CN117313006A - Online identification method suitable for abnormal values of multiple instrument measurement results - Google Patents
Online identification method suitable for abnormal values of multiple instrument measurement results Download PDFInfo
- Publication number
- CN117313006A CN117313006A CN202311049296.1A CN202311049296A CN117313006A CN 117313006 A CN117313006 A CN 117313006A CN 202311049296 A CN202311049296 A CN 202311049296A CN 117313006 A CN117313006 A CN 117313006A
- Authority
- CN
- China
- Prior art keywords
- data
- measurement results
- meters
- deviation
- abnormal
- 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
- 238000005259 measurement Methods 0.000 title claims abstract description 80
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000012952 Resampling Methods 0.000 claims description 3
- 108700041286 delta Proteins 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 9
- 230000005540 biological transmission Effects 0.000 abstract description 8
- 238000010276 construction Methods 0.000 abstract description 4
- 230000001960 triggered effect Effects 0.000 abstract description 4
- 238000013461 design Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an online identification method suitable for abnormal values of multiple instrument measurement results, and belongs to the technical field of power equipment; the method comprises the steps of collecting data of a plurality of meters, and setting normal deviation amount and deviation comparison; according to the intelligent operation and maintenance method, 3 or more meters are configured for measurement through obtaining a certain operation parameter of the equipment, wherein faults can occur in the measuring point, the meters and the data transmission process, when the faults occur, the obtained corresponding measurement results are abnormal, the abnormal measurement results are identified on line and do not participate in the subsequent algorithm, false alarms and false diagnoses triggered by the abnormal measurement results caused by the faults of the measuring point/the meters/the data transmission are avoided, and the intelligent operation and maintenance method can be widely applied to intelligent operation and maintenance construction of the equipment of the intelligent power station.
Description
Technical Field
The invention relates to an online identification method suitable for abnormal values of multiple instrument measurement results, and belongs to the technical field of power equipment.
Background
Along with the development of economy, the digitization and intelligent transformation of a power station become necessary routes for ensuring the production operation safety, improving the production operation efficiency and realizing energy conservation and emission reduction of power enterprises.
The intelligent power station comprises an intelligent equipment layer, an intelligent control layer, an intelligent production supervision layer and an intelligent management layer, wherein the intelligent operation and maintenance of the production equipment is an important component of the intelligent production supervision layer.
The intelligent operation and maintenance function of the equipment is realized, the operation data of the equipment is required to be collected, arranged, calculated and analyzed, if a measuring point or an instrument fails, the collected operation data is abnormal, and a calculation result and an analysis conclusion obtained based on the abnormal operation data cannot reflect the actual operation state of the equipment, but can trigger false alarm and false diagnosis. It is therefore important how to identify abnormal operation data due to station/meter faults.
Disclosure of Invention
The invention aims at: aiming at the problems, the online identification method for the abnormal values of the measurement results of the multiple meters is provided, wherein the multiple meters are configured with 3 or more meters for acquiring certain operation parameters of equipment, wherein the measuring points, the meters and the data transmission process can possibly fail, when the failure occurs, the acquired corresponding measurement results are abnormal, the abnormal measurement results are identified online, the follow-up algorithm is not involved, and the online identification method is an important link for improving the accuracy and the credibility of the intelligent operation and maintenance results.
The technical scheme adopted by the invention is as follows:
an online identification method suitable for abnormal values of multiple instrument measurement results comprises the following steps:
s1, designating an operation parameter A to be measured, and configuring at least 3 meters for the operation parameter A to measure;
s2, transmitting the data measured in the step S1 to a designated system or platform for storage in real time, and taking the stored measurement result as an original measurement result;
s3, acquiring real-time measurement results of the operation parameters A after the processing of a plurality of meters, and acquiring corresponding data A_D1, data A_D2, data A_D3, … … and data A_Dn, wherein n is the number of the meters;
s4, calculating the latest data A_D1, data A_D2, data A_D3 and … … with the same time stamp and the median A_Dm of the data A_Dn according to the data obtained in the step S3, and taking the median as a reference value;
s5, according to the median A_Dm obtained in the step S4, comparing and analyzing the obtained data A_D1, data A_D2, data A_D3, … … and data A_Dn with the median A_Dm respectively;
s6, according to the comparison analysis result, if the comparison analysis result is abnormal, the data measured by the corresponding instrument does not enter the subsequent calculation of the whole system; if the data measured by the corresponding instrument is judged to be normal, the data measured by the corresponding instrument is normally entered into subsequent calculation of the whole system, and the judgment result is stored.
S7, repeating the steps S3-S6, and realizing the online identification of abnormal values of the multiple instrument measurement results of the operation parameter A.
Further, in step S2, the time stamp and the period of the original measurement result of the operation parameter a are made the same by the resampling algorithm, the processed measurement result is stored, and the stored measurement result is referred to as the processed real-time measurement result of the operation parameter a.
Further, in step S3, the real-time measurement results after the processing of the plurality of meters are the plurality of meter measurement results for obtaining the latest running parameter a with the same time stamp.
Further, in step S5, a step S51 of setting a normal deviation δ of the operation parameter a with respect to the median a_dm and using the normal deviation as a standard contrast value is further included.
Further, the normal deviation amount is an absolute value or a relative value, and the normal deviation amount is a positive number.
Further, step S52 is further included, where n data with the same obtained timestamp are compared with the median a_dm, so as to obtain a deviation of each data, and take an absolute value of the deviation, and ensure that the algorithm of the deviation is consistent with the normal deviation algorithm.
Further, the obtained n data are subjected to offset calculation with the median a_dm, respectively, and then the offset value δ1, the offset value δ2, the offset values δ3, … …, and the offset value δn are obtained.
Further, step S53 is further included, where each obtained deviation value is compared with the normal deviation value δ.
Further, in step S6, when a certain deviation value is less than or equal to δ, it is determined that the corresponding meter measurement result is in a normal state; and when a certain deviation value is larger than delta, judging that the corresponding instrument measurement result is in an abnormal state.
Further, in step S6, a determination is stored that the measurement result of each meter of the operation parameter a is normal or abnormal.
Further, another operation parameter is designated, 3 or more meters are configured for measurement, and the steps S1 to S7 are repeated. .
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
the invention relates to an online identification method suitable for abnormal values of multiple instrument measurement results, which is characterized in that 3 or more instruments or meters are configured to measure by acquiring certain operation parameters of equipment, wherein the measuring points, the instruments and the data transmission process can all have faults, when the faults occur, the acquired corresponding measurement results are abnormal, the abnormal measurement results are identified online without participating in a subsequent algorithm, false alarms and false diagnoses triggered by the abnormal measurement results caused by the faults of the measuring points/the instruments/the data transmission are avoided, and the online identification method can be widely applied to the intelligent operation and maintenance construction of the equipment of an intelligent power station.
Drawings
The invention will now be described by way of example and with reference to the accompanying drawings in which:
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
All of the features disclosed in this specification, or all of the steps in a method or process disclosed, may be combined in any combination, except for mutually exclusive features and/or steps.
Any feature disclosed in this specification may be replaced by alternative features serving the same or equivalent purpose, unless expressly stated otherwise. That is, each feature is one example only of a generic series of equivalent or similar features, unless expressly stated otherwise.
Examples
An online identification method suitable for abnormal values of multiple instrument measurement results is shown in fig. 1, and comprises the following steps:
s1, designating an operation parameter A to be measured, and configuring at least 3 meters for the operation parameter A to measure;
s2, transmitting the data measured in the step S1 to a designated system or platform for storage in real time, and taking the stored measurement result as an original measurement result;
s3, acquiring real-time measurement results of the operation parameters A after a plurality of instruments are processed, and acquiring corresponding data A_D1, data A_D2, data A_D3, … … and data A_Dn, wherein n is the number of the instruments;
s4, calculating the latest corresponding data A_D1, data A_D2, data A_D3 and … … with the same time stamp and the median A_Dm of the data A_Dn according to the data obtained in the step S3, and taking the median as a reference value;
s5, according to the median A_Dm obtained in the step S4, comparing and analyzing the obtained data A_D1, data A_D2, data A_D3, … … and data A_Dn with the median A_Dm respectively;
s6, according to the comparison analysis, if the comparison analysis is judged to be normal and abnormal, the data measured by the corresponding instrument does not enter the subsequent calculation of the whole system; if the data measured by the corresponding instrument is judged to be normal, the data measured by the corresponding instrument is normally entered into subsequent calculation of the whole system, and the judgment result is stored.
S7, repeating the steps S3-S6, and realizing the online identification of abnormal values of the multiple instrument measurement results of the operation parameter A.
In this embodiment, unlike the conventional identification method, the method adopts a plurality of devices to collect related data of specified parameters, performs further processing on the collected data, identifies whether the data collection of each measurement device is abnormal according to a certain comparison method, can accurately identify if the data collection is abnormal without affecting the whole subsequent calculation, and simultaneously avoids false alarm and false diagnosis triggered by abnormal measurement results caused by measuring points/meters/data transmission faults, so that the method can be widely applied to the intelligent operation and maintenance construction of the intelligent power station.
More specifically, the system or platform supports algorithmic model operations. And, the system or platform can obtain the real-time raw measurement results of the above-mentioned meters.
In the above specific step design, more specifically, in step S2, the time stamp and the period of the original measurement result of the operation parameter a are made to be the same by the resampling algorithm, the measurement result after processing is stored, and the stored measurement result is referred to as the real-time measurement result after processing of the operation parameter a.
As a more specific design, in step S3, the real-time measurement results after the processing of the plurality of meters are a plurality of meter measurement results for obtaining the latest operation parameter a with the same time stamp.
For the design on the step, in the comparison analysis design of the whole parameters, further, in step S5, step S51 is further included, and the normal deviation delta of the operation parameter relative to the median a_dm is set, and the normal deviation delta is used as a standard comparison value.
More specifically, the normal deviation amount is an absolute value or a relative value, and the normal deviation amount is a positive number. Positive values are used as a comparison analysis, which is more accurate and also allows the presence of positive and negative deviations.
Based on the above specific design, the method further includes step S52, comparing the obtained n data with the median a_dm, respectively, obtaining the deviation of each data, and taking the absolute value thereof, and ensuring that the deviation algorithm is consistent with the normal deviation algorithm in claim 5.
Further, the optimal design is that n data with the same obtained time stamp are respectively subjected to deviation calculation with the median A_Dm, and then a deviation value delta 1, a deviation value delta 2, deviation values delta 3, … … and deviation values delta n are obtained, wherein n is the number of meters.
Specifically, step S53 is further included, where each obtained deviation value is compared with the normal deviation value δ.
Further, in step S6, when a certain deviation value is less than or equal to δ, it is determined that the corresponding meter measurement result is in a normal state; and when a certain deviation value is larger than delta, judging that the corresponding instrument measurement result is in an abnormal state.
Further, in step S6, a determination is stored that the measurement result of each meter of the operation parameter a is normal or abnormal.
And designating another operation parameter in the measurement application of the other operation parameter, configuring 3 or more meters for measurement, and repeating the steps S1-S7. And carrying out on-line identification of abnormal values of the measurement results of the multiple meters by adopting the same method.
In summary, the method for online identifying abnormal values of measurement results of multiple meters is configured to measure 3 or more meters by acquiring a certain operation parameter of the device, wherein the measurement points, the meters and the data transmission processes may all have faults, when the faults occur, the acquired corresponding measurement results are abnormal, the abnormal measurement results are identified online, the follow-up algorithm is not participated, false alarm and false diagnosis triggered by the abnormal measurement results caused by the faults of the measurement points/meters/data transmission are avoided, and the method can be widely applied to intelligent operation and maintenance construction of the device of an intelligent power station.
The invention is not limited to the specific embodiments described above. The invention extends to any novel one, or any novel combination, of the features disclosed in this specification, as well as to any novel one, or any novel combination, of the steps of the method or process disclosed.
Claims (10)
1. An online identification method suitable for abnormal values of multiple instrument measurement results is characterized in that: the method comprises the following steps:
s1, designating an operation parameter A to be measured, and configuring at least 3 meters for the operation parameter A to measure;
s2, transmitting the data measured in the step S1 to a designated system or platform for storage in real time, and taking the stored measurement result as an original measurement result;
s3, acquiring real-time measurement results of the operation parameters A after measurement processing of a plurality of meters to obtain corresponding data A_D1, data A_D2, data A_D3, … … and data A_Dn, wherein n is the number of the meters;
s4, calculating the median A_Dm of the data A_D1, the data A_D2, the data A_D3 and … … and the data A_Dn according to the data obtained in the step S3, and taking the median as a reference value;
s5, comparing and analyzing data A_D1, data A_D2, data A_D3, … … and data A_Dn with the median A_Dm according to the median A_Dm obtained in the step S4;
s6, according to the comparison analysis result, if the comparison analysis result is abnormal, the data measured by the corresponding instrument does not enter the subsequent calculation of the whole system; if the data measured by the corresponding instrument is judged to be normal, the data measured by the corresponding instrument is normally entered into subsequent calculation of the whole system, and the judgment result is stored.
S7, repeating the steps S3-S6, and realizing the online identification of abnormal values of the multiple instrument measurement results of the operation parameter A.
2. The on-line identification method for abnormal values of measurement results of a plurality of meters according to claim 1, wherein: in step S2, the time stamp and the period of the original measurement result of the operation parameter a are made the same by the resampling algorithm, the processed measurement result is stored, and the stored measurement result is referred to as the processed real-time measurement result of the operation parameter a.
3. The on-line identification method for abnormal values of measurement results of a plurality of meters according to claim 1, wherein: in step S3, the real-time measurement results after the processing of the plurality of meters are the acquired latest operation parameter a plurality of meters with the same time stamp.
4. The on-line identification method for abnormal values of measurement results of a plurality of meters according to claim 1, wherein: in step S5, a step S51 of setting a normal deviation amount δ of the operation parameter a with respect to the median a_dm and comparing the normal deviation amount with the standard deviation amount is further included.
5. The on-line identification method for abnormal values of measurement results of a plurality of meters according to claim 1, wherein: the normal deviation amount is an absolute value or a relative value, and the normal deviation amount is a positive number.
6. The on-line identification method for abnormal values of multiple meter measurement results according to claim 4, wherein: the method also comprises a step S52 of comparing the obtained n data of the same operation parameter A with the median A_Dm respectively, obtaining the deviation of each data, taking the absolute value of the deviation, and ensuring that the algorithm of the deviation is consistent with the normal deviation in the claim 4.
7. The on-line identification method for abnormal values of multiple meter measurement results according to claim 6, wherein: and respectively carrying out deviation calculation on the n data of the acquired operation parameters A and the median A_Dm, and then acquiring a deviation value delta 1, a deviation value delta 2, deviation values delta 3 and … … and a deviation value delta n.
8. The method for online identification of abnormal values of measurement results of a plurality of meters according to claim 7, wherein: further comprising step S53, comparing each deviation value of the acquired operation parameter a with the normal deviation delta.
9. The on-line identification method for abnormal values of measurement results of a plurality of meters according to claim 8, wherein: in step S6, when a certain deviation value is less than or equal to δ, determining that the corresponding meter measurement result is in a normal state; when a certain deviation value is larger than delta, judging that the measurement result of the corresponding instrument is in an abnormal state; and simultaneously storing the judgment result that the measurement result of each instrument of the operation parameter A is normal or abnormal.
10. The on-line identification method for abnormal values of measurement results of a plurality of meters according to claim 1, wherein: and designating another operation parameter, configuring 3 or more meters for measurement, and repeating the steps S1-S7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311049296.1A CN117313006A (en) | 2023-08-18 | 2023-08-18 | Online identification method suitable for abnormal values of multiple instrument measurement results |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311049296.1A CN117313006A (en) | 2023-08-18 | 2023-08-18 | Online identification method suitable for abnormal values of multiple instrument measurement results |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117313006A true CN117313006A (en) | 2023-12-29 |
Family
ID=89254262
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311049296.1A Pending CN117313006A (en) | 2023-08-18 | 2023-08-18 | Online identification method suitable for abnormal values of multiple instrument measurement results |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117313006A (en) |
-
2023
- 2023-08-18 CN CN202311049296.1A patent/CN117313006A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111508216B (en) | Intelligent early warning method for dam safety monitoring data | |
CN115687983A (en) | Bridge health state monitoring method and system and electronic equipment | |
CN115225463A (en) | Hardware fault monitoring method and system based on IT operation and maintenance | |
CN118016202B (en) | Chemical equipment operation analysis method and system based on steam-water quality | |
CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
CN112926656A (en) | Method, system and equipment for predicting state of circulating water pump of nuclear power plant | |
CN112580858A (en) | Equipment parameter prediction analysis method and system | |
CN117421998A (en) | Multi-mode data-based power transmission overhead line health state evaluation system | |
CN114459523B (en) | Calibration early warning method of online quality detection instrument | |
CN117290795A (en) | Online identification method suitable for abnormal values of measurement results of single instrument | |
CN109211564B (en) | Self-adaptive threshold detection method for health assessment of ball screw pair | |
CN117826693A (en) | Intelligent oil depot monitoring and early warning system and method | |
WO2024179001A1 (en) | Method for dynamic verification of online chemical instrument of thermal power plant | |
CN117313006A (en) | Online identification method suitable for abnormal values of multiple instrument measurement results | |
CN117009741A (en) | Abnormal analysis method and system based on generated energy | |
CN109614758A (en) | The monitoring method of circular shape error with spatial coherence | |
CN110020000A (en) | Determine the method and apparatus of abnormal air speed data | |
CN118071168B (en) | Comprehensive energy management system | |
CN118396252B (en) | MES client data analysis optimization method based on cloud computing | |
CN118395222B (en) | Abnormality monitoring method and system for transformer | |
CN117874687B (en) | Data interaction method of industrial tablet personal computer | |
CN117978628B (en) | Communication control method and system based on intelligent park | |
CN118509821B (en) | Highway bridge construction management system and method | |
CN117723917B (en) | Monitoring application method based on optical fiber extrinsic Fabry-Perot type ultrasonic sensor | |
CN114386730A (en) | Combustion stability evaluation method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |