CN110553789A - state detection method and device of piezoresistive pressure sensor and brake system - Google Patents
state detection method and device of piezoresistive pressure sensor and brake system Download PDFInfo
- Publication number
- CN110553789A CN110553789A CN201910870746.0A CN201910870746A CN110553789A CN 110553789 A CN110553789 A CN 110553789A CN 201910870746 A CN201910870746 A CN 201910870746A CN 110553789 A CN110553789 A CN 110553789A
- Authority
- CN
- China
- Prior art keywords
- current data
- pressure sensor
- piezoresistive pressure
- characteristic
- state
- 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
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measuring Fluid Pressure (AREA)
Abstract
The invention discloses a method and a device for detecting the state of a piezoresistive pressure sensor and a braking system, wherein the method is used for obtaining target current data of the piezoresistive pressure sensor in a diagnosis time period; determining characteristic current data which is different from normal current data in the target current data; then judging whether the characteristic current data meet a preset open circuit condition or not; if the characteristic current data are determined to meet the preset open-circuit condition, obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open circuit or open circuit state; and if the characteristic current data are determined not to meet the preset open-circuit condition, analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy. Therefore, the detection of the state of the piezoresistive pressure sensor can be achieved.
Description
Technical Field
The invention relates to the technical field of urban rail train control, in particular to a method and a device for detecting the state of a piezoresistive pressure sensor and a braking system.
background
The operation safety of urban rail trains is an important problem faced by rail transit. In an urban rail train, a braking system is very important for safe and reliable operation of the urban rail train.
Pressure sensors are important components of brake systems. At present, a piezoresistive diffused silicon pressure sensor, namely a piezoresistive pressure sensor, is mainly adopted as a pressure sensor in a braking system. The state of the piezoresistive pressure sensor is important for the braking system.
In the prior art, a related method for detecting the state of the piezoresistive pressure sensor is lacked, so that a subsequent control system cannot obtain effective sensor state information.
therefore, a method for detecting the state of the piezoresistive pressure sensor is needed to effectively detect the state of the piezoresistive pressure sensor and provide effective sensor state information for a control system.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for detecting a state of a piezoresistive pressure sensor, and a braking system, so as to solve the technical problem in the prior art that effective sensor information is not provided for a control system.
In order to achieve the purpose, the invention provides the following technical scheme:
The invention discloses a state detection method of a piezoresistive pressure sensor, which comprises the following steps:
Obtaining target current data of the piezoresistive pressure sensor in a diagnosis time period;
determining characteristic current data which is different from normal current data in the target current data;
judging whether the characteristic current data meet a preset open circuit condition or not;
if the characteristic current data are determined to meet the preset open-circuit condition, obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open circuit or open circuit state;
and if the characteristic current data are determined not to meet the preset open-circuit condition, analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy.
optionally, the obtaining target current data of the piezoresistive pressure sensor in the diagnosis time period includes:
obtaining a current signal of the piezoresistive pressure sensor during working through a microcomputer analog board connected with the piezoresistive pressure sensor;
the current signal within the diagnostic period is converted to target current data.
Optionally, the determining the characteristic current data different from the normal current data in the target current data includes:
storing the target current data to a new current measurement database;
Comparing the newly measured current database with a historical current database, wherein normal current data corresponding to the piezoresistive pressure sensor in a normal state are stored in the historical current database;
determining difference data in the new measured current database and the historical current database;
And taking the difference data as characteristic current data.
optionally, the determining whether the characteristic current data meets a preset open-circuit condition includes:
judging whether the characteristic current data comprises a specific numerical value, wherein the specific numerical value represents a numerical value corresponding to a current signal of the piezoresistive pressure sensor in an open circuit or a disconnected state;
if the specific numerical value is included, determining that the characteristic current data meets a preset open circuit condition;
otherwise, determining that the characteristic current data does not accord with a preset open circuit condition.
Optionally, analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for characterizing a fault state of the piezoresistive pressure sensor includes:
Performing time domain analysis on the characteristic current data to obtain time domain analysis parameters;
carrying out waveform analysis on the characteristic current data to obtain waveform analysis parameters;
extracting key features from the feature current data to obtain key feature parameters;
Taking the time domain analysis parameters, the waveform analysis parameters and the key characteristic parameters as input parameters of the fault diagnosis model to obtain a fault type output by the fault diagnosis model;
And taking the fault type as a second diagnosis result.
optionally, the analyzing the characteristic current data by using a preset fault diagnosis model to obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy includes:
performing time domain analysis on the characteristic current data to obtain time domain analysis parameters;
Carrying out waveform analysis on the characteristic current data to obtain waveform analysis parameters;
extracting key features from the feature current data to obtain key feature parameters;
performing cluster analysis on the time domain analysis parameters, the waveform analysis parameters and the key characteristic parameters to obtain a relatively homogeneous group represented by the health state of the piezoresistive pressure sensor;
Performing statistical analysis on the group to obtain a cluster analysis result of whether the piezoresistive pressure sensor is in a healthy state;
and taking the cluster analysis result as a third diagnosis result.
Optionally, the fault diagnosis model is obtained by training fault current data of the piezoresistive pressure sensor during a fault and a fault type corresponding to the fault current data.
In another aspect, the present invention discloses a state detection device for a piezoresistive pressure sensor, comprising:
obtaining means for obtaining target current data of the piezoresistive pressure sensor over a diagnostic period;
Determining means for determining characteristic current data which is different from normal current data in the target current data;
the judging device is used for judging whether the characteristic current data meet the preset open circuit condition or not;
the first detection device is used for obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open circuit or disconnected state if the characteristic current data are determined to meet the preset open circuit condition;
And the second detection device is used for analyzing the characteristic current data by using a preset fault diagnosis model if the characteristic current data is determined not to meet the preset open-circuit condition, so as to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy.
optionally, the obtaining device specifically includes:
The acquisition unit is used for acquiring a current signal of the piezoresistive pressure sensor during working through a microcomputer analog board connected with the piezoresistive pressure sensor;
and the conversion unit is used for converting the current signal in the diagnosis time period into target current data.
optionally, the determining means includes:
the storage unit is used for storing the target current data into a new measured current database;
the comparison unit is used for comparing the newly measured current database with a historical current database, and normal current data corresponding to the piezoresistive pressure sensor in a normal state are stored in the historical current database;
The calculation unit is used for determining difference data in the new current measurement database and the historical current database;
and the output unit is used for taking the difference data as characteristic current data.
optionally, the determining device includes:
The judging unit is used for judging whether the characteristic current data comprises a specific numerical value, and the specific numerical value represents a numerical value corresponding to a current signal of the piezoresistive pressure sensor in an open circuit or a disconnected state;
The first determining unit is used for determining that the characteristic current data meet a preset open circuit condition if the specific numerical value is included;
And the second determining unit is used for determining that the characteristic current data does not meet the preset open circuit condition if the specific numerical value is not included.
the invention also discloses an urban rail train braking system which comprises a braking device, a piezoresistive pressure sensor and a diagnosis device connected with the piezoresistive pressure sensor, wherein the diagnosis device comprises a processor, and the processor is used for executing the state detection method.
according to the technical scheme, compared with the prior art, the invention discloses a state detection method, a state detection device and a brake system of a piezoresistive pressure sensor, wherein the method is used for obtaining target current data of the piezoresistive pressure sensor in a diagnosis time period; determining characteristic current data which is different from normal current data in the target current data; then judging whether the characteristic current data meet a preset open circuit condition or not; if the characteristic current data are determined to meet the preset open-circuit condition, obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open circuit or open circuit state; and if the characteristic current data are determined not to meet the preset open-circuit condition, analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy. Therefore, the detection of the state of the piezoresistive pressure sensor can be achieved.
drawings
in order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting a state of a piezoresistive pressure sensor according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a state detection device of a piezoresistive pressure sensor according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention is mainly applied to the technical field of urban rail trains, and particularly aims at the state detection of the piezoresistive pressure sensor in the braking system of the urban rail train.
Most of the detection of the brake system still stays in a 'timing maintenance' or 'after-repair' stage, the timing maintenance is likely to cause excessive maintenance, and the after-repair is obviously processed after an accident, so that the loss is large.
Therefore, the embodiment of the invention provides a method and a device for detecting the state of a piezoresistive pressure sensor and a braking system. By carrying out characteristic extraction and cluster analysis on the current data of the piezoresistive pressure sensor, detection results such as fault type, health state and the like can be obtained to provide effective basis for a control system, so that huge loss caused by excessive maintenance of the traditional 'regular maintenance' or 'after maintenance' is avoided.
the following describes embodiments of the present application in detail.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for detecting a state of a piezoresistive pressure sensor according to an embodiment of the present invention.
The invention provides a state detection method of a piezoresistive pressure sensor, which comprises the following steps:
S100, obtaining target current data of the piezoresistive pressure sensor in a diagnosis time period;
The obtaining target current data of the piezoresistive pressure sensor in a diagnosis time period comprises:
obtaining a current signal of the piezoresistive pressure sensor during working through a microcomputer analog board connected with the piezoresistive pressure sensor;
The current signal within the diagnostic period is converted to target current data.
In the embodiment of the invention, the piezoresistive pressure sensor is mainly used,
In the embodiment of the invention, the target current data is obtained firstly. The diagnosis time period is preset according to actual needs, and can be acquired in the whole course. The frequency of acquisition may be every 100 ms.
in practical use, the piezoresistive pressure sensor can collect a current signal of 4-20mA, and in the embodiment of the application, the current signal of the piezoresistive pressure sensor during operation can be obtained by data collection through a microcomputer analog panel, and is converted into target current data. The microcomputer simulation panel comprises a singlechip and can execute the processes of acquisition, conversion and the like.
S200, determining characteristic current data which are different from normal current data in the target current data;
in the embodiment of the invention, the normal current data refers to current data with a current range not exceeding 4-20mA, no mutation and no zero drift.
Normally, the current data should be characteristic of normal current data, and if there is an anomaly, it is considered that there may be some problem and further processing is required. Thus, these differential characteristic current data are determined.
S300, judging whether the characteristic current data meet a preset open circuit condition or not;
S400, if the characteristic current data are determined to meet the preset open-circuit condition, obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open-circuit or open-circuit state;
s500, if the characteristic current data are determined not to meet the preset open circuit condition, analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy.
specifically, the judging whether the characteristic current data meets a preset open circuit condition includes:
Judging whether the characteristic current data comprises a specific numerical value, wherein the specific numerical value represents a numerical value corresponding to a current signal of the piezoresistive pressure sensor in an open circuit or a disconnected state;
if the specific numerical value is included, determining that the characteristic current data meets a preset open circuit condition;
otherwise, determining that the characteristic current data does not accord with a preset open circuit condition.
in the embodiment of the invention, whether the characteristic current data meets the preset open circuit condition is judged. The preset open circuit condition is a condition for judging whether the piezoresistive pressure sensor is open circuit or not.
The preset open-circuit condition may be to determine whether a specific value, for example, 65535, is included in the characteristic current data. This is because when the current loop is opened or broken, the collected current signal becomes a specific value such as 65535 after being converted into the target current data. Based on this, it can be directly derived by analyzing the current loop that the piezoresistive pressure sensor is in a fault state.
in the embodiment of the invention, if the preset open-circuit condition is met, a first diagnosis result is obtained, and the first diagnosis result indicates that the current loop of the piezoresistive pressure sensor is in an open-circuit or open-circuit fault state.
in the embodiment of the invention, if the fault state is not in the open circuit or open fault state, the fault state or the health state specifically represented by the characteristic current data is further analyzed.
In the embodiment of the invention, the fault diagnosis model is obtained by training fault current data of the piezoresistive pressure sensor during fault and a fault type corresponding to the fault current data.
In practical use, the embodiment of the present invention performs analysis by using a preset fault diagnosis model, which is a model that has been subjected to machine learning in advance. The fault diagnosis model is a classification model constructed by using the current of the sensor in advance in the modes of time domain analysis, waveform analysis, key feature extraction and the like, wherein the method for constructing the classification model refers to the machine learning mode in the prior art, and is not repeated herein. As long as the attribute values of the samples are input, the corresponding categories may be output.
Therefore, in the embodiment of the invention, the state of the piezoresistive pressure sensor can be detected, the diagnosis result such as the first diagnosis information, the second diagnosis information or the third diagnosis information can be obtained, and a real-time and reliable data basis is provided for the control system.
In the foregoing embodiment, the obtaining of the target current data and the using of the normal current data are described, but in the embodiment of the present invention, the target current data and the normal current data are respectively stored in different databases.
In an embodiment of the present invention, the determining the characteristic current data, which is different from the normal current data, in the target current data includes:
storing the target current data to a new current measurement database;
comparing the newly measured current database with a historical current database, wherein normal current data corresponding to the piezoresistive pressure sensor in a normal state are stored in the historical current database;
determining difference data in the new measured current database and the historical current database;
and taking the difference data as characteristic current data.
In the embodiment of the invention, the obtained target current data is stored in a newly measured current database, and the historical current database stores normal current data.
therefore, the difference between the newly measured current database and the historical current database can be compared in real time, and the characteristic current data with the abnormality can be obtained.
the comparison may be performed according to preset comparison software, or may be performed according to query statements, or may be performed in real time, or may be performed according to a cycle.
Therefore, in the embodiment of the invention, the obtained target current data is stored in the newly-measured database, so that the data can be stored in real time.
In the embodiment of the invention, if faults such as circuit breaking and the like do not exist, a second diagnosis result of which fault exists and/or a third diagnosis result representing a health state can be determined. This process is described below.
The analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor comprises the following steps:
performing time domain analysis on the characteristic current data to obtain time domain analysis parameters;
Carrying out waveform analysis on the characteristic current data to obtain waveform analysis parameters;
Extracting key features from the feature current data to obtain key feature parameters;
taking the time domain analysis parameters, the waveform analysis parameters and the key characteristic parameters as input parameters of the fault diagnosis model to obtain a fault type output by the fault diagnosis model;
And taking the fault type as a second diagnosis result.
In the embodiment of the invention, a second diagnosis result can be obtained, and the second diagnosis result is used for representing a specific fault type. For example: if the sensor is a current type piezoresistive pressure sensor, the normal current range is 4-20mA, the normal current range of the voltage sensor is 0-5V, and if the normal current range exceeds the range, the sensor is considered to be abnormal.
in the embodiment of the invention, the processes of time domain analysis, waveform analysis, key feature extraction and the like are performed on the feature current data. The time domain analysis is used for testing a time domain signal of an output current when the piezoresistive pressure sensor is in a working state and analyzing whether a steady state value and a transient state value of the piezoresistive pressure sensor are normal or not. The time domain analysis parameters may include steady state parameters including whether current values and voltage values are within normal ranges, transient values including whether current values and voltage values are accidentally mutated, and the waveform analysis is to compare the measured current waveform with reference waveform characteristic parameters in a historical database, measure the similarity of the measured current waveform and the reference waveform characteristic parameters, and identify abnormal waveforms. The waveform analysis parameters may include the amplitude of the waveform, similarity to historical normal waveforms. The key characteristic parameters may include that the maximum amplitude of the standard waveform cannot be exceeded, and the similarity with the historical normal waveform cannot be lower than 95%.
And performing machine learning by taking the obtained time domain analysis parameters, the obtained waveform analysis parameters and the obtained key characteristic parameters as input parameters of a fault diagnosis model to obtain an output fault type. In this way, it is possible to specifically determine which type of fault the piezoresistive pressure sensor is in.
in addition, the embodiment of the invention can also obtain the health state of the piezoresistive pressure sensor. Specifically, the method comprises the following steps.
in an embodiment of the present invention, the analyzing the characteristic current data by using a preset fault diagnosis model to obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy includes:
performing time domain analysis on the characteristic current data to obtain time domain analysis parameters;
Carrying out waveform analysis on the characteristic current data to obtain waveform analysis parameters;
extracting key features from the feature current data to obtain key feature parameters;
performing cluster analysis on the time domain analysis parameters, the waveform analysis parameters and the key characteristic parameters to obtain a relatively homogeneous group represented by the health state of the piezoresistive pressure sensor;
Performing statistical analysis on the group to obtain a cluster analysis result of whether the piezoresistive pressure sensor is in a healthy state;
and taking the cluster analysis result as a third diagnosis result.
in the embodiment of the invention, the health state of the piezoresistive pressure sensor is obtained in a clustering analysis mode.
The time domain analysis parameters, the waveform analysis parameters and the key characteristic parameters are subjected to cluster analysis to obtain a relatively homogeneous group represented by the health state of the piezoresistive pressure sensor, wherein the relatively homogeneous group represented by the health state of the piezoresistive pressure sensor comprises that the current or voltage value acquired in real time is within a standard output range, no transient abnormal value occurs, and the similarity between the waveform and the waveform of a historical database is not lower than 95%.
the statistical analysis of the population can be performed by regression analysis and hypothesis testing.
therefore, the health state of the piezoresistive pressure sensor under the condition of small fluctuation can be obtained, and the result with reference value such as whether damage is likely to happen or not can be analyzed.
it can be seen that embodiments of the present invention may include the following advantages:
1) the fault diagnosis type of the piezoresistive pressure sensor can be analyzed by analyzing the current signals collected in real time of the piezoresistive pressure sensor, comparing historical current signal information and combining collected loop current analysis. And obtaining a first diagnosis result and a second diagnosis result.
2) and evaluating the health condition of the piezoresistive pressure sensor by establishing characteristic current data of the piezoresistive pressure sensor and adopting a clustering analysis method to obtain a third diagnosis result.
Therefore, the state of the piezoresistive pressure sensor can be obtained, and reliable information can be provided for other follow-up systems.
Corresponding to the embodiment, the embodiment of the invention also discloses a state monitoring device of the piezoresistive pressure sensor.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a state detection device of a piezoresistive pressure sensor according to an embodiment of the present invention.
The state detection device of the piezoresistive pressure sensor provided by the embodiment of the invention comprises:
An obtaining device 1 for obtaining target current data of the piezoresistive pressure sensor in a diagnosis time period;
The determining device 2 is used for determining characteristic current data which is different from the normal current data in the target current data;
the judging device 3 is used for judging whether the characteristic current data meet the preset open circuit condition or not;
the first detection device 4 is used for obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open circuit or disconnected state if the characteristic current data is determined to meet the preset open circuit condition;
And the second detection device 5 is configured to, if it is determined that the characteristic current data does not meet a preset open-circuit condition, analyze the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for representing what fault state the piezoresistive pressure sensor is in or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy.
optionally, the obtaining device specifically includes:
the acquisition unit is used for acquiring a current signal of the piezoresistive pressure sensor during working through a microcomputer analog board connected with the piezoresistive pressure sensor;
and the conversion unit is used for converting the current signal in the diagnosis time period into target current data.
optionally, the determining means includes:
the storage unit is used for storing the target current data into a new measured current database;
the comparison unit is used for comparing the newly measured current database with a historical current database, and normal current data corresponding to the piezoresistive pressure sensor in a normal state are stored in the historical current database;
the calculation unit is used for determining difference data in the new current measurement database and the historical current database;
and the output unit is used for taking the difference data as characteristic current data.
optionally, the determining device includes:
the judging unit is used for judging whether the characteristic current data comprises a specific numerical value, and the specific numerical value represents a numerical value corresponding to a current signal of the piezoresistive pressure sensor in an open circuit or a disconnected state;
the first determining unit is used for determining that the characteristic current data meet a preset open circuit condition if the specific numerical value is included;
and the second determining unit is used for determining that the characteristic current data does not meet the preset open circuit condition if the specific numerical value is not included.
it can be understood that, for the functions of each module unit in the state detection device of the piezoresistive pressure sensor provided in the embodiment of the present invention, reference may be made to each step of the state detection method of the piezoresistive pressure sensor in the foregoing embodiment, and specific function implementation is not described herein again.
In the embodiment of the invention, the state of the piezoresistive pressure sensor can be detected.
On the other hand, the invention also discloses an urban rail train braking system which comprises a braking device and a piezoresistive pressure sensor and is characterized by further comprising a diagnosis device connected with the piezoresistive pressure sensor, wherein the diagnosis device comprises a processor, and the processor is used for executing the state detection method.
in the embodiment of the present invention, a diagnostic device is added to the brake system, and a processor in the diagnostic device may implement all processes in the state detection method for the piezoresistive pressure sensor in the foregoing embodiment, which is not described herein again.
in the embodiment of the invention, the state of the piezoresistive pressure sensor can be detected.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
the circuits proposed by the present invention have been described above with reference to the accompanying drawings, and the above description of the embodiments is only intended to help understand the core idea of the present invention. For those skilled in the art, variations can be made in the specific embodiments and applications without departing from the spirit of the invention. In view of the above, the present disclosure should not be construed as limiting the invention.
the previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (12)
1. A method of detecting a state of a piezoresistive pressure sensor, comprising:
Obtaining target current data of the piezoresistive pressure sensor in a diagnosis time period;
determining characteristic current data which is different from normal current data in the target current data;
judging whether the characteristic current data meet a preset open circuit condition or not;
if the characteristic current data are determined to meet the preset open-circuit condition, obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open circuit or open circuit state;
And if the characteristic current data are determined not to meet the preset open-circuit condition, analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy.
2. The method of claim 1, wherein obtaining target current data for the piezoresistive pressure sensor over a diagnostic time period comprises:
obtaining a current signal of the piezoresistive pressure sensor during working through a microcomputer analog board connected with the piezoresistive pressure sensor;
the current signal within the diagnostic period is converted to target current data.
3. The method of claim 1, wherein the determining the characteristic current data of the target current data that differs from normal current data comprises:
Storing the target current data to a new current measurement database;
comparing the newly measured current database with a historical current database, wherein normal current data corresponding to the piezoresistive pressure sensor in a normal state are stored in the historical current database;
determining difference data in the new measured current database and the historical current database;
and taking the difference data as characteristic current data.
4. the method of claim 1, wherein the determining whether the characteristic current data meets a predetermined trip condition comprises:
Judging whether the characteristic current data comprises a specific numerical value, wherein the specific numerical value represents a numerical value corresponding to a current signal of the piezoresistive pressure sensor in an open circuit or a disconnected state;
If the specific numerical value is included, determining that the characteristic current data meets a preset open circuit condition;
Otherwise, determining that the characteristic current data does not accord with a preset open circuit condition.
5. the method according to any one of claims 1 to 4, wherein the analyzing the characteristic current data by using a preset fault diagnosis model to obtain a second diagnosis result for indicating a fault state of the piezoresistive pressure sensor comprises:
performing time domain analysis on the characteristic current data to obtain time domain analysis parameters;
Carrying out waveform analysis on the characteristic current data to obtain waveform analysis parameters;
Extracting key features from the feature current data to obtain key feature parameters;
taking the time domain analysis parameters, the waveform analysis parameters and the key characteristic parameters as input parameters of the fault diagnosis model to obtain a fault type output by the fault diagnosis model;
And taking the fault type as a second diagnosis result.
6. The method of any one of claims 1 to 4, wherein analyzing the characteristic current data using a preset fault diagnosis model to obtain a third diagnosis result for indicating whether the piezoresistive pressure sensor is healthy comprises:
performing time domain analysis on the characteristic current data to obtain time domain analysis parameters;
Carrying out waveform analysis on the characteristic current data to obtain waveform analysis parameters;
Extracting key features from the feature current data to obtain key feature parameters;
Performing cluster analysis on the time domain analysis parameters, the waveform analysis parameters and the key characteristic parameters to obtain a relatively homogeneous group represented by the health state of the piezoresistive pressure sensor;
Performing statistical analysis on the group to obtain a cluster analysis result of whether the piezoresistive pressure sensor is in a healthy state;
And taking the cluster analysis result as a third diagnosis result.
7. The method according to claim 1, wherein the fault diagnosis model is obtained by training fault current data of the piezoresistive pressure sensor during fault and a fault type corresponding to the fault current data.
8. a state detection device of a piezoresistive pressure sensor, comprising:
Obtaining means for obtaining target current data of the piezoresistive pressure sensor over a diagnostic period;
Determining means for determining characteristic current data which is different from normal current data in the target current data;
the judging device is used for judging whether the characteristic current data meet the preset open circuit condition or not;
The first detection device is used for obtaining a first diagnosis result representing that the piezoresistive pressure sensor is in an open circuit or disconnected state if the characteristic current data are determined to meet the preset open circuit condition;
and the second detection device is used for analyzing the characteristic current data by using a preset fault diagnosis model if the characteristic current data is determined not to meet the preset open-circuit condition, so as to obtain a second diagnosis result for representing the fault state of the piezoresistive pressure sensor or obtain a third diagnosis result for representing whether the piezoresistive pressure sensor is healthy.
9. The apparatus according to claim 8, wherein the obtaining means specifically comprises:
the acquisition unit is used for acquiring a current signal of the piezoresistive pressure sensor during working through a microcomputer analog board connected with the piezoresistive pressure sensor;
and the conversion unit is used for converting the current signal in the diagnosis time period into target current data.
10. the apparatus of claim 8, wherein the determining means comprises:
the storage unit is used for storing the target current data into a new measured current database;
the comparison unit is used for comparing the newly measured current database with a historical current database, and normal current data corresponding to the piezoresistive pressure sensor in a normal state are stored in the historical current database;
the calculation unit is used for determining difference data in the new current measurement database and the historical current database;
and the output unit is used for taking the difference data as characteristic current data.
11. the apparatus according to claim 8, wherein the judging means comprises:
the judging unit is used for judging whether the characteristic current data comprises a specific numerical value, and the specific numerical value represents a numerical value corresponding to a current signal of the piezoresistive pressure sensor in an open circuit or a disconnected state;
The first determining unit is used for determining that the characteristic current data meet a preset open circuit condition if the specific numerical value is included;
and the second determining unit is used for determining that the characteristic current data does not meet the preset open circuit condition if the specific numerical value is not included.
12. An urban rail train braking system comprising a braking device and a piezoresistive pressure sensor, characterized by further comprising a diagnostic device connected to the piezoresistive pressure sensor, the diagnostic device comprising a processor for performing the condition detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910870746.0A CN110553789A (en) | 2019-09-16 | 2019-09-16 | state detection method and device of piezoresistive pressure sensor and brake system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910870746.0A CN110553789A (en) | 2019-09-16 | 2019-09-16 | state detection method and device of piezoresistive pressure sensor and brake system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110553789A true CN110553789A (en) | 2019-12-10 |
Family
ID=68740355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910870746.0A Pending CN110553789A (en) | 2019-09-16 | 2019-09-16 | state detection method and device of piezoresistive pressure sensor and brake system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110553789A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111707341A (en) * | 2020-06-24 | 2020-09-25 | 北京恒通安泰科技有限公司 | Data acquisition device and data acquisition method for rail weighbridge and rail weighbridge |
| CN112051464A (en) * | 2020-08-25 | 2020-12-08 | 中国航空工业集团公司沈阳飞机设计研究所 | Fault detection method and system for dual-channel airborne pressure sensor |
| CN112798180A (en) * | 2021-01-04 | 2021-05-14 | 珠海格力电器股份有限公司 | Fault detection method of force sensor and computer-readable storage medium |
| CN116821834A (en) * | 2023-08-29 | 2023-09-29 | 浙江北岛科技有限公司 | Vacuum circuit breaker overhauling management system based on embedded sensor |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201859190U (en) * | 2010-11-05 | 2011-06-08 | 中环天仪股份有限公司 | Sensor fault self-diagnosis circuit of intelligent pressure transmitter in industry |
| CN105424236A (en) * | 2015-11-19 | 2016-03-23 | 南京信息工程大学 | Multi-range array pressure sensing chip and detection method thereof |
| CN105974223A (en) * | 2016-04-27 | 2016-09-28 | 深圳职业技术学院 | Method used for carrying out on-line detection on electric equipment work state and system thereof |
| CN106597160A (en) * | 2016-12-13 | 2017-04-26 | 广东金赋科技股份有限公司 | Electronic device fault detection method and apparatus |
| CN107607321A (en) * | 2017-09-06 | 2018-01-19 | 成都大汇物联科技有限公司 | A kind of equipment fault accurate positioning method |
| CN109947080A (en) * | 2019-03-21 | 2019-06-28 | 北京明略软件系统有限公司 | A kind of method, apparatus of fault diagnosis, computer storage medium and terminal |
| CN110146120A (en) * | 2019-05-19 | 2019-08-20 | 浙江大学 | A kind of sensor fault diagnosis method and system |
-
2019
- 2019-09-16 CN CN201910870746.0A patent/CN110553789A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201859190U (en) * | 2010-11-05 | 2011-06-08 | 中环天仪股份有限公司 | Sensor fault self-diagnosis circuit of intelligent pressure transmitter in industry |
| CN105424236A (en) * | 2015-11-19 | 2016-03-23 | 南京信息工程大学 | Multi-range array pressure sensing chip and detection method thereof |
| CN105974223A (en) * | 2016-04-27 | 2016-09-28 | 深圳职业技术学院 | Method used for carrying out on-line detection on electric equipment work state and system thereof |
| CN106597160A (en) * | 2016-12-13 | 2017-04-26 | 广东金赋科技股份有限公司 | Electronic device fault detection method and apparatus |
| CN107607321A (en) * | 2017-09-06 | 2018-01-19 | 成都大汇物联科技有限公司 | A kind of equipment fault accurate positioning method |
| CN109947080A (en) * | 2019-03-21 | 2019-06-28 | 北京明略软件系统有限公司 | A kind of method, apparatus of fault diagnosis, computer storage medium and terminal |
| CN110146120A (en) * | 2019-05-19 | 2019-08-20 | 浙江大学 | A kind of sensor fault diagnosis method and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111707341A (en) * | 2020-06-24 | 2020-09-25 | 北京恒通安泰科技有限公司 | Data acquisition device and data acquisition method for rail weighbridge and rail weighbridge |
| CN112051464A (en) * | 2020-08-25 | 2020-12-08 | 中国航空工业集团公司沈阳飞机设计研究所 | Fault detection method and system for dual-channel airborne pressure sensor |
| CN112798180A (en) * | 2021-01-04 | 2021-05-14 | 珠海格力电器股份有限公司 | Fault detection method of force sensor and computer-readable storage medium |
| CN116821834A (en) * | 2023-08-29 | 2023-09-29 | 浙江北岛科技有限公司 | Vacuum circuit breaker overhauling management system based on embedded sensor |
| CN116821834B (en) * | 2023-08-29 | 2023-11-24 | 浙江北岛科技有限公司 | Vacuum circuit breaker overhauling management system based on embedded sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110553789A (en) | state detection method and device of piezoresistive pressure sensor and brake system | |
| CN109186813B (en) | Temperature sensor self-checking device and method | |
| CN112955839B (en) | Abnormality detection device, abnormality detection method, and program | |
| KR101316486B1 (en) | Error detection method and system | |
| CN109783903B (en) | Industrial water pipeline fault diagnosis method and system based on time sequence | |
| KR102427205B1 (en) | Apparatus and method for generating training data of artificial intelligence model | |
| CN113657221B (en) | Power plant equipment state monitoring method based on intelligent sensing technology | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN115268417B (en) | Self-adaptive ECU fault diagnosis control method | |
| CN110231529A (en) | A kind of control cabinet intelligent Fault Diagnose Systems and method for diagnosing faults | |
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| CN116520236B (en) | Abnormality detection method and system for intelligent ammeter | |
| CN105572492A (en) | City rail train auxiliary inverter fault diagnosis device | |
| CN103267652B (en) | Intelligent online diagnosis method for early failures of equipment | |
| CN115034094B (en) | Prediction method and system for operation state of metal processing machine tool | |
| KR20210077496A (en) | Equipment failure prediction system having multi-channel sensors for receiving acoustic signals in the ultrasonic band | |
| CN112711850A (en) | Unit online monitoring method based on big data | |
| CN115683319A (en) | Power transformer winding state evaluation method | |
| CN106959397A (en) | A kind of method for designing of small fault diagnostic system for high ferro inverter | |
| JP3333494B2 (en) | Device abnormality diagnosis method | |
| CN117668751A (en) | High-low voltage power system fault diagnosis method and device | |
| CN117169639B (en) | Product detection method and system for power adapter production | |
| CN104569814B (en) | A kind of DC traction motor health status real-time analysis method based on approximate entropy | |
| CN105651537B (en) | A kind of truss structure damage real-time monitoring system of high susceptibility to damage | |
| CN110057587B (en) | Intelligent fault diagnosis method and system for pump bearing for nuclear power |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191210 |
|
| RJ01 | Rejection of invention patent application after publication |