CN111550763A - Method for monitoring ash pollution on heating surface of boiler - Google Patents
Method for monitoring ash pollution on heating surface of boiler Download PDFInfo
- Publication number
- CN111550763A CN111550763A CN202010066978.3A CN202010066978A CN111550763A CN 111550763 A CN111550763 A CN 111550763A CN 202010066978 A CN202010066978 A CN 202010066978A CN 111550763 A CN111550763 A CN 111550763A
- Authority
- CN
- China
- Prior art keywords
- data
- heating surface
- pollution
- boiler
- steps
- 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
- 238000010438 heat treatment Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 230000008859 change Effects 0.000 claims abstract description 13
- 238000009826 distribution Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000007664 blowing Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 10
- 239000004071 soot Substances 0.000 claims description 9
- 238000011109 contamination Methods 0.000 claims description 8
- 239000002893 slag Substances 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000003245 coal Substances 0.000 claims description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 2
- 238000000265 homogenisation Methods 0.000 claims 1
- 230000008021 deposition Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 abstract description 6
- 238000000513 principal component analysis Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004140 cleaning Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 5
- 230000036541 health Effects 0.000 description 4
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 239000000428 dust Substances 0.000 description 3
- 239000003546 flue gas Substances 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005137 deposition process Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 239000011593 sulfur Substances 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F22—STEAM GENERATION
- F22B—METHODS OF STEAM GENERATION; STEAM BOILERS
- F22B37/00—Component parts or details of steam boilers
- F22B37/02—Component parts or details of steam boilers applicable to more than one kind or type of steam boiler
- F22B37/38—Determining or indicating operating conditions in steam boilers, e.g. monitoring direction or rate of water flow through water tubes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a method for monitoring ash pollution on a heating surface of a boiler, which comprises the following steps: historical data of each measuring point of the unit is obtained from a data source, data preprocessing is carried out, then data in a clean state are selected to establish a PCA model, real-time data are input into the model, SPE indexes are obtained, and the change trend of the SPE indexes can be used for monitoring the pollution condition of the heating surface. When the pollution is found to have a serious trend, the distribution of the polluted parts can be positioned by analyzing the time average contribution diagram. The invention provides a method for monitoring the ash pollution on the heating surface of a boiler, which can realize the prediction and positioning of the slagging and ash deposition on the heating surface.
Description
Technical Field
The invention relates to a method for monitoring ash pollution on a heating surface of a boiler, belonging to the technical field of monitoring slagging and ash deposition on the heating surface of a coal-fired boiler.
Background art:
the boiler is one of three main devices of a thermal power generating unit, and factors influencing the operation safety and the economical efficiency of the boiler are many, wherein the most common problems are pollution problems such as slag bonding and ash deposition on a heating surface, and the slag bonding pollution on the heating surface of the boiler is a typical performance degradation process. In China, coal used in boilers generally contains high ash content and sulfur content, and residues formed after combustion are easy to soften and adhere to a heating surface in a high-temperature environment in a hearth. Contamination and slagging of a water cooling wall in a hearth, contamination of a superheater and a reheater, and dust accumulation and blocking on a heating surface at the tail part can often occur. The heat conductivity of the ash slag is much lower than that of the heating surface material, so that the heat conversion of the boiler is seriously influenced, the exhaust gas temperature is overhigh, and the boiler efficiency is reduced. When the ash deposition is serious, the resistance of the flue is increased, so that the output of the boiler is increased, and the boiler is stopped seriously. In addition, the problems of high-temperature corrosion, abrasion and the like caused by the pollution of the heating surface originally cause the main reason of tube explosion of the boiler.
Most power plants at present adopt a soot blower to remove ash on a heating surface. However, soot blowing at any time has been a problem due to the lack of effective monitoring of contamination of the heated surfaces. Generally, a timing periodic soot blowing mode is adopted, and the method has certain blindness and is easy to cause over-blowing or under-blowing. Over-blowing adds additional cost and can erode the heated surface, affecting its life. Under-blowing affects the thermal efficiency of the boiler and cannot fundamentally solve the influence of the accumulated dust on the economy of the unit. Therefore, it is desired to solve the problem of contamination of the heating surface, and it is essential to effectively monitor the contamination of the heating surface.
The current methods for monitoring the pollution of the heating surface mainly comprise on-line measurement and model prediction. On-line measurement aims at directly diagnosing the slagging and ash deposition conditions of a heating surface through various measuring instruments such as a heat flow meter and the like, but due to the influences of measurement precision, instrument cost and the like, direct diagnosis methods are often found in scientific research and cannot be popularized and applied to actual production. The model prediction refers to establishing a model capable of reflecting the pollution characteristics of the heating surface of the boiler by a certain means, so as to predict and monitor the pollution state of the heating surface. At present, model prediction methods are mainly divided into a mechanism model and a data driving model. The mechanism model is a pollution mechanism model of the heating surface established by equations of heat transfer efficiency of the heating surface, smoke resistance characteristics and the like. However, the operation of the boiler is a comprehensive and disordered variable working condition process, the structure of the heating surface is complex, and many parameters such as hearth radiation heat and the like in the mechanism modeling process are difficult to calculate, so that the difficulty of mechanism modeling is increased, and the monitoring effect is not ideal. In addition, the soot blowing action of the power plant also brings disturbance, which affects the ash accumulation speed and heat transfer performance of the heating surface and various operation parameters, and brings great interference to quantitative accurate calculation.
The invention content is as follows:
the purpose of the invention is as follows: in order to overcome the defects of the existing method, the invention provides a method for monitoring the ash pollution on the heating surface of the boiler, which can predict and diagnose the ash deposition and slagging pollution condition of the heating surface of the boiler based on the unit operation data, can well predict the ash pollution process of each stage of the heating surface, and can position the part with relatively serious ash deposition, thereby avoiding blind ash blowing and creating conditions for intelligent ash blowing.
The technical scheme is as follows: in order to solve the problems, the invention provides a method for monitoring the ash pollution of a heating surface of a boiler, which comprises the following steps:
(1) and collecting historical data of the measuring points. Historical data of time span required by each measuring point is collected from an SIS data source of the unit, and data including load, coal mill current, furnace oxygen amount, SO2 content, flue gas pressure, temperature measuring points of each heating surface and the like are collected at intervals of 1 min. The data to be collected is arranged in time sequence, wherein the time span of the data and the collection interval can be customized.
(2) And (4) preprocessing data. There may be some outliers in the operational data due to sensor failures or signal interruptions; in addition, due to the fact that various data in the power plant have certain delay, the situation that the various data cannot be accurately corresponding can occur. Data pre-processing is therefore performed prior to data analysis.
And (2.1) removing abnormal values. For some abnormal values possibly existing in the data, for example, the value exceeds the upper and lower limits of normal operation and the value is kept unchanged for a period of time, the data needs to be eliminated, and the reliability of the result is ensured.
And (2.2) data are homogenized. Aiming at the situation that data can not be accurately corresponded, the problem can be effectively improved by carrying out time equalization processing on the data for a certain time, for example, carrying out 30min accumulation on each item of data.
(3) And (6) data processing. After each item of data is preprocessed to obtain correct operation data, zero-mean standardization processing is carried out on the data in order to prevent overlarge quantity level difference between the data.
(3.1) with X0The method is characterized in that a historical data set of m measuring points with N measuring points is subjected to standardization, so that the raw data become a data set with a mean value of 0 and a variance of 1, and the formula is as follows:
wherein, X0Representing the data to be normalized, E (X)0(i) Is) represents the mean of the data to be normalized,
representing normalized data variance.
(4) And selecting a section of data after long-time blowing or overhaul as data for cleaning the heated surface, and establishing a PCA model. And selecting the number of the principal elements in the principal element space according to the accumulated contribution value of more than 85 percent.
(4.1) the covariance matrix S of dataset X can be expressed as:
(4.2) singular value decomposition is carried out on S to obtain
In the formula, P ∈ Rm×lIs the principal component of the load of the principal element,
is the residual load component;
Λ＝diag{λ1,λ2,Lλl}，
for each set of data x, it can be mapped as a projection of the pivot space
Projection of sum residual space
Namely, it is
Wherein,
the principal component space and residual space mapping matrices are provided.
(5) And inputting the real-time data into the model to obtain a statistical index SPE value of a residual error space, wherein the change of the index represents the degree of deviation of the pollution condition of the heated surface from cleaning, and the index is used for monitoring the ash pollution of the heated surface.
(5.1) on the basis of the PCA model, two statistics of SPE or T2 can be used as a measure to quantify the current pollution level of the equipment. The SPE index measures the projection of the sample on the residual space, and is calculated as follows:
(5.2), T2 is used to measure the projection of the sample in the principal component space, and the calculation method is as follows:
T2＝xTPΛ-1PTx＝xTDx
wherein, D is P Λ-1PT；P∈Rm×lIs the principal component load component.
(6) And when the SPE index change meets the set alarm condition, analyzing the pollution degree distribution position of each heating surface by adopting a Q contribution graph method.
And (6.1) comparing the contribution value of each operation measuring point to the SPE by using a Q contribution graph method, thereby further positioning the ash pollution condition of the heating surface. The contribution of each station to SPE is given by:
wherein, the contribution value of the ith measuring point to the SPE is represented. The larger the value is, the greater the influence of the change of the variable of the measuring point on the change of the SPE index is, and the greater the severity and the probability of pollution near the measuring point are.
(7) Comparing the contribution values of the measurement points based on the contribution map obtained in step (6), the site of the measurement point having a large occupancy ratio is considered to be a site having a high contamination level. And then corresponding soot blowing measures are respectively made according to the slag bonding severity of different parts.
The invention provides an SPE index of a PCA model based on operation data for monitoring the ash pollution of a heating surface of a boiler. The method can well predict the ash pollution process of each stage of the heating surface. And the part with relatively serious ash deposition can be positioned, thereby avoiding blind ash blowing and creating conditions for intelligent ash blowing. The method meets the requirements of engineering and fully exerts the advantages of big data of the unit. The method aims to evaluate and monitor the ash pollution degree of the heating surface of the boiler and analyze the ash distribution of each heating surface.
Has the advantages that: compared with the prior art, the invention has the following advantages:
(1) the method is based on the historical operation data of the unit, the advantages of big data are played, and the problems that prediction errors and the like caused by the fact that an experiment method cannot reflect an actual flue gas field are solved.
(2) A brand-new evaluation index of the pollution degree of the heating surface of the boiler is provided, and a precursor of serious pollution of the heating surface can be monitored in advance.
(3) When the ash pollution is monitored, the method provides a Q contribution diagram for positioning the distribution condition of the actual pollution degree of each heating surface.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of the operational parameters required to monitor the model;
FIG. 3 is a distribution diagram of the SPE values as a statistical indicator of the residual space;
FIG. 4 is a distribution diagram of the average contribution values of the measurement points in the third time (c) ash deposition process.
The specific implementation mode is as follows:
the present invention will be further described with reference to the accompanying drawings.
The data driving model is a black box model, and by utilizing massive historical operating data related to the heating surface of the hearth in the power station SIS, the pollution rule of the heating surface hidden behind the data is excavated through methods such as a neural network, machine learning and artificial intelligence. According to the method, details such as a heat transfer mechanism in an ash pollution process are not considered, and the ash pollution characteristic of the heating surface of the boiler can be learned through a certain mathematical method as long as relevant characteristic parameters and a certain number of data samples are selected. The data-driven prediction method generally has the following processes: selecting characteristic parameters, preprocessing data, constructing health indexes and evaluating equipment states. The key is how to construct an effective health index to identify and quantify the process of performance degradation of the device.
The invention provides a health index construction method based on PCA (principal component analysis). the method comprises the steps of dividing characteristic data into a principal component space and a residual error space, constructing a health index by using SPE (Square prediction error) statistics to monitor the performance degradation process of heating surface pollution, setting a proper alarm threshold value, and positioning the heating surface of a boiler with serious slagging and dust accumulation by calculating the contribution value of each measuring point variable to SPE through a Q contribution graph method. Therefore, the early warning action is carried out in advance before a serious slag-bonding accident comes, and corresponding soot blowing measures are taken according to the pollution condition of each part.
The invention provides a method for monitoring ash pollution on a heating surface of a boiler, which comprises the following steps:
(1) and collecting historical data of the measuring points. Historical data of time span required by each measuring point is collected from an SIS data source of the unit, and data including load, coal mill current, furnace oxygen amount, SO2 content, flue gas pressure, temperature measuring points of each heating surface and the like are collected at intervals of 1 min. The data to be collected is arranged in time sequence, wherein the time span of the data and the collection interval can be customized.
(2) And (4) preprocessing data. There may be some outliers in the operational data due to sensor failures or signal interruptions; in addition, due to the fact that various data in the power plant have certain delay, the situation that the various data cannot be accurately corresponding can occur. Data pre-processing is therefore performed prior to data analysis.
And (2.1) removing abnormal values. For some abnormal values possibly existing in the data, for example, the value exceeds the upper and lower limits of normal operation and the value is kept unchanged for a period of time, the data needs to be eliminated, and the reliability of the result is ensured.
And (2.2) data are homogenized. Aiming at the situation that data can not be accurately corresponded, the problem can be effectively improved by carrying out time equalization processing on the data for a certain time, for example, carrying out 30min accumulation on each item of data.
(3) And (6) data processing. After each item of data is preprocessed to obtain correct operation data, zero-mean standardization processing is carried out on the data in order to prevent overlarge quantity level difference between the data.
(3.1) with X0The method is characterized in that a historical data set of m measuring points with N measuring points is subjected to standardization, so that the raw data become a data set with a mean value of 0 and a variance of 1, and the formula is as follows:
wherein, X0Representing the data to be normalized, E (X)0(i) Is) represents the mean of the data to be normalized,
representing normalized data variance.
(4) And selecting a section of data after long-time blowing or overhaul as data for cleaning the heated surface, and establishing a PCA model. And selecting the number of the principal elements in the principal element space according to the accumulated contribution value of more than 85 percent.
(4.1) the covariance matrix S of dataset X can be expressed as:
(4.2) singular value decomposition is carried out on S to obtain
In the formula, P ∈ Rm×lIs the principal component of the load of the principal element,
is the residual load component;
Λ＝diag{λ1,λ2,Lλl}，
for each set of data x, it can be mapped as a projection of the pivot space
Projection of sum residual space
Namely, it is
Wherein C ═ PPT；
The principal component space and residual space mapping matrices are provided.
(5) And inputting the real-time data into the model to obtain a statistical index SPE value of a residual error space, wherein the change of the index represents the degree of deviation of the pollution condition of the heated surface from cleaning, and the index is used for monitoring the ash pollution of the heated surface.
(5.1) on the basis of the PCA model, two statistics of SPE or T2 can be used as a measure to quantify the current pollution level of the equipment. The SPE index measures the projection of the sample on the residual space, and is calculated as follows:
(5.2) T2 is used to measure the projection of the sample in the principal component space, and the calculation method is as follows:
T2＝xTPΛ-1PTx＝xTDx
wherein, D is P Λ-1PT；P∈Rm×lIs the principal component load component.
(6) And when the SPE index change meets the set alarm condition, analyzing the pollution degree distribution position of each heating surface by adopting a Q contribution graph method.
And (6.1) comparing the contribution value of each operation measuring point to the SPE by using a Q contribution graph method, thereby further positioning the ash pollution condition of the heating surface. The contribution of each station to SPE is given by:
wherein, the contribution value of the ith measuring point to the SPE is represented. The larger the value is, the greater the influence of the change of the variable of the measuring point on the change of the SPE index is, and the greater the severity and the probability of pollution near the measuring point are.
(7) Comparing the contribution values of the measurement points based on the contribution map obtained in step (6), the site of the measurement point having a large occupancy ratio is considered to be a site having a high contamination level. And then corresponding soot blowing measures are respectively made according to the slag bonding severity of different parts.
Example 1
The detection method provided by the invention is further introduced by data samples of a heating surface of a certain 700MW coal-fired boiler:
data were collected after long blow or overhaul in the SIS system at 15min intervals (as the case may be). The framework of the invention mainly comprises core modules of data acquisition, data preprocessing, data processing, model construction, monitoring analysis, pollution positioning and the like, and a detailed flow chart is shown in figure 1:
1) and collecting historical data of the measuring points. Historical data of each measuring point shown in figure 2 is collected from an SIS data source of the unit to obtain X0。
2) And (4) preprocessing data. There may be some outliers in the operational data due to sensor failures or signal interruptions; in addition, due to the fact that various data in the power plant have certain delay, the situation that the various data cannot be accurately corresponding can occur. Data pre-processing is therefore performed prior to data analysis.
3) And (6) data processing. After each item of data is preprocessed to obtain correct operation data, zero-mean standardization processing is carried out on the data in order to prevent the magnitude difference between the data from being too large, and a through formula
i∈(1,m)
To obtain Xm×N。
4) And selecting a section of data after long-time blowing or overhaul as data for cleaning the heated surface, and establishing a PCA model. The covariance S of the data is determined and S is decomposed as a singular value as follows:
5) and inputting the real-time data into the model to obtain a statistical index SPE value of a residual error space, wherein the change of the index represents the degree of deviation of the pollution condition of the heating surface from the cleaning time as shown in figure 3 and is used for monitoring the ash pollution of the heating surface. In the figure, the four times of ash deposition of a, b, c and d are obvious respectively. SPE is calculated as follows:
6) and when the SPE index changes and meets the set alarm conditions, analyzing the distribution positions of the pollution degree of each heating surface by adopting a Q contribution graph method. The contribution of each station to SPE is given by:
7) according to the contribution diagram obtained in the step 6), the average contribution value distribution of each measuring point in the third time (c) ash deposition process is shown in FIG. 4. And judging the distribution condition of the pollution of each heating surface by comparing the contribution values of the measuring points. The measuring points at the parts with larger contribution values can be regarded as the parts with serious pollution, and soot blowing measures with different specifications are respectively adopted according to the distribution condition of the pollution of the heating surface.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (7)
1. The method for monitoring the ash pollution on the heating surface of the boiler is characterized by comprising the following steps: the measuring steps are as follows:
step one, collecting historical data of time span required by each measuring point from an SIS data source of a unit, and preprocessing the historical data;
step two, carrying out zero-mean standardization processing on the data;
step three, establishing a PCA model;
inputting real-time data into the model, and measuring the ash pollution degree of the heating surface by adopting an SPE or T2 index;
step five, when the change of the measurement index meets the set alarm condition, analyzing the pollution degree distribution position of each heating surface by adopting a Q contribution graph method; and respectively making corresponding soot blowing measures according to the slag bonding severity of different parts by comparing the contribution values of the measuring points.
2. The method for monitoring the ash pollution of the heating surface of the boiler as claimed in claim 1, wherein the method comprises the following steps: the step one of collecting historical data comprises:
the method comprises the steps of load, coal mill current, hearth oxygen content and SO at equal time intervals2Content, smoke pressure, and temperature measuring point data of each heating surface; and arranging the data to be collected according to a time sequence, wherein the time span and the collection interval of the data are self-defined.
3. The method for monitoring the ash pollution of the heating surface of the boiler as claimed in claim 1, wherein the method comprises the following steps: in the first step, the specific steps of preprocessing the historical data are as follows:
step 1.1, removing abnormal values;
and 1.2, carrying out time homogenization processing on the data within set time when the data cannot be accurate.
4. The method for monitoring the ash pollution of the heating surface of the boiler as claimed in claim 1, wherein the method comprises the following steps: the second step specifically comprises the following steps:
step 2.1, with X0The method is characterized in that a historical data set of m measuring points with N measuring points is subjected to standardization, so that the raw data become a data set with a mean value of 0 and a variance of 1, and the formula is as follows:
wherein, X0Representing the data to be normalized, E (X)0(i) Is) represents the mean of the data to be normalized,
representing the normalized data variance.
5. The method for monitoring the ash pollution of the heating surface of the boiler as claimed in claim 4, wherein the method comprises the following steps: the third step comprises the following specific steps:
step 3.1, the covariance matrix S of the dataset X can be expressed as:
wherein X is the normalized data set;
step 3.2, singular value decomposition is carried out on S to obtain
In the formula, P ∈ Rm×lIs the principal component of the load of the principal element,
is the residual load component;
Λ＝diag{λ1,λ2,Lλl}，
for each set of data x, it can be mapped as a projection of the pivot space
Projection of sum residual space
Namely, it is
Wherein,
the principal component space and residual space mapping matrices are provided.
6. The method for monitoring the ash pollution of the heating surface of the boiler as claimed in claim 1, wherein the method comprises the following steps: the fourth concrete step is as follows:
step 4.1, on the basis of the PCA model, SPE is used as a measurement index to quantify the current pollution degree of the equipment, and the calculation method is as follows:
step 4.2, T2The method is used for measuring the projection of the sample in the principal component space and has the following formula：
T2＝xTPΛ-1PTx＝xTDx，
Wherein, D is P Λ-1PT；P∈Rm×lIs the principal component load component.
7. The method for monitoring the ash pollution of the heating surface of the boiler as claimed in claim 1, wherein the method comprises the following steps: the concrete steps of the fifth step are as follows:
and comparing the contribution value of each operation measuring point to the SPE by using a Q contribution graph method, so as to further position the ash contamination condition of the heating surface, wherein the contribution value of each measuring point to the SPE is as follows:
the larger the value is, the greater the influence of the change of the variable of the measuring point on the change of the SPE index is, and the greater the severity and the possibility of the pollution near the measuring point are.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010066978.3A CN111550763A (en) | 2020-01-20 | 2020-01-20 | Method for monitoring ash pollution on heating surface of boiler |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010066978.3A CN111550763A (en) | 2020-01-20 | 2020-01-20 | Method for monitoring ash pollution on heating surface of boiler |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111550763A true CN111550763A (en) | 2020-08-18 |
Family
ID=71997645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010066978.3A Pending CN111550763A (en) | 2020-01-20 | 2020-01-20 | Method for monitoring ash pollution on heating surface of boiler |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111550763A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112784405A (en) * | 2021-01-06 | 2021-05-11 | 润电能源科学技术有限公司 | Boiler slagging prediction method based on numerical simulation and related device |
| CN112800672A (en) * | 2021-01-27 | 2021-05-14 | 上海电气集团股份有限公司 | Boiler fouling coefficient evaluation method, system, medium and electronic equipment |
| CN113255795A (en) * | 2021-06-02 | 2021-08-13 | 杭州安脉盛智能技术有限公司 | Equipment state monitoring method based on multi-index cluster analysis |
| CN113958937A (en) * | 2021-10-26 | 2022-01-21 | 华中科技大学 | Method for judging pollution degree of heating surface of power station boiler |
| CN114440205A (en) * | 2022-03-11 | 2022-05-06 | 国家能源集团山西电力有限公司 | Safety diagnosis system and method for heating surface of boiler system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458522A (en) * | 2009-01-08 | 2009-06-17 | 浙江大学 | Multi-behavior process monitoring method based on pivot analysis and vectorial data description support |
| CN104699050A (en) * | 2015-02-13 | 2015-06-10 | 浙江中烟工业有限责任公司 | Leaf-shred preparation segment on-line monitoring and fault diagnosing method for cigarette filament treatment driven by data |
| CN107608335A (en) * | 2017-09-14 | 2018-01-19 | 山东科技大学 | A kind of UAV Flight Control System fault detect and the data-driven method of fault reconstruction |
| CN109062196A (en) * | 2018-10-31 | 2018-12-21 | 东北大学 | The blast furnace process monitoring of integrated PCA-ICA a kind of and method for diagnosing faults |
| CN110207094A (en) * | 2019-04-16 | 2019-09-06 | 浙江大学 | IQGA-SVR boiler heating surface fouling characteristics discrimination method based on principal component analysis |
-
2020
- 2020-01-20 CN CN202010066978.3A patent/CN111550763A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458522A (en) * | 2009-01-08 | 2009-06-17 | 浙江大学 | Multi-behavior process monitoring method based on pivot analysis and vectorial data description support |
| CN104699050A (en) * | 2015-02-13 | 2015-06-10 | 浙江中烟工业有限责任公司 | Leaf-shred preparation segment on-line monitoring and fault diagnosing method for cigarette filament treatment driven by data |
| CN107608335A (en) * | 2017-09-14 | 2018-01-19 | 山东科技大学 | A kind of UAV Flight Control System fault detect and the data-driven method of fault reconstruction |
| CN109062196A (en) * | 2018-10-31 | 2018-12-21 | 东北大学 | The blast furnace process monitoring of integrated PCA-ICA a kind of and method for diagnosing faults |
| CN110207094A (en) * | 2019-04-16 | 2019-09-06 | 浙江大学 | IQGA-SVR boiler heating surface fouling characteristics discrimination method based on principal component analysis |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112784405A (en) * | 2021-01-06 | 2021-05-11 | 润电能源科学技术有限公司 | Boiler slagging prediction method based on numerical simulation and related device |
| CN112784405B (en) * | 2021-01-06 | 2024-06-11 | 润电能源科学技术有限公司 | Boiler slagging prediction method and related device based on numerical simulation |
| CN112800672A (en) * | 2021-01-27 | 2021-05-14 | 上海电气集团股份有限公司 | Boiler fouling coefficient evaluation method, system, medium and electronic equipment |
| CN112800672B (en) * | 2021-01-27 | 2024-04-16 | 上海电气集团股份有限公司 | Evaluation method, system, medium and electronic equipment for boiler fouling coefficient |
| CN113255795A (en) * | 2021-06-02 | 2021-08-13 | 杭州安脉盛智能技术有限公司 | Equipment state monitoring method based on multi-index cluster analysis |
| CN113958937A (en) * | 2021-10-26 | 2022-01-21 | 华中科技大学 | Method for judging pollution degree of heating surface of power station boiler |
| CN114440205A (en) * | 2022-03-11 | 2022-05-06 | 国家能源集团山西电力有限公司 | Safety diagnosis system and method for heating surface of boiler system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111550763A (en) | Method for monitoring ash pollution on heating surface of boiler | |
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| WO2022170698A1 (en) | Fault identification and pre-warning method for industrial boiler, and intelligent system | |
| CN115329812B (en) | Bridge infrastructure anomaly monitoring method based on artificial intelligence | |
| CN111651933B (en) | Industrial boiler fault early warning method and system based on statistical inference | |
| CN113705924B (en) | Intelligent diagnosis method and system for thermal control equipment | |
| CN112799898B (en) | Interconnection system fault node positioning method and system based on distributed fault detection | |
| CN112597696B (en) | Boiler four-pipe leakage early warning method based on extreme learning machine principle | |
| CN110991692B (en) | Heat exchanger group operation condition monitoring, cleaning and early warning method based on dynamic envelope curve method | |
| CN115222141A (en) | Multivariable time sequence abnormity detection method, system, medium, equipment and terminal | |
| Pang et al. | An integrated LSTM-AM and SPRT method for fault early detection of forced-oxidation system in wet flue gas desulfurization | |
| CN115496188A (en) | Coal mill fault early warning method based on deep learning convolutional neural network | |
| CN117346172A (en) | On-line fault diagnosis model for heating surface of boiler | |
| CN111765449A (en) | Superheater explosion and leakage early warning method based on long-term and short-term memory network | |
| CN115200033A (en) | Rotary air preheater thermal monitoring system based on digital twinning technology | |
| CN114297265A (en) | Intelligent operation and maintenance method based on Internet of things technology | |
| CN111898794B (en) | Abnormal monitoring method for thermal efficiency of large coal-fired boiler | |
| CN117705121A (en) | Multi-dimensional inspection system for power plant | |
| CN112304657A (en) | Method for dividing key easy-scaling groups of air preheater and monitoring heat exchange efficiency state | |
| CN113836794B (en) | Soft and hard combined fly ash carbon content online monitoring method | |
| CN116429269A (en) | Infrared intelligent analysis system for ethylene cracking furnace tube | |
| CN114440205A (en) | Safety diagnosis system and method for heating surface of boiler system | |
| CN106382842A (en) | Pipe explosion monitoring method and system for cement plant waste heat recovery multi-loop heat exchanger | |
| CN114151291B (en) | Early fault monitoring method for wind turbine generator | |
| CN114625036B (en) | Cloud platform for remote real-time monitoring and alarming and application thereof |
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: 20200818 |