CN116734911A - Sensor state monitoring method and device - Google Patents
Sensor state monitoring method and device Download PDFInfo
- Publication number
- CN116734911A CN116734911A CN202310761858.9A CN202310761858A CN116734911A CN 116734911 A CN116734911 A CN 116734911A CN 202310761858 A CN202310761858 A CN 202310761858A CN 116734911 A CN116734911 A CN 116734911A
- Authority
- CN
- China
- Prior art keywords
- data
- target
- data set
- determining
- working condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 230000002159 abnormal effect Effects 0.000 claims abstract description 37
- 238000012806 monitoring device Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 102100037651 AP-2 complex subunit sigma Human genes 0.000 description 1
- 101000806914 Homo sapiens AP-2 complex subunit sigma Proteins 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application provides a method and a device for monitoring a sensor state, wherein the method comprises the following steps: after a first operation parameter value of a target object monitored by a target sensor in a current period and a first data set of the target sensor are obtained, the first operation parameter value is matched with a reference operation parameter value corresponding to each working condition, a target working condition of the target sensor is determined, a second data set of the target sensor in a history period under the target working condition is obtained, a corresponding baseline of the target sensor under the target working condition is determined according to the second data set, and whether the state of the target sensor under the target working condition is abnormal or not is determined according to the baseline and the first data set. Therefore, according to the second data set of the target sensor under the target working condition in the history period, the baseline of the target sensor under the target working condition is determined in a targeted manner, whether the state of the target sensor under the target working condition is abnormal or not is determined based on the baseline and the first data set, and therefore the accuracy of monitoring the state of the target sensor is improved.
Description
Technical Field
The present application relates to the field of sensor technologies, and in particular, to a method and an apparatus for monitoring a sensor state.
Background
The sensor device is a hardware device that is typically installed in a fixed location for collecting specific data. Due to factors such as working environment and sensor aging, the data acquired by the sensor may be inaccurate, and the sensor state is abnormal. Therefore, the state of the sensor needs to be monitored, and the abnormality of the data is found in time, so that the reliability of the data collected by the sensor is ensured.
Disclosure of Invention
The application provides a method and a device for monitoring a sensor state. The specific scheme is as follows:
an embodiment of an aspect of the present application provides a method for monitoring a sensor state, including:
acquiring a first operation parameter value of a target object monitored by a target sensor in a current period and a first data set of the target sensor;
matching the first operation parameter value with a reference operation parameter value corresponding to each working condition, and determining a target working condition of a target sensor;
acquiring a second data set of the target sensor under the target working condition in the history period;
determining a corresponding base line of the target sensor under the target working condition according to the second data set;
and determining whether the state of the target sensor under the target working condition is abnormal according to the base line and the first data set.
Another embodiment of the present application provides a device for monitoring a sensor state, including:
the acquisition module is used for acquiring a first operation parameter value of a target object monitored by the target sensor in the current period and a first data set of the target sensor;
the first determining module is used for matching the first operation parameter value with the reference operation parameter value corresponding to each working condition to determine the target working condition of the target sensor;
the acquisition module is used for acquiring a second data set of the target sensor under the target working condition in the history period;
the second determining module is used for determining a corresponding baseline of the target sensor under the target working condition according to the second data set;
and the third determining module is used for determining whether the state of the target sensor under the target working condition is abnormal or not according to the base line and the first data set.
In another aspect, an embodiment of the present application provides a computer device, including a processor and a memory;
wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory for implementing the method as in the above embodiment.
Another aspect of the present application provides a computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor implements the method of the above embodiment.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic flow chart of a method for monitoring a sensor state according to an embodiment of the present application;
FIG. 2 is a flow chart of another method for monitoring sensor status according to an embodiment of the present application;
FIG. 3 is a flowchart of another method for monitoring a sensor status according to an embodiment of the present application;
FIG. 4 is a flowchart of another method for monitoring a sensor status according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a sensor state monitoring device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
A method of monitoring a sensor state according to an embodiment of the present application is described below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for monitoring a sensor state according to an embodiment of the present application.
The method for monitoring the sensor state is executed by the device for monitoring the sensor state (hereinafter referred to as a monitoring device) provided by the embodiment of the application, and the device can be configured in a terminal device to monitor the sensor state, and the reliability of data collected by a sensor is realized.
As shown in fig. 1, the method for monitoring the sensor state includes:
step 101, obtaining a first operation parameter value of a target object monitored by a target sensor in a current period and a first data set of the target sensor.
The first operation parameter value may be power, load, oil temperature, etc. The target object may be a machine or the like.
In the application, the first data set acquired by the target sensor in the current period can be acquired. And acquiring, by other sensors or dedicated measuring devices, first operating parameter values of one or more operating parameters of the target object during the current time period.
Step 102, matching the first operation parameter value with the reference operation parameter value corresponding to each working condition, and determining the target working condition of the target sensor.
In the application, the reference operation parameter values corresponding to the working conditions can be preset in the system. And then, determining the difference between the first operation parameter value and the reference operation parameter value corresponding to each working condition, and determining the working condition corresponding to the reference operation parameter value with the smallest difference as the target working condition.
Step 103, obtaining a second data set of the target sensor under the target working condition in the history period.
Wherein, the historical period is separated from the current period by a preset time length.
In the application, the second data set under the target working condition in the history period can be obtained from the history operation data of the target sensor. Further, the duration of the history period may be the same as or different from the duration of the current period.
It will be appreciated that the object sensor is in an abnormal state and that the data collected by the object sensor will be shifted, i.e. the distribution of the first data collected by the object sensor during the current period is different from the distribution of the second data collected during the historical period. Thus, the distribution characteristics of the second data acquired during the history period can be used as a reference for determining whether the first data is shifted. Thereby improving the accuracy of the target sensor monitoring.
And 104, determining a corresponding baseline of the target sensor under the target working condition according to the second data set.
According to the application, the corresponding base line of the target sensor under the target working condition can be determined according to the statistical characteristic value of the second data set. For example, the average value and/or the first standard deviation of each second data in the second data set may be determined as a baseline corresponding to the target sensor under the target working condition. Alternatively, the baseline corresponding to the target sensor under the target working condition may be determined according to the frequency of each second data in the second data set. The application is not limited in this regard.
In addition, the data distribution of the target sensor is different under different working conditions, so that different base lines are determined according to different working conditions, and the accuracy of determining the state of the target sensor is improved.
Step 105, determining whether the state of the target sensor under the target working condition is abnormal according to the baseline and the first data set.
In the application, when the baseline is the third mean value of each second data in the second data set, the difference value between each first data in the first data set and the third mean value can be calculated, and the number of the first data with the difference value between the first data set and the third mean value larger than the second threshold value is determined. And then, if the number is larger than a third threshold value, determining that the state of the target sensor under the target working condition is abnormal.
Therefore, based on the quantity of the first data, the difference value between the first data set and the third mean value of which is larger than the second threshold value, whether the state of the target sensor under the target working condition is an abnormal state or not is determined from the overall data distribution characteristics of the first data set, the influence of single abrupt change data on the state monitoring of the target sensor is avoided, and the accuracy of the state monitoring of the target sensor is improved.
Alternatively, in the case where the baseline is the third standard deviation of each second data in the second data set, a fourth standard deviation of each first data in the first data set may be calculated, and a difference between the fourth standard deviation and the third standard deviation may be determined. And then, if the difference is larger than a fourth threshold value, determining that the state of the target sensor under the target working condition is abnormal.
Optionally, in the case that the baseline is the third mean value and the third standard deviation of each second data in the second data set, a difference between each first data in the first data set and the third mean value may be calculated, and the number of first data in the first data set and the third mean value, where the difference between the first data set and the third mean value is greater than the second threshold, may be determined. And simultaneously calculating a fourth standard deviation of each first data in the first data set, and determining a difference between the fourth standard deviation and the third standard deviation. Then, in the case where the number is greater than the third threshold value or the difference is greater than the fourth threshold value, it is determined that the state of the target sensor under the target condition is abnormal. And determining that the state of the target sensor under the target working condition is normal when the number is smaller than or equal to a third threshold value and the difference between the third standard deviation and the fourth standard deviation is smaller than or equal to a fourth threshold value.
In the application, after a first operation parameter value of a target object monitored by a target sensor in a current period and a first data set of the target sensor are obtained, the first operation parameter value is matched with a reference operation parameter value corresponding to each working condition to determine a target working condition of the target sensor, a second data set of the target sensor in a history period under the target working condition is obtained, and then a corresponding baseline of the target sensor under the target working condition is determined according to the second data set, so that whether the state of the target sensor under the target working condition is abnormal or not is determined according to the baseline and the first data set. Therefore, according to the second data set of the target sensor under the target working condition in the history period, the baseline of the target sensor under the target working condition is determined in a targeted manner, whether the state of the target sensor under the target working condition is abnormal or not is determined based on the baseline and the first data set, and therefore the accuracy of monitoring the state of the target sensor is improved.
Fig. 2 is a flow chart of a method for monitoring a sensor state according to an embodiment of the present application.
As shown in fig. 2, the method for monitoring the sensor state includes:
step 201, obtaining a first operation parameter value of a target object monitored by a target sensor in a current period and a first data set of the target sensor.
Step 202, matching the first operation parameter value with the reference operation parameter value corresponding to each working condition, and determining the target working condition of the target sensor.
Step 203, obtaining a second data set of the target sensor under the target working condition in the history period.
And 204, determining a corresponding baseline of the target sensor under the target working condition according to the second data set.
Step 205, determining whether the state of the target sensor under the target working condition is abnormal according to the baseline and the first data set.
In the present application, the specific implementation process of step 201 to step 205 may refer to the detailed description of any embodiment of the present application, and will not be repeated here.
In step 206, when the state of the target sensor under the target working condition is abnormal, a calibration model is determined according to the first data set and the second data set.
According to the method and the device, under the condition that the state of the target sensor under the target working condition is abnormal, the calibration model can be determined again in a targeted mode according to the first data set and the second data set. The method and the device can realize self-adaptive updating of the calibration model, thereby improving the accuracy of the first data calibration.
In the application, the first data can be sequenced and divided, a plurality of data subintervals are determined, a first mean value and a first standard deviation of third data in each data subinterval in the first data set are determined, and a second mean value and a second standard deviation of fourth data in each data subinterval in the second data set are determined. Then, a first parameter corresponding to each data subinterval may be determined based on a quotient of the first standard deviation and the second standard deviation corresponding to each data subinterval, and a second parameter corresponding to each data subinterval may be determined based on the quotient, the first average value, and the second average value corresponding to each data subinterval. Then, based on the first parameter and the second parameter corresponding to each data subinterval, a calibration model corresponding to each data subinterval is generated. Therefore, under the condition that the working curve of the target sensor is nonlinear, the accuracy of the calibration model is ensured and the complexity of determining the calibration model is reduced through piecewise fitting.
For example, assume that the first dataset contains 1, 3, 4, 6, 7, 9, 10, 12, 13. The second data set comprises 2, 3, 4, 5, 6, 7, 8, 9, 10. When the first data set is divided into 3 data subintervals, it may be determined that the interval length of each data subinterval is 12 +.3=4. Then it may be determined that data subinterval 1 is [1,5 ], data subinterval 2 is [5,9 ], and data subinterval 3 is [9,13]. Based on the first data 1, 3, 4, a first mean and a first standard deviation of the data subinterval 1 are calculated. Based on the first data 2, 3, 4, a second mean and a second standard deviation of the data subinterval 1 are calculated. And the same calculation is performed to determine a first average value, a first standard deviation, a second average value and a second standard deviation of the data subinterval 2 and the data subinterval 3.
In the application, the calibration model corresponding to the data subinterval can be determined by referring to the following formula:
y＝αx+β
where x is first data, y is data after calibration of the first data, α is a linear coefficient, and β is a fixed offset. Above-mentionedMu 1 is a second mean value corresponding to the data subinterval, sigma 1 is a second standard deviation corresponding to the data subinterval, mu 2 is a first mean value corresponding to the data subinterval, sigma 2 is a pair of the data subintervalsA first standard deviation is applied.
Optionally, the first data set is input into an initial calibration model, and a prediction data set output by the initial calibration model is obtained. And then, determining a loss value based on the difference between the predicted data and the second data set, and correcting the initial calibration model according to the loss value to obtain the calibration model. Thereby improving the accuracy of the calibration model.
Alternatively, each first data may be ordered and divided, and determined as N data subintervals. The linear coefficient α and the initial fixed offset β in the initial calibration model for each data subinterval are denoted α1, α2. And then, correcting each first data by using the initial calibration model corresponding to each data subinterval, obtaining a corrected data set, and determining a frequency curve of each fifth data in the corrected data set and a frequency curve of each second data in the second data set. Then, a difference (such as KL divergence) between the two frequency curves is determined, and a loss value is determined based on the KL divergence, so as to adjust the linear coefficient alpha and the initial fixed offset beta in the initial calibration model corresponding to each data subinterval according to the loss value.
In addition, assuming that there are C different working conditions, a frequency curve of historical time period data of the target sensor under each working condition and a frequency curve obtained by piecewise linear calibration of the current time period data are calculated respectively, and then KL divergence between the two frequency curves under each working condition can be calculated. Get C for each training B The data for each condition is taken as a mini-batch, the sum of KL divergences is calculated, and α1, α2..α2n, α01, α12..α5n is updated based on the sum. And (3) after all working conditions are traversed, recording as a training iteration, stopping training when KL divergence of all C working conditions is minimum after the iteration is repeated, and obtaining the final alpha 31, alpha 42. And generating the initial calibration model based on αn, β1, β2.
Step 207, based on the calibration model, each first data in the first data set is modified.
In the application, when each data subinterval in the first data set corresponds to a different calibration model, each first data in the first data set can be substituted into the calibration model corresponding to the data subinterval to which the first data set belongs, so as to obtain corrected data output by the calibration model.
In the case that the first data set corresponds to one calibration model, the first data set may be input into the calibration model, and corrected data output by the calibration model may be obtained.
In the application, when the state of the target sensor under the target working condition is abnormal, a calibration model is determined according to the first data set and the second data set, and each first data in the first data set is corrected based on the calibration model. Therefore, the accuracy of the first data calibration acquired by the target sensor is improved through the self-adaptive updating of the calibration model.
Fig. 3 is a flow chart of a method for monitoring a sensor state according to an embodiment of the present application.
As shown in fig. 3, the method for monitoring the sensor state includes:
step 301, obtaining a first operation parameter value of a target object monitored by a target sensor in a current period, and a first data set of the target sensor.
Step 302, the first operation parameter value is matched with the reference operation parameter value corresponding to each working condition, and the target working condition of the target sensor is determined.
Step 303, obtaining a second data set of the target sensor under the target working condition in the history period.
In the present application, the specific implementation process of step 301 to step 303 can be referred to the detailed description of any embodiment of the present application, and will not be repeated here.
Step 304 determines the frequency of each second data in the second set of data.
In the application, the frequency of each second data in the second data set can be counted. And determining a corresponding base line of the target sensor under the target working condition according to the frequency of each second data.
Step 305, determining a baseline according to the frequency of each second data.
In the present application, the frequency of each second data may be directly determined as the baseline. Alternatively, a first frequency curve may be generated based on the frequency of each of the second data, and the first frequency curve may be determined as the baseline. Thereby improving the reliability of the baseline.
Step 306 determines the difference between the frequency of each first data in the first dataset and the corresponding frequency of each first data in the baseline.
In the present application, the frequency of each first data in the first data set may be determined. The difference between the frequency of each first data in the first data set and its corresponding frequency in the baseline may then be determined as the difference between the frequency of each first data and its corresponding frequency in the baseline.
And step 307, determining that the state of the target sensor under the target working condition is abnormal under the condition that the sum of the differences corresponding to the first data is larger than a first threshold value.
In the application, under the condition that the sum of the differences corresponding to the first data is larger than a first threshold value, the data acquired by the target sensor in the current period is indicated to deviate. Therefore, it is possible to determine that the state of the target sensor in the target condition at the present period is abnormal.
Alternatively, a second frequency curve may be generated based on the frequency of each first data, and a KL (Kullback-Leibler) divergence between the first frequency curve and the second frequency curve may be determined. And under the condition that the KL divergence is larger than a preset threshold value, determining that the state of the target sensor under the target working condition is abnormal.
And step 308, determining that the state of the target sensor under the target working condition is normal under the condition that the sum of the differences corresponding to the first data is smaller than or equal to a first threshold value.
In the application, under the condition that the sum of the differences corresponding to the first data is smaller than or equal to the first threshold value, the data acquired by the target sensor in the current period is not shifted. Therefore, it can be determined that the state of the target sensor in the target condition at the present period is normal.
It will be appreciated that the baseline includes data distribution characteristics of the target sensor under the target conditions. Comparing the baseline characteristic (frequency) of the first dataset to the baseline to determine the state of the target sensor improves the accuracy and reliability of determining the state of the target sensor.
In the application, after a second data set of a target sensor under a target working condition in a history period is acquired, the frequency of each second data in the second data set can be determined, a base line is determined according to the frequency of each second data, then the difference between the frequency of each first data in the first data set and the frequency corresponding to each first data in the base line is determined, the state of the target sensor under the target working condition is determined to be abnormal under the condition that the sum of the differences corresponding to each first data is larger than a first threshold value, and the state of the target sensor under the target working condition is determined to be normal under the condition that the sum of the differences corresponding to each first data is smaller than or equal to the first threshold value. Therefore, the base line is determined according to the frequency of each second data, the reliability of the base line is improved, whether the state of the target sensor under the target working condition is abnormal or not is determined according to the difference between the frequency of each first data in the first data set and the corresponding frequency of each first data in the base line, and the accuracy and the reliability of the state monitoring of the target sensor are improved.
Fig. 4 is a flow chart of a method for monitoring a sensor state according to an embodiment of the present application.
As shown in fig. 4, the method for monitoring the sensor state includes:
step 401, obtaining a second sequence of operating parameters of the target object in the history period.
The second operation parameter sequence comprises a plurality of second operation parameter values, the second operation parameter sequence corresponds to one operation parameter, and the operation parameter corresponding to the second operation parameter value is the same as the operation parameter corresponding to the first operation parameter value.
In the application, the second operation parameter sequence of one or more operation parameters of the target object in the current period can be acquired through other sensors or special measuring equipment.
Step 402, determining a reference operation parameter value corresponding to each working condition according to the second operation parameter sequence.
In the application, when the second operation parameter sequence corresponding to one operation parameter of the target object in the history period is obtained, each second operation parameter value in the second operation parameter sequence can be determined as a reference operation parameter value corresponding to one working condition.
For example, assume that the second series of operating parameters corresponds to an operating speed of the machine, including 1500 rpm, 2000 rpm, 2500 rpm. Three working conditions can be determined for the machine, the reference operation parameter value corresponding to the working condition 1 is 1500 rpm, the reference operation parameter value corresponding to the working condition 2 is 2000 rpm, and the reference operation parameter value corresponding to the working condition 3 is 2500 rpm.
When the second operation parameter sequences corresponding to the operation parameters of the target object in the history period are obtained, the second operation parameter values in the second operation parameter sequences can be arranged and combined, and each combination of the second operation parameter values is determined to be a reference operation parameter value corresponding to a working condition.
For example, assume that among 2 second operating parameter sequences, the second operating parameter sequence 1 corresponds to the speed at which the machine is operating and the second operating parameter sequence 2 corresponds to the machine operating duration. The second operation parameter sequence 1 contains 1500 rpm and 2000 rpm, and the second operation parameter sequence 2 contains 5 hours and 10 hours. Four conditions of the machine can be determined, and the reference operation parameter value corresponding to the condition 1 comprises 1500 revolutions/second and 5 hours. The reference operating parameter values corresponding to condition 2 include 2000 rpm, 5 hours. The reference operating parameter values for condition 3 include 1500 rpm and 10 hours. The reference operating parameter values corresponding to operating condition 4 include 2000 revolutions per second, 10 hours.
Optionally, the second operation parameter sequence may be divided into intervals, and each interval in the plurality of second operation parameter sequences may be arranged and combined to determine a reference operation parameter value corresponding to each working condition.
And determining the reference operation parameter value corresponding to each working condition by monitoring the second operation parameter sequence of the target object in the history period and arranging and combining the second operation parameter values in the second operation parameter sequences. The method realizes comprehensive and accurate division of different working conditions.
Step 403, obtaining a first operation parameter value of the target object monitored by the target sensor in the current period, and a first data set of the target sensor.
And step 404, matching the first operation parameter value with the reference operation parameter value corresponding to each working condition, and determining the target working condition of the target sensor.
Step 405, obtaining a second data set of the target sensor under the target working condition in the history period.
And step 406, determining a corresponding baseline of the target sensor under the target working condition according to the second data set.
Step 407, determining whether the state of the target sensor under the target working condition is abnormal according to the baseline and the first data set.
In the present application, the specific implementation process of step 403 to step 407 may refer to the detailed description of any embodiment of the present application, and will not be repeated here.
In the application, after a second operation parameter sequence of a target object in a history period is acquired, a reference operation parameter value corresponding to each working condition can be determined according to the second operation parameter sequence, then a first operation parameter value of the target object monitored by a target sensor in a current period and a first data set of the target sensor are acquired, the first operation parameter value is matched with the reference operation parameter value corresponding to each working condition, the target working condition of the target sensor is determined, so as to acquire a second data set of the target sensor in the history period under the target working condition, then a corresponding base line of the target sensor under the target working condition is determined according to the second data set, and whether the state of the target sensor under the target working condition is abnormal or not is determined according to the base line and the first data set. And determining the reference operation parameter value corresponding to each working condition according to the second operation parameter sequence by monitoring the second operation parameter sequence of the target object in the historical period. Therefore, different working conditions are comprehensively and accurately divided, and the accuracy of state monitoring of the target sensor is improved.
In order to achieve the above embodiment, the embodiment of the present application further provides a device for monitoring a sensor state. Fig. 5 is a schematic structural diagram of a sensor state monitoring device according to an embodiment of the present application.
As shown in fig. 5, the monitoring device for a sensor state includes an acquisition module 510, a first determination module 520, a second determination module 530, and a third determination module 540:
an obtaining module 510, configured to obtain a first operation parameter value of a target object monitored by the target sensor in a current period, and a first data set of the target sensor;
the first determining module 520 is configured to match the first operation parameter value with a reference operation parameter value corresponding to each working condition, and determine a target working condition of the target sensor;
the acquiring module 510 is configured to acquire a second data set of the target sensor under the target working condition in the history period;
a second determining module 530, configured to determine, according to the second data set, a baseline corresponding to the target sensor under the target working condition;
the third determining module 540 is configured to determine, according to the baseline and the first data set, whether the state of the target sensor under the target working condition is abnormal.
In a possible implementation manner of the embodiment of the present application, the device further includes a calibration module, configured to:
under the condition that the state of the target sensor under the target working condition is abnormal, determining a calibration model according to the first data set and the second data set;
each first data in the first data set is modified based on the calibration model.
In one possible implementation manner of the embodiment of the present application, the calibration module is configured to:
sequencing and dividing each first data, and determining a plurality of data subintervals;
determining a first mean and a first standard deviation of third data in each data subinterval, wherein the third data belongs to a first data set;
determining a second mean and a second standard deviation of fourth data in each data subinterval, wherein the fourth data belongs to a second data set;
determining a first parameter corresponding to each data subinterval based on the quotient of the first standard deviation and the second standard deviation corresponding to each data subinterval;
determining a second parameter corresponding to each data subinterval based on the quotient, the first average value and the second average value corresponding to each data subinterval;
and generating a calibration model corresponding to each data subinterval based on the first parameter and the second parameter corresponding to each data subinterval.
In one possible implementation manner of the embodiment of the present application, the calibration module is configured to:
inputting the first data set into an initial calibration model to obtain a prediction data set output by the initial calibration model;
determining a loss value based on a difference between the predicted data and the second data set;
and correcting the initial calibration model according to the loss value to obtain the calibration model.
In one possible implementation manner of the embodiment of the present application, the second determining module 530 is configured to:
determining the frequency of each second data in the second data set;
a baseline is determined based on the frequency of each second data.
In one possible implementation manner of the embodiment of the present application, the third determining module 540 is configured to:
determining a difference between a frequency of each first data in the first dataset and a corresponding frequency of each first data in the baseline;
under the condition that the sum of differences corresponding to the first data is larger than a first threshold value, determining that the state of the target sensor under the target working condition is abnormal;
and under the condition that the sum of the differences corresponding to the first data is smaller than or equal to a first threshold value, determining that the state of the target sensor under the target working condition is normal.
In one possible implementation manner of the embodiment of the present application, the second determining module 530 is configured to:
and determining a third mean value and/or a third standard deviation of each second data in the second data set as a baseline.
In one possible implementation manner of the embodiment of the present application, the third determining module 540 is configured to:
determining the number of first data, the difference between the first data set and the third mean value of which is greater than a second threshold value, and a fourth standard deviation of each first data in the first data set;
under the condition that the number is larger than a third threshold value and/or the difference value between the third standard deviation and the fourth standard deviation is larger than a fourth threshold value, determining that the state of the target sensor under the target working condition is abnormal;
and under the condition that the number is smaller than or equal to a third threshold value and the difference value between the third standard deviation and the fourth standard deviation is smaller than or equal to a fourth threshold value, determining that the state of the target sensor under the target working condition is normal.
In a possible implementation manner of the embodiment of the present application, the method further includes a fourth determining module, configured to:
acquiring a second operation parameter sequence of the target object in the history period;
and determining the reference operation parameter value corresponding to each working condition according to the second operation parameter sequence.
It should be noted that the explanation of the embodiment of the method for monitoring the sensor state is also applicable to the device for monitoring the sensor state of this embodiment, and thus will not be repeated here.
In the application, after a first operation parameter value of a target object monitored by a target sensor in a current period and a first data set of the target sensor are obtained, the first operation parameter value is matched with a reference operation parameter value corresponding to each working condition to determine a target working condition of the target sensor, a second data set of the target sensor in a history period under the target working condition is obtained, and then a corresponding baseline of the target sensor under the target working condition is determined according to the second data set, so that whether the state of the target sensor under the target working condition is abnormal or not is determined according to the baseline and the first data set. Therefore, according to the second data set of the target sensor under the target working condition in the history period, the baseline of the target sensor under the target working condition is determined in a targeted manner, whether the state of the target sensor under the target working condition is abnormal or not is determined based on the baseline and the first data set, and therefore the accuracy of monitoring the state of the target sensor is improved.
In order to implement the above embodiments, the embodiments of the present application further provide a computer device, including a processor and a memory;
wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory for realizing the monitoring method of the sensor state of the above embodiment.
In order to achieve the above-described embodiments, the embodiments of the present application also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for monitoring a sensor state according to the above-described embodiments.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (10)
1. A method for monitoring a sensor condition, comprising:
acquiring a first operation parameter value of a target object monitored by a target sensor in a current period and a first data set of the target sensor;
matching the first operation parameter value with a reference operation parameter value corresponding to each working condition, and determining a target working condition of the target sensor;
acquiring a second data set of the target sensor under the target working condition in a history period;
determining a corresponding baseline of the target sensor under the target working condition according to the second data set;
and determining whether the state of the target sensor under the target working condition is abnormal or not according to the baseline and the first data set.
2. The method as recited in claim 1, further comprising:
determining a calibration model according to the first data set and the second data set under the condition that the state of the target sensor under the target working condition is abnormal;
and correcting each first data in the first data set based on the calibration model.
3. The method of claim 2, wherein the determining a calibration model from the first data set and the second data set comprises:
sorting and dividing the first data to determine a plurality of data subintervals;
determining a first mean and a first standard deviation of third data in each data subinterval, wherein the third data belongs to the first data set;
determining a second mean and a second standard deviation of fourth data in each data subinterval, wherein the fourth data belongs to the second data set;
determining a first parameter corresponding to each data subinterval based on the quotient of the first standard deviation and the second standard deviation corresponding to each data subinterval;
determining a second parameter corresponding to each data subinterval based on the quotient, the first average value and the second average value corresponding to each data subinterval;
and generating a calibration model corresponding to each data subinterval based on the first parameter and the second parameter corresponding to each data subinterval.
4. The method of claim 2, wherein the determining a calibration model from the first data set and the second data set comprises:
inputting the first data set into an initial calibration model to obtain a predicted data set output by the initial calibration model;
determining a loss value based on a difference between the predicted data and the second data set;
and correcting the initial calibration model according to the loss value to obtain a calibration model.
5. The method of claim 1, wherein determining a baseline for the target sensor at the target operating condition based on the second data set comprises:
determining the frequency of each second data in the second data set;
a baseline is determined based on the frequency of each of the second data.
6. The method of claim 5, wherein determining whether the state of the target sensor under the target condition is abnormal based on the baseline and the first data set comprises:
determining a difference between a frequency of each first data in the first dataset and a corresponding frequency of each first data in a baseline;
determining that the state of the target sensor under the target working condition is abnormal under the condition that the sum of differences corresponding to the first data is larger than a first threshold value;
and under the condition that the sum of differences corresponding to the first data is smaller than or equal to the first threshold value, determining that the state of the target sensor under the target working condition is normal.
7. The method of claim 1, wherein determining a baseline for the target sensor at the target operating condition based on the second data set comprises:
and determining a third mean value and/or a third standard deviation of each second data in the second data set as a baseline.
8. The method of claim 7, wherein determining whether the state of the target sensor under the target condition is abnormal based on the baseline and the first data set comprises:
determining the number of first data in which the difference between the first data set and the third mean is greater than a second threshold, and a fourth standard deviation of each first data in the first data set;
determining that the state of the target sensor under the target working condition is abnormal under the condition that the number is larger than a third threshold value and/or the difference value between the third standard deviation and the fourth standard deviation is larger than the fourth threshold value;
and determining that the state of the target sensor under the target working condition is normal under the condition that the number is smaller than or equal to the third threshold value and the difference value between the third standard deviation and the fourth standard deviation is smaller than or equal to the fourth threshold value.
9. The method as recited in claim 1, further comprising:
acquiring a second operation parameter sequence of the target object in the history period;
and determining a reference operation parameter value corresponding to each working condition according to the second operation parameter sequence.
10. A device for monitoring a sensor condition, comprising:
the acquisition module is used for acquiring a first operation parameter value of a target object monitored by the target sensor in the current period and a first data set of the target sensor;
the first determining module is used for matching the first operation parameter value with a reference operation parameter value corresponding to each working condition to determine a target working condition of the target sensor;
the acquisition module is used for acquiring a second data set of the target sensor under the target working condition in a history period;
the second determining module is used for determining a corresponding baseline of the target sensor under the target working condition according to the second data set;
and the third determining module is used for determining whether the state of the target sensor under the target working condition is abnormal or not according to the baseline and the first data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310761858.9A CN116734911A (en) | 2023-06-26 | 2023-06-26 | Sensor state monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310761858.9A CN116734911A (en) | 2023-06-26 | 2023-06-26 | Sensor state monitoring method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116734911A true CN116734911A (en) | 2023-09-12 |
Family
ID=87904349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310761858.9A Pending CN116734911A (en) | 2023-06-26 | 2023-06-26 | Sensor state monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116734911A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118981187A (en) * | 2024-10-22 | 2024-11-19 | 际华三五一三实业有限公司 | A method for monitoring the operating status of numerical control equipment in a footwear production line |
| CN119936544A (en) * | 2025-04-07 | 2025-05-06 | 河北科技大学 | A DCDC energy feedback aging system based on microgrid electrical characteristics |
-
2023
- 2023-06-26 CN CN202310761858.9A patent/CN116734911A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118981187A (en) * | 2024-10-22 | 2024-11-19 | 际华三五一三实业有限公司 | A method for monitoring the operating status of numerical control equipment in a footwear production line |
| CN119936544A (en) * | 2025-04-07 | 2025-05-06 | 河北科技大学 | A DCDC energy feedback aging system based on microgrid electrical characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116734911A (en) | Sensor state monitoring method and device | |
| US9465387B2 (en) | Anomaly diagnosis system and anomaly diagnosis method | |
| JP6622497B2 (en) | Failure prediction apparatus and failure prediction method | |
| JP5827425B1 (en) | Predictive diagnosis system and predictive diagnosis method | |
| JP7224469B2 (en) | Abnormality Diagnosis Method, Abnormality Diagnosis Device and Abnormality Diagnosis Program | |
| JP5827426B1 (en) | Predictive diagnosis system and predictive diagnosis method | |
| CN118070195B (en) | Mining alternating current frequency converter abnormal data state monitoring system | |
| US20190265088A1 (en) | System analysis method, system analysis apparatus, and program | |
| CN111103851A (en) | System and method for anomaly characterization based on joint historical and time series analysis | |
| KR20160014067A (en) | Method for monitoring operational parameters in an internal combustion engine | |
| CN118731548B (en) | New energy vehicle charger automatic test system | |
| WO2017150286A1 (en) | System analyzing device, system analyzing method, and computer-readable recording medium | |
| CN118462630B (en) | Automatic detection device and detection method for fan manufacturing | |
| CN111258854B (en) | Model training method, alarm method based on prediction model and related device | |
| CN112834942A (en) | Battery management system life test method and device based on temperature alternating test | |
| CN118575145A (en) | Method, device and computer medium for calculating residual service life of electronic system | |
| CN114083987A (en) | Battery monitoring parameter correction method and device and computer equipment | |
| JP5771318B1 (en) | Abnormality diagnosis apparatus and abnormality diagnosis method | |
| CN109581125B (en) | Method and device for detecting service life of power module of wind power converter and storage medium | |
| WO2022190748A1 (en) | Diagnosis device | |
| KR102797798B1 (en) | Diagnostic device and diagnostic method and plasma processing device and semiconductor device manufacturing system | |
| CN111651503B (en) | Power distribution network data anomaly identification method and system and terminal equipment | |
| JP2719439B2 (en) | Equipment failure diagnosis system | |
| JP2023102657A (en) | Equipment diagnosis apparatus and equipment diagnosis method | |
| US11650577B2 (en) | Plant operation data monitoring device and method |
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 |