CN116611017B - Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace - Google Patents
Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace Download PDFInfo
- Publication number
- CN116611017B CN116611017B CN202310868188.0A CN202310868188A CN116611017B CN 116611017 B CN116611017 B CN 116611017B CN 202310868188 A CN202310868188 A CN 202310868188A CN 116611017 B CN116611017 B CN 116611017B
- Authority
- CN
- China
- Prior art keywords
- data
- concentration
- temperature
- data point
- excess air
- 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.)
- Active
Links
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 title claims abstract description 105
- IJGRMHOSHXDMSA-UHFFFAOYSA-N nitrogen Substances N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 title claims abstract description 69
- 238000002485 combustion reaction Methods 0.000 title claims abstract description 67
- 229910052757 nitrogen Inorganic materials 0.000 title claims abstract description 52
- 238000010438 heat treatment Methods 0.000 title claims abstract description 43
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims description 36
- 229910052760 oxygen Inorganic materials 0.000 claims description 22
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 19
- 239000001301 oxygen Substances 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 description 19
- 230000002159 abnormal effect Effects 0.000 description 14
- 239000000446 fuel Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 239000007789 gas Substances 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 238000012888 cubic function Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000002028 Biomass Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 239000002283 diesel fuel Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 125000004430 oxygen atom Chemical group O* 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Mathematical Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Food Science & Technology (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Combustion & Propulsion (AREA)
- Medicinal Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Biochemistry (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Regulation And Control Of Combustion (AREA)
Abstract
The invention discloses a nitrogen oxide emission detection method of a low-nitrogen combustion heating furnace, which belongs to the technical field of data processing, and comprises the following steps: according to the embodiment, through the scheme, data acquired by a sensor arranged in a low-nitrogen combustion heating furnace are preprocessed to obtain a NOx concentration data sequence, a temperature data sequence and an excessive air coefficient data sequence; calculating a concentration anomaly factor based on the temperature anomaly factor and the excess air coefficient anomaly factor of the related data sequence; and determining a weight coefficient for correcting the local outlier factor in the LOF algorithm based on the concentration outlier factor to obtain an outlier. Therefore, the concentration anomaly factors are determined based on the correlation degree among the temperature data, the concentration data and the excess air coefficient data, and the local outlier factors of the LOF algorithm are corrected based on the concentration anomaly factors so as to obtain concentration anomaly data points, so that the accuracy of the nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace is greatly improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a nitrogen oxide emission detection method of a low-nitrogen combustion heating furnace.
Background
The low-nitrogen combustion heating furnace is a device for converting heat energy generated by combustion into heat energy, and is widely applied to high-temperature combustion work in industries of steel, chemical industry, electric power, environmental protection and the like by the characteristics of high efficiency, environmental protection and cleanness. However, in the operation process of the low-nitrogen combustion heating furnace, the problems of equipment aging, improper maintenance, mechanical faults and the like occurProblem of abnormal emission of (nitrogen oxides), thus for early discovery and resolution +.>Abnormal emission, ensuring the normal operation of the low-nitrogen combustion heating furnace, and requiring the control of +.>Is monitored.
The local anomaly factor (Local Outlier Factor, LOF) algorithm is a density-based anomaly detection algorithm with good detection effect on general nonlinear distribution data, but the LOF algorithm depends on the data information around the detected data during detection, and has good detection effect on the dataIs to use LOF algorithm to enter the data with partial abnormal data closely connected with normal dataThe problem of false detection may occur during abnormal detection, so that the accuracy of the detection result is not high enough.
Disclosure of Invention
The invention provides a nitrogen oxide emission detection method of a low-nitrogen combustion heating furnace, aiming at improving the accuracy of nitrogen oxide emission detection.
In order to achieve the above object, the present invention provides a method for detecting nitrogen oxide emissions of a low nitrogen combustion heating furnace, the method comprising:
preprocessing data acquired by a sensor arranged in a low-nitrogen combustion heating furnace to obtainA concentration data sequence, a temperature data sequence, and an excess air factor data sequence;
based on the temperature data sequenceObtaining a first fitting curve by using first data points at the same moment in a concentration data sequence;
determining a temperature anomaly factor for each first data point based on the first data point and the first fitted curve;
based on excess air factor data sequenceConstruction of an excess air factor for a second data point at the same time in a concentration data sequence>A concentration coordinate system;
based on the excess air ratioDetermining an excess air anomaly factor of each second data point by the concentration coordinate system;
calculation of the temperature anomaly factor based on each first data point, the excess air factor anomaly factor of each second data point, and the correlationA concentration anomaly factor for each time data point in the concentration data sequence;
and determining a weight coefficient for correcting the local outlier factor in the LOF algorithm based on the concentration outlier factor, obtaining an outlier concentration point based on the weight coefficient, and determining the outlier concentration point and the moment corresponding to the outlier concentration point as a nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace.
Optionally, the data collected by the sensor arranged in the low-nitrogen combustion heating furnace is preprocessed to obtainThe concentration data sequence, the temperature data sequence, and the excess air ratio data sequence include:
collecting exhaust port of low-nitrogen combustion heating furnace through sensorThe concentration data, oxygen concentration data, and temperature data in the combustion chamber are stored as +.>A concentration data sequence, an oxygen concentration data sequence, and a temperature data sequence;
respectively putting the above-mentionedNormalizing the concentration data sequence and the temperature data sequence to obtain +.>A concentration data sequence and a temperature data sequence;
and calculating an excess air coefficient data sequence corresponding to the oxygen concentration data sequence based on an excess air coefficient calculation formula.
Optionally, the step of generating the temperature data sequence is based on the temperature data sequence andconcentration data sequence mesophaseObtaining a first fitted curve from the first data point at the same time comprises:
sequencing the temperature dataAnd->The value at the same time in the concentration data sequence is determined as an ordinal number pair;
the ordinal number pair is taken as the construction temperature-A first data point of a concentration coordinate system;
and performing curve fitting on the first data points based on a least square method to obtain a first fitting curve.
Optionally, the determining the temperature anomaly factor for each first data point based on the first data point and the first fitted curve includes:
determining a first fit distance and a first standard fit distance for each first data point based on the first data points and the first fit curve;
calculating a first standard deviation of the first fitting distance and the first standard fitting distance;
determining a temperature-A temperature anomaly factor for each first data point in the concentration coordinate system.
Optionally, the determining a first fitting distance and a first standard fitting distance for each first data point based on the first data points and the first fitting curve includes:
calculating a first fitting distance between each first data point and the first fitting curve;
grouping the first data points based on the temperature values, determining the data with the same temperature value as the same temperature value data set, and calculating a first fitting distance average value of the temperature value data sets;
determining the density degree of first data points corresponding to each temperature based on the first fitting distance, the first fitting distance average value and the number of the first data points;
and calculating a first standard fitting distance of each first data point by the first fitting distance mean value based on the intensity level of the first data points.
Optionally, based on the excess air ratioDetermining excess air anomaly factors for each second data point in the concentration coordinate system includes:
based on the excess air ratioDetermining the local density of each second data point and a second fitting curve by the concentration coordinate system;
calculating a second fitting distance between each second data point and the second fitting curve, and calculating a second standard fitting distance of the second data point based on the second fitting distance of the second data point and the local density;
calculating a second standard deviation of the second fitting distance and the second standard fitting distance;
an excess air anomaly factor for each second data point is determined based on the second fit distance, the second standard fit distance, and the second standard deviation.
Optionally, based on the excess air ratioDetermining the local density of each second data point by the concentration coordinate system, and a second fitting curve comprises:
in excess air ratio-Setting windows with preset sizes in the concentration coordinate system by taking each second data point as a center, and based on the window sizes and the second data points in the windowsCalculating the local density of each second data point;
grouping second data points with the same excess air coefficient value to obtain a plurality of excess air coefficient value groups;
determining a second data point corresponding to the local density maximum value in each excess air coefficient value group as a mark data point;
and fitting the marked data points by using a cubic spline difference method to obtain a second fitting curve.
Optionally, the calculating is based on the temperature anomaly factor of each first data point, the excess air factor anomaly factor of each second data point and the correlation degreeThe concentration anomaly factor for each time data point in the concentration data sequence comprises:
based onConcentration data sequence, temperature data sequence and excess air factor data sequence, temperature pair is obtained using grey correlation analysis>First degree of association of concentration->A second degree of correlation of temperature to excess air ratio;
calculating a first product of the first correlation and a temperature anomaly factor of the first data point, and calculating a second product of the first correlation and an excess air coefficient anomaly factor of the second data point;
and determining a normalized value of the sum of the first product and the second product as a concentration anomaly factor of the data point at the corresponding moment.
Compared with the prior art, the nitrogen oxide emission detection method of the low-nitrogen combustion heating furnace provided by the invention comprises the following steps: preprocessing data acquired by a sensor arranged in a low-nitrogen combustion heating furnace to obtainA concentration data sequence, a temperature data sequence, and an excess air factor data sequence; based on the temperature data sequence and +.>Obtaining a first fitting curve by using first data points at the same moment in a concentration data sequence; determining a temperature anomaly factor for each first data point based on the first data point and the first fitted curve; based on the excess air factor data sequence and +.>Construction of an excess air factor for a second data point at the same time in a concentration data sequence>A concentration coordinate system; based on the excess air ratioDetermining an excess air anomaly factor of each second data point by the concentration coordinate system; calculating +.>A concentration anomaly factor for each time data point in the concentration data sequence; and determining a weight coefficient for correcting the local outlier factor in the LOF algorithm based on the concentration outlier factor, obtaining an outlier concentration point based on the weight coefficient, and determining the outlier concentration point and the moment corresponding to the outlier concentration point as a nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace. Therefore, the concentration anomaly factors are determined based on the correlation degree among the temperature data, the concentration data and the excess air coefficient data, and the local outlier factors of the LOF algorithm are corrected based on the concentration anomaly factors so as to obtain concentration anomaly data points, so that the accuracy of the nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace is greatly improved.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of a method for detecting nitrogen oxide emissions in a low nitrogen combustion furnace according to the present invention;
FIG. 2 is a schematic diagram of a first refinement of an embodiment of a method for detecting emissions of nitrogen oxides in a low nitrogen combustion furnace according to the present invention;
FIG. 3 is a schematic diagram of a second refinement of an embodiment of a method for detecting emissions of nitrogen oxides in a low nitrogen combustion furnace according to the present invention;
FIG. 4 is a schematic diagram of a third refinement of an embodiment of a method for detecting emissions of nitrogen oxides in a low nitrogen combustion furnace according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a flow chart of a first embodiment of a method for detecting nitrogen oxide emission in a low nitrogen combustion heating furnace according to the present invention.
As shown in fig. 1, a first embodiment of the present invention proposes a method for detecting nitrogen oxide emissions of a low nitrogen combustion heating furnace, the method comprising:
step S101, preprocessing data acquired by a sensor arranged in the low-nitrogen combustion heating furnace to obtainConcentration data sequence->Temperature data sequence->An excess air ratio data sequence P;
the mechanism of formation of (a) includes thermal->Fuel type->Quick->. Since low nitrogen combustion furnaces generally use clean fuels such as natural gas, liquefied gas, biomass gas, light diesel oil, etc. as fuel, these fuels produce + ->Mainly thermodynamic->Generally can reach +>Total amount of produced->The above. At combustion temperatures below 1000>When (I)>The emissions are extremely low, whereas when the combustion temperature exceeds 1000 +.>When (I)>The amount of emissions can increase significantly. The present example detects a low-nitrogen combustion heating furnace using clean fuel such as natural gas, liquefied gas, and biomass gas, and is a scene for high-temperature processing of materials such as metal and glass.
Referring to fig. 2, fig. 2 is a schematic diagram of a first refinement of an embodiment of a method for detecting nitrogen oxide emission in a low-nitrogen combustion heating furnace according to the present invention, as shown in fig. 2, step S101 includes:
in step S1011 of the process,collecting exhaust port of low-nitrogen combustion heating furnace through sensorThe concentration data, oxygen concentration data, and temperature data in the combustion chamber are stored as +.>A concentration data sequence a, an oxygen concentration data sequence B, and a temperature data sequence C;
the exhaust port of the low-nitrogen combustion heating furnace is provided withGas sensor and oxygen sensor, a galvanic sensor is arranged in the combustion chamber, and the sensor is arranged in the combustion chamber by +.>A gas sensor to collect +.>Concentration data, oxygen concentration data at the exhaust port is collected through an oxygen sensor, and temperature data in the combustion chamber is collected through a thermocouple sensor. In the embodiment, the operation data of the formal combustion stage after the preheating stage of the low-nitrogen combustion heating furnace is finished is used, and the data of the formal operation stage is accurate and representative. The data amount collected by each sensor in this embodiment is recorded as +.>The time interval between two adjacent acquisitions is recorded as +.>. Co-acquisition->Data, data amount collected by each sensor +.>Interval->The present embodiment can be set to +.>,。
The embodiment stores the obtained data as respectivelyConcentration data sequence->Oxygen concentration data sequence->Temperature data sequence->。
Step S1012, respectively comparing theNormalizing the concentration data sequence A and the temperature data sequence C to obtain +.>Concentration data sequence->And temperature data sequence>;
Due toThe concentration data sequence A and the temperature data sequence C have different dimensions, for the convenience of subsequent processing, for +.>Normalized concentration data sequence A and temperature data sequence CDimensionality removal processing, in which the processed data are stored as +.>Concentration data sequence->And temperature data sequence>. The normalized dimensionality removing method is a known technology, and the embodiment is not described in detail.
In step S1013, the excess air ratio data sequence P corresponding to the oxygen concentration data sequence B is calculated based on the excess air ratio calculation formula.
The air excess ratio refers to the ratio of the amount of air actually supplied to the fuel combustion to the theoretical amount of air. Is an important parameter reflecting the fuel to air ratio. The excess air ratio calculation formula is:
in this way, the corresponding excess air ratio is obtained based on the respective oxygen concentration data in the oxygen concentration data series B, thereby obtaining the excess air ratio data series P.
Step S102, based on the temperature data sequenceAnd->Concentration data sequence->Obtaining a first fitting curve from the first data points at the same time;
specifically, the temperature data is sequencedAnd->Concentration data sequence->The value at the same time in (a) is determined as an ordinal number pair; taking said ordinal pair as construction temperature->A first data point of a concentration coordinate system; and performing curve fitting on the first data points based on a least square method to obtain a first fitting curve.
Temperature data sequenceAnd->Concentration data sequence->The data in (a) are all acquired at a time, thus are all from the temperature data sequence +.>And->Concentration data sequence->Data at the same time is selected as a data pair. In this embodiment, the temperature data sequence +.>Is used as x-axis coordinate value (expressed as +.>) Will->Concentration data sequence->Is used as the y-axis coordinate value (expressed as +.>) Thus n ordinal pairs +.>. N ordinal pairs to be obtained +.>As construction temperature- & lt- & gt>The first data point of the concentration coordinate system, the ordinal numbers are corresponding to +.>The corresponding coordinate value is marked at temperature->In the concentration coordinates, such temperature ∈ ->There are n first data points in the concentration coordinate system.
Performing curve fitting on n first data points through a least square method to obtain a first fitting curve, wherein the first fitting curve is expressed as:
wherein,,、respectively representing a temperature value and a concentration value;、、Representing the fitting coefficients. The resulting first fitted curve can be used to represent the temperature +.>Overall trend of change of the first data point in the concentration coordinate system.
Step S103, determining the temperature abnormality factor of each first data point based on the first data point and the first fitting curve;
Referring to fig. 3, fig. 3 is a schematic diagram of a second refinement of an embodiment of a method for detecting nitrogen oxide emission in a low-nitrogen combustion heating furnace according to the present invention, as shown in fig. 3, step S103 includes:
step S1031, determining a first fitting distance and a first standard fitting distance for each first data point based on the first data points and the first fitting curve;
specifically, first, calculating a first fitting distance from each first data point to the first fitting curve; in this embodiment, the Euclidean distance between the first data point and the first fitting curve is determined as a first fitting distance, and the first fitting distance is expressed as。
Grouping the first data points based on the temperature values, determining the data with the same temperature value as the same temperature value data set, and calculating a first fitting distance average value of the temperature value data sets; the same temperature value is often present at different times, and therefore the first data points are grouped based on the temperature values, and a first fitted distance average of the grouped temperature value data sets is calculated.
Determining the density degree of first data points corresponding to each temperature based on the first fitting distance, the first fitting distance average value and the number of the first data points; first data point corresponding to temperature cIs expressed as the density ofThen:
wherein,,indicating a temperature value of +.>Is dense with respect to the first data points;Indicating a temperature value of +.>Is the number of data points;Indicate->A first fitting distance of the first data points;Indicating this->A first fitted distance mean of the first data points. The smaller the difference in the first fitting distance between the first data points, the denser degree +.>The greater the value of (2).
Then based on the intensity level of the first data points, the first fitting distance average valueCalculate the first data point of eachA standard fitting distance.
Calculating the intensity of the first data corresponding to each temperature value c respectively, and expressing the intensity of the first data of the ith temperature value asThe first standard fitting distance is expressed as +.>Then:
wherein,,indicating temperature-/->The number of temperature values in all the first data points in the concentration coordinate graph;Indicating thisThe first part of the temperature values>Temperature values of the individual temperature values;Indicating a temperature value of +.>A first fitted distance average of all first data points;Indicating a temperature value of +.>Is dense between all first data points;The normalization function is represented and acts to normalize the values in brackets.The higher the corresponding degree of density is +.>The greater the specific gravity.
Step S1032, calculating a first standard deviation between the first fitting distance and the first standard fitting distance;
the standard deviation (Standard Deviation) is the arithmetic square root of the arithmetic mean (i.e., variance) from the square of the mean deviation, and the first standard deviation is calculated according to a well-known standard deviation calculation formula in this embodiment, which is not described herein.
Step S1033, fitting a distance based on the first criterionA first fitting distance of the respective first data points and said first standard deviation determine a temperature +.>A temperature anomaly factor for each first data point in the concentration coordinate system. Temperature abnormality factor->Then:
wherein,,indicating temperature-/->First data point in concentration coordinate System +.>Temperature abnormality factor->;Representing the first data point +.>Is a first fitting distance of (a);Representing a first standard fitting distance;Indicating temperature-/->A first standard deviation between the first fitting distance and the first standard fitting distance for all the first data points in the concentration coordinate system;Indicating temperature-/->Degree of deviation of normal data points in the concentration coordinate system, +.>Taking an experience value of 2;Representing the first fitting distance +.>Deviation from the first standard fitting distance ∈>The extent of (3);Indicating that the maximum value is taken. Wherein the first fitting distanceDegree of deviation is greater than->Is suspected to be an abnormal data point, and the greater the degree of deviation means the greater the degree of suspected of the first data point, i.e. the temperature abnormality factor +.>The greater the value of (2).
Excess air ratio of low nitrogen combustion heating furnace and method for producing the sameExhibits an "inverted U-shaped" relationship between the amounts of production, specifically, an excess air ratio +.>At the same time, with the excess air factor->The oxygen concentration in the air in the combustion chamber is increased, and the concentration of oxygen atoms obtained by decomposing oxygen molecules is increased under high temperature conditions, so that the thermal type +.>The amount of production of (2) increases; excess air coefficient->At the same time, with the excess air factor->The oxygen concentration in the air will also increase, which will dilute +.>And the combustion temperature of the combustion chamber is reduced, further allowing +.>Is decreased and is greater than the increase in oxygen concentration>The effect of the increase in the amount of production is large, so that the total +.>The amount of production is reduced. I.e. at +.>And air excess factor->On the relation of->Time->Maximum concentration of->Or alternatively,The concentration of (c) decreases. Therefore, it is necessary to make the basis +.>Concentration data->And excess air ratio data->Is to acquire->Excess air coefficient abnormality factor of concentration data +.>。
Step S104, based on the excess air ratio data sequenceAnd->Concentration data sequence->Construction of an excess air factor for the second data point at the same instant in>A concentration coordinate system;
sequencing excess air factor dataAnd->Concentration data sequence->The values of the data points at the same time in (a) are taken as the abscissa +.>And ordinate +.>Obtain->Pairs of ordinal numbers->. By means of the->Pairs of ordinal numbers->Establishing an excess air factor +_ as second data point>Concentration coordinate systemWherein each second data point in the coordinate system +.>All represent the excess air factor at the same instant +.>And->Concentration value->And at the excess air factor->And marking the time corresponding to each second data point in the concentration coordinate graph.
Step S105, based on the excess air ratioDetermining an excess air anomaly factor of each second data point by the concentration coordinate system;
referring to fig. 4, fig. 4 is a schematic diagram of a third refinement of an embodiment of a method for detecting nitrogen oxide emission in a low-nitrogen combustion heating furnace according to the present invention, as shown in fig. 4, step S105 includes:
step S1051, based on the excess air ratioDetermining the local density of each second data point and a second fitting curve by the concentration coordinate system;
first, at the excess air ratioSetting a window with a preset size by taking each second data point as a center in a concentration coordinate system, and calculating the local density of each second data point based on the size of the window and the number of the second data points in the window; the window of the preset size of this embodiment is set to one +.>Window of size->The empirical value is taken as 3, i.e. the abscissa and ordinate lengths of 3 units of length. Further obtaining the excess air factor->Local density of each second data point of the concentration coordinate system, the local density of the second data point is expressed as +.>Then:
wherein,,representing a number of second data points in a window centered around the second data point;Is the size of the window. The more the number of second data points in the window in which the second data points are located, the more localized density of the data points is represented>The greater the value of (2).
Then, grouping the second data points with the same excess air coefficient value to obtain a plurality of excess air coefficient value groups; air coefficient acquisitionAir excess factor +.>The number of different values of +.>And the value +.>The same value->Is determined as a set, and a plurality of groupings of excess air coefficient values are obtained.
Determining a second data point corresponding to the local density maximum value in each excessive air coefficient value group as a mark data point; marking the value of each excess air ratio asA second data point of the local density maximum. If the value of the excess air ratio is +.>If there are a plurality of second data points with the maximum local density, the corresponding +.>Concentration->Mean>. Since the normal second data point is more concentrated, the second data point is obtained>Are all suspected to be normal data points, and wherein the excess air factor +.>Concentration value of the second data point of +.>Will be along with the excess air coefficient->Is increased by (a)And increase, excess air ratio->Concentration value of the second data point of +.>Will be along with the excess air coefficient->Is decreased for individual second data points which do not satisfy this relationship +.>Using second data point +.>Replacing the second data point with the mean value of (c), and marking the second data points replaced by the mean value in the graph. The marker data points thus marked include the second data point corresponding to the local density maximum and the replaced second data point that does not satisfy the above relationship.
And finally, fitting the marked data points by using a cubic spline difference method to obtain a second fitting curve.
Performing curve fitting on the marked data points in the coordinate graph by using a cubic spline interpolation method, wherein the cubic spline interpolation method is a known technology and is not repeated, and the obtained second fitted curve is a piecewise cubic function, wherein the third fitted curve is the piecewise cubic functionThe cubic functions are:
wherein,,,respectively representing a concentration value and an excess air ratio;、、、Representing the fitting coefficients. The resulting fitted curve can be used to represent the excess air factor ±>Overall trend of change for the second data point in the concentration graph.
Step S1052, calculating a second fitting distance between each second data point and the second fitting curve, and calculating a second standard fitting distance of the second data point based on the second fitting distance of the second data point and the local density;
determining the Euclidean distance between the second data point and the second fitting curve as a second fitting distance, and representing the second fitting distance as。
The calculation method of the second standard fitting distance is the same as the calculation method of the first standard fitting distance.
Step S1053, calculating a second standard deviation of the second fitting distance and the second standard fitting distance; the present embodiment calculates the second standard deviation using a well-known algorithm of standard deviation.
Step S1054, determining an excess air anomaly factor for each second data point based on the second fitting distance, the second standard fitting distance, and the second standard deviation. The excess air anomaly factor of the second data point is expressed asThen:
wherein,,representing excess air factor->Second data point in concentration graph +.>Excessive air coefficient abnormality factor->;Representing a second data point->Is a second fitting distance of (2);Representing excess air factor->A second standard fitting distance in the concentration graph;Representing excess air factor->A second standard deviation between a second fitting distance and a second standard fitting distance for all second data points in the concentration graph;Representing excess air factor->Degree of deviation of normal second data point in concentration graph, +.>Taking an experience value of 1.5;Representing the second fitting distance +.>Deviation from the second standard fitting distance->The extent of (3);Indicating that the maximum value is taken. Wherein the degree of deviation of the fitting distance is greater than +.>Is suspected to be an abnormal data point, and the greater the degree of deviation means the greater the degree of suspected of the data point, i.e. the excess air factor abnormality factor of the data point +.>The greater the value of (2).
Step S106, based on the temperature anomaly factors of the first data pointsExcess air coefficient abnormality factor of each second data point +.>Correlation degree calculation +.>Concentration data sequence->Concentration variation of each time data point in (a)A constant factor; wherein the correlation degree comprises a temperature pair +.>First degree of association of concentration->Second degree of correlation of temperature to excess air coefficient +.>。
Based onConcentration data sequence->Temperature data sequence->Air excess factor data sequence +.>Temperature pairs were obtained using grey correlation analysis (Grey relational analysis, GRA)>First degree of association of concentration->Second correlation of temperature to excess air coefficient +.>The method comprises the steps of carrying out a first treatment on the surface of the Calculating a first product of the first correlation and a temperature anomaly factor of the first data point, and calculating a second product of the first correlation and an excess air coefficient anomaly factor of the second data point; and determining a normalized value of the sum of the first product and the second product as a concentration anomaly factor of the data point at the corresponding moment. The first association degree and the second association degree are determined based on the known steps in the gray association analysis GRA in this embodiment, and will not be described herein.
Representing the concentration anomaly factor asThe following steps are:
wherein,,representation->Concentration data sequence->Middle->Concentration anomaly factors for the time point of each moment;representing a normalization function, which acts to normalize the values in brackets;Indicating temperature-/->First data point corresponding to first data point in concentration graph>Temperature abnormality factor of the individual time data, i.e. +.>Concentration data sequence->Middle->A temperature anomaly factor for the individual time data;Representing excess air factor->Second data point in concentration graph>The excess air factor abnormality factor of the individual time data, i.e. +.>Concentration data sequence->Middle->A temperature anomaly factor for the individual time data;The correlation between the temperature abnormality factor and the excess air factor abnormality factor is expressed.Concentration data sequence->Temperature abnormality factor corresponding to a data point at a certain time>Excess air factor abnormality factor->And their corresponding association degree->The larger the value of (2) indicates that the data point is abnormal, the concentration abnormality factor +.>The greater the value of (2).
Step S107, based on the concentration abnormality factorAnd determining a weight coefficient for correcting the local outlier factor in the LOF algorithm, obtaining an abnormal concentration point based on the weight coefficient, and determining the abnormal concentration point and the moment corresponding to the abnormal concentration point as a nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace.
LOF algorithm based determinationConcentration data sequence->Local reachable density and local outlier factor of each concentration data in the database, and the specific acquisition mode is as follows:
determination ofConcentration data sequence->Each of->K-proximity distances of concentration data points, on the basis of which the respective +.>K-distance neighborhood of concentration data points; wherein the k-neighbor distance may be a hamming distance, a euclidean distance, or a mahalanobis distance. The present embodiment may determine the euclidean distance as a k-neighbor distance. Will->The k-nearest neighbor of the concentration data point P is denoted +.>(P), then:
wherein d (P, O) representsConcentration data points P and->The k-adjacent distance between the concentration data points O.
Given a givenK-adjacent distance of the concentration data point P, +.>The k-distance neighborhood of the concentration data point P contains AND +.>Each object whose distance of the concentration data point P is not greater than the k-adjacent distance +.>Concentration data point Q, these subjects->The concentration data point Q is referred to as k neighbors of P, abbreviated as Nk (P). To->The concentration data point P is used as a circle center, a circle is drawn by taking a k adjacent distance dk (P) as a radius, and the range within the circle is a k-distance neighborhood, and the formula is as follows:
computing each from the k-distance neighborhoodThe reachable distance of the concentration data points;
the definition of the reachable distance is related to the K-neighbor distance, which, given the parameter K,concentration data points P to->The reachable distance of the concentration data point O reach_distk (P, O) is the k-adjacent distance of the data point O and +.>Concentration data points P and->The maximum value of the direct distance between the concentration data points O.
And then calculate each based on the reachable distance, k-distance neighborhoodLocally reachable densities of the concentration data points.
The local reachable density of the concentration data point P is based on +.>The nearest neighbor of the concentration data point P has an average reachable distance inverse, the greater the distance, the less the density. Simple understanding is +.>K neighbors to +.>The average value of the distances of the concentration data points P will +.>The local reachable density of the concentration data point P is expressed as +.>Then:
where reach_distk (P, O) represents the achievable distance of data point P from data point O.
And determining local anomaly factors based on the local reachable densities,the local relative density (local abnormality factor) of the concentration data point P is +.>Average local reachable density of points within the neighborhood of the concentration data point P and +.>Local reachable density of the concentration data point P>Is expressed as +.>Then:
and determining a weight coefficient for correcting the local outlier factor in the LOF algorithm based on the concentration outlier factor, obtaining an outlier concentration point based on the weight coefficient, and determining the outlier concentration point and the moment corresponding to the outlier concentration point as a nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace.
Will be+1 as local abnormality factor->Obtaining the corrected abnormality factor +.>:
The embodiment will be abnormal factorsAnd threshold->Comparison is made with->Taking experience value of 1.3, and adding +.>Is->The concentration data points are outlier concentration data points. And determining the corresponding time of the abnormal concentration data, wherein the abnormal concentration data point and the time corresponding to the abnormal concentration point are determined as the nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace.
According to the embodiment, through the scheme, the data acquired by the sensor arranged in the low-nitrogen combustion heating furnace is preprocessed to obtainA concentration data sequence, a temperature data sequence, and an excess air factor data sequence; based on the temperature data sequence and +.>Obtaining a first fitting curve by using first data points at the same moment in a concentration data sequence; determining a temperature anomaly factor for each first data point based on the first data point and the first fitted curve; based on the excess air factor data sequence and +.>Construction of an excess air factor for a second data point at the same time in a concentration data sequence>A concentration coordinate system; based on the excess air factor->Determining an excess air anomaly factor of each second data point by the concentration coordinate system; calculating +.>A concentration anomaly factor for each time data point in the concentration data sequence; and determining a weight coefficient for correcting the local outlier factor in the LOF algorithm based on the concentration outlier factor, obtaining an outlier concentration point based on the weight coefficient, and determining the outlier concentration point and the moment corresponding to the outlier concentration point as a nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace. Therefore, the concentration anomaly factors are determined based on the correlation degree among the temperature data, the concentration data and the excess air coefficient data, and the local outlier factors of the LOF algorithm are corrected based on the concentration anomaly factors so as to obtain concentration anomaly data points, so that the accuracy of the nitrogen oxide emission detection result of the low-nitrogen combustion heating furnace is greatly improved.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or modifications in the structures or processes described in the specification and drawings, or the direct or indirect application of the present invention to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. A method for detecting nitrogen oxide emissions from a low nitrogen combustion heating furnace, the method comprising:
preprocessing data acquired by a sensor arranged in a low-nitrogen combustion heating furnace to obtainConcentration data sequence, temperature data sequence and excess air factor data sequence;
Based on the temperature data sequenceObtaining a first fitting curve by using first data points at the same moment in a concentration data sequence;
determining a temperature anomaly factor for each first data point based on the first data point and the first fitted curve;
based on excess air factor data sequenceConstruction of an excess air factor for a second data point at the same time in a concentration data sequence>A concentration coordinate system;
based on the excess air ratioDetermining an excess air anomaly factor of each second data point by the concentration coordinate system;
calculation of the temperature anomaly factor based on each first data point, the excess air factor anomaly factor of each second data point, and the correlationA concentration anomaly factor for each time data point in the concentration data sequence;
determining a weight coefficient for correcting local outliers in an LOF algorithm based on the concentration outliers, obtaining outlier concentration points based on the weight coefficient, and determining the outlier concentration points and the moments corresponding to the outlier concentration points as nitrogen oxide emission detection results of the low-nitrogen combustion heating furnace;
the calculation of the temperature anomaly factor based on each first data point, the excess air factor anomaly factor of each second data point and the correlation degreeThe concentration anomaly factor for each time data point in the concentration data sequence comprises:
based onConcentration data sequence, temperature data sequence and excess air factor data sequence, temperature pair is obtained using grey correlation analysis>First degree of association of concentration->A second degree of correlation of temperature to excess air ratio;
calculating a first product of the first correlation and a temperature anomaly factor of the first data point, and calculating a second product of the first correlation and an excess air coefficient anomaly factor of the second data point;
and determining a normalized value of the sum of the first product and the second product as a concentration anomaly factor of the data point at the corresponding moment.
2. The method for detecting nitrogen oxide emissions in a low nitrogen combustion furnace according to claim 1, wherein the data collected by a sensor provided in the low nitrogen combustion furnace is preprocessed to obtainThe concentration data sequence, the temperature data sequence, and the excess air ratio data sequence include:
collecting exhaust port of low-nitrogen combustion heating furnace through sensorThe concentration data, oxygen concentration data, and temperature data in the combustion chamber are stored as +.>Concentration data sequenceA train, an oxygen concentration data sequence, and a temperature data sequence;
respectively putting the above-mentionedNormalizing the concentration data sequence and the temperature data sequence to obtain +.>A concentration data sequence and a temperature data sequence;
and calculating an excess air coefficient data sequence corresponding to the oxygen concentration data sequence based on an excess air coefficient calculation formula.
3. The method for detecting nitrogen oxide emissions in a low nitrogen combustion heating furnace according to claim 1, wherein the temperature data sequence and the temperature data sequence are based onObtaining a first fitted curve from a first data point at the same time in the concentration data sequence comprises:
sequencing the temperature dataThe value at the same time in the concentration data sequence is determined as an ordinal number pair;
the ordinal number pair is taken as the construction temperature-A first data point of a concentration coordinate system;
and performing curve fitting on the first data points based on a least square method to obtain a first fitting curve.
4. The method of detecting nitrogen oxide emissions from a low nitrogen combustion furnace of claim 1, wherein said determining a temperature anomaly factor for each first data point based on said first data point and said first fitted curve comprises:
determining a first fit distance and a first standard fit distance for each first data point based on the first data points and the first fit curve;
calculating a first standard deviation of the first fitting distance and the first standard fitting distance;
determining a temperature-A temperature anomaly factor for each first data point in the concentration coordinate system.
5. The method of detecting nitrogen oxide emissions from a low nitrogen combustion furnace of claim 4, wherein said determining a first fitting distance and a first standard fitting distance for each first data point based on said first data point and said first fitting curve comprises:
calculating a first fitting distance between each first data point and the first fitting curve;
grouping the first data points based on the temperature values, determining the data with the same temperature value as the same temperature value data set, and calculating a first fitting distance average value of the temperature value data sets;
determining the density degree of first data points corresponding to each temperature based on the first fitting distance, the first fitting distance average value and the number of the first data points;
and calculating a first standard fitting distance of each first data point by the first fitting distance mean value based on the intensity level of the first data points.
6. A method for detecting nitrogen oxide emissions of a low nitrogen combustion heating furnace as recited in claim 1, wherein said method is based on said excess air ratio-Determining the excess of each second data point in the concentration coordinate systemThe air anomaly factors include:
based on the excess air ratioDetermining the local density of each second data point and a second fitting curve by the concentration coordinate system;
calculating a second fitting distance between each second data point and the second fitting curve, and calculating a second standard fitting distance of the second data point based on the second fitting distance of the second data point and the local density;
calculating a second standard deviation of the second fitting distance and the second standard fitting distance;
an excess air anomaly factor for each second data point is determined based on the second fit distance, the second standard fit distance, and the second standard deviation.
7. A method for detecting nitrogen oxide emissions of a low nitrogen combustion heating furnace as recited in claim 6, wherein said method is based on said excess air ratio-Determining the local density of each second data point by the concentration coordinate system, and a second fitting curve comprises:
in excess air ratio-Setting a window with a preset size by taking each second data point as a center in a concentration coordinate system, and calculating the local density of each second data point based on the size of the window and the number of the second data points in the window;
grouping second data points with the same excess air coefficient value to obtain a plurality of excess air coefficient value groups;
determining a second data point corresponding to the local density maximum value in each excess air coefficient value group as a mark data point;
and fitting the marked data points by using a cubic spline difference method to obtain a second fitting curve.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310868188.0A CN116611017B (en) | 2023-07-17 | 2023-07-17 | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310868188.0A CN116611017B (en) | 2023-07-17 | 2023-07-17 | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116611017A CN116611017A (en) | 2023-08-18 |
CN116611017B true CN116611017B (en) | 2023-09-19 |
Family
ID=87678537
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310868188.0A Active CN116611017B (en) | 2023-07-17 | 2023-07-17 | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116611017B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116805065B (en) * | 2023-08-25 | 2023-11-14 | 山东荣信集团有限公司 | Intelligent management method for monitoring data of coal powder heating furnace burner |
CN117171685B (en) * | 2023-09-01 | 2024-02-09 | 武汉中核仪表有限公司 | Operation monitoring method of turbidity measurement system |
CN116955737B (en) * | 2023-09-19 | 2023-11-28 | 源康(东阿)健康科技有限公司 | Abnormal characteristic retrieval method used in gelatin production process |
CN117251744B (en) * | 2023-11-16 | 2024-03-15 | 苏州科恩新能科技股份有限公司 | Kiln operation abnormal state detection method based on artificial intelligence |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2043551A1 (en) * | 1990-07-25 | 1992-01-26 | Daniel Reed Clark | Method and apparatus for optimizing fuel-to-air ratio in the combustible gas supply of a radiant burner |
CN107741945A (en) * | 2017-08-25 | 2018-02-27 | 国网吉林省电力有限公司 | A kind of CEMS system trouble analysis methods of outlier detection based on density |
WO2020019403A1 (en) * | 2018-07-26 | 2020-01-30 | 平安科技(深圳)有限公司 | Electricity consumption abnormality detection method, apparatus and device, and readable storage medium |
CN112232571A (en) * | 2020-10-19 | 2021-01-15 | 广东长天思源环保科技股份有限公司 | Method for predicting concentration of main pollutants in waste gas |
CN112267998A (en) * | 2020-11-26 | 2021-01-26 | 长安大学 | Method for testing highest temperature in cylinder and nonuniformity of cylinders of multi-cylinder diesel engine |
CN115267066A (en) * | 2022-07-21 | 2022-11-01 | 中国矿业大学 | Fossil fuel carbon dioxide emission calculation method based on satellite observation of concentration of pollution gas |
CN115963041A (en) * | 2022-12-26 | 2023-04-14 | 北京石油化工学院 | Method for evaluating relationship between concentration of fine particulate matters and carbon emission in atmospheric environment |
CN116340795A (en) * | 2023-05-29 | 2023-06-27 | 山东一然环保科技有限公司 | Operation data processing method for pure oxygen combustion heating furnace |
CN116413395A (en) * | 2023-06-08 | 2023-07-11 | 山东瑞程数据科技有限公司 | Intelligent detection method for environmental abnormality |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10387445B2 (en) * | 2016-01-06 | 2019-08-20 | International Business Machines Corporation | Hybrid method for anomaly classification |
-
2023
- 2023-07-17 CN CN202310868188.0A patent/CN116611017B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2043551A1 (en) * | 1990-07-25 | 1992-01-26 | Daniel Reed Clark | Method and apparatus for optimizing fuel-to-air ratio in the combustible gas supply of a radiant burner |
CN107741945A (en) * | 2017-08-25 | 2018-02-27 | 国网吉林省电力有限公司 | A kind of CEMS system trouble analysis methods of outlier detection based on density |
WO2020019403A1 (en) * | 2018-07-26 | 2020-01-30 | 平安科技(深圳)有限公司 | Electricity consumption abnormality detection method, apparatus and device, and readable storage medium |
CN112232571A (en) * | 2020-10-19 | 2021-01-15 | 广东长天思源环保科技股份有限公司 | Method for predicting concentration of main pollutants in waste gas |
CN112267998A (en) * | 2020-11-26 | 2021-01-26 | 长安大学 | Method for testing highest temperature in cylinder and nonuniformity of cylinders of multi-cylinder diesel engine |
CN115267066A (en) * | 2022-07-21 | 2022-11-01 | 中国矿业大学 | Fossil fuel carbon dioxide emission calculation method based on satellite observation of concentration of pollution gas |
CN115963041A (en) * | 2022-12-26 | 2023-04-14 | 北京石油化工学院 | Method for evaluating relationship between concentration of fine particulate matters and carbon emission in atmospheric environment |
CN116340795A (en) * | 2023-05-29 | 2023-06-27 | 山东一然环保科技有限公司 | Operation data processing method for pure oxygen combustion heating furnace |
CN116413395A (en) * | 2023-06-08 | 2023-07-11 | 山东瑞程数据科技有限公司 | Intelligent detection method for environmental abnormality |
Non-Patent Citations (2)
Title |
---|
煤粉工业锅炉空气深度分级数值模拟研究;王鹏涛;王乃继;程晓磊;王永英;梁兴;;洁净煤技术(第05期);全文 * |
钢铁企业高炉煤气发生量异常数据检测;王红君;白鹏;赵辉;岳有军;;化工自动化及仪表(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116611017A (en) | 2023-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116611017B (en) | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace | |
CN116340795B (en) | Operation data processing method for pure oxygen combustion heating furnace | |
CN109492319B (en) | Soft measurement method for oxygen content of boiler flue gas of thermal power plant | |
CN110245850B (en) | Sintering process working condition identification method and system considering time sequence | |
CN1877193A (en) | Method and apparatus for online monitoring tube wall temperature in boiler overheater and reheater | |
CN112418306B (en) | Gas turbine compressor fault early warning method based on LSTM-SVM | |
CN105241669B (en) | Based on the gas turbine combustion system on-line monitoring method for comparing coding | |
CN102564644A (en) | Temperature online measuring method for plate blank in production process of heating furnace | |
CN117056644B (en) | Industrial kiln temperature prediction method and system based on machine learning | |
CN112685964B (en) | Boiler heating surface pipe wall leakage prediction method based on convolutional neural network | |
CN112989694A (en) | Segmented monitoring system and method for ash on heating surface | |
CN116825243A (en) | Multi-source data-based thermal barrier coating service life prediction method and system | |
CN110737975B (en) | Wind power plant wind speed and power prediction and abnormality correction method based on empirical mode decomposition and autoregressive model | |
CN111401652A (en) | Boiler optimization method and system based on CO online detection | |
CN116805065B (en) | Intelligent management method for monitoring data of coal powder heating furnace burner | |
CN109521735B (en) | On-line assessment method for use state risk of high-temperature heating surface of boiler | |
CN111859822B (en) | Method for predicting generation amount of nitrogen oxides in glass melting furnace | |
CN117078023B (en) | Kiln fault risk assessment method based on big data analysis | |
CN117251744B (en) | Kiln operation abnormal state detection method based on artificial intelligence | |
CN117494531B (en) | Medium carbon steel decarburization depth prediction method based on finite element and XGBoost algorithm | |
CN115113519A (en) | Coal-gas co-combustion boiler denitration system outlet NO x Concentration early warning method | |
CN117829342A (en) | Coal-fired power plant nitrogen oxide emission prediction method based on improved random forest algorithm | |
CN108730943B (en) | Flue gas dynamic temperature evaluation method | |
CN116429269A (en) | Infrared intelligent analysis system for ethylene cracking furnace tube | |
CN114534466B (en) | Method for controlling nitrogen oxide emission by control 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |