CN118468152B - Dynamic operation characteristic calculation modeling method for waste heat boiler - Google Patents
Dynamic operation characteristic calculation modeling method for waste heat boiler Download PDFInfo
- Publication number
- CN118468152B CN118468152B CN202410925896.8A CN202410925896A CN118468152B CN 118468152 B CN118468152 B CN 118468152B CN 202410925896 A CN202410925896 A CN 202410925896A CN 118468152 B CN118468152 B CN 118468152B
- Authority
- CN
- China
- Prior art keywords
- authenticity
- data
- boiler
- correlation
- obtaining
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention relates to the technical field of decision tree construction of boiler dynamic operation data, in particular to a dynamic operation characteristic calculation modeling method for an exhaust-heat boiler. The method obtains first authenticity according to the time sequence variation stability of the environmental parameters of the waste heat boiler, obtains second authenticity according to the time sequence variation correlation between the boiler load and the fuel supply, between the fuel supply and the exhaust gas temperature and between the boiler load and the water level in the boiler, and further obtains data authenticity. And obtaining the optimal information entropy according to the data authenticity. And constructing a final decision tree according to the information gain of the optimal information entropy, and predicting the pressure characteristic in the real-time operation process. According to the invention, through the operation characteristics of the waste heat boiler, the data authenticity is obtained, so that the optimal information entropy of the data characteristics which can accurately represent the influence factors is obtained, an accurate final decision tree is constructed, and the accuracy of the pressure prediction of the waste heat boiler is improved.
Description
Technical Field
The invention relates to the technical field of decision tree construction of boiler dynamic operation data, in particular to a dynamic operation characteristic calculation modeling method for an exhaust-heat boiler.
Background
The exhaust-heat boiler is an apparatus for generating steam or heating water using waste heat generated in an industrial process, which improves energy utilization efficiency and reduces environmental pollution by recovering heat energy generated in a combustion process. The pressure dynamic operation characteristic calculation modeling of the waste heat boiler can help to predict and optimize operation, diagnose faults and early warning, evaluate performance and improve, optimize energy utilization and environmental protection benefits, and provide support for decision and operation.
In the prior art, the ID3 decision tree model can be constructed by utilizing the related influence factors of the boiler through average classification of related factors and pressure and through information entropy distribution of the category of the data value. However, in the actual data acquisition process, because the operation condition of the waste heat boiler is complex, the dimension of influencing factors is more, certain data are easy to be noise data in the data acquisition process, the reality is poor, if the information entropy is obtained by directly adopting the distribution of the category of the data value, the noise data are easy to influence the information entropy and the calculation effectiveness of the information gain, the accuracy of a built decision tree is lower, and the effective prediction of the dynamic operation pressure of the waste heat boiler cannot be realized.
Disclosure of Invention
In order to solve the technical problems that in the prior art, the accuracy of a decision tree of a framework is low and effective prediction of dynamic operation pressure of a waste heat boiler cannot be realized due to the fact that data authenticity is not considered, the invention aims to provide a dynamic operation characteristic calculation modeling method for the waste heat boiler, and the adopted technical scheme is as follows:
The invention provides a dynamic operation characteristic calculation modeling method for an exhaust-heat boiler, which comprises the following steps:
Obtaining influence factor data of the waste heat boiler at each sampling time in the historical operation process; the influence factor data comprise valve states, boiler loads, fuel supply, exhaust gas temperatures, water levels and environmental parameters;
obtaining first authenticity according to the change stability of the environmental parameter on time sequence at each sampling time; obtaining a second authenticity according to the time sequence variation correlation of the boiler load and the fuel supply, the time sequence variation correlation of the fuel supply and the exhaust gas temperature and the time sequence variation correlation of the boiler load and the water level; fusing the first authenticity and the second authenticity to obtain data authenticity at each sampling time;
According to the data authenticity of the influence factor data of each dimension, correcting the original information entropy of the influence factor data of each dimension to obtain an optimal information entropy, and constructing a final decision tree according to the information gain of the optimal information entropy; the leaf nodes of the final decision tree are boiler pressures;
And predicting the pressure in the real-time operation process according to the final decision tree.
Further, the method for acquiring the first authenticity includes:
and for each sampling moment, obtaining the environmental parameter difference between the corresponding sampling moment and other sampling moments in a preset neighborhood range on time sequence, carrying out negative correlation mapping on fluctuation characteristics of the environmental parameter difference, obtaining the change stability, and obtaining the first authenticity according to the change stability.
Further, the method for acquiring the change correlation includes:
for each sampling moment, forming an analysis time period under the corresponding sampling moment with other sampling moments in a preset neighborhood range in time sequence; and taking the Pearson correlation coefficient between the influence factor data as the change correlation over the analysis time period.
Further, the second authenticity obtaining method includes:
Fusing the time sequence change correlation of the boiler load and the fuel supply and the time sequence change correlation of the fuel supply and the exhaust gas temperature as a forward correlation factor; taking the change correlation of the boiler load and the water level in time sequence as a negative correlation factor;
The second authenticity is obtained from the difference of the positive correlation factor and the negative correlation factor.
Further, the method for acquiring the data authenticity comprises the following steps:
and multiplying the first authenticity by the second authenticity, and then carrying out normalization operation to obtain the data authenticity.
Further, the method for obtaining the optimal information entropy comprises the following steps:
Dividing the influence factor data of each dimension into a preset number of categories according to the size of the data value; and for each category, taking the accumulated value of the data authenticity corresponding to each influence factor data in the category as a child, taking the accumulated value of the data authenticity of all the categories as a denominator, obtaining the data authenticity probability of the corresponding category, and substituting the data authenticity probability into an information entropy formula to obtain the optimal information entropy.
Further, the preset neighborhood range is 10 in size.
Further, in the construction process of the final decision tree, the accuracy of the final decision tree is adjusted by changing the category number of each influence factor data.
Further, the fluctuation of the environmental parameter difference is characterized by a variance of the environmental parameter difference.
Further, the environment parameters include an environment temperature and an environment humidity, a first initial authenticity is obtained according to the environment temperature, a second initial authenticity is obtained according to the environment humidity, the first initial authenticity and the second initial authenticity are fused, and the first authenticity at the corresponding sampling time is obtained.
The invention has the following beneficial effects:
the acquired influence factors comprise two types, namely, in-furnace factors and environmental factors, and the environmental factors are considered to be relatively fixed, so that obvious change does not occur, and the first authenticity can be obtained according to the change stability of the environmental parameters on time sequence; further considering that there is a significant time-series dependency between the boiler load and the fuel supply, between the fuel supply and the exhaust gas temperature, and between the boiler load and the water level among the in-furnace factors, the second authenticity is obtained. The data availability is represented by the data authenticity, and the optimal information entropy is obtained by the data authenticity, so that the optimal information entropy can more represent the data characteristics of the corresponding influence factors, and an accurate final decision tree is constructed. The final decision tree can show the relation between the characteristics and the boiler pressure in the dynamic operation process of the waste heat boiler, and the accurate prediction of the boiler pressure can be realized by utilizing the final decision tree.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a dynamic operation characteristic calculation modeling method for an exhaust-heat boiler according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of the dynamic operation characteristic calculation modeling method for the waste heat boiler according to the invention, which is provided by the invention, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of a dynamic operation characteristic calculation modeling method for an exhaust-heat boiler, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a dynamic operation characteristic calculation modeling method for an exhaust-heat boiler according to an embodiment of the present invention is shown, where the method includes:
step S1: obtaining influence factor data of the waste heat boiler at each sampling time in the historical operation process; the influencing factor data include valve status, boiler load, fuel supply, exhaust gas temperature, water level, environmental parameters.
In the embodiment of the invention, the valve state, the boiler load, the fuel supply, the exhaust gas temperature and the water level are used as furnace influencing factors, and the environmental parameters are used as environmental influencing factors. And in the subsequent process, carrying out data authenticity analysis according to the furnace influencing factors and the environment influencing factors.
It should be noted that, in one embodiment of the present invention, the sampling frequency is set to be once collected every second, and for the boiler load, the fuel supply, the exhaust gas temperature, the water level and the environmental parameters, the data under the corresponding dimensions can be collected and then standardized, the dimensions are removed, so that the subsequent operation is convenient. For the valve state, for example, the waste heat boiler comprises 3 valves which are respectively opened, closed and opened, and can be quantified by a marking method, in the embodiment of the invention, the opening is marked as 1, the closing is marked as 0, namely, the marking data of the corresponding state is [1,0,1], all the marking data can be counted, the same marking data is the valve state and further marked, if the waste heat boiler comprises m valves, each valve has two states, the waste heat boiler can comprise all the valve states togetherThe state of the valve can be from 1 sign toAnd the quantification of the valve state is realized.
Step S2: obtaining first authenticity according to the change stability of the environmental parameter on time sequence at each sampling time; obtaining a second authenticity according to the time sequence variation correlation of the boiler load and the fuel supply, the time sequence variation correlation of the fuel supply and the exhaust gas temperature and the time sequence variation correlation of the boiler load and the water level; fusing the first authenticity and the second authenticity to obtain the data authenticity at each sampling time;
Firstly, for the environmental parameters of the waste heat boiler, because the environmental parameters are less influenced by the operation of the boiler, the environmental parameters cannot be obviously mutated in a short time, if the environmental parameters are obviously mutated, the data acquired at the corresponding time are influenced by noise, and the reality is lower; otherwise, if the environmental parameter does not have obvious mutation at a certain sampling time, the stability of the change in time sequence is higher, and the data authenticity at the sampling time is higher. The first authenticity can thus be obtained for each sampling instant from the varying stability of the environmental parameter over time.
Preferably, in one embodiment of the present invention, it is considered that the main environmental parameters of the waste heat boiler are humidity and temperature, and thus the collected environmental parameters include the environmental temperature and the environmental humidity. And further, respectively analyzing the ambient temperature and the ambient humidity, obtaining a first initial authenticity according to the ambient temperature, obtaining a second initial authenticity according to the ambient humidity, and fusing the first initial authenticity and the second initial authenticity to obtain the first authenticity at the corresponding sampling time.
Preferably, in one embodiment of the present invention, considering that the environmental parameters between the time-series local ranges should remain in a stable state, the first method of obtaining authenticity therefore comprises:
And for each sampling time, obtaining the environmental parameter difference between the corresponding sampling time and other sampling times in a preset neighborhood range on time sequence. The environmental parameter difference is the absolute value of the difference between the two environmental parameters. And carrying out negative correlation mapping on the fluctuation characteristics of the environmental parameter difference to obtain the change stability. That is, the stronger the fluctuation characteristic of the environmental parameter difference is, the more unstable the data change at the corresponding sampling time is, the more likely the time is to be affected by noise, the lower the change stability is, and the first reality is lower. The first authenticity is obtained from the varying stability.
It should be noted that, because in one embodiment of the present invention, the environmental parameter includes two dimensions of the environmental humidity and the environmental temperature, the first initial authenticity and the second initial authenticity may be obtained by substituting the environmental parameter and the environmental temperature based on the first authenticity obtaining method, and the first initial authenticity and the second initial authenticity may be integrated by multiplying or adding the first initial authenticity and the second initial authenticity to obtain the final first authenticity.
In one embodiment of the invention, the neighborhood range is set to 10, i.e. around 10 other sampling instants, centered around each sampling instant, constitutes the neighborhood range of the corresponding sampling instant.
In one embodiment of the invention, the negative correlation mapping is performed on the fluctuation features of the environmental parameter differences by adopting a function mapping method, and the inverse number of the fluctuation features is used as the power of an exponential function based on a natural constant to obtain a negative correlation mapping result. It should be noted that, in other embodiments of the present invention, other negative correlation mapping methods such as the opposite number and the inverse number may be selected, which are all technical means well known to those skilled in the art, and are not described and limited herein.
In one embodiment of the present invention, the first authenticity is obtained after normalizing the stability of the change.
Preferably, in one embodiment of the invention, the fluctuation feature is a fluctuation feature of the environmental parameter difference is a variance of the environmental parameter difference. In other embodiments of the present invention, statistical indexes such as standard deviation, etc. that characterize characteristic fluctuation may be selected, and are not described and limited herein.
For various in-furnace influencing factors of the waste heat boiler, the boiler load refers to the heat or steam quantity required to be provided by the boiler; the fuel supply refers to the amount of fuel supplied to the boiler, such as natural gas amount, fuel oil amount, etc. The increase in the boiler load requires the support of a fuel supply, i.e. the fuel supply shows a clear correlation with the boiler load for normal data, the larger the fuel supply the larger the boiler load. The exhaust gas temperature refers to the temperature of the exhaust gas generated after the fuel is combusted, and similarly, the larger the fuel supply is, the more fuel is in the waste heat boiler for combustion, so the corresponding exhaust gas temperature is also increased, namely, the fuel supply and the exhaust gas temperature show obvious correlation for normal data. The water level is the height of water in the waste heat boiler, and the greater the boiler load, the greater the heat or steam quantity in the boiler, the consumption of water in the boiler can become great, namely the water level can be reduced, so for normal data, the boiler load and the water level have obvious change correlation in time sequence. The second authenticity at each sampling instant can be obtained from the perspective of the furnace impact factors by analyzing the varying correlations between the different dimensional impact factor data.
Preferably, in one embodiment of the present invention, the method for acquiring the change correlation includes:
For each sampling moment, in time sequence, the analysis time period corresponding to the sampling moment is formed with other sampling moments in a preset neighborhood range. That is, the influence factor data of each dimension corresponds to a sequence in the analysis period, and the pearson correlation coefficient between the influence factor data is taken as the variation correlation in the analysis period. The pearson correlation coefficient can represent the variation correlation between two sequences, and the larger the pearson correlation coefficient is, the more relevant the variation between two sequences is illustrated, and the specific acquisition method is a technical means well known to those skilled in the art, and will not be described herein.
Preferably, in one embodiment of the present invention, the second method for acquiring authenticity includes:
The time-series change correlation between the boiler load and the fuel supply and the time-series change correlation between the fuel supply and the exhaust gas temperature are fused as forward correlation factors. The time sequence change correlation of the boiler load and the water level is used as a negative correlation factor. The greater the forward correlation factor. The smaller the negative correlation factor is, the more the influence factor data change at the current moment is compounded with the normal scene, and the greater the corresponding authenticity is. The second authenticity may thus be obtained from the difference of the positive correlation factor and the negative correlation factor.
In one embodiment of the invention, the second authenticity is obtained by subtracting the negative correlation factor from the result of the addition of the two positive correlation factors. In other embodiments of the present invention, the difference between the two positive correlation factors and the negative correlation factor may be calculated, and then the two differences may be summed to obtain the second authenticity, which is not described in detail herein.
After the first authenticity and the second authenticity are obtained, the two authentications can be fused, and the data authenticity at each sampling time can be obtained. I.e. each sampling instant corresponds to a set of influencing factor data and a boiler pressure data and to a data authenticity.
In one embodiment of the present invention, in order to facilitate the subsequent decision tree construction, all data may be counted to construct a data matrix, where a column in the data matrix corresponds to data of one dimension and a row corresponds to all data at one sampling time.
Preferably, in one embodiment of the present invention, the data authenticity is obtained by multiplying the first authenticity with the second authenticity and then performing a normalization operation.
It should be noted that, the normalization method in the embodiment of the present invention may use pole difference normalization, and may also select other basic mathematical means such as hyperbolic tangent function mapping to implement normalization, which is not described herein.
Step S3: obtaining information entropy of the data authenticity of the influence factor data of each dimension, and constructing a final decision tree according to the information gain of the information entropy; the leaf nodes of the final decision tree are boiler pressures.
For the prior art, before the information entropy is obtained, the data range of data is divided into a plurality of categories according to a certain influence factor, for example, the range of data values of the boiler load after dimension processing is 0 to 100, and the data ranges can be equally divided into 10 categories. In the prior art, the information entropy is directly constructed according to the number of data points contained in the interval corresponding to each category, namely the adopted distribution probability is the ratio of the number of categories in the interval to the total number of categories. The information entropy obtained by the method does not consider the authenticity of the information, so that the accuracy of the decision tree is affected. The data authenticity at each sampling time has been obtained in step S2, so that the data authenticity can be used for correction on the basis of the original information entropy by means of the data authenticity, so that an optimal information entropy is obtained. And constructing a final decision tree by utilizing the information gain of the optimal information entropy. And the leaf nodes of the final decision tree are boiler pressure, and each boiler pressure node can correspond to a data range, so that the prediction of pressure data is realized.
Preferably, in one embodiment of the present invention, the method for obtaining the optimal information entropy includes:
Dividing the influence factor data of each dimension into a preset number of categories according to the size of the data value; for each category, taking the accumulated value of the data authenticity corresponding to each influence factor data in the category as a son, and taking the accumulated value of the data authenticity of all the categories as a denominator, so as to obtain the data authenticity probability of the corresponding category. It should be noted that, for the original information entropy, the calculation is directly performed by taking the quantitative ratio as the probability, and the authenticity probability is obtained by accumulating the data authenticity, which is equivalent to weighting each data by using the data authenticity, so as to realize the correction of the original information entropy. And substituting the probability of the data authenticity into an information entropy formula to obtain the optimal information entropy. The calculation formula of the optimal information entropy can be expressed as:
; wherein the method comprises the steps of The optimal information entropy of the D-th influence factor data,The number of categories divided for the D-th influencing factor data,For the amount of data contained in the i-th category,For the data authenticity of the j-th data in the i-th class,Is a logarithmic function based on Z. It should be noted that the information entropy calculation formula is a technical means well known to those skilled in the art, and will not be described herein.
After the optimal information entropy is obtained, a final decision tree can be constructed according to an information gain ID3 algorithm, and the information entropy required to be calculated when the final decision tree is constructed is the optimal information entropy obtained by correcting the data authenticity.
In the embodiment of the present invention, the pressure data may be first divided into a plurality of categories, that is, each category is a pressure interval. And constructing a final decision tree according to a traditional information gain ID3 algorithm, and selecting the influence factor data with the maximum information gain as a root node. Splitting is carried out according to the category of the root node, information gain is recalculated in the data of the category corresponding to the root node, and the influence factor of the maximum information gain is selected as a child node, so that further splitting is carried out. In the process of judging splitting, whether the pressure data in the corresponding state only contains one type or not can be judged, if the pressure data in the corresponding state only contains one type, the node is judged not to need splitting any more, the pressure data in the corresponding type is directly used as a leaf node in the corresponding state, otherwise, splitting is continued, and the corresponding child nodes are determined until a final decision tree is obtained. It should be noted that the method for constructing the final decision tree by using the conventional information gain ID3 algorithm is a technical means well known to those skilled in the art, and will not be described herein.
Preferably, in one embodiment of the present invention, in the process of constructing the final decision tree, the accuracy of the final decision tree is adjusted by changing the number of categories of each influence factor data. For example, the boiler load in the final decision tree constructed for the first time is 10 categories, so that the accuracy of the final decision tree is improved, the final decision tree can be further divided into 20 categories, and other influencing factors are the same.
Step S4: and predicting the pressure in the real-time operation process according to the final decision tree.
The final decision tree reflects the dynamic characteristics of the waste heat boiler in the running process through the path relation among the nodes. In the process of predicting the pressure characteristic of the real-time operation process, the data collected in the implementation operation process can be substituted into a final decision tree, the path in the final decision tree is determined, and the predicted pressure interval can be obtained according to the leaf node corresponding to the path. The staff can judge whether the current boiler state is normal or not according to the predicted pressure interval.
In summary, according to the embodiment of the invention, the first authenticity is obtained according to the time sequence variation stability of the environmental parameters of the waste heat boiler, and the second authenticity is obtained according to the time sequence variation correlation between the boiler load and the fuel supply, between the fuel supply and the exhaust gas temperature, and between the boiler load and the water level in the boiler, thereby obtaining the data authenticity. And obtaining the optimal information entropy according to the data authenticity. And constructing a final decision tree according to the information gain of the optimal information entropy, and predicting the pressure characteristic in the real-time operation process. According to the embodiment of the invention, the data authenticity is obtained through the operation characteristics of the waste heat boiler, so that the optimal information entropy of the data characteristics capable of accurately representing the influence factors is obtained, an accurate final decision tree is constructed, and the accuracy of the pressure prediction of the waste heat boiler is improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (7)
1. The dynamic operation characteristic calculation modeling method for the waste heat boiler is characterized by comprising the following steps of:
Obtaining influence factor data of the waste heat boiler at each sampling time in the historical operation process; the influence factor data comprise valve states, boiler loads, fuel supply, exhaust gas temperatures, water levels and environmental parameters;
obtaining first authenticity according to the change stability of the environmental parameter on time sequence at each sampling time; obtaining a second authenticity according to the time sequence variation correlation of the boiler load and the fuel supply, the time sequence variation correlation of the fuel supply and the exhaust gas temperature and the time sequence variation correlation of the boiler load and the water level; fusing the first authenticity and the second authenticity to obtain data authenticity at each sampling time;
According to the data authenticity of the influence factor data of each dimension, correcting the original information entropy of the influence factor data of each dimension to obtain an optimal information entropy, and constructing a final decision tree according to the information gain of the optimal information entropy; the leaf nodes of the final decision tree are boiler pressures;
Predicting the pressure in the real-time operation process according to the final decision tree;
The first authenticity obtaining method comprises the following steps:
for each sampling moment, obtaining the environmental parameter difference between the corresponding sampling moment and other sampling moments in a preset neighborhood range on time sequence, carrying out negative correlation mapping on fluctuation characteristics of the environmental parameter difference, obtaining the change stability, and obtaining the first authenticity according to the change stability;
The second authenticity obtaining method comprises the following steps:
Fusing the time sequence change correlation of the boiler load and the fuel supply and the time sequence change correlation of the fuel supply and the exhaust gas temperature as a forward correlation factor; taking the change correlation of the boiler load and the water level in time sequence as a negative correlation factor;
obtaining the second authenticity according to the difference between the positive correlation factor and the negative correlation factor;
The method for acquiring the optimal information entropy comprises the following steps:
Dividing the influence factor data of each dimension into a preset number of categories according to the size of the data value; and for each category, taking the accumulated value of the data authenticity corresponding to each influence factor data in the category as a child, taking the accumulated value of the data authenticity of all the categories as a denominator, obtaining the data authenticity probability of the corresponding category, and substituting the data authenticity probability into an information entropy formula to obtain the optimal information entropy.
2. The method for modeling dynamic operation characteristics of a waste heat boiler according to claim 1, wherein the method for obtaining the change correlation comprises:
for each sampling moment, forming an analysis time period under the corresponding sampling moment with other sampling moments in a preset neighborhood range in time sequence; and taking the Pearson correlation coefficient between the influence factor data as the change correlation over the analysis time period.
3. The method for modeling dynamic operation characteristics of a waste heat boiler according to claim 1, wherein the method for obtaining the authenticity of the data comprises the following steps:
and multiplying the first authenticity by the second authenticity, and then carrying out normalization operation to obtain the data authenticity.
4. A method for modeling dynamic operation characteristics of a waste heat boiler according to claim 1 or 3, wherein the preset neighborhood range is 10.
5. The method for modeling dynamic operation characteristics of a waste heat boiler according to claim 1, wherein the accuracy of the final decision tree is adjusted by changing the number of categories of each influence factor data in the construction process of the final decision tree.
6. The method for modeling dynamic operation characteristics calculation of a waste heat boiler according to claim 1, wherein the fluctuation characteristic of the environmental parameter difference is a variance of the environmental parameter difference.
7. The method for modeling dynamic operation characteristics of a waste heat boiler according to claim 1, wherein the environmental parameters include an environmental temperature and an environmental humidity, a first initial authenticity is obtained according to the environmental temperature, a second initial authenticity is obtained according to the environmental humidity, and the first initial authenticity and the second initial authenticity are fused to obtain the first authenticity at a corresponding sampling time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410925896.8A CN118468152B (en) | 2024-07-11 | 2024-07-11 | Dynamic operation characteristic calculation modeling method for waste heat boiler |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410925896.8A CN118468152B (en) | 2024-07-11 | 2024-07-11 | Dynamic operation characteristic calculation modeling method for waste heat boiler |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118468152A CN118468152A (en) | 2024-08-09 |
| CN118468152B true CN118468152B (en) | 2024-09-17 |
Family
ID=92164102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410925896.8A Active CN118468152B (en) | 2024-07-11 | 2024-07-11 | Dynamic operation characteristic calculation modeling method for waste heat boiler |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118468152B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119128450B (en) * | 2024-11-13 | 2025-03-21 | 江苏太湖锅炉股份有限公司 | Boiler thermal efficiency evaluation and prediction method based on data analysis |
| CN119175835B (en) * | 2024-11-25 | 2025-02-28 | 天津市全福车业有限公司 | A method and system for controlling constant temperature of a bicycle saddle foaming mold |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108364467A (en) * | 2018-02-12 | 2018-08-03 | 北京工业大学 | A kind of traffic information prediction technique based on modified decision Tree algorithms |
| CN112066355A (en) * | 2020-09-10 | 2020-12-11 | 河北工业大学 | Data-driven valve adaptive adjustment method of waste heat boiler |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7627161B2 (en) * | 2005-11-28 | 2009-12-01 | Fuji Xerox Co., Ltd. | Authenticity determination method, apparatus and program |
| CN116085823A (en) * | 2022-12-01 | 2023-05-09 | 国家能源集团新能源技术研究院有限公司 | Boiler combustion control method and system |
| CN117879118B (en) * | 2024-03-11 | 2024-05-14 | 珠海汇众能源科技有限公司 | Operation strategy method of self-adaptive optical storage and filling system |
| CN118194607B (en) * | 2024-05-16 | 2024-08-02 | 江苏太湖锅炉股份有限公司 | A method and system for dynamic modeling of boiler unit data |
-
2024
- 2024-07-11 CN CN202410925896.8A patent/CN118468152B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108364467A (en) * | 2018-02-12 | 2018-08-03 | 北京工业大学 | A kind of traffic information prediction technique based on modified decision Tree algorithms |
| CN112066355A (en) * | 2020-09-10 | 2020-12-11 | 河北工业大学 | Data-driven valve adaptive adjustment method of waste heat boiler |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118468152A (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118468152B (en) | Dynamic operation characteristic calculation modeling method for waste heat boiler | |
| CN112801388B (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| CN103324980B (en) | A kind of method for forecasting | |
| CN114119273B (en) | Non-invasive load decomposition method and system for park comprehensive energy system | |
| CN111735177B (en) | Central air conditioning system cold load prediction method based on SVR algorithm | |
| CN112381673B (en) | Park electricity utilization information analysis method and device based on digital twin | |
| CN117422167A (en) | Electric power carbon emission predictive analysis method based on tree model | |
| CN118657059B (en) | Dynamic prediction method for residual life of PEMFC (proton exchange membrane fuel cell) based on attention neural network | |
| CN116010884A (en) | Fault Diagnosis Method of SSA-LightGBM Oil-immersed Transformer Based on Principal Component Analysis | |
| CN112418504A (en) | Wind speed prediction method based on mixed variable selection optimization deep belief network | |
| CN108537581B (en) | Time series prediction method and device of energy consumption based on GMDH selective combination | |
| CN119988925A (en) | A method, medium and system for generating extreme weather scenes based on CGAN algorithm | |
| CN119250845B (en) | Construction industry carbon emission prediction method and system based on random forest algorithm | |
| CN116204779A (en) | Method, system and readable storage medium for judging operation state of energy storage salt cavern | |
| CN116245019A (en) | A load forecasting method, system, device and storage medium based on Bagging sampling and improved random forest algorithm | |
| CN119671328A (en) | Urban natural gas consumption prediction method based on XGB-PSO-LSTM model | |
| CN115345297A (en) | A method and system for generating station area samples based on generative confrontation network | |
| CN118690918B (en) | An electricity-carbon model construction and ecological carbon sink calculation system | |
| CN119090067A (en) | Short-term carbon emission prediction method based on CNN-Bi-LSTM neural network model | |
| CN117634678A (en) | Carbon emission prediction method for low-carbon parks based on actual operating scenarios | |
| CN113962456B (en) | A medium- and long-term load forecasting method taking into account industry correlation | |
| CN116565850A (en) | A method for ultra-short-term forecasting of wind power based on QR-BLSTM | |
| CN120525137B (en) | Method and system for predicting and checking combustion carbon emission factor of gas generator set | |
| CN120511670B (en) | Power grid load prediction method and system based on time sequence correlation analysis | |
| Liu et al. | Analysis and Forecasting of CO 2 Emissions in the Power Sector Based on GRA and LSTM |
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 |