CN110826024A - Sampling discrimination method for sensor data abnormity - Google Patents
Sampling discrimination method for sensor data abnormity Download PDFInfo
- Publication number
- CN110826024A CN110826024A CN201911130196.5A CN201911130196A CN110826024A CN 110826024 A CN110826024 A CN 110826024A CN 201911130196 A CN201911130196 A CN 201911130196A CN 110826024 A CN110826024 A CN 110826024A
- Authority
- CN
- China
- Prior art keywords
- data
- sensor
- sampling
- batch
- judgment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Safety Devices In Control Systems (AREA)
Abstract
The invention discloses a sampling judgment method for sensor data abnormity, and belongs to the technical field of detection. The method can find the faults which cannot be judged by rules such as signal disappearance, signal maintenance or exceeding of upper and lower limits and the like in the sensor signals to be incapable of measuring the measured target so as to obtain real monitoring data. The method utilizes mature technology and tools of the SPC method, does not need to rely on other reference standards, thereby being capable of effectively distinguishing the sensor fault in time and giving an alarm, carrying out equipment shutdown, sensor maintenance or replacement, ensuring the requirements of controlled and safe measured targets and the like, and avoiding loss of production out of control, equipment fault and the like caused by faults.
Description
Technical Field
The invention belongs to the technical field of detection, and particularly relates to a sampling judgment method for sensor data abnormity.
Background
In the industrial civilized society, detection and sensing devices cannot be used for human life, industrial production, social operation and the like, and especially normal operation of equipment and facilities in the industries of manufacturing, communication, electric power, traffic, logistics and the like is very dependent on detection and monitoring of the sensors on the states of corresponding equipment. If the sensor breaks down, the monitoring and control of the equipment state can be influenced, and even safety accidents occur. If the fault of the production processing input sensor can cause the loss such as unqualified process and unqualified product, if the raw material proportion of the metallurgical production is not accurate, the produced tower drum can not meet the requirement, and the product can be returned or scrapped; the failure of the feedback control sensor can cause out-of-control, if the wind speed and the wind direction of the fan are measured inaccurately, the control is not in place, and the generated energy is reduced; the failure of the safety monitoring sensor can cause the factor to be over-limit, so that failure damage or safety accidents occur, if the temperature monitoring of the generator does not give an alarm, the generator can be burnt by over-temperature or explode by fire; if the index sensor fails, a decision-making error may be caused, for example, if the electric quantity statistical sensor fails, economic accounting loss or debugging error may be caused.
The sensor fault types are various, generally, the performance such as signal disappearance, signal maintenance or exceeding upper and lower limits can be easily distinguished, but when the monitoring value slightly fluctuates in a normal range, the signal is difficult to distinguish from a normal measurement state signal. Meanwhile, the existing discrimination means all need to have a reference standard, such as: the comparison between a predicted value and a measured value, the relationship between a monitoring numerical value and another detection quantity, the similarity change of a plurality of position sensors and the like, the application range is small, and the requirements of modern industry cannot be met.
Disclosure of Invention
In order to solve the above problems, an object of the present invention is to provide a method for sampling and determining sensor data anomalies, which can find out, from a sensor signal itself, a fault that cannot be determined by rules such as signal disappearance, signal retention, or exceeding upper and lower limits, and cannot be measured, so as to obtain real monitoring data and ensure the requirements of control, safety, and the like of a measured target.
The invention is realized by the following technical scheme:
a sampling discrimination method for sensor data abnormity comprises the following steps:
1) extracting a plurality of batches of data containing a plurality of sample numbers from the recorded data of the sensor;
2) selecting a control chart according to a statistical process control method, and calculating a statistical value of each batch of data;
3) solving the central line and upper and lower limit control limits of the control chart;
4) determining uncontrolled state data and the rest controlled state data in the batch of data according to a statistical process judgment standard;
5) calculating a fault index of the sensor;
6) comparing the fault index of the sensor with a sensor alarm threshold, and when the fault index of the sensor is larger than the sensor alarm threshold, alarming to complete the judgment, and turning to the step 1); and when the fault index of the sensor is less than or equal to the sensor alarm threshold, no alarm is given, the judgment is finished, and the step 1) is carried out.
Preferably, in step 1), before extracting the data, it is determined whether the data is in a sampleable state, and then the data is extracted in the sampleable state.
Preferably, in step 1), the extraction is periodically extracted in time series.
Preferably, the time intervals between the data of the plurality of batches are equal, and the time intervals between the data of each batch are equal.
Preferably, in step 2), the control chart is a mean-standard deviation control chart, and the statistical value of each batch of data comprises the mean and the standard deviation of each batch of data.
Further preferably, the mean and standard deviation are the results of the last sample data calculation.
Preferably, in step 4), when 0 < the data quantity of the controlled state < the total quantity of the batch of data, the fault index of the sensor is the data quantity of the controlled state/the total quantity of the batch of data.
Compared with the prior art, the invention has the following beneficial technical effects:
the sampling judgment method for the sensor data abnormity can find the fault which cannot be judged by the rules of signal disappearance, signal maintenance or exceeding the upper limit and the lower limit and the like in the sensor signal to obtain the real monitoring data. The method utilizes mature technology and tools of the SPC method, does not need to rely on other reference standards, thereby being capable of effectively distinguishing the sensor fault in time and giving an alarm, carrying out equipment shutdown, sensor maintenance or replacement, ensuring the requirements of controlled and safe measured targets and the like, and avoiding loss of production out of control, equipment fault and the like caused by faults.
Furthermore, before data is extracted, whether the data is in a sampling state or not is judged, and the situation that the data measured by the sensor is judged to be in a fault without fluctuation, such as that sampling cannot be carried out when the equipment is stopped, is avoided.
Further, the extraction is performed periodically in time sequence, since the sensor status will change with time and usually will not be faulty at the time of installation, but will be faulty for a while of use, so the data extraction and subsequent analysis are performed at intervals.
Furthermore, the time intervals among a plurality of batches of data are equal, and the time intervals of a plurality of data in each batch of data are equal, so that the data can be consistent, and the parameter consistency during calculation is ensured.
Furthermore, the control chart is a mean-standard deviation control chart, the mean value and the standard deviation of each batch of data are used as statistical values, the operation is simple, and quantitative data can be provided for the next step of judgment.
Further, when the sensor fails, the mean value and the standard deviation are the calculation results of the last sampling data, because the mean value and the standard deviation are always unchanged theoretically if the working condition is stable during production control, otherwise, the production is abnormal. On the contrary, the measured data of the sensor is the same, and the mean value and the standard deviation of the measured data are changed all the time theoretically, otherwise, the measured object is not changed all the time (generally, the measured wind speed, the measured air temperature, the measured oil pressure and the like are not possible) or the sensor is abnormal. Therefore, the selection of the mean value, the standard deviation and the like as the judgment standard also needs to be dynamically updated, namely the result of the last sampling data calculation is taken as the standard.
Further, the data quantity of the controlled state is 0 < the total quantity of the batch of data, and when the data quantity of the controlled state is 0, the data of all the controlled states are normal measurement data of the sensor; when the data amount of the controlled state is equal to the total amount of the batch of data, it is possible that the target amount to be measured does so. When the fault index is between the two types, the data occupation ratio of the controlled state is used as the fault index of the sensor, and the fault index is simple and effective.
Drawings
FIG. 1 is a flow chart of a sampling discrimination method of the present invention.
Detailed Description
The invention will now be described in further detail with reference to the drawings and specific examples, which are given by way of illustration and not by way of limitation.
Referring to fig. 1, a flow chart of a method for sampling and determining sensor data anomalies according to the present invention is divided into the following steps:
1) when the sensor is judged to be in a sampling state, 1 time of data is extracted every 1 hour from 24-hour recorded data of the sensor, each time of the data is extracted for 1 minute, the sampling interval is 1 second, 24 batches of data are obtained, and the sample volume of each batch of data is 60.
2) Selecting a mean-standard deviation control chart according to a statistical process control method, and calculating a statistical value of each batch of data: mean value
And standard deviation si(i ═ 1,2, … … 24); other control charts, such as median-range, can also be selectedAnd single value-moving range, etc. according to the corresponding requirements to calculate the required statistical value.
3) Finding the control chart centerline:upper and lower limit control limits:
partitioning: zone A (-3 sigma to-2 sigma, 3 sigma to 2 sigma), zone B (-2 sigma to-sigma, 2 sigma to sigma), zone C (-sigma to sigma). Due to the fact that
Where σ is unknown, using its unbiased estimationInstead, the upper and lower control limits of the mean-standard deviation control chart are
In the formula (I), the compound is shown in the specification,
is composed of
The average value of (a) of (b),
is siMean value of (C)4、A3The coefficient of the control line is calculated, and the coefficient table of the control line can be determined by looking up the table 2 metering control chart in the GB-T4091-2001 conventional control chart.
4) Determining the data of the uncontrolled state in the batch of data and the rest data of the controlled state according to the judgment standard of the SPC statistical process; according to eight mode tests of GB-T4091-2001, several of them can be selected or tested by other models, and according to sensor characteristics optimization, the correspondent out-of-control point is marked as data (non-random fluctuation point) of uncontrolled state.
5) Calculating a fault index of the sensor; if all the data (non-random fluctuation points) in the uncontrolled state are judged, the data are the normal measurement data of the sensor; if all the data (random fluctuations) determining the controlled state are determined, a sensor may malfunction, which is not absolutely required for excluding the target quantity to be measured. In the meantime, an index (0-100%) can be used, for example, the dot data ratio, i.e. when 0 < the data quantity of the controlled state < the total quantity of the batch of data, the failure index of the sensor is the data quantity of the controlled state/the total quantity of the batch of data. It can also be weighted according to time, with the weight being larger near the last sample and smaller far (increasing the weight after failure, decreasing the normal weight early, finding failure as early as possible).
6) Comparing the fault index of the sensor with a set sensor alarm threshold, when the fault index of the sensor is larger than the sensor alarm threshold, alarming, finishing the judgment, turning to the step 1 after equipment is shut down, and the sensor is maintained or replaced, and starting the next judgment; and when the fault index of the sensor is less than or equal to the sensor alarm threshold, the alarm is not given, the judgment is finished, and the step 1) is carried out to start the next judgment.
Claims (7)
1. A sampling judgment method for sensor data abnormity is characterized by comprising the following steps:
1) extracting a plurality of batches of data containing a plurality of sample numbers from the recorded data of the sensor;
2) selecting a control chart according to a statistical process control method, and calculating a statistical value of each batch of data;
3) solving the central line and upper and lower limit control limits of the control chart;
4) determining uncontrolled state data and the rest controlled state data in the batch of data according to a statistical process judgment standard;
5) calculating a fault index of the sensor;
6) comparing the fault index of the sensor with a sensor alarm threshold, and when the fault index of the sensor is larger than the sensor alarm threshold, alarming to complete the judgment, and turning to the step 1); and when the fault index of the sensor is less than or equal to the sensor alarm threshold, no alarm is given, the judgment is finished, and the step 1) is carried out.
2. The method for judging sampling of sensor data abnormality according to claim 1, wherein in step 1), before the data is extracted, it is judged whether or not the data is in a sampleable state, and then the data is extracted in the sampleable state.
3. The method for sampling and discriminating a sensor data abnormality according to claim 1, wherein in the step 1), the extraction is periodically performed in time series.
4. The method for sampling and discriminating the abnormality of the sensor data according to claim 1 wherein the time intervals between the plurality of data batches are equal and the time intervals between the plurality of data batches are equal.
5. The method for sampling and discriminating the abnormality of the sensor data according to claim 1, wherein in the step 2), the control chart is a mean-standard deviation control chart, and the statistical value of each batch of data includes the mean and the standard deviation of each batch of data.
6. The method of claim 5, wherein the mean and standard deviation are the results of the last calculation of the sampled data.
7. The sampling discrimination method for sensor data abnormality according to claim 1, wherein in step 4), when 0 < the data quantity of the controlled state < the total quantity of the batch of data, the fault index of the sensor is the data quantity of the controlled state/the total quantity of the batch of data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911130196.5A CN110826024A (en) | 2019-11-18 | 2019-11-18 | Sampling discrimination method for sensor data abnormity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911130196.5A CN110826024A (en) | 2019-11-18 | 2019-11-18 | Sampling discrimination method for sensor data abnormity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110826024A true CN110826024A (en) | 2020-02-21 |
Family
ID=69556771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911130196.5A Pending CN110826024A (en) | 2019-11-18 | 2019-11-18 | Sampling discrimination method for sensor data abnormity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110826024A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597398A (en) * | 2020-05-14 | 2020-08-28 | 易思维（杭州）科技有限公司 | Nelsen rule exception judgment system and method based on streaming measurement data |
| CN112528230A (en) * | 2020-12-10 | 2021-03-19 | 中国空间技术研究院 | Parameter consistency control method and device based on precision and distribution conversion correction |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1206862A (en) * | 1997-07-29 | 1999-02-03 | 林恒延 | Universal monitor apparatus for quality control by using control diagram principle |
| CN105676817A (en) * | 2016-01-14 | 2016-06-15 | 西安电子科技大学 | Statistical process control method of mean-standard deviation control charts of samples of different sizes |
| CN108897954A (en) * | 2018-06-29 | 2018-11-27 | 龙源（北京）风电工程技术有限公司 | Wind turbines temperature pre-warning method and its system based on BootStrap confidence calculations |
-
2019
- 2019-11-18 CN CN201911130196.5A patent/CN110826024A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1206862A (en) * | 1997-07-29 | 1999-02-03 | 林恒延 | Universal monitor apparatus for quality control by using control diagram principle |
| CN105676817A (en) * | 2016-01-14 | 2016-06-15 | 西安电子科技大学 | Statistical process control method of mean-standard deviation control charts of samples of different sizes |
| CN108897954A (en) * | 2018-06-29 | 2018-11-27 | 龙源（北京）风电工程技术有限公司 | Wind turbines temperature pre-warning method and its system based on BootStrap confidence calculations |
Non-Patent Citations (1)
| Title |
|---|
| 国家质量监督检验检疫总局质量管理司组织编写: "《质量专业理论与实务 中级》", 31 March 2002 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597398A (en) * | 2020-05-14 | 2020-08-28 | 易思维（杭州）科技有限公司 | Nelsen rule exception judgment system and method based on streaming measurement data |
| CN111597398B (en) * | 2020-05-14 | 2023-09-08 | 易思维（杭州）科技有限公司 | Nelson rule judging system and method based on flow measurement data |
| CN112528230A (en) * | 2020-12-10 | 2021-03-19 | 中国空间技术研究院 | Parameter consistency control method and device based on precision and distribution conversion correction |
| CN112528230B (en) * | 2020-12-10 | 2024-04-09 | 中国空间技术研究院 | Parameter consistency control method and device based on precision and distribution conversion correction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110849404B (en) | Continuous discrimination method for sensor data abnormity | |
| CN109933905B (en) | Mechanical equipment health state assessment method based on multi-dimensional early warning analysis | |
| CN106372735B (en) | Relay protection state evaluation method | |
| CN102182671B (en) | State analysis monitoring method of gas compressor | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| CN110826024A (en) | Sampling discrimination method for sensor data abnormity | |
| CN103942735A (en) | Method for evaluating relay protection states | |
| EP3553044A1 (en) | System and method of remote object monitoring | |
| CN106017729A (en) | SPC (Statistical Process Control) based motor temperature monitoring method | |
| CN111913056B (en) | Method for estimating working condition starting state of self-adaptive super real-time unit | |
| CN106845826B (en) | PCA-Cpk-based cold continuous rolling production line service quality state evaluation method | |
| CN111222247A (en) | Early fault early warning method for rotary machine | |
| CN115423355A (en) | Power plant coal mill fault early warning method and system | |
| CN108416386A (en) | A kind of method and system judged extremely for Hydropower Unit bearing temperature | |
| CN113007040A (en) | Online monitoring and fault early warning system and method for main shaft assembly movement of wind turbine generator | |
| EP2631724B1 (en) | Method for measuring health index of plant in which state of lower component is reflected, and computer-readable storage medium in which program for performing the method is stored | |
| CN112326246A (en) | Bearing safety state online monitoring method based on periodic data and nuclear density estimation | |
| CN108844662A (en) | A kind of numerically-controlled machine tool electrical cabinet state evaluating method | |
| CN115270982A (en) | Switch cabinet fault prediction method based on multi-data neural network | |
| CN104078381A (en) | Method for setting specification limit of measurement machine monitoring chart | |
| CN104731056B (en) | The method of the quick operation stability for judging chemical production device | |
| CN113739841A (en) | Multivariable steady-state detection method and system based on uncertainty theory | |
| CN117968405B (en) | Pressure sintering furnace monitoring method based on clustering algorithm | |
| CN114151291B (en) | Early fault monitoring method for wind turbine generator | |
| CN117234257B (en) | Factory workshop temperature regulation and control method based on data analysis |
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: 20200221 |
|
| RJ01 | Rejection of invention patent application after publication |