CN107741945A - A kind of CEMS system trouble analysis methods of outlier detection based on density - Google Patents
A kind of CEMS system trouble analysis methods of outlier detection based on density Download PDFInfo
- Publication number
- CN107741945A CN107741945A CN201710741799.3A CN201710741799A CN107741945A CN 107741945 A CN107741945 A CN 107741945A CN 201710741799 A CN201710741799 A CN 201710741799A CN 107741945 A CN107741945 A CN 107741945A
- Authority
- CN
- China
- Prior art keywords
- sensor
- density
- parameter
- fault diagnosis
- cems
- 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
- 238000000738 capillary electrophoresis-mass spectrometry Methods 0.000 title claims abstract description 19
- 238000013450 outlier detection Methods 0.000 title claims abstract description 15
- 238000004458 analytical method Methods 0.000 title claims abstract description 10
- 238000003745 diagnosis Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000013480 data collection Methods 0.000 claims abstract description 7
- 238000009412 basement excavation Methods 0.000 claims abstract description 6
- 239000003500 flue dust Substances 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000002572 peristaltic effect Effects 0.000 claims description 2
- 239000000523 sample Substances 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 3
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 8
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 239000003546 flue gas Substances 0.000 description 3
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 238000011109 contamination Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229960004424 carbon dioxide Drugs 0.000 description 1
- 229910002090 carbon oxide Inorganic materials 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The present invention relates to a kind of CEMS system trouble analysis methods of outlier detection based on density, comprise the following steps：Step 1 gathers the corresponding parameter of CEMS systems and system data by sensor；The parameter of each sensor of acquisition is exported into background host computer database and stored by step 2；The parameter of each sensor is established into fault diagnosis data collection in the way of time slip-window simultaneously；Step 3 is to the fault diagnosis data collection established in step 2, the degree that peels off of the parameter of newest each sensor is calculated with the outlier excavation method based on density as the whether normal foundation of physical characteristic for judging current time system, and carries out real-time fault diagnosis in exception and obtains fault diagnosis result；Step 4 exports judged result and fault diagnosis result in running state information, step 3 to background host computer database.The present invention can plan maintenance scheme according to the usage scenario of instrument, ensure the reliability service of equipment.
Description
Technical field
The present invention relates to flue gas monitoring technical field, the CEMS systems of more particularly to a kind of outlier detection based on density
Failure analysis methods.
Background technology
As current ecological environment constantly deteriorates, especially PM2.5 getting worses, emission of the China to coal-burning power plant
There are more strict requirements, the gaseous state that coal-burning power plant is discharged to air（Flue gas）Pollutant（Sulfur dioxide, nitrogen oxides, one
Carbonoxide etc.）And solid pollutant（Flue dust）Control is needed in certain scope.The continuous prison of CEMS fixed-contaminations material resource discharge
Examining system（Continuous Emissions Monitoring System）For long-term and continuous monitoring fixed-contamination material resource
The flue gas and flue dust of discharge, emission status of the reflection flue dust within certain a period of time.But CEMS is one kind is operated in more dirt, height
System in the unstable environment of wet, corrosivity and flow field, severe, precision instrument the damage of environment can all cause system acquisition dirty
Contaminate the inaccuracy of thing concentration data.Good data source can be that power network is transported to the discharge of power plant pollution thing, desulphurization denitration equipment
Row monitoring provides data-guiding, and decision support is provided for power network energy-saving power generation dispatching and the examination of desulphurization denitration electricity.It is then desired to
Exceptional data point is screened out using the method for outlier detection, finds CEMS intersystem problem equipment.
So-called outlier, it is exactly the data of those distinguished remote routine data objects.Because outlier is not total
It is isolated appearance, it is likely that occur in the form of microcommunity, that is, the cluster that peels off occurs.In all types of detection algorithms, based on cluster
Outlier detection algorithm will not belong to the point of any cluster and be defined as outlier, have preferable effect for Outliers Detection.
The content of the invention
1st, technical problem to be solved：
Invention is directed to deficiencies of the prior art, proposes a kind of CEMS system failures of the outlier detection based on density
Analysis method, screened using exceptional data point in the thought detection CEMS systems of the outlier detection based on density in data mining
Out, threshold test is coordinated to determine the corresponding failure that may occur in equipment.Using the fault diagnosis result of the present invention, can implement
Specific aim maintenance forecasting, maintenance scheme is planned according to the usage scenario of instrument, ensured the reliability service of equipment.
2nd, technical scheme：
A kind of CEMS system trouble analysis methods of outlier detection based on density, it is characterised in that：Comprise the following steps：
Step 1：The corresponding parameter of CEMS systems and system data are gathered by sensor, and will by Zigbee agreements
The corresponding physical characteristic of sensor measurement is uploaded in collector, and main frame is obtained in real time by carrying out serial communication with collector
Each parameter of current system operation；
Step 2, the parameter of each sensor of acquisition is sorted out according to unified form collator, identifies each self-corresponding source
And type, then export into background host computer database and stored；Simultaneously by the parameter of each sensor according to sliding time
The mode of window establishes fault diagnosis data collection；
Step 3, to the fault diagnosis data collection established in step 2, calculated with the outlier excavation method based on density
The degree that peels off of the parameter of newest each sensor as the whether normal foundation of physical characteristic for judging current time system,
And carry out real-time fault diagnosis in exception and obtain fault diagnosis result；
Step 4, judged result and fault diagnosis result in running state information, step 3 are exported to background host computer database
In, and real-time physical characteristics coefficient and warning information are shown by background host computer.
Further, the outlier excavation method based on density based on density calculates newest each sensor
The degree of peeling off of parameter comprise the following steps：
S21：Preset a period, calculate this each period sensor local density a little average value；
S22：Calculate the density for being currently located sensor；
S23：Calculate it is current peel off factor k for sensor local density a little average value/be currently located sensor
Density；
S24：The current factor that peels off is more than corresponding predetermined threshold value, then judges corresponding value that sensor at that time measures to be different
Often.
Further, described sensor includes flowmeter sensor, peristaltic pump tube monitoring sensor, sampling probe filter core
Sensor and temperature sensor group.
Further, the parameter includes SO2、NOX、CO、O2, flue dust, flow, humidity, pressure, temperature.
2nd, beneficial effect：
（1）The present invention use wireless sensor technology, directly SO2, NOX of acquisition CEMS systems, CO, O2, flue dust, flow, wet
Degree, pressure, the data of temperature, and using the outlier detection based on density method by SO this moment2、NOX、CO、O2, flue dust,
A large amount of homogeneous datas of the states such as flow, humidity, pressure, temperature and history carry out lateral comparison, analyze misoperation therein
Situation, and then diagnose the purpose whether corresponding sensor breaks down.
（2）The method for the outlier detection based on density that the present invention uses is avoided because straight tube flue is partially short, is caused
Particle distribution in flue is uneven, causes monitoring point to reflect real situation without representativeness, the data of acquisition.
Brief description of the drawings
Fig. 1 is the flow chart of the present invention；
Fig. 2 is the abnormity point of the present invention and the design sketch of verification and measurement ratio.
Embodiment
Embodiment 1
As shown in Fig. 1, the present embodiment operating procedure is as follows：
（1）Sensor gathers the SO of CEMS systems2、NOX、CO、O2, flue dust, flow, humidity, pressure, the parameter such as temperature, by logical
Cross the corresponding physical characteristic that Zigbee agreements measure sensor to upload in collector, main frame with collector by carrying out
Serial communication obtains each parameter of current system operation in real time；
（2）Pre-processed for the running state information collected, establish the data set for equipment fault monitoring；Each
Sensor wherein establishes a database in the storage of main frame, for storing the data of the sensor.
（3）The fault diagnosis data collection of foundation, calculated with the outlier excavation method based on density newest each
The degree that peels off of the parameter of sensor is as the whether normal foundation of physical characteristic for judging current time system, and when abnormal
Carry out real-time fault diagnosis and obtain fault diagnosis result.
Described real-time fault diagnosis refers to：By historical data of the sensor more to be measured under identical environment to examine
Measure some peculiar individual data items.
Data in the present invention are that the data set that default certain period of time such as uses is typically nearest first quarter moon or one
The data in individual week, so with faster processing speed.
Because sensor measures parameters include SO2、NOX、CO、O2, flue dust, flow, humidity, pressure, temperature etc., therefore
It is not individually to consider single environment during default each threshold value, it is also contemplated that the threshold value under varying environment is different.On the whole
Leveled off to if the factor k that currently peels off and illustrate that the data point may be a normal point if 1., if the current factor k that peels off
Compare high, then the point is the Probability maximum of abnormity point.
Although the present invention disclosed as above with preferred embodiment, they be not for limit the present invention, it is any ripe
This those skilled in the art is practised, without departing from the spirit and scope of the invention, can make various changes or retouch from working as, therefore the guarantor of the present invention
What shield scope should be defined by claims hereof protection domain is defined.
Claims (4)
1. a kind of CEMS system trouble analysis methods of outlier detection based on density, it is characterised in that：Comprise the following steps
：
Step 1：The corresponding parameter of CEMS systems and system data are gathered by sensor, and will by Zigbee agreements
The corresponding physical characteristic of sensor measurement is uploaded in collector, and main frame is obtained in real time by carrying out serial communication with collector
Each parameter of current system operation；
Step 2, the parameter of each sensor of acquisition is sorted out according to unified form collator, identifies each self-corresponding source
And type, then export into background host computer database and stored；Simultaneously by the parameter of each sensor according to sliding time
The mode of window establishes fault diagnosis data collection；
Step 3, to the fault diagnosis data collection established in step 2, calculated with the outlier excavation method based on density
The degree that peels off of the parameter of newest each sensor as the whether normal foundation of physical characteristic for judging current time system,
And carry out real-time fault diagnosis in exception and obtain fault diagnosis result；
Step 4, judged result and fault diagnosis result in running state information, step 3 are exported to background host computer database
In, and real-time physical characteristics coefficient and warning information are shown by background host computer.
2. a kind of CEMS system data failure analysis methods based on outlier detection according to claim 1, its feature
It is：The outlier excavation method based on density based on density calculates peeling off for the parameter of newest each sensor
Degree comprises the following steps：
S21：Preset a period, calculate this each period sensor local density a little average value；
S22：Calculate the density for being currently located sensor；
S23：Calculate it is current peel off factor k for sensor local density a little average value/be currently located sensor
Density；
S24：The current factor that peels off is more than corresponding predetermined threshold value, then judges corresponding value that sensor at that time measures to be different
Often.
3. a kind of CEMS system data failure analysis methods based on outlier detection according to claim 1, its feature
It is：The sensor includes flowmeter sensor, peristaltic pump tube monitoring sensor, sampling probe filter core sensor and temperature and passed
Sensor group.
4. a kind of CEMS system data failure analysis methods based on outlier detection according to claim 1, its feature
It is：The parameter includes SO2、NOX、CO、O2, flue dust, flow, humidity, pressure, temperature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710741799.3A CN107741945A (en) | 2017-08-25 | 2017-08-25 | A kind of CEMS system trouble analysis methods of outlier detection based on density |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710741799.3A CN107741945A (en) | 2017-08-25 | 2017-08-25 | A kind of CEMS system trouble analysis methods of outlier detection based on density |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107741945A true CN107741945A (en) | 2018-02-27 |
Family
ID=61235557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710741799.3A Pending CN107741945A (en) | 2017-08-25 | 2017-08-25 | A kind of CEMS system trouble analysis methods of outlier detection based on density |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107741945A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109491311A (en) * | 2018-11-13 | 2019-03-19 | 江苏常熟发电有限公司 | A kind of CEMS data transmission failure judgment method |
| CN111024141A (en) * | 2019-11-23 | 2020-04-17 | 宜宾学院 | On-line detection system of environmental pollution detection equipment based on wireless communication |
| CN113722384A (en) * | 2021-11-02 | 2021-11-30 | 西安热工研究院有限公司 | Detection method, system and equipment for abnormal value of measured point data based on density algorithm |
| CN116611017A (en) * | 2023-07-17 | 2023-08-18 | 山东一然环保科技有限公司 | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103338188A (en) * | 2013-06-08 | 2013-10-02 | 北京大学 | Dynamic authentication method of client side suitable for mobile cloud |
| CN104135074A (en) * | 2014-07-31 | 2014-11-05 | 上海交通大学 | Extra-high-voltage substation equipment temperature monitoring and alarming method based on outlier detection |
| CN105654735A (en) * | 2016-03-24 | 2016-06-08 | 安徽四创电子股份有限公司 | Rapid fake-licensed car recognizing method based on outlier analysis algorithm |
| KR20170080525A (en) * | 2015-12-31 | 2017-07-10 | 강릉원주대학교산학협력단 | Remote Sensed Image Simulation System and Method for feasibility test of observed image data |
-
2017
- 2017-08-25 CN CN201710741799.3A patent/CN107741945A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103338188A (en) * | 2013-06-08 | 2013-10-02 | 北京大学 | Dynamic authentication method of client side suitable for mobile cloud |
| CN104135074A (en) * | 2014-07-31 | 2014-11-05 | 上海交通大学 | Extra-high-voltage substation equipment temperature monitoring and alarming method based on outlier detection |
| KR20170080525A (en) * | 2015-12-31 | 2017-07-10 | 강릉원주대학교산학협력단 | Remote Sensed Image Simulation System and Method for feasibility test of observed image data |
| CN105654735A (en) * | 2016-03-24 | 2016-06-08 | 安徽四创电子股份有限公司 | Rapid fake-licensed car recognizing method based on outlier analysis algorithm |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109491311A (en) * | 2018-11-13 | 2019-03-19 | 江苏常熟发电有限公司 | A kind of CEMS data transmission failure judgment method |
| CN111024141A (en) * | 2019-11-23 | 2020-04-17 | 宜宾学院 | On-line detection system of environmental pollution detection equipment based on wireless communication |
| CN113722384A (en) * | 2021-11-02 | 2021-11-30 | 西安热工研究院有限公司 | Detection method, system and equipment for abnormal value of measured point data based on density algorithm |
| CN116611017A (en) * | 2023-07-17 | 2023-08-18 | 山东一然环保科技有限公司 | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace |
| CN116611017B (en) * | 2023-07-17 | 2023-09-19 | 山东一然环保科技有限公司 | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107741945A (en) | A kind of CEMS system trouble analysis methods of outlier detection based on density | |
| WO2019149230A1 (en) | High-low frequency multi-core sensor system | |
| WO2018028005A1 (en) | Fault detection algorithm for battery panel in large-scale photovoltaic power station | |
| CN108092622B (en) | Photovoltaic string fault diagnosis method based on resistance calculation | |
| CN106599271A (en) | Emission monitoring time series data abnormal value detection method for coal-fired unit | |
| CN107862052A (en) | A kind of fault case storehouse, fault tree and fault spectrum construction method | |
| CN110927654B (en) | Batch running state evaluation method for intelligent electric energy meters | |
| CN104796082A (en) | System and method for diagnosing faults of photovoltaic power generation systems in online manner | |
| CN108005893A (en) | A kind of energy-saving air compressor machine analysis and diagnosis system and its control method | |
| CN107292523A (en) | The evaluation method and system of fired power generating unit environmental-protecting performance | |
| CN107144085A (en) | A kind of method for determining breakdown of refrigerator, apparatus and system | |
| CN116887569B (en) | Data center energy consumption prediction and energy saving adjustment method, system and storage medium | |
| CN116823226A (en) | Electric power district fault monitoring system based on big data | |
| CN107862459A (en) | Metering equipment state evaluation method and system based on big data | |
| CN107657798A (en) | A kind of Wind turbines state intelligent monitoring system | |
| CN103687254B (en) | Troubleshooting method and troubleshooting system for energy-saving lamps | |
| CN117196590A (en) | Intelligent maintenance efficiency evaluation system for operation and maintenance of communication equipment | |
| CN109299080B (en) | Cleaning method for power production operation data and computing equipment | |
| CN111931969A (en) | Merging unit equipment state prediction method based on time sequence analysis | |
| CN115809805A (en) | Power grid multi-source data processing method based on edge calculation | |
| CN110750760A (en) | Abnormal theoretical line loss detection method based on situation awareness and control chart | |
| CN113790102B (en) | Intelligent operation and maintenance system of gas turbine air inlet filter | |
| CN111245097A (en) | Intelligent power grid management and control system and method | |
| CN117996966B (en) | Intelligent management method and system for power screen cabinet based on optimization algorithm | |
| CN116232222B (en) | Cloud edge cooperative dust accumulation degree monitoring method and system for distributed photovoltaic 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180227 |