storage medium | |
| CN111124816B (en) | HDP algorithm-based server log analysis method and system | |
| CN117171547A (en) | Fault diagnosis method, device, equipment and storage medium based on large model | |
| CN109086186A (en) | log detection method and device | |
| CN115588439B (en) | Fault detection method and device of voiceprint acquisition device based on deep learning | |
| CN111738259A (en) | Tower state detection method and device | |
| CN112242929B (en) | Log detection method and device | |
| CN116956853A (en) | Method and device for acquiring configuration template and electronic equipment | |
| CN111626313A (en) | Feature extraction model training method, image processing method and device | |
| CN114021759A (en) | Method for managing digital factory equipment based on AIOT and MR technology | |
| CN113392739B (en) | Rolling bearing state monitoring method, device, equipment and storage medium | |
| CN117349189B (en) | APP new version testing method, equipment and medium | |
| CN116183010B (en) | Fault diagnosis method, device and equipment for dynamic weighing sensor and storage medium | |
| US10534344B2 (en) | Operation management system and measurement system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |